Edit: /opt/imh-python/lib/python3.9/site-packages/numpy/random/mtrand.cpython-39-x86_64-linux-gnu.so (787720B)
ELF > X @ @ 8 @ HB HB P P P
H- (
(
(
8 8 8 $ $ Ptd
Qtd Rtd
GNU xkZsĻrzN .ڹ B gl
\ s G *
-
j
.
! > " 0 . >
x Y 4 &
T v : % T
" v
]
W
I
q Q j I
r '
p d
U
h a y &
b p p ~ { H I 9
b m Q 8 B
4
G S R " r
9 = P
; __gmon_start__ _init _fini _ITM_deregisterTMCloneTable _ITM_registerTMCloneTable __cxa_finalize _Py_NoneStruct PyBaseObject_Type PyExc_TypeError PyErr_Format PyDict_Next Py_EnterRecursiveCall Py_LeaveRecursiveCall PyErr_Occurred PyObject_Call PyExc_SystemError PyErr_SetString PyObject_GetAttr memcpy _Py_Dealloc PyExc_DeprecationWarning PyErr_WarnFormat PyLong_AsLong PyExc_OverflowError PyLong_Type PyObject_GC_UnTrack PyObject_GC_IsFinalized PyObject_CallFinalizerFromDealloc PyErr_NormalizeException PyException_SetTraceback PyDict_New PyImport_ImportModuleLevelObject PyObject_GetAttrString PyDict_GetItemString PyModule_GetName PyExc_ImportError PyCapsule_IsValid PyCapsule_GetName PyCapsule_GetPointer PyDict_SetItemString PyExc_AttributeError PyErr_ExceptionMatches PyErr_Clear PyThreadState_Get PyInterpreterState_GetID PyModule_NewObject PyModule_GetDict PyUnicode_Type memcmp PyObject_RichCompare _Py_TrueStruct _Py_FalseStruct PyObject_IsTrue _PyUnicode_Ready PyDict_GetItemWithError PyExc_KeyError PyErr_SetObject PyTuple_Pack PyExc_ValueError PyOS_snprintf PyErr_WarnEx PyList_Type PyLong_FromSsize_t PyObject_SetItem PySlice_New _PyType_Lookup PyTuple_Type PyObject_GetItem PyUnicode_Compare PyTuple_New PyUnicode_InternFromString PyUnicode_Decode PyUnicode_FromStringAndSize PyBytes_FromStringAndSize PyObject_Hash PyExc_RuntimeError PyFloat_Type PyErr_GivenExceptionMatches PyUnicode_FromString PyUnicode_Concat PyImport_GetModule PyCFunction_Type PyType_IsSubtype PyObject_GenericGetAttr PyType_Ready _PyObject_GetDictPtr _PyDict_GetItem_KnownHash PyMethod_Type _PyThreadState_UncheckedGet PyExc_StopIteration PyObject_Not PyFrame_New PyTraceBack_Here PyObject_SetAttr PyCode_NewEmpty PyUnicode_FromFormat PyUnicode_AsUTF8 memmove PyMem_Realloc _PyObject_GenericGetAttrWithDict PyMem_Malloc PyDict_SetItem PyNumber_Add PyNumber_InPlaceAdd PyNumber_Index PyLong_AsSsize_t PyExc_IndexError PyList_New PyObject_GetIter PyDict_Size PyExc_NameError PyLong_FromLong PyFloat_AsDouble PyFloat_FromDouble PyBool_Type PyUnicode_Format PyNumber_Remainder PyImport_AddModule PyObject_SetAttrString Py_GetVersion PyLong_FromString PyImport_GetModuleDict _Py_EllipsisObject PyCode_NewWithPosOnlyArgs PyImport_Import PyErr_Fetch PyErr_Restore PyCapsule_New malloc free PyImport_ImportModule PyCapsule_Type PyExc_Exception PyType_Modified PyCMethod_New _PyDict_NewPresized PyDict_Copy PySequence_Contains PyObject_Size PyObject_IsInstance PyUnicode_New _PyUnicode_FastCopyCharacters PyObject_Format PyDict_Type PyEval_SaveThread PyEval_RestoreThread PySequence_Tuple PyNumber_Long PyNumber_Multiply PyList_AsTuple PySequence_List PyList_Append PyNumber_InPlaceTrueDivide PyNumber_Subtract PyInit_mtrand PyModuleDef_Init log exp log1p expf log1pf pow sqrt powf logf sqrtf expm1 floor __isnan acos fmod memset ceil libm.so.6 libc.so.6 GLIBC_2.14 GLIBC_2.2.5
0 ui ui
P<
<
^ ( ( h[ 8 w x
PB P pr
< pE H ` X < < ? ` h ` o y P `9 `4 ( 8 @- @ H u X & ` h h Pl x % @ 4 + ` ` { x ( pC 8 @ H X ` s h ` x ` ` ` @ i @ @ I ( 8 @ H P X ` ` h x @ 8 | s @ `g P ] 0 `K ( P 8 @> @ H p X @. ` h x @ ` @ ` ` ( 8 @ H X ` h h P@ x _ ` V p8 1 Q 1 0+ x ( Q 8 h @ G H $ X \ ` h A x F @ 9 ! 0z - `( `# y ( 8 @ H X ` ` h x p # !
h x h
z z
) ( 0 0 1 8 2 @ 3 H N P Q X R ` U h W p ^ o r t u w { ( 0 8 @ H P X
` h p x ! " # $ % & ' ( ( 0 * 8 + @ , H - P . X / ` 4 h 5 p 6 x 7 8 9 : ; < = > ? @ A B C D E F G H I J K L ( M 0 O 8 P @ R H S P T X V ` X h Y p Z x [ \ ] _ ` a b c d e f g i j k l m n p q s v ( x 0 y 8 | @ } H ~ P X ` h p x ( 0 8 @ H P X ` h p HHM
Htk H 5
%
@ %
h %ڿ
h %ҿ
h %ʿ
h %¿
h %
h %
h %
h p%
h `%
h P%
h
@%
h 0%
h %z
h
%r
h %j
h %b
h %Z
h %R
h %J
h %B
h %:
h %2
h %*
h p%"
h `%
h P%
h @%
h 0%
h %
h %
h %
h %
h %ھ
h! %Ҿ
h" %ʾ
h# %¾
h$ %
h% %
h& %
h' p%
h( `%
h) P%
h* @%
h+ 0%
h, %z
h- %r
h. %j
h/ %b
h0 %Z
h1 %R
h2 %J
h3 %B
h4 %:
h5 %2
h6 %*
h7 p%"
h8 `%
h9 P%
h: @%
h; 0%
h< %
h= %
h> %
h? %
h@ %ڽ
hA %ҽ
hB %ʽ
hC %½
hD %
hE %
hF %
hG p%
hH `%
hI P%
hJ @%
hK 0%
hL %z
hM %r
hN %j
hO %b
hP %Z
hQ %R
hR %J
hS %B
hT %:
hU %2
hV %*
hW p%"
hX `%
hY P%
hZ @%
h[ 0%
h\ %
h] %
h^ %
h_ %
h` %ڼ
ha %Ҽ
hb %ʼ
hc %¼
hd %
he %
hf %
hg p%
hh `%
hi P%
hj @%
hk 0%
hl %z
hm %r
hn %j
ho %b
hp %Z
hq %R
hr %J
hs %B
ht %:
hu %2
hv %*
hw p%"
hx `%
hy P%
hz @%
h{ 0%
h| %
h} %
h~ %
h %
h %ڻ
h %һ
h %ʻ
h %»
h %
h %
h %
h p%
h `%
h P%
h @%
h 0AWIAVIH5 AUIATUSHAP|H LHHEIHu(LLH5c HHi
H81qLHu9LLHIMLHH
H5I H81)LLHHtHM A u H&HM uHAZD[]A\A]A^A_AWIAVIH5 AUIATUSHAPH LHHHIHu(LLH5 HHl
H81
qLHu9LLHIMLHH
H5ԗ H81)LLHHtHM A u H)HM uHAZD[]A\A]A^A_AVIAUIHATUSDHt5H;i
HuE1tHLLVAHM u)H H|
AH8tE1[D]A\A]A^AVAUIATUQ8Hx?H
HuH
Ht #H9t H
H5 H8E1 L%r
Mt I$ H5 LIHtH
IHuLHtHIH A H
HLH xkA H
LLH xHA H
| LLH{ ix%E1H
o LLHk IxIHM H4ZL]A\A]A^AVIHAUIATUDSHH H IH@ u#H5
LLH5 H81> ML$(ID$ Mt
I LLIL9v#Hޱ
ILLH5ޕ H81AuNH9sIHl$RLIPMH* H1H117Y^yI $uL3E1H L[]A\A]A^UHe
H
SHE HD$H HD$HF
HD$0HR HD$8H6
HD$XHz HD$`H&
H$ H H$ H
H$ Hi H$ H
HD$A HD$ fD$( D$* HD$@ HD$H fD$P D$RHD$h& HD$p fD$x D$z HDŽ$ HDŽ$ fDŽ$ Ƅ$ HDŽ$ HDŽ$ fDŽ$ Ƅ$ H$ H5 H$ H6
H$ H H$ H
H$ HA H$( H$P HAH$p H H$x HAH$ H H$ HAH$H HDŽ$ > HDŽ$ fDŽ$ Ƅ$ HDŽ$ HDŽ$ fDŽ$ Ƅ$ HDŽ$0 HDŽ$8 fDŽ$@ Ƅ$B HDŽ$X HDŽ$` fDŽ$h Ƅ$j HDŽ$ $ HDŽ$ fDŽ$ Ƅ$ HDŽ$ H$ H H$ HA H(H$ H3 H H$ H$ HAH$8 Hq H$@ HAH$` Hv H$h HAH$ HDŽ$ fDŽ$ Ƅ$ HDŽ$ HDŽ$ fDŽ$ Ƅ$ HDŽ$ HDŽ$ fDŽ$ Ƅ$
HDŽ$ HDŽ$( fDŽ$0 Ƅ$2 HDŽ$H ! HDŽ$P fDŽ$X Ƅ$Z HDŽ$p HDŽ$x fDŽ$ Ƅ$ H$ Hz H$ HA H$ H H$ HA(H$ H
z H$ HA0H$ H H$ HA8H$( H H$0 HA@H$P H H$X HAHHDŽ$ " HDŽ$ fDŽ$ Ƅ$ HDŽ$ HDŽ$ fDŽ$ Ƅ$ HDŽ$ " HDŽ$ fDŽ$ Ƅ$ HDŽ$ # HDŽ$ fDŽ$ Ƅ$" HDŽ$8 HDŽ$@ fDŽ$H Ƅ$J HDŽ$` H$x Hx H$ HAPH$ Hh H$ HAXH$ H
x H$ HA`H$ H H$ HAhH$ H H$ HApHDŽ$h fDŽ$p Ƅ$r HDŽ$ " HDŽ$ fDŽ$ Ƅ$ HDŽ$ HDŽ$ fDŽ$ Ƅ$ HDŽ$ ' HDŽ$ fDŽ$ Ƅ$ HDŽ$ HDŽ$ fDŽ$ Ƅ$ HDŽ$( ! HDŽ$0 fDŽ$8 Ƅ$: H$@ Hv H$H HAxH$h H1v H$p H H$ Hs H$ H H$ Hu H$ H H$ H H$ H H$ H H$ H HDŽ$P " HDŽ$X fDŽ$` Ƅ$b HDŽ$x " HDŽ$ fDŽ$ Ƅ$ HDŽ$ $ HDŽ$ fDŽ$ Ƅ$ HDŽ$ , HDŽ$ fDŽ$ Ƅ$ HDŽ$ * HDŽ$ fDŽ$ Ƅ$ HDŽ$ - H$0 H] H$8 H H$X H? H$` H H$ H H$ H H$ H H$ H H$ HE H$ H HDŽ$ fDŽ$( Ƅ$* HDŽ$@ % HDŽ$H fDŽ$P Ƅ$R HDŽ$h HDŽ$p fDŽ$x Ƅ$z HDŽ$ HDŽ$ fDŽ$ Ƅ$ HDŽ$ $ HDŽ$ fDŽ$ Ƅ$ HDŽ$ HDŽ$ fDŽ$ Ƅ$ H$ HW H$ H H$ H H$( H H$H H[ H$P H H$p H H$x H H$ H H$ H H$ H H$ H HDŽ$ HDŽ$ fDŽ$ Ƅ$ HDŽ$0 HDŽ$8 fDŽ$@ Ƅ$B HDŽ$X HDŽ$` fDŽ$h Ƅ$j HDŽ$ HDŽ$ fDŽ$ Ƅ$ HDŽ$ ( HDŽ$ fDŽ$ Ƅ$ HDŽ$ % H$ H% H$ H H$ H H$ H H$8 HI H$@ H H$` H H$h H H$ H H$ H HDŽ$ fDŽ$ Ƅ$ HDŽ$ ! HDŽ$ fDŽ$ Ƅ$
HDŽ$ HDŽ$( fDŽ$0 Ƅ$2 HDŽ$H HDŽ$P fDŽ$X Ƅ$Z HDŽ$p ( HDŽ$x fDŽ$ Ƅ$ HDŽ$ , HDŽ$ fDŽ$ Ƅ$ H$ Ho H$ H( H$ H! H$ H0 H$ H H$ H8 H$( H H$0 H@ H$P HG H$X HH H$x H) H$ HP HDŽ$ ' HDŽ$ fDŽ$ Ƅ$ HDŽ$ ( HDŽ$ fDŽ$ Ƅ$ HDŽ$ # HDŽ$ fDŽ$ Ƅ$" HDŽ$8 HDŽ$@ fDŽ$H Ƅ$J HDŽ$` # HDŽ$h fDŽ$p Ƅ$r HDŽ$ H$ H H$ HX H$ HO H$ H` H$ H H$ Hh H$ H H$ Hp H$@ H H$H Hx HDŽ$ fDŽ$ Ƅ$ HDŽ$ ! HDŽ$ fDŽ$ Ƅ$ HDŽ$ HDŽ$ fDŽ$ Ƅ$ HDŽ$ HDŽ$ fDŽ$ Ƅ$ HDŽ$( HDŽ$0 fDŽ$8 Ƅ$: HDŽ$P HDŽ$X fDŽ$` Ƅ$b H$h H H$p H H$ H H$ H H$ H+ H$ H H$ H H$ H H$
H H$
H H$0
H H$8
H HDŽ$x HDŽ$ fDŽ$ Ƅ$ HDŽ$ HDŽ$ fDŽ$ Ƅ$ HDŽ$ > HDŽ$ fDŽ$ Ƅ$ HDŽ$ HDŽ$ fDŽ$
Ƅ$
HDŽ$
G HDŽ$
fDŽ$(
Ƅ$*
HDŽ$@
L H$X
H H$`
H H$
Hj H$
H H$
H H$
H H$
Hs H$
H H$
H H$ H HDŽ$H
fDŽ$P
Ƅ$R
HDŽ$h
HDŽ$p
fDŽ$x
Ƅ$z
HDŽ$
! HDŽ$
fDŽ$
Ƅ$
HDŽ$
HDŽ$
fDŽ$
Ƅ$
HDŽ$
HDŽ$
fDŽ$
Ƅ$
HDŽ$ HDŽ$ fDŽ$ Ƅ$ H$ H H$( H H$H H H$P H H$p H H$x H H$ H H$ H H$ HO H$ H H H$ HT H$ HDŽ$0 HDŽ$8 fDŽ$@ Ƅ$B HDŽ$X HDŽ$` fDŽ$h Ƅ$j HDŽ$ HDŽ$ fDŽ$ Ƅ$ HDŽ$ HDŽ$ fDŽ$ Ƅ$ HDŽ$ HDŽ$ fDŽ$ Ƅ$ HDŽ$ H$ HBH$8 H1 H$@ HBH$` H6g H$h HBH$ H H$ HB H$ H H$ HB(H$ HDŽ$ fDŽ$ Ƅ$
HDŽ$ HDŽ$( fDŽ$0 Ƅ$2 HDŽ$H HDŽ$P fDŽ$X Ƅ$Z HDŽ$p 0 HDŽ$x fDŽ$ Ƅ$ HDŽ$ HDŽ$ fDŽ$ Ƅ$ HDŽ$ & HDŽ$ fDŽ$ Ƅ$ H$ He H$ HB0H$
H H$
HB8H$(
H H$0
HB@H$P
HL H$X
HBHH$x
H H$
HBPH$
H H$
HBXHDŽ$ 5 HDŽ$ fDŽ$ Ƅ$ HDŽ$
HDŽ$
fDŽ$
Ƅ$"
HDŽ$8
HDŽ$@
fDŽ$H
Ƅ$J
HDŽ$`
HDŽ$h
fDŽ$p
Ƅ$r
HDŽ$
HDŽ$
fDŽ$
Ƅ$
HDŽ$
H$
HM H$
HB`H$
H H$
HBhH$ H H$ HBpH$@ H H$H HBxH$h H H$p H HDŽ$
fDŽ$
Ƅ$
HDŽ$
HDŽ$
fDŽ$
Ƅ$
HDŽ$ HDŽ$ fDŽ$ Ƅ$ HDŽ$( HDŽ$0 fDŽ$8 Ƅ$: HDŽ$P HDŽ$X fDŽ$` Ƅ$b HDŽ$x HDŽ$ fDŽ$ Ƅ$ H$ H H$ H H$ H H$ H H$ Hr H$ H H$ Ha H$ H H$0 H H$8 H H$X H] H$` HDŽ$ HDŽ$ fDŽ$ Ƅ$ HDŽ$ HDŽ$ fDŽ$ Ƅ$ HDŽ$ HDŽ$ fDŽ$ Ƅ$ HDŽ$ HDŽ$ fDŽ$( Ƅ$* HDŽ$@ HDŽ$H fDŽ$P Ƅ$R HDŽ$h H$ H H H$ H H$ H$ HBH$ H H$ HBH$ H H$ H(H$ H$( HDŽ$p fDŽ$x Ƅ$z HDŽ$ HDŽ$ fDŽ$ Ƅ$ HDŽ$ HDŽ$ fDŽ$ Ƅ$ HDŽ$ HDŽ$ fDŽ$ Ƅ$ HDŽ$ HDŽ$ fDŽ$ Ƅ$ HDŽ$0 HDŽ$8 fDŽ$@ Ƅ$B H$P HB H$p HP H$x HB(H$ H H$ HB0H$ H H$ HB8H$ HP H$ HB@H$ H H$ HBHHPH$H HZHHXHDŽ$X HDŽ$` fDŽ$h Ƅ$j HDŽ$ HDŽ$ fDŽ$ Ƅ$ HDŽ$ HDŽ$ fDŽ$ Ƅ$ HDŽ$ HDŽ$ fDŽ$ Ƅ$ HDŽ$ HDŽ$ fDŽ$ Ƅ$
HDŽ$ H$8 H H$@ H$h HBH$ HQL H$ HBH$ H H$ HBH$ H H$` H$ HDŽ$( fDŽ$0 Ƅ$2 HDŽ$H HDŽ$P fDŽ$X Ƅ$Z HDŽ$p HDŽ$x fDŽ$ Ƅ$ HDŽ$ HDŽ$ fDŽ$ Ƅ$ HDŽ$ ( HDŽ$ fDŽ$ Ƅ$ HDŽ$ HDŽ$ fDŽ$ Ƅ$ H$ HB(H$( H H$0 HB0H$P H] H$X HB8H$x H
H$ HB@H$ H H$ H$ HBPH$ H H$ Hà HDŽ$ HDŽ$ fDŽ$ Ƅ$" HDŽ$8 HDŽ$@ fDŽ$H Ƅ$J HDŽ$` HDŽ$h fDŽ$p Ƅ$r HDŽ$ 4 HDŽ$ fDŽ$ Ƅ$ HDŽ$
HDŽ$ fDŽ$ Ƅ$ HDŽ$
H$ HP@ H$ HBXH`H$ HrxH H$ H$H HBH$h H*2 H$p HBH$ H H$ HBH$@ HDŽ$ fDŽ$ Ƅ$ HDŽ$ 6 HDŽ$ fDŽ$ Ƅ$ HDŽ$( HDŽ$0 fDŽ$8 Ƅ$: HDŽ$P HDŽ$X fDŽ$` Ƅ$b HDŽ$x
HDŽ$ fDŽ$ Ƅ$ HDŽ$
HDŽ$ fDŽ$ Ƅ$ H$ H H$ HB H$ H H$ HB(H$ H H$ HB0H$0 HD H$8 HB8H$X HP H$` HB@H$ H] H$ HBHHDŽ$ HDŽ$ fDŽ$ Ƅ$ HDŽ$ HDŽ$ fDŽ$ Ƅ$ HDŽ$ HDŽ$ fDŽ$( Ƅ$* HDŽ$@ HDŽ$H fDŽ$P Ƅ$R HDŽ$h HDŽ$p fDŽ$x Ƅ$z HDŽ$ H$ H H$ HBPH$ HA H$ HBXH$ H H$ HB`H$ H8 H$( H$P HBpH$H H HDŽ$ fDŽ$ Ƅ$ HDŽ$ % HDŽ$ fDŽ$ Ƅ$ HDŽ$ 3 HDŽ$ fDŽ$ Ƅ$ HDŽ$ HDŽ$ fDŽ$ Ƅ$ HDŽ$0 HDŽ$8 fDŽ$@ Ƅ$B HDŽ$X HDŽ$` fDŽ$h Ƅ$j H$p H H$x H$ H H$ H H$ H$ H H H$ H H H$ H$@ HBH$ Hƨ H$ H H$8 HDŽ$ HDŽ$ fDŽ$ Ƅ$ HDŽ$ HDŽ$ fDŽ$ Ƅ$ HDŽ$ HDŽ$ fDŽ$ Ƅ$ HDŽ$ HDŽ$ fDŽ$ Ƅ$
HDŽ$
HDŽ$( fDŽ$0 Ƅ$2 HDŽ$H
H$` Hh H$h HBH$ H5 H$ HBH$ H6 H$ HB H$ H H$ HB(H$ H H$ HB0HDŽ$P fDŽ$X Ƅ$Z HDŽ$p a HDŽ$x fDŽ$ Ƅ$ HDŽ$ HDŽ$ fDŽ$ Ƅ$ HDŽ$ HDŽ$ fDŽ$ Ƅ$ HDŽ$ HDŽ$ fDŽ$ Ƅ$ HDŽ$ HDŽ$ fDŽ$ Ƅ$" H$( H H$0 HB8H$P H^ H$X HB@H$x H H$ HBHH$ HH H$ HBPH$ H H$ HBXH$ H H$ HB`HDŽ$8 HDŽ$@ fDŽ$H Ƅ$J HDŽ$` HDŽ$h fDŽ$p Ƅ$r HDŽ$ HDŽ$ fDŽ$ Ƅ$ HDŽ$
HDŽ$ fDŽ$ Ƅ$ HDŽ$ HDŽ$ fDŽ$ Ƅ$ HDŽ$ H$ H! H$ HBhH$@ H H$H H$p HBxH$ H H$ H H$ HS H$h H H$ HDŽ$ fDŽ$ Ƅ$ HDŽ$( HDŽ$0 fDŽ$8 Ƅ$: HDŽ$P HDŽ$X fDŽ$` Ƅ$b HDŽ$x HDŽ$ fDŽ$ Ƅ$ HDŽ$
HDŽ$ fDŽ$ Ƅ$ HDŽ$ HDŽ$ fDŽ$ Ƅ$ H$ H H$ HP H$ H H$0 Hk H$8 H H$X HG H$` H H$ Hv H$ H H$ HI H$ H H$ Hư HDŽ$ HDŽ$ fDŽ$ Ƅ$ HDŽ$ HDŽ$ fDŽ$( Ƅ$* HDŽ$@ HDŽ$H fDŽ$P Ƅ$R HDŽ$h HDŽ$p fDŽ$x Ƅ$z HDŽ$ HDŽ$ fDŽ$ Ƅ$ HDŽ$ H$ H H$ H$ H H$ H H$( H H$H H H$P H H$p H5 H$x H H$ HǠ HDŽ$ fDŽ$ Ƅ$ HDŽ$ HDŽ$ fDŽ$ Ƅ$ HDŽ$ HDŽ$ fDŽ$ Ƅ$ HDŽ$0 HDŽ$8 fDŽ$@ Ƅ$B HDŽ$X HDŽ$` fDŽ$h Ƅ$j HDŽ$ HDŽ$ fDŽ$ Ƅ$ H$ H6 H$ H$ H H$ H H$ H H$ H H$ H H H$8 H% H$@ H$h HBH$ H H$` HDŽ$
HDŽ$ fDŽ$ Ƅ$ HDŽ$
HDŽ$ fDŽ$ Ƅ$ HDŽ$ { HDŽ$ fDŽ$ Ƅ$
HDŽ$ HDŽ$( fDŽ$0 Ƅ$2 HDŽ$H HDŽ$P fDŽ$X Ƅ$Z HDŽ$p H$ H H$ H$ HBH$ Hʯ H$ HB H$ H H$ HB(H$( H H$ H( H$0 HDŽ$x fDŽ$ Ƅ$ HDŽ$
HDŽ$ fDŽ$ Ƅ$ HDŽ$
HDŽ$ fDŽ$ Ƅ$ HDŽ$ u HDŽ$ fDŽ$ Ƅ$ HDŽ$ HDŽ$ fDŽ$ Ƅ$" HDŽ$8 HDŽ$@ fDŽ$H Ƅ$J H$X HB8H$x Hr H$ HB@H$ H H$ HBHH$ Hc H$ HBPH$ HQ H$ H$ HB`H$P Hh H$ H` HDŽ$` HDŽ$h fDŽ$p Ƅ$r HDŽ$ ! HDŽ$ fDŽ$ Ƅ$ HDŽ$
HDŽ$ fDŽ$ Ƅ$ HDŽ$ HDŽ$ fDŽ$ Ƅ$ HDŽ$ HDŽ$ fDŽ$ Ƅ$ HDŽ$( H$@ H H$H HBhH$h H H$p HBpH$ H H$ HBxH$ H H$ H H$ H H$ H HDŽ$0 fDŽ$8 Ƅ$: HDŽ$P n HDŽ$X fDŽ$` Ƅ$b HDŽ$x HDŽ$ fDŽ$ Ƅ$ HDŽ$ HDŽ$ fDŽ$ Ƅ$ HDŽ$ HDŽ$ fDŽ$ Ƅ$ HDŽ$ HDŽ$ fDŽ$ Ƅ$ H$ H} H$ H H$0 Hb H$8 H H$X H> H$` H H$ H H$ H H$ H/ H$ H H$ H H$ H HDŽ$ HDŽ$ fDŽ$( Ƅ$* HDŽ$@ HDŽ$H fDŽ$P Ƅ$R HDŽ$h HDŽ$p fDŽ$x Ƅ$z HDŽ$ HDŽ$ fDŽ$ Ƅ$ HDŽ$ HDŽ$ fDŽ$ Ƅ$ HDŽ$ H$ H H$ H H$ H H$( H H$H H H$P H H$p H9 H$x H H$ H H$ H HDŽ$ fDŽ$ Ƅ$ HDŽ$
HDŽ$ fDŽ$ Ƅ$ HDŽ$0 HDŽ$8 fDŽ$@ Ƅ$B HDŽ$X HDŽ$` fDŽ$h Ƅ$j HDŽ$ HDŽ$ fDŽ$ Ƅ$ HDŽ$ HDŽ$ fDŽ$ Ƅ$ H$ He H$ H H$ Hg H$ H H$ H H$ H H$8 H H$@ H$h H H$ He H$ H H$` H HDŽ$ HDŽ$ fDŽ$ Ƅ$ HDŽ$ HDŽ$ fDŽ$ Ƅ$
HDŽ$ HDŽ$( fDŽ$0 Ƅ$2 HDŽ$H HDŽ$P fDŽ$X Ƅ$Z HDŽ$p HDŽ$x fDŽ$ Ƅ$ HDŽ$ H$ H H$ H H$ H H$ H H( H$ ! H H$! H$0! HBH$P! H H$(! H$X! HDŽ$ fDŽ$ Ƅ$ HDŽ$ HDŽ$ fDŽ$ Ƅ$ HDŽ$ HDŽ$ fDŽ$ Ƅ$ HDŽ$! HDŽ$! fDŽ$ ! Ƅ$"! HDŽ$8! HDŽ$@! fDŽ$H! Ƅ$J! HDŽ$`! HDŽ$h! fDŽ$p! Ƅ$r! H$! HBH$! H H$! HB H$! HY H$! HB(H$! H H$! HB0H$" H H$ " HB8H$@" H H$H" HB@H$x! H HDŽ$! HDŽ$! fDŽ$! Ƅ$! HDŽ$!
HDŽ$! fDŽ$! Ƅ$! HDŽ$! HDŽ$! fDŽ$! Ƅ$! HDŽ$ " HDŽ$" fDŽ$" Ƅ$" HDŽ$(" HDŽ$0" fDŽ$8" Ƅ$:" HDŽ$P" H$h" H H$p" HBHH$" H H$" HBPH$" H H$" HBXH$" H H$" HB`H$# HY H$# HBhHDŽ$X" fDŽ$`" Ƅ$b" HDŽ$x" T HDŽ$" fDŽ$" Ƅ$" HDŽ$" HDŽ$" fDŽ$" Ƅ$" HDŽ$" HDŽ$" fDŽ$" Ƅ$" HDŽ$" HDŽ$" fDŽ$ # Ƅ$# HDŽ$# HDŽ$ # fDŽ$(# Ƅ$*# H$0# H H$8# H$`# HBxH$# H\ H$# H H$# H H$# H H$# H H$# H$ $ H H$X# HƸ H$# HǨ HDŽ$@# HDŽ$H# fDŽ$P# Ƅ$R# HDŽ$h# HDŽ$p# fDŽ$x# Ƅ$z# HDŽ$# HDŽ$# fDŽ$# Ƅ$# HDŽ$# HDŽ$# fDŽ$# Ƅ$# HDŽ$# HDŽ$# fDŽ$# Ƅ$# HDŽ$$ H$ $ H H$($ H H$H$ HO H$P$ H$x$ H H$$ Hѥ H$$ H H H$$ H H$p$ Hè H$$ HDŽ$$ fDŽ$$ Ƅ$$ HDŽ$0$ p HDŽ$8$ fDŽ$@$ Ƅ$B$ HDŽ$X$
HDŽ$`$ fDŽ$h$ Ƅ$j$ HDŽ$$
HDŽ$$ fDŽ$$ Ƅ$$ HDŽ$$ HDŽ$$ fDŽ$$ Ƅ$$ HDŽ$$
HDŽ$$ fDŽ$$ Ƅ$$ H$$ HBH$% H H$% HBH$8% H H$@% HBH$`% H4 H$h% HB H$% Hy H$% HB(H$% H H$$ H$% HDŽ$$
HDŽ$ % fDŽ$% Ƅ$
% HDŽ$ % HDŽ$(% fDŽ$0% Ƅ$2% HDŽ$H% HDŽ$P% fDŽ$X% Ƅ$Z% HDŽ$p% HDŽ$x% fDŽ$% Ƅ$% HDŽ$% HDŽ$% fDŽ$% Ƅ$% HDŽ$% H$% HB8H$ & HU H$& HB@H$(& H H$0& HBHH$P& H H$X& HBPH$x& H\ H$& HBXH$% H HDŽ$% fDŽ$% Ƅ$% HDŽ$% HDŽ$% fDŽ$% Ƅ$% HDŽ$& # HDŽ$& fDŽ$ & Ƅ$"& HDŽ$8& HDŽ$@& fDŽ$H& Ƅ$J& HDŽ$`& HDŽ$h& fDŽ$p& Ƅ$r& HDŽ$&
HDŽ$& fDŽ$& Ƅ$& H$& Hʺ H$& HB`H$& H H$& H$& HBpH$' Hd H$ ' H$H' H H$h' H H$p' H H$& HpH$@' HDŽ$& HDŽ$& fDŽ$& Ƅ$& HDŽ$& HDŽ$& fDŽ$& Ƅ$& HDŽ$ ' HDŽ$' fDŽ$' Ƅ$' HDŽ$(' HDŽ$0' fDŽ$8' Ƅ$:' HDŽ$P' HDŽ$X' fDŽ$`' Ƅ$b' HDŽ$x' Q H$' HV H$' H$' H H$' Hq H$' H H¨ HH$( H H$( H$8( HBH$' HH$0( HDŽ$' fDŽ$' Ƅ$' HDŽ$' HDŽ$' fDŽ$' Ƅ$' HDŽ$' HDŽ$' fDŽ$' Ƅ$' HDŽ$' HDŽ$' fDŽ$ ( Ƅ$( HDŽ$( HDŽ$ ( fDŽ$(( Ƅ$*( HDŽ$@( HDŽ$H( fDŽ$P( Ƅ$R( H$X( H H$`( HBH$( Hh H$( H$( HB H$( H@ H$( HB(H$( HG H$ ) H$() HB8H$( HxH$ ) HxHDŽ$h( HDŽ$p( fDŽ$x( Ƅ$z( HDŽ$( HDŽ$( fDŽ$( Ƅ$( HDŽ$( HDŽ$( fDŽ$( Ƅ$( HDŽ$( HDŽ$( fDŽ$( Ƅ$( HDŽ$) HDŽ$) fDŽ$) Ƅ$) HDŽ$0) H$H) Hna H$P) HB@H$p) H H$x) HBHH$) Hշ H$) H$) HBXH$) H5 H$) HB`H$) HxHDŽ$8) fDŽ$@) Ƅ$B) HDŽ$X)
HDŽ$`) fDŽ$h) Ƅ$j) HDŽ$)
HDŽ$) fDŽ$) Ƅ$) HDŽ$) HDŽ$) fDŽ$) Ƅ$) HDŽ$) HDŽ$) fDŽ$) Ƅ$) HDŽ$) HDŽ$ * fDŽ$* Ƅ$
* H$* H H$* H$@* HBpHxH$`* Hw H$h* H$* HBH$* HS H$* HBH$* H1 H$8* Hø H$* H$* HDŽ$ * HDŽ$(* fDŽ$0* Ƅ$2* HDŽ$H* HDŽ$P* fDŽ$X* Ƅ$Z* HDŽ$p* HDŽ$x* fDŽ$* Ƅ$* HDŽ$* HDŽ$* fDŽ$* Ƅ$* HDŽ$* HDŽ$* fDŽ$* Ƅ$* HDŽ$*
H$+ HB H$(+ HD H$0+ HB(H$P+ H> H$X+ H$+ HB8H$+ H4 H$+ HB@H$ + H H$x+ H HDŽ$* fDŽ$* Ƅ$* HDŽ$+
HDŽ$+ fDŽ$ + Ƅ$"+ HDŽ$8+ p
HDŽ$@+ fDŽ$H+ Ƅ$J+ HDŽ$`+ HDŽ$h+ fDŽ$p+ Ƅ$r+ HDŽ$+ HDŽ$+ fDŽ$+ Ƅ$+ HDŽ$+ HDŽ$+ fDŽ$+ Ƅ$+ H$+ H{ H$+ HBHH$+ H H$+ H$ , HBXH$@, Hs H$H, HB`H$h, H3 H$p, HBhH$, H H$, HBpH$, H HDŽ$+ HDŽ$+ fDŽ$+ Ƅ$+ HDŽ$ , HDŽ$, fDŽ$, Ƅ$, HDŽ$(, HDŽ$0, fDŽ$8, Ƅ$:, HDŽ$P, HDŽ$X, fDŽ$`, Ƅ$b, HDŽ$x, ' HDŽ$, fDŽ$, Ƅ$, HDŽ$, " H$, H& H$, HBxH$, Hc H$, H H$- H H$- H H$0- H H$8- H H$X- H H$`- H HDŽ$, fDŽ$, Ƅ$, HDŽ$,
HDŽ$, fDŽ$, Ƅ$, HDŽ$, HDŽ$, fDŽ$ - Ƅ$- HDŽ$- HDŽ$ - fDŽ$(- Ƅ$*- HDŽ$@- HDŽ$H- fDŽ$P- Ƅ$R- HDŽ$h- HDŽ$p- fDŽ$x- Ƅ$z- H$- H; H$- H H$- Hu H$- H$- H H$- Hק H$ . H H H$ . Hz H$(. H$P. HBH$- Hð H$H. HDŽ$- HDŽ$- fDŽ$- Ƅ$- HDŽ$- HDŽ$- fDŽ$- Ƅ$- HDŽ$- HDŽ$- fDŽ$- Ƅ$- HDŽ$. HDŽ$. fDŽ$. Ƅ$. HDŽ$0. HDŽ$8. fDŽ$@. Ƅ$B. HDŽ$X. H$p. H H$x. HBH$. HG H$. H$. HB H$. H܁ H$. HB(H$/ H H$/ HB0H$. H HDŽ$`. fDŽ$h. Ƅ$j. HDŽ$. HDŽ$. fDŽ$. Ƅ$. HDŽ$. HDŽ$. fDŽ$. Ƅ$. HDŽ$. HDŽ$. fDŽ$. Ƅ$. HDŽ$. HDŽ$ / fDŽ$/ Ƅ$
/ HDŽ$ / HDŽ$(/ fDŽ$0/ Ƅ$2/ H$8/ H H$@/ H$h/ HB@H$/ Hv H$/ HBHH$/ Hy H$/ HBPH$/ H H$/ HBXH$ 0 HD H$`/ H H$0 HDŽ$H/ HDŽ$P/ fDŽ$X/ Ƅ$Z/ HDŽ$p/ HDŽ$x/ fDŽ$/ Ƅ$/ HDŽ$/ HDŽ$/ fDŽ$/ Ƅ$/ HDŽ$/ HDŽ$/ fDŽ$/ Ƅ$/ HDŽ$/ HDŽ$/ fDŽ$/ Ƅ$/ HDŽ$0 H$00 HBhH$P0 H
H$X0 HBpH$x0 H( H$0 HBxH$0 H- H$0 H H$0 H H$0 H H$(0 Hǰ HDŽ$0 fDŽ$ 0 Ƅ$"0 HDŽ$80 HDŽ$@0 fDŽ$H0 Ƅ$J0 HDŽ$`0
HDŽ$h0 fDŽ$p0 Ƅ$r0 HDŽ$0 # HDŽ$0 fDŽ$0 Ƅ$0 HDŽ$0 HDŽ$0 fDŽ$0 Ƅ$0 HDŽ$0 HDŽ$0 fDŽ$0 Ƅ$0 H$0 Hƫ H$0 H H$1 H H$ 1 H$H1 H H$h1 H H$p1 H H$1 H8 H$1 H H$1 H7 H$1 H H H$@1 HÈ HDŽ$ 1 HDŽ$1 fDŽ$1 Ƅ$1 HDŽ$(1 HDŽ$01 fDŽ$81 Ƅ$:1 HDŽ$P1 HDŽ$X1 fDŽ$`1 Ƅ$b1 HDŽ$x1 HDŽ$1 fDŽ$1 Ƅ$1 HDŽ$1 HDŽ$1 fDŽ$1 Ƅ$1 HDŽ$1 H$1 H/ H$1 H$2 HBH$02 H7 H$82 HBH$X2 Hbm H$`2 HBH$2 H/ H$2 H$2 HDŽ$1 fDŽ$1 Ƅ$1 HDŽ$1 HDŽ$1 fDŽ$ 2 Ƅ$2 HDŽ$2 HDŽ$ 2 fDŽ$(2 Ƅ$*2 HDŽ$@2 HDŽ$H2 fDŽ$P2 Ƅ$R2 HDŽ$h2 q HDŽ$p2 fDŽ$x2 Ƅ$z2 HDŽ$2 HDŽ$2 fDŽ$2 Ƅ$2 H$2 HB(H$2 H H$2 HB0H$2 H H$ 3 H$(3 HB@H$H3 Hb H$P3 HBHH$p3 H H$2 HxH$ 3 HH$x3 HDŽ$2 HDŽ$2 fDŽ$2 Ƅ$2 HDŽ$2 v HDŽ$2 fDŽ$2 Ƅ$2 HDŽ$3 HDŽ$3 fDŽ$3 Ƅ$3 HDŽ$03 HDŽ$83 fDŽ$@3 Ƅ$B3 HDŽ$X3 ( HDŽ$`3 fDŽ$h3 Ƅ$j3 HDŽ$3 H$3 HBXH$3 H: H$3 H$3 HBhH$4 H7 H$4 HBpHxH$84 H H$3 Hǰ H$3 Hø H$@4 HDŽ$3 fDŽ$3 Ƅ$3 HDŽ$3 HDŽ$3 fDŽ$3 Ƅ$3 HDŽ$3 HDŽ$3 fDŽ$3 Ƅ$3 HDŽ$3 HDŽ$ 4 fDŽ$4 Ƅ$
4 HDŽ$ 4 HDŽ$(4 fDŽ$04 Ƅ$24 HDŽ$H4 HDŽ$P4 fDŽ$X4 Ƅ$Z4 H$h4 HBH$4 HGY H$4 HBH$4 H, H$4 HBH$4 H H$4 H$5 HB(H$(5 Hg H$05 HB0H$`4 H$ 5 H HDŽ$p4 HDŽ$x4 fDŽ$4 Ƅ$4 HDŽ$4 HDŽ$4 fDŽ$4 Ƅ$4 HDŽ$4 HDŽ$4 fDŽ$4 Ƅ$4 HDŽ$4 HDŽ$4 fDŽ$4 Ƅ$4 HDŽ$5 HDŽ$5 fDŽ$ 5 Ƅ$"5 HDŽ$85 H$P5 HQ H$X5 HB8H$x5 HӠ H$5 H$5 HBHH$5 H H$5 HBPH$5 H- H$5 HBXH$5 HƠ HDŽ$@5 fDŽ$H5 Ƅ$J5 HDŽ$`5 HDŽ$h5 fDŽ$p5 Ƅ$r5 HDŽ$5 HDŽ$5 fDŽ$5 Ƅ$5 HDŽ$5 HDŽ$5 fDŽ$5 Ƅ$5 HDŽ$5
HDŽ$5 fDŽ$5 Ƅ$5 HDŽ$ 6 HDŽ$6 fDŽ$6 Ƅ$6 H$6 Ht H$ 6 HB`H$@6 H0 H$H6 HBhH$h6 H
H$p6 HBpH$6 H H$6 HBxH$6 H H$6 H H$6 HN H$6 HDŽ$(6 HDŽ$06 fDŽ$86 Ƅ$:6 HDŽ$P6 HDŽ$X6 fDŽ$`6 Ƅ$b6 HDŽ$x6 HDŽ$6 fDŽ$6 Ƅ$6 HDŽ$6
HDŽ$6 fDŽ$6 Ƅ$6 HDŽ$6 HDŽ$6 fDŽ$6 Ƅ$6 HDŽ$6 H$7 H H$07 Hb H$87 H H$X7 H[ H$`7 H$7 H H° H$7 H H$7 HhH$7 HhH$7 HDŽ$6 fDŽ$ 7 Ƅ$7 HDŽ$7 HDŽ$ 7 fDŽ$(7 Ƅ$*7 HDŽ$@7 HDŽ$H7 fDŽ$P7 Ƅ$R7 HDŽ$h7 HDŽ$p7 fDŽ$x7 Ƅ$z7 HDŽ$7 HDŽ$7 fDŽ$7 Ƅ$7 HDŽ$7 HDŽ$7 fDŽ$7 Ƅ$7 H$7 HBH$7 Hϙ H$ 8 HBH$ 8 H̟ H$(8 H$P8 HB H$p8 HP H$x8 HB(H$8 H H$7 H$H8 HpH$8 HDŽ$7 HDŽ$7 fDŽ$7 Ƅ$7 HDŽ$8
HDŽ$8 fDŽ$8 Ƅ$8 HDŽ$08 HDŽ$88 fDŽ$@8 Ƅ$B8 HDŽ$X8 HDŽ$`8 fDŽ$h8 Ƅ$j8 HDŽ$8 w HDŽ$8 fDŽ$8 Ƅ$8 HDŽ$8 H$8 HB8H$8 H H$8 H$9 HBHH$89 H H$@9 HBPH$`9 H H$8 HƘ H$9 HǠ H$h9 HDŽ$8 fDŽ$8 Ƅ$8 HDŽ$8 HDŽ$8 fDŽ$8 Ƅ$8 HDŽ$8
HDŽ$ 9 fDŽ$9 Ƅ$
9 HDŽ$ 9
HDŽ$(9 fDŽ$09 Ƅ$29 HDŽ$H9 ? HDŽ$P9 fDŽ$X9 Ƅ$Z9 HDŽ$p9 HDŽ$x9 fDŽ$9 Ƅ$9 H$9 HB`HhH$9 HV H$9 H$9 HBH$ : H#I H$: HBH$(: HÜ H$0: HBH$P: H H$9 Hà H$9 H$X: HDŽ$9 HDŽ$9 fDŽ$9 Ƅ$9 HDŽ$9 HDŽ$9 fDŽ$9 Ƅ$9 HDŽ$9 HDŽ$9 fDŽ$9 Ƅ$9 HDŽ$: HDŽ$: fDŽ$ : Ƅ$": HDŽ$8: HDŽ$@: fDŽ$H: Ƅ$J: HDŽ$`: H$: HB(H$: H H$: HB0H$: Hp H$: HB8H$: HP H$: HB@H$; H, H$ ; HBHH$x: HDŽ$h: fDŽ$p: Ƅ$r: HDŽ$: HDŽ$: fDŽ$: Ƅ$: HDŽ$:
HDŽ$: fDŽ$: Ƅ$: HDŽ$: HDŽ$: fDŽ$: Ƅ$: HDŽ$ ; HDŽ$; fDŽ$; Ƅ$; HDŽ$(; HDŽ$0; fDŽ$8; Ƅ$:; H$@; H H$H; HBPH$h; H H$p; HBXH$; H H$; H$; HBhH$; H; H$; HBpH$< H H$; H$< HDŽ$P; HDŽ$X; fDŽ$`; Ƅ$b; HDŽ$x; HDŽ$; fDŽ$; Ƅ$; HDŽ$; HDŽ$; fDŽ$; Ƅ$; HDŽ$; HDŽ$; fDŽ$; Ƅ$; HDŽ$; A
HDŽ$; fDŽ$ < Ƅ$< HDŽ$< H$8< H H$X< HQ6 H$`< H H$< H H$< H$< H H$< H* H$< H H¨ HxH$0< H H H$< H HDŽ$ < fDŽ$(< Ƅ$*< HDŽ$@< HDŽ$H< fDŽ$P< Ƅ$R< HDŽ$h< 6 HDŽ$p< fDŽ$x< Ƅ$z< HDŽ$< HDŽ$< fDŽ$< Ƅ$< HDŽ$< HDŽ$< fDŽ$< Ƅ$< HDŽ$< HDŽ$< fDŽ$< Ƅ$< H$< H H$ = H$(= HBH$H= H ! H$P= HBH$p= H H$x= H$= HB H$= H H$= HB(H$ = H$= H HDŽ$= HDŽ$= fDŽ$= Ƅ$= HDŽ$0= HDŽ$8= fDŽ$@= Ƅ$B= HDŽ$X= z HDŽ$`= fDŽ$h= Ƅ$j= HDŽ$= HDŽ$= fDŽ$= Ƅ$= HDŽ$= HDŽ$= fDŽ$= Ƅ$= HDŽ$= H$= H H$= H$> HB8H$8> Hˈ H$@> HB@H$`> H` H$h> HBHH$> H H$> HBPH$> H HDŽ$= fDŽ$= Ƅ$= HDŽ$= HDŽ$ > fDŽ$> Ƅ$
> HDŽ$ > HDŽ$(> fDŽ$0> Ƅ$2> HDŽ$H> HDŽ$P> fDŽ$X> Ƅ$Z> HDŽ$p> ! HDŽ$x> fDŽ$> Ƅ$> HDŽ$> HDŽ$> fDŽ$> Ƅ$> H$> H H$> HBXH$> H H$> HB`H$ ? H H$? HBhH$(? H H$0? HBpH$P? H H$X? HBxH$x? H[ H$? H HDŽ$> HDŽ$> fDŽ$> Ƅ$> HDŽ$> HDŽ$> fDŽ$> Ƅ$> HDŽ$? HDŽ$? fDŽ$ ? Ƅ$"? HDŽ$8? HDŽ$@? fDŽ$H? Ƅ$J? HDŽ$`? HDŽ$h? fDŽ$p? Ƅ$r? HDŽ$? H$? H H$? H H$? Hz H$? H H$? H̏ H$? H H$@ H H$ @ H H$@@ H H$H@ H HDŽ$? fDŽ$? Ƅ$? HDŽ$? HDŽ$? fDŽ$? Ƅ$? HDŽ$? HDŽ$? fDŽ$? Ƅ$? HDŽ$ @ HDŽ$@ fDŽ$@ Ƅ$@ HDŽ$(@ HDŽ$0@ fDŽ$8@ Ƅ$:@ HDŽ$P@ S HDŽ$X@ fDŽ$`@ Ƅ$b@ H$h@ H H$p@ H$@ H H$@ H H$@ H H$@ HŐ H$@ H H$A H H$A H H$0A H H$8A H H$@ HǸ HDŽ$x@ HDŽ$@ fDŽ$@ Ƅ$@ HDŽ$@ HDŽ$@ fDŽ$@ Ƅ$@ HDŽ$@
HDŽ$@ fDŽ$@ Ƅ$@ HDŽ$@ HDŽ$@ fDŽ$ A Ƅ$A HDŽ$A HDŽ$ A fDŽ$(A Ƅ$*A HDŽ$@A H$XA Hō H$`A H H$A H H$A H H$A HJ H$A H H$A H H$A H$ B H H$A Hð HDŽ$HA fDŽ$PA Ƅ$RA HDŽ$hA HDŽ$pA fDŽ$xA Ƅ$zA HDŽ$A HDŽ$A fDŽ$A Ƅ$A HDŽ$A HDŽ$A fDŽ$A Ƅ$A HDŽ$A HDŽ$A fDŽ$A Ƅ$A HDŽ$B HDŽ$B fDŽ$B Ƅ$B H$ B H H$(B H H$HB H H$PB H H$pB H H$xB H H H$B H7 H$B H$B HBH$B Ht H$B HBHDŽ$0B HDŽ$8B fDŽ$@B Ƅ$BB HDŽ$XB HDŽ$`B fDŽ$hB Ƅ$jB HDŽ$B HDŽ$B fDŽ$B Ƅ$B HDŽ$B HDŽ$B fDŽ$B Ƅ$B H$B HDŽ$B HDŽ$B fDŽ$B Ƅ$B HDŽ$B
H$C Hu H$C H$@C HB H$`C H H$hC HB(H$C H2 H$C H$C HB8HDŽ$ C fDŽ$C Ƅ$
C HDŽ$ C HDŽ$(C fDŽ$0C Ƅ$2C H$8C HDŽ$HC HDŽ$PC fDŽ$XC Ƅ$ZC HDŽ$pC k HDŽ$xC fDŽ$C Ƅ$C HDŽ$C HDŽ$C fDŽ$C Ƅ$C H$C HDŽ$C HDŽ$C fDŽ$C Ƅ$C H$C H H$C HB@H$ D Hg H$D H$0D HBPH$PD H~ H$XD HBXH$xD Hq H$D HB`H$D Hԋ H$D HBhHDŽ$C HDŽ$C fDŽ$C Ƅ$C HDŽ$D HDŽ$D fDŽ$ D Ƅ$"D H$(D HDŽ$8D HDŽ$@D fDŽ$HD Ƅ$JD HDŽ$`D
HDŽ$hD fDŽ$pD Ƅ$rD HDŽ$D
HDŽ$D fDŽ$D Ƅ$D HDŽ$D H$D Hg H$D HBpH$D H H$D HBxH$E Hp H$ E H H$@E HA H$HE H$pE H H$hE H\$HDŽ$D fDŽ$D Ƅ$D HDŽ$D / HDŽ$D fDŽ$D Ƅ$D HDŽ$ E HDŽ$E fDŽ$E Ƅ$E HDŽ$(E HDŽ$0E fDŽ$8E Ƅ$:E HDŽ$PE HDŽ$XE fDŽ$`E Ƅ$bE HDŽ$xE HDŽ$E fDŽ$E Ƅ$E H$E HFp H$E HDŽ$E HDŽ$E fDŽ$E Ƅ$E HDŽ$E HDŽ$E HDŽ$E HDŽ$E fDŽ$E Ƅ$E H+HteC
C!H{Hst5{" t /HE 0HSHHt
1覀HE ۀHE HzHE H} HtH(HE 1[]ATE1UQH53\
{HtC1HHdIHu }HuH7
H5 H8\{HM uHzLZ]A\AWAVAUATIUSHH(LwH7
I9 t
ig H* I tLL<~IHuEL*|y H H@ u1L MtH D$ D$ E1 D$ E1Hm~HtBH8Ht:HIT$LH|$+}H|$HH {H|$Huy|$ Mt HSHLAIHu:Lyy0LM H47
IVLH5 H81~ H HG6
H9EusH;]umL}IHM uHyHt$LH HD$ H\$a IIu`LxVH HuxMtIuLx뀺 Ht$HHD$ H? HM Iu
HxE1H(L[]A\A]A^A_AVIAUATUVzH H5w[
HI HH H5U
H IHuHM u>Hx4H;5
L;%h5
u L;%5
uL{tMtV1I $uLwHtAHM uHwIM uLwzHtyYL]1A\1A]A^k yZL]A\A]A^AWAVAUATUSH H_
Ht)1H9` Hz4
H5! H8w` HH=q_
|HM
HU H H=: vHvM
HU H H=: vH_M
HU H H=_
H5p: H6M
v~U \}Ld$8A HHJ: L1 w1A u
0 v 8u HHuD$@ 11D$D LL$@.uBtIHl$H 1LH! HLy< Sw1 HuT r@ v뷹 AHHu1xHUL
HT 1H=!8 vuH?L
HT 1H=8 8{H)L
HT fyAv A 1 W4wHZ
Ht wHZ
Htǂ wH{Z
Ht vHjZ
Ht1wH_Z
Hw vHMZ
H]11H=8 zH5Z
H=HvH$Z
H$=A
utHHS 4HHS
H5S
H=\
}wyAv A
H5: HwHtH=hQ
0 H[
HtJ0Hf\
H5x: HryAv A
H=fM
y0 HZ[
HuAv A q
H= M
K0 H$[
HtH=L
30 H[
HtH=U
0 HtH=J
0 HZ
HtH=K
/ HZ
HuH=L
/ HZ
HYH=oU
/ HDH=J
/ HVZ
H(H=fJ
/ H2Z
H H5S
1fyHWX
HuAv A ^ H5R
11yH*X
HtH5nP
1yHX
HtH5I
1xHW
HtH5(M
1xHW
HjHY
H5O
1xHW
H@H53P
1xHW
H H5U
1dxHW
HH5U
1AxHzW
HH5ZT
1 xH_W
HHV
H5 N
1wH=W
HHV
H5NN
1wHW
H`L%.
1LLLwHV
H4HWX
H5H
1twHV
H
H=V
H5&V
1JwHV
HH5{J
1'wHV
HH5`J
1wH}V
HH5-J
1vHbV
HwH5J
1vHGV
HTH5P
1vH,V
H1H5I
1xvHV
HH5P
1UvHU
HH5P
12vHU
HH5P
1vHU
HH5F
1uHU
HH5F
1uHU
H_H5F
1uHoU
H
A
E111H
8A
A Qh 5L
5J
RRPRR1Q qHPHQ
HH@
E111H@
A Rh 5 L
5J
PP5@Q
PPR1pHPHSQ
HHH[@
H H
.
H6R
H_T fHnfHnHV H7@
flH<-
H
A
)@
H4 H=>.
Hq L&-
H9 HD HPH&
H5 Av A H81nH=Q
tKH=?
t tH
+ DDH=/ z H=eQ
Ht7HHRQ
u'i lHuH&
H5E/ H8i1H= Q
WR Hu?H t5HHH&
LH5 Av A H81m3HH=E
jHHuH=D
QoHHt,H5E
HIHu+HE HHE uH-hAv A H;%
AL;%b%
EuL;%x%
t LkAI $uLgE~'H5C
HHHsHug
A]H=+
H
+
hiH%+
E HT$HHt$@H|$8kH5WC
HHHu
u%Ht
Hu3gHT$HHt$@H|$8e?H|$8Ht
Hu gH|$@Ht
HufH|$HHt
HufHM uHfH=O
11H =
kHHxH H5G
HokHE EHHE uHrfH =
E1LP L A~Mt M LcHcA HiH HJHD$D|$M9|$ KDH HHuIL IL9t$tI>u+I Ht$LD$Ht$LD$IFIIH9tIHuOLct$H5 KDAv A HHH HPH"
H81jHcM \gHcHx<
H5<
H=jM
-hH=( IhHHeH A p HH( H5t( oHu;
HB HM uHdH=J( gHHH A HH) H5 ( ]oH&;
HcB HM uHgdH=' gHHG A HH( H5' oH:
H B HM uHdH=' DgHH`G A ` HH' H5' nH:
HA A H
HH' H5|' ~nH_:
HA A 0 HHg' H5K' MnH6:
HSA A P HH@' H5' nH
:
H"A A HH' H5& mH9
H@ A HH& H5& mH9
H@ A HH& H5& mH9
H@ A HH& H5V& XmHi9
H^@ A HHb& H5%& 'mH@9
H-@ A HHA& H5% lH9
H? A HH & H5% lH8
H? A HH% H5% lH8
H? A HH% H5a% clH8
Hi? A HH% H50% 2lHs8
H8? A HHw% H5$ lHJ8
H? HM uH aH=L% ?dHH[D A ` HH# H5 % kH7
H> A @ HH% H5$ ykH7
H> H |Hj> A HH$ H5$ 3kH7
H9> HM uH=`H=$ qcHHC H
$ HG
HH5$ g> H
$ HG
HH5$ f= H
$ HG
HH5$ f= HM uH_H= bHH$C H
HG
HH5=$ pg= H
H}G
HH5%$ Kg= H
HPG
HH5
$ &g_= H
H#G
HH5# g:= H
] HF
HH5# f= H
8 HF
HH5# f< H
HF
HH5# f< H
HoF
HH5# mf< H
HBF
HH5w# Hf< HM uH5^H=" iaHHA H
HE
HH57# e6< H
HE
HH5## e< H
&# H}E
HH51# e; H
HPE
HH5# e; H
2 H#E
HH5" ie; H
5 HD
HH5" De}; H
0 HD
HH5" eX; H
#
HD
HH5" d3; H
HoD
HH5" d; HM uH\H=#=
?HH; H5 =
H= 3
Htag6 HM uH~\H=WA
HH; H5?A
H=2
H0a46 HM uH:\ ZHH; HU5
HH HH5
HEHH=R7
1O IH5 HM uH[H55
La HHp? H54
H=(2
H`5 HM uH[I $uL[H=;
HH: H5};
H=1
H>`? HM uHH[ YIH: H2
LH H2
ID$HH=:
O HH> I $uLZH5l2
H` IH4 H5I2
H=21
H_4 I $uLZHM uHZHD$ HD$( HD$0 HD$8 HD$@ HD$H [YHL$0HT$(H Ht$ IM\ H=
q]IH H5 HYIHuLZHuH
H5 H8ZC H
H9Et-H
H5
H8cZHM HY 1H"_HM HA
uHYHA
HuH
H5 H8 Z = HA
t& H5
Ho
H81^ HpA
w'
H5
H3
H81i^T ÅuH
H5 H8uY0tH
H5 H8XYH|$ H H
Il$XL(I9 Hu A d IEH I]1H9~I;l HE1L9~KtH9 HE @t~HFH s] @tTHX HtHJ1H9~5H;t+ HHH H9 HuH;5f
Ies
H*[ H X HU te @t\ sVA @tLHX Ht$HJ1H9L;l HHtH I9usL;-
tjLHWuVzHuVHD$ H|$(Ht
HuVHD$( H|$0H H V H
H= 2h HL$HHT$@LHt$8H x@H5;
H==
1B HHt0HV HM u/HA I 9V%9 A E A I A I$ HL$0HT$(Ht$ vW H|$8Ht
HuUH|$@Ht
HuUH|$HH&4 H 4 U4 H=
mWHHA5 H,
H5[6
HH TZ/ HM uH^UH=,
RX Ht$PH
H=,
H?HD$H H H:
^ HH4 H5c6
H=t+
HYR/ HM uHTHO+
H
*
H9Hu)H*
Ht H H-*
.H= 6
> H H=5
H*
H5*
HHU4 H5.
HdA IH. HM uHZTH5.
H=*
L$Y 8 I $uL.TH*
H
0*
H9Hu)H*
Ht H L% *
.H=S5
I H=B5
H)
H5)
IM3 H5L.
L@ HH7 I $uLSH5#.
H=*
HlX. HM uHvSH)
H
h)
H9Hu)HS)
Ht H H-D)
.H=4
H H=4
H#)
H5$)
? HH3 H5-
H? IH- HM uHRH5-
H=L)
LW6 I $uLRH')
H
(
H9Hu)H(
Ht H L%|(
.H=3
I H=3
H[(
H5\(
IM`2 H5\-
L IHA, HM uHzQH5,
H='
LDV5 I $uLNQH'
H
'
H9Hu)H&
Ht H L%&
.H=s2
I H=b2
H&
H5&
IM1 H5,
L= HH5 I $uLPH5s,
H=$'
HUq+ HM uHPH&
H
H&
H9Hu)H3&
Ht H H-$&
.H=1
H H=1
H&
H5&
_ HHk0 H5T,
H= IH* HM uH
PH5+,
H=l&
LTA4 I $uLOHG&
H
%
H9Hu)Hk%
Ht H L%\%
.H=1
6 I H=0
H;%
H5<%
IM/ H5+
L\< HH3 I $uLROH5+
H=%
H T&* HM uH&OH%
H
$
H9Hu)H$
Ht H H-$
.H=K0
~ H H=:0
Hs$
H5t$
HH / H54+
H; IH) HM uHNH5 +
H=$
LdS2 I $uLnNH$
H
#
H9Hu)H#
Ht H L%#
.H=/
I H=/
H#
H5#
7
IMv. H5*
L: HH~2 I $uLMH5*
H=D$
HR( HM uHMH $
H
(#
H9Hu)H#
Ht H H-#
.H=.
H H=.
H"
H5"
HH- H5)
H4: IH`( HM uH*MH5)
H=#
LQ1 I $uLLHg#
H
`"
H9Hu)HK"
Ht H L%<"
.H=#.
V I H=.
H"
H5 "
IM(- H5)
L|9 HH41 I $uLrLH5[)
H="
HGH
H
H9Hu)H
Ht H L%
.H=c(
I H=R(
H
H5
IM' H5T&
L3 HH , I $uLFH5+&
H=
H|Kd" HM uHFH
H
X
H9Hu)HC
Ht H H-4
.H='
H H='
H
H5
O HHI' H5%
H3 IH! HM uHEH5%
H=\
LJ;+ I $uLEH7
H
H9Hu)H{
Ht H L%l
.H=&
& I H=&
HK
H5L
IM& H5D%
LL2 HH* I $uLBEH5%
H=
H J! HM uHEH
H
H9Hu)H
Ht H H-
.H=;&
n H H=*&
H
H5
HH% H5$
H1 IH HM uHDH5{$
H=
LTI) I $uL^DH
H
H9Hu)H
Ht H L%
.H=%
I H=r%
H
H5
' IMT% H5|$
L0 HHx) I $uLCH5S$
H=4
HH HM uHCH
H
8
H9Hu)H#
Ht H H-
.H=$
H H=$
H
H5
o HH$ H5#
H$0 IHS HM uHCH5#
H=|
LG( I $uLBHW
H
p
H9Hu)H[
Ht H L%L
.H=$
F I H=$
H+
H5,
IM$ H5D#
Ll/ HH.( I $uLbBH5#
H=
H,G HM uH6BH
H
H9Hu)H
Ht H H-
.H=[#
H H=J#
Hc
H5d
HH_# H5"
H. IH HM uHAH5"
H=
LtF]' I $uL~AH
H
H9Hu)H
Ht H L%
.H="
I H="
H
H5
G IM" H5\"
L- HH& I $uL@H53"
H=T
HE8 HM uH@H/
H
H9Hu)H
Ht H H-
.H=!
H H=!
H
H5
HH" H5!
HD- IH HM uH:@H5!
H=
LE& I $uL@Hw
H
P
H9Hu)H;
Ht H L%,
.H=3!
f I H="!
H
H5
IMj! H5$!
L, HH% I $uL?H5
H=
HLD HM uHV?H
H
H9Hu)Hs
Ht H H-d
.H={
H H=j
HC
H5D
HH H5
H+ IHr HM uH>H5[
H=,
LC$ I $uL>H
H
H9Hu)H
Ht H L%
.H=
I H=
H{
H5|
g IM H5
L + HHP$ I $uL>H5
H=t
HB HM uH=HO
H
H9Hu)H
Ht H H-
.H=
> H H=
H
H5
HHu H5<
Hd* IH' HM uHZ=H5
H=
L$B# I $uL.=H
H
0
H9Hu)H
Ht H L%
.H=S
I H=B
H
H5
IM H5
L) HH# I $uL HM uH9H
H
H
H9Hu)H3
Ht H H-$
.H=
H H=
H
H5
_ HH H5
H& IHF HM uH
9H5k
H=l
L= I $uL8HG
H
H9Hu)Hk
Ht H L%\
.H=
6 I H=
H;
H5<
IM H5
L\% HH( I $uLR8H5
H=
H =s HM uH&8H
H
H9Hu)H
Ht H H-
.H=K
~ H H=:
Hs
H5t
HH= H5T
H$ IH HM uH7H5+
H=
Ld<W I $uLn7H
H
H9Hu)H
Ht H L%
.H=
I H=
H
H5
7 IM H54
L# HH I $uL6H5
H=D
H;" HM uH6H
H
(
H9Hu)H
Ht H H-
.H=
H H=
H
H5
HH H5
H4# IH HM uH*6H5
H=
L:
I $uL5Hg
H
`
H9Hu)HK
Ht H L%<
.H=#
V I H=
H
H5
IMH H54
L|" HH I $uLr5H5
H=
H<: HM uHF5H
H
H9Hu)H
Ht H H-t
.H=k
H H=Z
HS
H5T
HH H5
H! IHS HM uH4H5k
H=
L9 I $uL4H
H
H9Hu)H
Ht H L%
.H=
I H=
H
H5
W IM H5
L ! HHJ I $uL4H5
H=d
H8 HM uH3H?
H
H9Hu)H
Ht H H-
.H=
. H H=
H
H5
HHS H5
HT IH HM uHJ3H5k
H=
L8y IM uL 3H_
11H= w3IH H5|
H=]
H7: IM uL2H
11H=M (3IH H5e
H=
Hv7 IM uL2H
11H= 2IHp H5
H=
H'7 IM uL12Hr
11H=o 2IH2 H5g
H=p
H6} IM uL1H#
11H= ;2IH H5
H=!
H6> IM uL15 /IH H
H IEH
HH
H IEH
HPH
H IEH
HPH<
H IEH.
HPH;
H IEH-
HP H
H IEH
HP(H
H IEH
HP0H
H IEH
HP8H/
H IEH!
HP@H>
H IEH0
HPHHE
H IEH7
HPPH<
H IEH.
HPXHC
H IEH5
HP`HR
H IEHD
HPhH
H IEH
HPpH
H Hv
IEHPxH
H IEHq
H H{
H IEHm
H H
H IEH
H H
H IEH
H H
H IEH
H H+
H IEH
H H'
H IEH
H H#
H IEH
H H
H IEH
H H
H IEH
H H
H IEH
H H
H IEH
H H
H IEH
H H
H IEH
H H
H IEH
H H
H H
IEH H
H IEH
H H
H IEH
H H
H IEH
H H
H IEH
H H
H IEH
H H+
H IEH
H( H'
H IEH
H0 H
H IEH
H8 H'
H IEH
H@ Hk
H IEH]
HH Hg
H IEHY
HP Hc
H IEHU
HX H_
H IEHQ
H` H[
H IEHM
Hh H
H IEH
Hp H
H H
IEHx H
H IEH
H H
H IEH
H H
H IEH
H HC
H IEH5
H H
H H
IEH=R
H H5
L0q IM uL+- 1IH H1
H5J
Hj0? HK
H5
LL0, H
H5>
L.0 H
H5
L0 HI
H5
L/ H{
H5
L/ H
H5
L/ H
H5
L/ H1
H5
Lz/ H
H5
L\/ H
H5
L>/ H
H5
L /n H
H5
L/[ H
H5l
L.H Hm
H5
L.5 H_
H5
L." H
H5
L. H
H5
Ll. H
H5F
LN. H7
H5
L0. H
H5
L. H
H5
L- H
H5
L- H
H5H
L- H
H5
L-w H
H5$
L|-d H
H5
L^-Q Ho
H5p
L@-> H
H5j
L"-+ H
H5T
L- H%
H5
L, H
H5
L, H
H5
L, HS
H5t L, H-
H5 Ln, HO
H5 LP, H
H5z
L2,~ H
H5< L,h HM
H5. L+R H
H50 L+< H1
H5" L+& H
H5 L+ Hu
H5 L~+ Hw
H5H L`+ H!
H5 LB+ H5c
H= L$+ IM QL*&DA w A Aw A E1A'w A MA A,w E1AKw A } MA AMw i Acw A X A{w A G E1Aw A 3 Aw A " E1Aw A Aw A E1Aw A Aw A E1Aw A Aw A E1Aw A Ax A E1A x A z A/x A i E1A;x A U AMx A D E1AYx A 0 Akx A E1Awx A Ax A E1Ax A Ax A E1Ax A Ax A E1Ax A Ax A E1Ax A w Ay A f E1A
y A R A y A A E1A+y A - A=y A E1AIy A A[y A E1Agy A Ayy A E1Ay A Ay A E1Ay A Ay A E1Ay A wAy A iE1Ay A XAy A JE1Ay A 9Az A +E1Az A A-z A A9z A HM uH<" MظIM ɸL"鼸HM p HAv A !锸HM ^ HAv A !lHM L HAv A !DDAXw H
H= Ai 3 Av A 1Av A 1Av A 1ݷAv A 1ʷAv A 1鷷Av A 1餷Av A 1鑷Av A 1~Av A hA
w A RAw A x M廏 AJx M廐 A\x M廑 Ahx o M廒 Azx \ M廓 Ax I M廔 Ax 6 M廕 Ax # M廖 Ax M廗 Ax M廘 Ax M廙 Ax M廚 Ax M廛 Ax M廜 Ay M廝 A y M廞 A.y x M廟 A:y e M廠 ALy R M廡 AXy ? M廢 Ajy , M廣 Avy M廤 Ay M廥 Ay M廦 Ay M廧 Ay M廨 Ay M廩 Ay M廪 Ay M廫 Ay M廬 A z n M廭 A z [ M廮 A z H M廯 A*z 5 A{ A?{ A@{ AA{ AB{ AC{ AD{ AE{ AF{ AG{ AH{ AI{ AJ{ ~AK{ vAL{ nAM{ fAN{ ^AO{ VAP{ NAQ{ FAR{ >AS{ 6AT{ .AU{ &AV{ AW{ AX{ AY{ AZ{ AHH []A\A]A^A_H=
h H= H H9tHN Ht H= H5 H)HH?HHHtH Htf D = u/UH= Ht H= h ] {f. H GP HGX H D ATIUHSHHHt HՅu!H 1Ht[LH]A\ []A\ff. HGH HG H u310 Ht!H/ HPHl HHPH HHy H5J 18 AVAUATIUSHHHGH$ ILl$HD$ tFH HOH $H LH5 H81H1[]A\A]A^1LLHpt4H$H@ uHT LH5
H81`1 @ u H $Hu H[]A\A]A^f D AUIATIUHSHHGH Ht]H= u:LLHIMtHL[]A\A] {IHt"HE1[L]A\A]fH[]A\A]aH2 H5 H8f HGH Htf D AWL~AVAUATUSHL$M~qLHG HIHHD$MLf H|$L3r H $HLIL4LYHHLKHHL=L)IuH H H[]A\A]A^A_f. UHSHHt:HHH}H/tH]H1[] @ H]H1[]f D H y ff. @ UHGHL@ t3H L Hm H81AHEu&]f D H HHH5 H81Hm t 1] H`1ff. ATUHHG HGHPHv2H HtJEHcAH9 HD]A\ E1HtDgDHDDH]DA\ @ G WH H HcAH9tH) H5: H8BAf. G WH H HHcAH9uHD]A\f. HuuHtf D H@`HtfH HtZHHtPH H9Eu' @ HHm AHHH5* HHu7H)H H5m AH8Qff. UHGHH unHVH}HtHE H/t?H HtHDž H/tHEH]H@ ;f +f [uHUHlH9B0tHzd]ATfHnfHnUflHLGXLg`GXHohHOhMtI(tLMtI,$t0HtHm t H]A\ @ HH]A\f Lxf D Lhf D AUfIATIUHSHH(HGXHT$Ht$HD$HG`GXHD$HGhHGh H|$HD$;H{X Ht$Ht H|$ HD$HtH HD$HtH HD$Ht H HD$HT$IU I$HD$HE H H8L`HHT$HhHPHT$HPHtH/t=MtI,$tAHtHm tH(1[]A\A] H8
f D +
f L
f D H|$IE I$ HE HtH/t8H|$HtH/tHH|$HtH/t(H([]A\A] f f f USHHH- HHE HkHHE Ht
H/tAHE H HH HE HtH/t H1[] H1[]f f AUIATIUSHHtTH5M HLALHHm ItHL[]A\A]ÐH HL[]A\A]f. HE1[L]A\A]ff. @ H9t+HX Ht/HJH~F1 fHH9t7H9tu f. H H9tHu1H;5 f1ff. fAUAATUSHH9 H H9GHIH9F A|$ HUI9T$ HEIL$H9@H@t
H u ED$ D8 @ ! H}HA c IL$0It$HA@HEȃU \ DA9uBH H 1Au&1 @ H Y H9u t1AH[]A\A] @ I9uuHDL HH H; H;- uH9u8Hm uHD$ Z D$ @ 1AH[]A\A] @ H
f D HM0H}H@HE @ L:f Lh5f D It$Hf D D @ Dff. ATUHHqIHtH HL]A\f. HuHEH uH H8g 1HHtHH H8?Hm uHff. AUATIUHSHHGH; tsHXpHtBH{ t;H IH LHHSIm AtqHD[]A\A] H@hHtgH@(Ht^HLH[]A\A] @ HGA HHOHt1Hx
H 1H f. H;I toU HhHH H; H;-[ u4H;-u t+H Hm tDH]f D 1f D f1H*f.G E @ HD$ D$ 몸ff. @ LVIIM 1f HI9tM9Du f. 1f D ITHB tv @tmL9tIX Ht,HqH~S1 HH9t?H;Tuf D L D H H9xHuH;\ ff D HI9k1HHtGHH9t.HX HtRHJH~q1 D HH9t_H;tu Hf D HA H5d H81H H D H H9tHuH;5 tf D HA HNH5& HWH81H 1 @ HG @t~HFH tt @tkH9t.HX Ht*HJH~A1 D HH9t/H;tu fH H9tHu1H;5 f1 D t @ AWAVAUIATUHSHHGH Ht IMt"HL[]A\A]A^A_IMu H H8u H~ LH5 H81HHHt&HHtH5 H/IHteLH IHtjHI/Ht#I.t'Hm t*HpI3 D LLHHm :H-1f D HG t{HGHPHvHtOHt1 @ HtHcWHHcHHE @ G WH H f. G WH H H UHH@`HtvH HtjHHt`H H9Eu H8Hm t)H]HH5@ HHuH HHD$HD$HuH H5l H8TfAUIHATIUSHHEH H1 HHHHTHI9uIEH H H= vuU1HLIMt1Hm tHL[]A\A]f D HHL[]A\A]IHt7E1 HE1[L]A\A] 1HLIH H50 H8@pff. AVH?AUIATIUHHHH H5[ H9 HU tHB8HD H L L- M H=x ;u01LHAIdM IHE HE1]LA\A]A^ D Ht: HG8HD H HLLH1]A\A]A^ H5q H9 H} D HUBLjE1 t>H= b1QLAIM)HL]A\A]A^fLef. HLLH]A\A]A^' HUB^Mu E1Lj uLeH= LjH H5 H8 fHLH1]A\A]A^ff. @ AWAVAUATUSHLoMz HIH1 HI9t H9\uIH[]A\A]A^A_ D HC0E1HD$ @ NdI9 H H9CI9D$ { A|$ HSI;T$ ID$HsH9@H@t
H DK A|$ Dȉ@@8uA ] LKH@ j It$0IH@ID A9DA9u7H LL$E1HL$A IM91H[]A\A]A^A_f. L5! L9uuM9uuL HL$IHtH; L$L;% uM9u:I,$DtIEnErKH[]A\A]A^A_f. LL$I,$L$AuLL$L$ @ A@HsHHEt$I@ It$H HL$,L$A|$ @ LL$L$1A9D`A9DS ATUHHHG H LeID$Hv-ItoItYH1IHm t1HL]A\ @ MtHcEIHcHEHm IuHHL]A\ De EI I De EI I I D H@`Ht_H HtSHHtIH@H; 'HH5 iHHuCI> D HI";HuH_ H5 H8H@ D ATUSLXXMu1[]A\ HH H0L9ufHkhHCh fLc`CXI+t8MtI,$t HtHm uHf D Lpf D L`f D ICL t^A @tTHFH t| @tsIX Ht|HJ1H~ @ H;t?HH9uutL[XfLc`HkhCXHCh M t4tLH H9HuH;5, Izff. AWAVAUIATAUHSH8BH= IH H@XMwhIGh fH$IG`AGXHD$HH H8H H9G Lպ M H- I9t L;Q LC E1 H5 EAH/ D D׃ HcHD9t 1f }0H9} )HcHTD9~߉9|D9A9 HHHD9p L I$Hc 1LL&HHt6XlH#I,$uLHm Ht H8[]A\A]A^A_ I,$uLH8[]A\A]A^A_Ha HH oIH5 I|$XL I9t"Ht+I@ . Ljt111L8c Hy H5Z E1H= ~$IXMW`MGhMwhD$AGXHt
H/ Mt
I* Mt
I(g EH5 H D AD׃V1Uf D IGXfH$IG`AGXHD$IGhIGh HD$E LHIM ~$IXHD$Mo`D$IohAGXIGhHt
H/ Mt Im Ht Hm H= EH D- D HcHD;t 1f D U9 )HcHDA9}IGXfH$IG`AGXHD$IGhIGh HD$LDH 1H=v UIH HqHH HIm ILG1 A9A9
HcHLE9p; D;- D L$)PIcHHHHHA9HNH HA9HNHtHHHL$AEpM D-Y I$%Im uLH $HtHHD$HH H\$HtHH$HHt H\$H HHH$HH DD9- A@IcHHHH HcD- D- HLA9LHLD$L$5LD$L$RLL$L$LIGXfAH$IG`AGXHD$IGhIGh HD$H=X H5 HGH H;/ . 1}HHyH|$'H|$H HHI HӤ H9 cHXHKTH>aL1D'*H5c HL$HVmHL$HI HL H@H HH@ H DpH L I$HcHL^HHH IHD$LD$sLD$HD$I8M H/ZOPHD$LD$HL$5L H HIH1I;|HH91H9ItH9HT$(HL$ LD$H|$HT$(HL$ LD$H|$H @ AWH AVAUATIUSHH(HD$H HD$ HD$H HL HkHEHH5 H H, IM/ H5c LG H5L LIH AoE HC AoMK0IE HC@HC HCHHCPHH H(tdHEH5 HH H HH H H/tSH H H I,$tH[]A\A] 땐LH$H$H[]A\A] D f f D {IMH
" H=| H1[]A\A] D H-Ѿ L- HEH H H=u b 1HLHH HHm " tnH
n H={ 1 @ H>" f D " @ Hr " @ Ht$ $y$t$ wH1LHHE @ " K\HuH8 H5t H8" fAWAVAUATIUHSH(HGHXpHt HSHtH(H[]A\A]A^A_ HPhHs HRHf H
g I9L$ Ml$IMH9 MulH; H; H H{ LIH HHSI,$6 H([]A\A]A^A_ IcD$IHcHEIIi HEH; H; teHXpL`hHt H{ oM IT$H M L D HE1H9 HEHH JMa HEIT HH9r HDH @ ' H H; H5n G 1HIH Ld$I}HD$ H;= tH5 6 f D IUB Ld$HZ1 uImH=r LHHD$ HD$H fIm ?LHD$hHD$(f D M. HEJ(LLt111L5 D HEHPHa H5x H81p1f LIHy HH @ LIHt"HI.ILH HEH; b H; I~f D I I AT$ AL$H H H;4 I3 H;D 1HELL LHD$HD$f HE11hIEHt$ teH@8ID HtW1ɺ L"H HH2 t)ID$L`H H5Hv LH811& LLbI1El$ AD$I I IHEL{II$HOHH= IT$I4HHJ IMIH MfXL(M9uMIEH IT$ 5A$ @& A @
I$X Ht!HJ1L;lHH9M$ M9MuL;- f HEM1`HuH H5Pn HD$H:[HD$1H" H87IT$fIM}1M;d8HI91I97ItI9LqH AWAVAUATUSH8H IH I~H5 HGH H IM IH;= _ IoHR MOHE II/ IyH5 Hl$(H9tL $L $ IQB Ll$(HZE1 & H=l L $~L $2 LLHHL $ Hm R HL $L $e LL $L $@ IA G H@8IH6 L $LHt$(1ɺ L $HHm tH H$ 1E1E1E1E1 A! @ HD$( H5X H9tKuBIG HP8M M 11Ht$0LAMHsf D IWBtHZ1 W H=Xk 1HHDMHp I) HCH;ۉ } HSH HC(LcLk H$I$IE H H+ HH H2 H HCH# HL= lHH H5 LHHA Hm I HHM HH H5 LHHx H8 6 I/ IEH; H;̈ n HXpH) H{ 1?HF HD$HLSLL$II)f M HHw LxLI$L` IFH5 H H| IMN )IH} HF H5 H IGH5L H H H=i HL$Ht$ Ht$HL$LLHD$LL$M I/ I. LL$LL$HIp fHnfHnHE flLH(@I,$ Im I @ H $HHD$HH Ht Hm H8L[]A\A]A^A_ D L H, Io LHt$( L $L $Hf D H@hH3 H@H& 1LI Ma H 4 E1LM
MtIm uLH<$ f D H H LIEH; IEL8IJ H Hxl HH E1E1RL
H H8H
݊ H5l 1XZZM}I Hy 1H5Ŋ HTE1 @ I H$ 1E1E1 A! 1MtI/t@HtH+tUH
% DH=$m 7MI,$kE1q LDT$T$gDT$T$ @ HDT$T$GDT$T$ @ SL $HuH+ H5e H8L $Hm MuHf D H$ M1E1E1 A! 1E1E1fI)t:MI.LDT$T$DT$T$ LDT$T$T$DT$ @ H H- H< H=d }M1HLZf D H;1 HHHg H+ HEHH IHh HIH HH$H HH Hm )H LLL$LL$!f LLL$cLL$f A5" E1H+t1Mab @ HLL$DT$T$T$DT$LL$fH Hx.HHE H
E HEH H5-j H813H$ E1E11A! E1E1E1 Xf. 1E1 A" E1E1E1A" A" HSH2HCL LhH@H$f. HI H5-i H81c+f D LL
IHeA6" A)" E1E1A1" Xf. kI| A'" E1A3" D sHRHK H5a H87 1HH HLH+IHL A6" E1 D E1A:" s D LL$A6" HPH H5 a LL$DT$H8T$T$DT$LL$ E1E11A" H8. E1 A'" X1HL@HH M4H( H+ H5g H81EL<$HMMH$ 1E1E1 A! E1E1E1E1H$ E1A! ?E1E1Hm t`u1IH LH
H5f HEH~ H81MH$ 1E1E1 A! E1H E1A MA vHMH$ 1E1E1E1E1 A! ff. AWH_ fAVfHnAUIHHX ATUSHHhHD$PH{ )D$ fHnflHD$0HD$X )D$@Hi HL4H H H HHIHD$ IL% M 1 @ HL9 L;duIHD$(H LaM LL$ HT$0L<} IfHF HFHIHD$0HFHD$(HHD$ H LL$ HD$(HT$0L| I HH=w8 IuHHE HAPA j 5 5u j5 Pj5 IHE HPM HHE < HhL[]A\A]A^A_f. H H HVLI| HT$0oHFL)T$ > HIH LHH $6H $HHD$ L}HW H
ɀ A HH{ H H5b SL
H81XD ZH
H=c E1HH
\ H^ AHMEI @ LY{ L
f H踽 H LHNH HD$0IL$f D HFHLaHD$(HT$ f D ID$0E1HD$ JtI9" H{ I9D$H9Ft l A|$ ~ IT$H;V HFI|$H9AHAt
H E\$ DF DD@@8 A I|$HA L^0HHA@IEDA A DD E9u>H4 LT$HH $OH $LT$ IM9HD$( %H HHAy H
Q~ H5_ jL
9 A H~ H813Y^D L1y M9uuL9usL LD$LT$H $ȻHHYH;x H $H;=x LT$uLD$L9 H/
K7 HHE H
z} D H=` HL$ HT$@ILL
} H豷:D LT$HL$H<$eLT$HL$H<$HfI|$HA@HE|$Hd]D 4 D D$LT$H $>D$LT$H $ @ LLT$Ht$H $蒸H $Ht$LT$ HLT$HL$H4$ZH4$HL$LT$ HvH. üHD oDD DD 葼HuH
{ A wD /AWHߔ fAVfHnAUIHxHx ATUSHHhHD$PH>t )D$ fHnflHD$0HD$X )D$@Hl HL4H H H HHIHD$ IL%D M 1 HL9 L;duIHD$(H LaM LL$ HT$0Lu IfHF HFHIHD$0HFHD$(HHD$ H LL$ HD$(HT$0Lu I HH=W? IuHHE HAPA j 5[ 5 j5m Pj5t ^ IHE HPM HHE < HhL[]A\A]A^A_f. H H HVLt HT$0oHFL)T$ > HIHݒ LHH $H $HHD$ L}HT H
iy A HH8t H} H5Z SL
1z H818XeB ZH
9y H=\ E1FHH
x Hx AHMEI @ Ls L
f HX HY LHH HD$0IL$f D HFHLaHD$(HT$ f D ID$0E1HD$ JtI9" Hs I9D$H9Ft l A|$ ~ IT$H;V HFI|$H9AHAt
H E\$ DF DD@@8 A I|$HA L^0HHA@IEDA A DD E9u>H4 LT$HH $H $LT$ IM9HD$( ŷH HHq H
v H5[X jL
w A Hy{ H81ӹY^GB Lq M9uuL9usL LD$LT$H $hHHYH;q H $H;=Wq LT$uLD$L9 H/
K7 HHE H
v B H=zY %HL$ HT$@ILL
uz HQ:SB LT$HL$H<$LT$HL$H<$HfI|$HA@HE|$H]EB 4 D D$LT$H $D$LT$H $ @ LLT$Ht$H $2H $Ht$LT$ HLT$HL$H4$H4$HL$LT$ HvH. cHNB oDD DD 1HuH
lt A =B /AWHW fAVfHnAUIHhH ATUSHHhHD$PHl )D$ fHnflHD$0HD$X )D$@Hi HL4H H H HHIHD$ IL% M 1 @ HL9 L;duIHD$(H LaM LL$ HT$0L|n IfHF HFHIHD$0HFHD$(HHD$ H LL$ HD$(HT$0L1n I HH=0 IuHHE HAPA j 5 5 j5 Pj5D IHE HPM HHE < HhL[]A\A]A^A_f. H H HVLm HT$0oHFL)T$ > HIH LHH $vH $HHD$ L}HW H
r A HHl HZr H5RS SL
r H81شX!M ZH
q ^ H=fU E1HH
q Hq AHMEI @ Ll L
f H H LH莺H HD$0IL$f D HFHLaHD$(HT$ f D ID$0E1HD$ JtI9" H[l I9D$H9Ft l A|$ ~ IT$H;V HFI|$H9AHAt
H E\$ DF DD@@8 A I|$HA L^0HHA@IEDA A DD E9u>H4 LT$HH $華H $LT$ IM9HD$( eH HHj H
o H5P jL
yp A Ho H81sY^M Lqj M9uuL9usL LD$LT$H $HHYH;5j H $H;=i LT$uLD$L9 H/
K7 HHE H
n WM H=BR ŽHL$ HT$@ILL
n H:M LT$HL$H<$襯LT$HL$H<$HfI|$HA@HE|$H褫]M 4 D D$LT$H $~D$LT$H $ @ LLT$Ht$H $ҩH $Ht$LT$ HLT$HL$H4$蚩H4$HL$LT$ HvH. H
M oDD DD ѭHuH
m A L /AWAVAUATIUHSHHK HEHE Hp IT$H5 LH H Hx IM: UIHy H5" HH? IFL=| L Mt H=EH LLLAI,M; I.a I,$F f D Hm HL[]A\A]A^A_ H IM I|$H;=ef M|$M Mt$III,$ I~H5g L|$H9P [C IF b H@8IHQ Ht$1ɺ LII/Z M M A A< H萨 HD$ H5pf H9tK辭uBID$ ( HP8MM 11Ht$LAMIj D IT$BtLrE1 uMl$H=mF 0H1LAIMUM I.:Lʧ- D IVBH\$LjE1 ] H=E a HLAIM I/uLa @ LP L@ L0 HIͥH1H5{m LSE1f A A< DDE1H
Si H=
M h+ A< I.A uL覦I,$uL藦 D Ht$ LήIf D LLL蒫IHf D A< Mf H L-| H: H=zD =U1LLf D A A< A A< 蛫I 苫I9 I. LA A< 肥 D 蓨HHkb H5C H8jHu HFb H5C H8ϥ I/MkL^f D #HJHa H5tC H8脥/L1LMIA A< f D AWAVAUATIUHSHHK HEHE Hp IT$H5 LH H Hx IM: uIHy H5B HH? IFL=z L Mt H=eB ( LLLAILM; I.a I,$F f D Hm HL[]A\A]A^A_ H IM I|$H;=` M|$M Mt$III,$ I~H56a L|$H9P {C IF b H@8IHQ Ht$1ɺ LII/Z M M A As= H谢 HD$ H5` H9tKާuBID$ ( HP8MM 11Ht$LAMIj D IT$BtLrE1 uMl$H=@ PH1LAIMuM I.:L- D IVBH\$LjE1 ] H= @ a HLAIM I/uL聡 @ Lp L` LP HIH1H5 d LsE1f A AS= DDE1H
sc H=UG 舲+ A= I.A uLƠI,$uL跠 D Ht$ LIf D LLL貥IHf D A= Mf H L-v H: H=> ]U1LLf D A A= A A_= 軥I 諥I9 I. LA A= 袟 D 賢HH\ H5> H8芢Hu Hf\ H5= H8 I/MkL3^f D CHJH\ H5= H8褟/L1LM IA A= f D AWAVAUATUSHH(HGH5 H H HH H}H;=[ % LuM L}IIHm Lt$L-M\ IL9tL蔣| IWBtqHt$HjE1 H=~< Ht$< LHt$IbMI I.) LםQ D Hȝb IG o H@8IH^ Ht$1ɺ LII.tM" I/ Li @ HD$ L-H[ L9tKL蓢u?HE ~ HP8LD Ml Ht$11HAII D HUBtLbE1 H=G;
| L1IAI/Mf I/; @ H=v H5
y HGH H IM@ H- H\$HD$ H}L9tL袡 f. HUB Ht$HZE1
H=~: Ht$f L( M1Ht$ @ H 0 ӞHHQ H
P[ E1H=P? [Y IHLOHHS HX SH59 H81 X]G ZH
!X 1 H=V< E1.HXL[]A\A]A^A_ @ H HZLVLT$(LLL$ oLVLA)D$ M LL$ HI$ It$HH=I A HE Hn HH=z AUj RPj RLPj5n | IHE HPM HHE 2H踔% Ly1H
Sn M f HL9twH;LuM LL$ Mh IM<$(* MLLyLL$ M~HHw LHݟIH HD$(MG E1HA0JtHD$H9A f D HQ H9AH9F+ # y ~ HQH;V HFHyH9AHAt
H DY DV DD@@8 A HyHA@HE|$A L^0HHA@IEDA A DD E9u9H $HtJLL$HLL$H $ IM9 JtH9O 0 @ L9uuL9uuHϺ LL$H $ВHHtiH;P H $H;=O LL$ L9 LL$HL$H<$LL$HL$H<$H/ GZHD$ !H
aT A L
ST HAG 1f. HHE tfH
>T G H=n8 I @ HL$ HT$0ILL
mT Hqx'LL$ ? HX됾MG @ D$LL$H $6D$LL$H $ @ ;HrHG _ HLL$Ht$H $jH $Ht$LL$ HLL$HL$H4$2H4$HL$LL$ HvH[ HyH1DD \DD Off. fAWHi AVAUATIUSHHXL-M HD$0H` HD$ HD$8HD$@ Ll$(H HL4H H HZ HH@R H
0R AHOL
R EHS IHLOHHL H}R SH5b3 H81X H ZH
Q H=N6 E1HXL[]A\A]A^A_ @ H HZLVLT$(LLL$ oLVLA)D$ M LL$ HI$ It$HH=i A HE HWh HH
t AUj RPj RLPj5ph Rv IHE HPM HHE 2H舎% Ly1H
#h M f HL9twH;LuM LL$ Mh IM<$(* MLLyLL$ M~Hq LH譙IH HD$(MG E1HA0JtHD$H9A f D HK H9AH9F+ # y ~ HQH;V HFHyH9AHAt
H DY DV DD@@8 A HyHA@HE|$A L^0HHA@IEDA A DD E9u9H $HtJLL$HΎLL$H $ IM9 JtH9O 0 @ L9uuL9uuHϺ LL$H $蠌HHtiH;I H $H;=I LL$ L9 LL$HL$H<$LL$HL$H<$H/ GZHD$ H
1N A L
#N HG 1f. HHE tfH
N BH H=f2 @ HL$ HT$0ILL
DN HAx'LL$ ? H(됾G @ D$LL$H $D$LL$H $ @ HrG _ HLL$Ht$H $:H $Ht$LL$ HLL$HL$H4$H4$HL$LL$ HvH[ HyH1DD \DD Off. fAWHe AVAUATIUSHHXL-G HD$0H HD$ HD$8HD$@ Ll$(H HL4H H HZ HHL H
L AHOL
K EHL IHLOHHF H1L SH52- H81XC ZH
K u H=F0 E1ΚHXL[]A\A]A^A_ @ H HZLVLT$(LLL$ oLVLA)D$ M LL$ HI$ It$HH= A HE H'b HHm AUj RPj RLPj5d "p IHE HPM HHE 2HX% Ly1H
c M f HL9twH;LuM LL$ Mh IM<$(* MLLyLL$ M~Hj LH}IH HD$(MG E1HA0JtHD$H9A f D HiE H9AH9F+ # y ~ HQH;V HFHyH9AHAt
H DY DV DD@@8 A HyHA@HE|$A L^0HHA@IEDA A DD E9u9H $HtJLL$H螈LL$H $ IM9 JtH9O 0 @ L9uuL9uuHϺ LL$H $pHHtiH;C H $H;=cC LL$ L9 LL$HL$H<$觉LL$HL$H<$H/ GZHD$ H
H A L
G HC 1f. HHE tfH
G D H=^, @ HL$ HT$0ILL
G Hx'LL$ ? H됾C @ D$LL$H $քD$LL$H $ @ ۇHrC _ HLL$Ht$H $
H $Ht$LL$ HLL$HL$H4$҂H4$HL$LL$ HvH[ HyH1DD \DD Off. fAWHf AVAUATIUSHHXL-VA HD$0HHHD$ HD$8HD$@ Ll$(H HL4H H H\ HHE H
E AHOL
E EHF IHLOHH@ H'F SH5' H81蒈X@ ZH
E H=H* E1蠔HXL[]A\A]A^A_f D H HXLVLT$(LLL$ oLVLA)D$ M LL$ HI$ It$HH= A HE H[ HHg AUj RPj RLPj5(e i IHE HPM HHE 0H(# Ly1H
d M f HL9twH;LuM LL$ Mh IM<$(* MLLyLL$ M~Hd LHMIH HD$(MG E1HA0JtHD$H9A f D H9? H9AH9F+ # y ~ HQH;V HFHyH9AHAt
H DY DV DD@@8 A HyHA@HE|$A L^0HHA@IEDA A DD E9u9H $HtJLL$HnLL$H $ IM9 JtH9O 0 @ L9uuL9uuHϺ LL$H $@HHtiH;q= H $H;=3= LL$ L9 LL$HL$H<$wLL$HL$H<$H/ GZHD$ 葂H
A A L
A H@ /f. HHE tfH
A f A H=^& 蹐 @ HL$ HT$0ILL
A H{x'LL$ ? H~됾@ @ D$LL$H $~D$LL$H $ @ 諁Hr@ ] HLL$Ht$H $|H $Ht$LL$ HLL$HL$H4$|H4$HL$LL$ HvH[ HyH1DD \DD Off. fAWH?Y AVAUATIUSHHXL-&; HD$0H HD$ HD$8HD$@ Ll$(H HL4H H HZ HH? H
? AHOL
? EH~@ IHLOHHY: H@ SH5 H81`XE ZH
a? e H=F$ E1nHXL[]A\A]A^A_ @ H HZLVLT$(LLL$ oLVLA)D$ M LL$ HI$ It$HH=Y A HE HU HHa AUj RPj RLPj5W c IHE HPM HHE 2H{% Ly1H
kW M f HL9twH;LuM LL$ Mh IM<$(* MLLyLL$ M~H^ LH IH HD$(MG E1HA0JtHD$H9A f D H 9 H9AH9F+ # y ~ HQH;V HFHyH9AHAt
H DY DV DD@@8 A HyHA@HE|$A L^0HHA@IEDA A DD E9u9H $HtJLL$H>|LL$H $ IM9 JtH9O 0 @ L9uuL9uuHϺ LL$H $zHHtiH;A7 H $H;=7 LL$ L9 LL$HL$H<$G}LL$HL$H<$H/ GZHD$ a|H
; A L
; HE 1f. HHE tfH
~; &F H=^ 艊 @ HL$ HT$0ILL
; Hux'LL$ ? Hx됾E @ D$LL$H $vxD$LL$H $ @ {{HrE _ HLL$Ht$H $vH $Ht$LL$ HLL$HL$H4$rvH4$HL$LL$ HvH[ HyH1DD \DD Off. fAWH7Q AVAUATIUSHHXL-4 HD$0H` HD$ HD$8HD$@ Ll$(H HL4H H HZ HH9 H
p9 AHOL
`9 EHN: IHLOHH)4 H9 SH5 H810|XH ZH
19
H=F E1>HXL[]A\A]A^A_ @ H HZLVLT$(LLL$ oLVLA)D$ M LL$ HI$ It$HH= A HE HO HHM[ AUj RPj RLPj5O ] IHE HPM HHE 2Hu% Ly1H
cO M f HL9twH;LuM LL$ Mh IM<$(* MLLyLL$ M~HXX LHIH HD$(MG E1HA0JtHD$H9A f D H2 H9AH9F+ # y ~ HQH;V HFHyH9AHAt
H DY DV DD@@8 A HyHA@HE|$A L^0HHA@IEDA A DD E9u9H $HtJLL$HvLL$H $ IM9 JtH9O 0 @ L9uuL9uuHϺ LL$H $sHHtiH;1 H $H;=0 LL$ L9 LL$HL$H<$wLL$HL$H<$H/ GZHD$ 1vH
q5 A L
c5 HH 1f. HHE tfH
N5 h
H H=^ Y @ HL$ HT$0ILL
5 Hox'LL$ ? Hhr됾H @ D$LL$H $FrD$LL$H $ @ KuHrH _ HLL$Ht$H $zpH $Ht$LL$ HLL$HL$H4$BpH4$HL$LL$ HvH[ HyH1DD \DD Off. fHGH H;. u 1qAVAUATUSHHt IMt%HL[]A\A]A^ D vIf D oHH. H{XH(H9 HtHEH HW @ @ HX H HJHN1 HH96H;luHkhHCh fLk`CXH/t`MtIm t[HHm HpHpH{XfLk`HkhHCh CXHuoLoLmM1 HI9t6H;|uKHH H98HuH;-0- &PE1JtH9kH|$tH|$TIM9uff. @ AWHQ AVfHnAUATIHH UfHnSHflHhfo2T H* HD$PL
T HD$X HT HT$0)D$@)T$ H HL4Hv H Hw LLyLL$ M HP LHzHE HD$(IMc LML-PQ Mi 1 HI9K L;luIHA HD$0I, @ HV HFLLyHD$0HFLL$ HD$(M LL$ HD$(LT$0H
A+ HI$ It$HH= A HE HG QHj R5R j5O Pj RL
U IHE HPM HHE twHhL[]A\A]A^A_ D H ,H H H
* ILLL$ IfHuZLVH
w* LT$0HFHD$( Hl| LyMK LT$0H
7* f. H
/ A HH) H3 H5R SL
/ H81qX;@ ZH
. H= E1}H
) IxHFHLyHD$(HT$ HH
s. Hu. IHII?IA[f D LL$ #f D E1IE0JtHD$I99 f D H) I9EH9F# A} ~ IUH;V HFIMH9@H@t
H A} D^ D8 @ IMH@HHE|$A HN0HHA@HEȃ D A9u5L $HtFLT$HlLT$L $ IM9 JtI9Kd @ H
' I9uuH9uuL HL$LT$L $jHHtnH;' L $H;=' LT$ HL$H9 LT$LL$H<$mLT$LL$H<$H/ 6IlH "@ Uf D HHE H
, q@ H=R %{1H
' IHG LHuIHtVHD$ I HL$ HT$@ILL
0 HfJ'@ lHz@ Hh1 D$LT$L $hD$LT$L $ @ LLT$Ht$L $gL $Ht$LT$ HLT$LL$H4$fH4$LL$LT$q HvH; I}H 3kH@ D D AWHGJ AVfHnAUATIHH UfHnSHflHhfoL H" HD$PL
L HD$X HL HT$0)D$@)T$ H HL4Hv H Hw LLyLL$ M HI LHrHE HD$(IMc LML- J Mi 1 HI9K L;luIHA HD$0I, @ HV HFLLyHD$0HFLL$ HD$(M LL$ HD$(HT$0H
# HI$ It$ H=A A HE QHj 5? 5tK j5H Pj 5D M IHE HPM HHE twHhL[]A\A]A^A_ D H ,H H H
J# HLLL$ IfHuZHVH
'# HT$0HFHD$( He| LyMK HT$0H
" f. H
' A HH" HD( H5 SL
( H81jXJ ZH
' G H= E1vH
q" HxHFHLyHD$(HT$ HH
#' H%' IHII?IA[f D LL$ #f D E1IE0JtHD$I99 f D HA" I9EH9F# A} ~ IUH;V HFIMH9@H@t
H A} D^ D8 @ IMH@HHE|$A HN0HHA@HEȃ D A9u5L $HtFLT$HzeLT$L $ IM9 JtI9Kd @ H
I9uuH9uuL HL$LT$L $DcHHtnH;u L $H;=7 LT$ HL$H9 LT$LL$H<$vfLT$LL$H<$H/ 6IeH J Uf D HHE H
$ +K H=*
s1H
HHq@ LHmIHtVHD$ I HL$ HT$@ILL
$ H^JJ dHzJ Ha1 D$LT$L $naD$LT$L $ @ LLT$Ht$L $_L $Ht$LT$ HLT$LL$H4$_H4$LL$LT$q HvH; I}H cHJ D D AWHC AVfHnAUATIHHUfHnSHflHhfoE Hu HD$PL
E HD$X HyE HT$0)D$@)T$ H HL4Hx H Hy LLyLL$ M HB LHxkHG HD$(IMe LML-B Mk 1 D HI9K L;luIHA HD$0I, @ HV HFLLyHD$0HFLL$ HD$(M LL$ HD$(HT$0H
HI$ It$HH= A HE QHj 5j8 5$D j5A Pj 5= mF IHE HPM HHE twHhL[]A\A]A^A_ D H ,H H H
HLLL$ IfHuZHVH
HT$0HFHD$( H0^| LyMK HT$0H
f. H
i A HH8 H H5 SL
1! H818cXK ZH
9 H= E1FoH
! HxHFHLyHD$(HT$ HH
H IHII?IA[f D LL$ #f D E1IE0JtHD$I99 f D H I9EH9F# A} ~ IUH;V HFIMH9@H@t
H A} D^ D8 @ IMH@HHE|$A HN0HHA@HEȃ D A9u5L $HtFLT$H*^LT$L $ IM9 JtI9Kd @ H
Y I9uuH9uuL HL$LT$L $[HHtnH;% L $H;= LT$ HL$H9 LT$LL$H<$&_LT$LL$H<$H/ 6II^H K Uf D HHE H
z K H=
l1H
a HH9 LHnfIHtVHD$ I HL$ HT$@ILL
HqWJK {]HxK H8Z1 D$LT$L $ ZD$LT$L $ @ LLT$Ht$L $rXL $Ht$LT$ HLT$LL$H4$:XH4$LL$LT$q HvH; I}H \HK D D AWH; AVfHnAUATIHH UfHnSHflHhfoB> H# HD$PL
/> HD$X H'> HT$0)D$@)T$ H HL4Hv H Hw LLyLL$ M H: LH&dHE HD$(IMc LML-`; Mi 1 HI9K L;luIHA HD$0I, @ HV HFLLyHD$0HFLL$ HD$(M LL$ HD$(HT$0H
Q HI$ It$ H= A HE QHj 51 5< j5: Pj 55 ? IHE HPM HHE twHhL[]A\A]A^A_ D H ,H H H
HLLL$ IfHuZHVH
HT$0HFHD$( HV| LyMK HT$0H
G f. H
A HH H H5b SL
H81[XyI ZH
m
H= E1gH
HxHFHLyHD$(HT$ HH
H IHII?IA[f D LL$ #f D E1IE0JtHD$I99 f D H I9EH9F# A} ~ IUH;V HFIMH9@H@t
H A} D^ D8 @ IMH@HHE|$A HN0HHA@HEȃ D A9u5L $HtFLT$HVLT$L $ IM9 JtI9Kd @ H
I9uuH9uuL HL$LT$L $THHtnH; L $H;= LT$ HL$H9 LT$LL$H<$WLT$LL$H<$H/ 6IVH `I Uf D HHE H
*
I H= 5e1H
HH1 LH _IHtVHD$ I HL$ HT$@ILL
_ H!PJeI +VHzRI HR1 D$LT$L $RD$LT$L $ @ LLT$Ht$L $"QL $Ht$LT$ HLT$LL$H4$PH4$LL$LT$q HvH; I}H CUHYI D D AWHW4 AVfHnAUATIHH UfHnSHflHhfo6 H HD$PL
6 HD$X H6 HT$0)D$@)T$ H HL4Hv H Hw LLyLL$ M H3 LH\HE HD$(IMc LML-4 Mi 1 HI9K L;luIHA HD$0I, @ HV HFLLyHD$0HFLL$ HD$(M LL$ HD$(HT$0H
HI$ It$ H= A HE QHj 5) 55 j52 Pj 5. 7 IHE HPM HHE twHhL[]A\A]A^A_ D H ,H H H
Z
HLLL$ IfHuZHVH
7
HT$0HFHD$( HO| LyMK HT$0H
f. H
A HH Ho H5 SL
H81TX7J ZH
H= E1`H
HxHFHLyHD$(HT$ HH
3 H5 IHII?IA[f D LL$ #f D E1IE0JtHD$I99 f D HQ I9EH9F# A} ~ IUH;V HFIMH9@H@t
H A} D^ D8 @ IMH@HHE|$A HN0HHA@HEȃ D A9u5L $HtFLT$HOLT$L $ IM9 JtI9Kd @ H
I9uuH9uuL HL$LT$L $TMHHtnH;
L $H;=G
LT$ HL$H9 LT$LL$H<$PLT$LL$H<$H/ 6IOH J Uf D HHE H
B mJ H= ]1H
HH* LHWIHtVHD$ I HL$ HT$@ILL
HHJ#J NHzJ HK1 D$LT$L $~KD$LT$L $ @ LLT$Ht$L $IL $Ht$LT$ HLT$LL$H4$IH4$LL$LT$q HvH; I}H MHJ D D AWH- AVfHnAUATIHxXH UfHnSflHHxL5 HD$`H/ HD$0 HD$h HD$8Lt$@)D$PH HLH HX H LLYLL$0M HD$8HT$@HI$ It$HH=o A HE HAVj 57# 5. j5!, Pj5p, :1 IHE HPM HHE HxL[]A\A]A^A_f D H HFLLYHD$@HFLL$0HD$8M LL$04 D Hn H H HHh H
X AHOL
H EH6 LOOD p @ HHC LYLHL$Hk+ L\$ITL$L\$HHD$0I IM`H
A L
HH HF H5 SH81MXA ZH
l H= E1YHy* LHL\$L$SL$L\$H HD$8IM HML-* H 1f HH9 L;luIHm HD$@IILLLL$0HVHT$@HFHD$8 @ HFHLYHD$8HT$0df D LL$0HT$@Bf IE0L\$E1HD$ L$Ld$IHH\$LM D O|L9 H H9CI9G { { A HSI;W IGHsH9@H@t
H { E_ D@@8 @ O HsH@HHE|$ A % Iw0IHA@IDDA} A D D>E9u*H HG f D IL9LL$H\$Ld$ D L9uuM9uuL HEIHtH; L;= M9 L!II/ oLL\$L$MH\$Ld$y;L$9HL$HtpA f D LL\$L$MH\$Ld$KFf D HHE tnH
F A H=V QV4 @ L9HL$0HT$PILL
HqAJA > HXDf D LD$,DDD$, HBu` LBhH IwH H{H LT$L $FL $LT$HA FH
A L
H@A aD D>D D>y AVAUIATUSHH= HGH H; u. 1LCIH HL[]A\A]A^ LH< IMuAIH I|$XH(H90 H HEH S HW @ @ HX H3 HJH~d1 HH9tWH;luIl$hfMt$`ID$h AD$XH/ Mt
I. HtHm uHBf D +EIHt E1 H LH5 H81MG GIHKBtI|$XfMt$`Il$hID$h AD$XHINADLuAFLuMS1 HI9t6H;|uHH H9HuH;- 1HtH9YH|$6FH|$BHI9uff. AUIHATUHSHHHWH=/ DIH H@IE L#MtI$HL[]A\A] D CHuHH[]A\A]ff. AWH" AVAUATIUSH(H LvHD$HD$ H\$H HMm I HFHHD$>H Lt$I9 H5 HF IFLH H| HH H/L ILID$LHHH: H/A Hm HY? @ M I MH H
HILH H?L
r MLIL@HHM AVHB H5 H81SDXv ZH
T H= A^PH(D[]A\A]A^A_ @ HP=IHH5! HHVAH HD$IEpf. H H
H9H H H H L- M I}H;=) HD$ H5 H9 EC IE HP8MD M Ht$11LAMH D H M @ A A Im H
DDH== OA D LvLt$ffK=f D IUBDHZ1 H= G<o1HHMm@H I. ID$LHHHUH
I A H= TNA? >H H
% H9H H H H L= M Hp I9G6 Ht$1LMHD$ EHHg Im $ HEH5Q HH H IMh H I9G/ I_H" MoHIE I/# fInfHnHt$Lfl )D$EH+I Mx Im I.Lk;f D [;f D LH;Y Im 1HL$HT$ML
h H8h $L: H9 H5 AH8t; H
G H= WLfL:& L: H
AH=:
L H= H H5 fIf D @H| M}MMuIIIm = L|$H5 I~H9t :?tfIVBt[Ll$HZ1 uInH=) 8t HLH=H; I/L9 @ IF t3H@8IHt&Ht$1ɺ LHI/f D Ht$ L~AHf H= I @ H 9j H H-r H4 H=B 8-1HLf D Ht$ LMLt$HD$ BI D ;HJc H= H
H5
vIf D H
AH= IbI_HMoHIE I/B Ht$ LH\$UAH+HH7 A A # H=) 4I, @ 1L7H
DDH=B IH {:HuHW H5 H87I/ML+7f D HXL[]A\A]A^A_ @ H> HZHVHT$(HHL$ oHVLA)D$ M HL$ HM$ It$ H= IL
n L' j AQAPj AQE1APA j5B QLX HIHPH% HI HIH Hm Hy+ @ Ly1H
M
f HL9 H;LuI HL$ H IMBHT$( L L*S HL}HL$ M~H
LH}6HH1 HD$(MG H
( Z H= 3<f D HI H
Z E1H= ;f D E1HA0JtHD$H9A f D H H9AH9F+ # y ~ HQH;V HFHyH9AHAt
H DY DV DD@@8 A HyHA@HE|$A | L^0HHA@IEDAw Az DD E9u9H $HtJLL$H>+LL$H $ IM9 JtH9K @ L9uuL9uuHϺ LL$H $)HHtiH;A H $H;= LL$ L9 LL$HL$H<$G,LL$HL$H<$H/ GZHD$ a+H
A L
HpiZ f. HL$ HT$0ILL
P H$xHL$ ouZ Ef D L'@ LL$HL$$'LL$HL$$5 @ *HrpZ HLL$Ht$H $%H $Ht$LL$C HLL$HL$H4$%H4$HL$LL$ HvH HyHaDD DD ff. fAWH' AVAUATIUSHHXL-& HD$0H HD$ HD$8HD$@ Ll$(H HL4H
H Hz HH H
AHOL
EH~ IHLOHHY H SH5 H81`+XW ZH
a H=V E1n7HXL[]A\A]A^A_ @ H> HZHVHT$(HHL$ oHVLA)D$ M HL$ HM$ It$ H= IL
L
j AQAPj AQE1APA j5 QL HIHPH% HI HIH Hm H$ @ Ly1H
3 M
f HL9 H;LuI HL$ H IMBHT$( L LX$S HL}HL$ M~HH LH/HH1 HD$(MG H
UW H=x 5f D HI H
S GW E1H=@ [5f D E1HA0JtHD$H9A f D Hi H9AH9F+ # y ~ HQH;V HFHyH9AHAt
H DY DV DD@@8 A HyHA@HE|$A | L^0HHA@IEDAw Az DD E9u9H $HtJLL$H$LL$H $ IM9 JtH9K @ L9uuL9uuHϺ LL$H $p"HHtiH; H $H;=c LL$ L9 LL$HL$H<$%LL$HL$H<$H/ GZHD$ $H
A L
HpV f. HL$ HT$0ILL
r HA xHL$ oW Ef D L !@ LL$HL$$!LL$HL$$5 @ $HrV HLL$Ht$H $: H $Ht$LL$C HLL$HL$H4$ H4$HL$LL$ HvH HyHaDD DD ff. fAWH AVAUATIUSHHXL- HD$0H` HD$ HD$8HD$@ Ll$(H HL4H
H Hz HH H
AHOL
EH IHLOHH H SH52 H81$XTV ZH
[ H= E10HXL[]A\A]A^A_ @ H> HZHVHT$(HHL$ oHVLA)D$ M HL$ HM$ It$ H=I IL
. L j AQAPj AQE1APA j5B QL HIHPH% HI HHIH Hm H9 @ Ly1H
M
f HL9 H;LuI HL$ H IMBHT$( L L S HL}HL$ M~H LH=)HH1 HD$(MG H
V H= .f D HI H
V E1H= .f D E1HA0JtHD$H9A f D H H9AH9F+ # y ~ HQH;V HFHyH9AHAt
H DY DV DD@@8 A HyHA@HE|$A | L^0HHA@IEDAw Az DD E9u9H $HtJLL$H LL$H $ IM9 JtH9K @ L9uuL9uuHϺ LL$H $HHtiH; H $H;= LL$ L9 LL$HL$H<$ LL$HL$H<$H/ GZHD$ ! H
a A L
S Hp8V f. HL$ HT$0ILL
HxHL$ oDV Ef D L@ LL$HL$$fLL$HL$$5 @ k Hr?V HLL$Ht$H $H $Ht$LL$C HLL$HL$H4$bH4$HL$LL$ HvH HyHaDD DD ff. fAWH fAVfHnAUIHH ATIUSHxHD$`Hk )D$0fHnflHD$@HD$h )D$PHy HL AA D D6E9uAHL$HtTLL$E1HLD$LD$LL$HL$A fIAL9 IJtH9Kf L5! L9uuL9uuHϺ LL$LD$HL$HHtPH; HL$H;= LD$LL$u L9 DH/] ELEaHD$8 %H% HHA H
Q H5 jL
9 A H3 H813Y^T H
( U H=p 3%f D HI$j H
U E1H=7 $ D HL$0HT$PMLL
H!T 7 LL$(LD$HL$H|$LL$(LD$HL$H|$A HyHT D LL$LD$HL$LL$LD$HL${HLL$(Ht$LD$HL$HL$LD$Ht$LL$(P HLL$(LD$HL$Ht$Ht$HL$LD$LL$(i HvH L HT D D6D D6HuH
$ A T AWH AVAUATUSHH HD$PH HD$XHP HD$`H HD$hH H|$HD$0 HD$8 HD$@ HD$p HD$HH LHL$0HT$PILL
O H yM HuM D HD$HL|$0H\$8Lt$@HD$H H( h E111HA LIH H8 H H( h E111HA HHH H8 HX L( h E111HA LAIH H8
EA;D$ H% H
H9H< H H H L
M@ IALL$LH5 H He LL$IMj I)X H H
2 H9H H Hu H H H HCH5 HH HW IHHM HH H I9A2 LHt$X LL$HD$P Ld$XHl$`LL$ILMo H) Hu I9G Ht$X LHD$P Lt$XMII.
MǺ
AcO M I( L; L;Y ^ L;o Q LLT$LT$w I*# H H
H9Hk H| H H L=h M7 IGH5 LH H IM I/ H H
H9H H H H H
H HALL$ HHL$H5 H H HL$LL$ IHHM\ HH H I9Fs Ht$X LLLL$HD$P Hl$XLl$`LL$IAO
M H+ HW I9A LHt$X LL$HD$P L|$XLL$ILI/ AO
M H+ L;n L;4 u
L;N I* H H
m H9H HT H H L
@ M IALL$LH5t H H LL$IM I) H H= H9x H H H H H HCH5 HH H IHHM HH H I9A LHt$X LL$HD$P Ld$XLl$`LL$ILMd H) Hd I9G Ht$X LLHD$P Lt$XII. Iߺ
AP M
H+& L; L;H L;^ LLT$ LT$ I*o HD$HH=g ML Hp IL
Lj AQAUj AQUj HT$PLT$H H@LT$HI I* L2 D H& H HH
p Hr AHMEIHH7 HX H5 SL
0 H817
XM ZH
8 H= E1EHĈ L[]A\A]A^A_H0 HFHD$HD$HLvo&H^L>Lt$@)d$0 @ HLAHD$0p LAH= LHLD$HD$0H LD$LuIN D HD$|f D L HLL$LL$HGA7O
H+ H߉T$LL$LL$T$LːMt
I/ Ht
H+ H
DH=a I,$A + Ht Hm M}Im rLef. H A;E*"L f.N f( LL$ v f.. L$ D$ HL$ N f. L$ f( f/V f/T$ f.L$F
Lt$f(T$ I HHL$ HL$HI T$ HD$(f(HL$LL$(HI9 D$LL$ HL$LL$ HH& HH HL5C j H A PH='c Sj PAWj PHT$`LL$hHL$X) HPHL$LL$HIB H) I)z I/ H+ I,$t0Hm D H( HI L ID$0LD$1HD$ H\$LMI̐NlM9 H I9FI9EU M A~ A} IVI;U IEIvH9@H@t
H EV EM DD@@8urA I~HA Iu0IHA@IDDA A DDE9u'H H II9HD$@ H HH H
H5k jL
A H H81Y^M L;5 uuL;-Կ urL LIHcH; L;-u u
L;- y Im LD$H\$L @ LD$H\$LIf. H߉T$T$9 M& ID$0LD$1HD$ H\$LMI̐NlM9 H+ I9FI9EU M A~ o A} y IVI;U IEIvH9@H@t
H EV EM DD@@8urA e I~HA Iu0IHA@IDDA\ AW DDE9u'H Hq II9HD$8 UH' HHq A H5 jL
j H
k H8Hr 1c_M AX&f D L;5a uuL;-T urL L IHcH;/ L;- u
L;- ! Im LD$H\$L @ LD$H\$LIf. LLT$ LD$ LT$ LD$ E1 A?N D LLT$LT$f ANN ^H
8 0N E1H= @ L LP} I~HA@HE|$ 1 D L(I~HA@HE|$ LLT$LT$g
AO MI*LT$T$DH
k H= LI_HfMGHI I/ fInfHnLǺ flHt$PLD$)D$PH+LD$I:HLT$ LD$]LT$ LD$
AgO %L6H=: H H5 7HM EM ; LD$(D$( LX. L@! LLL$LL$Xf LT$T$
IuHU H=q Hb H5c nIf D
A0O HLL$#LL$gf H= 蔸Is @ LL$If D
A2O La D LD$(D$(@L+[LwFHM HLL$cLL$ LLT$LLT$?
A5O 1H=9 H H5 6HIuHkDDHLT$LT$LyHLL$LL$XHiLRH= 'Hj IIYHIIHHI) fInfHnHϺ flHt$PHL$Hl$`)D$PH+HL$IHHL$HL$
ALO 1H)pHωT$T$[ D$L$H AoN A L$ L$ H AyN L$ D$(yL$ T$(H AN @ DDDDH5 H= 1AIH HAN wI/
vLT$T$aH54 H=- 1IH3 HAvO $I/
#H5 H= 1IH HAN I/
h
AO H=9 H
H5 6IH5 H=r 13IH HAN iI/
hHLL$LL$
AO 1!wI;H= ILLT$nLT$JH\H=` H! LL$H5 XLL$H DD
AN LE1
AO #H
S A HM HLT$LT$1AO
I)LωT$HL$HL$T$f D H= LL$LL$HT
AO ?-LL$ HL$ImL3MFMI^I HI. fInfHnHt$PHflƺ LL$ LD$Ll$`)D$PGLD$LL$ II(TLLL$LL$=A O
MqMOIYIHI) fInfInHt$PHflź )D$PI.I7LLT$7LT$ AO
nH5 H= 1HIH HAO ~I/
}LHL$HL$dH= H} H5~ ɳI)
AO /LLD$LD$H= IALL$I
AO o
AO 1H=; 趰H"AO
fI1
AO IYHAIIHHI) fInfHnHϺ flHt$PHL$Ll$`)D$PH+HL$I HHL$HL$MOM I_IHI/$ fInfInHt$PHflź LL$)D$PLL$II)LLT$
LT$
AP LLD$ LL$LL$LD$ H5P H=9 1IH HA&P 0I/
/
ACP cLt
ArO
AN
AN
AN LLL$"LL$LHL$ HL$3
AO
A"P LYf AWH AVfHnAUATUHSH H fHnflHxfo L- HD$`H H|$L5 HD$h HD$@)D$P)T$0HU IL H b L.Ll$0} D H H^H\$@LvLt$8f. H L@f. D$ L$f. \D$H H
Һ D$H9H H H
H L= M IGH5 LH Hp
IIHMC
IHG D$LD$ LD$ HI H I9@ LHt$X LL$XLL$(LD$ HD$P LD$ LL$(IMI) M I/ L;-ϧ L;- u
L;- ! DIm E Lt$D$M IE IHF D$IHK HC LMLH58 H H= j A HP5 j PASL\$Hj P L\$XIHPH Im I/ I+A A LLL$3LL$f HK LAM H\$@f H
Y A HH( HT H5 UL
! H81(X: ZH
) H=ޒ E16HxL[]A\A]A^A_ @ H $ @ Hh LL\$SL\$ f E1LLL$0LL$MHHm H L LvHLALt$8HD$0f D LLD$LD$zf LHH
H IHII?IA Ll$0kf D 1IF0ItHD$ I9B H! I9FH9F+ # A~ ( ~ V IVH;V HFI~H9AHAt
H En D^ DD@@8 A { I~HA@HE|$ A S Ln0HHA@IEDA( A D D.E9u8LL$HtHLD$E1HQLD$LL$A HI9 ItI9I\ @ L- M9uuL9uuL LL$LD$ HHtqH;Q LD$H;= LL$ L9 LL$(LD$H|$ULL$(LD$H|$AH/Q E8EJrH : E1E11E1E1{ : E1MtI/tjMt
I) MtI(t8H
p H=( MI,$E1 Lljt$t$f D Lt$LL$LD$t$LL$LD$m Lωt$LD$gt$LD$Vf E1E1E1E1| : D LL\$#L\$hf H O @ H LLLD$LD$HI HD$0If. HL$0HT$PILL
, L:: LLD$ {LD$ LLT$cLT$Qf LLL$L\$>LL$L\$ LK < E1f D LAƅQ; E1Im m Lt$E1E1t$E1E1 @ D4 .H E1E1 ; E1E1QD$D$HE1E1 ; E1E1 D H=9 H H5 6If D H= L\$臞L\$ILD$ LD$H: LZ L LM LD$D$ E1E1E1ɻ ; @H=i Hʰ H5˰ fIf D L0 E1E1M ; E1I+A L߉t$LL$LD$LD$LL$t$f H= TI5 @ IP LHD$LL$BMhMUMxIE II( fHnfInHt$PLflĺ Ld$`)D$PIm I;L,. E1E1ɻ ; E1E1 ; E1 ; f D H= H2 H53 ޞI-f D LL\$LL$L\$LL$9 LL\$HD$vL\$LL$ E1 ; .f D H=Q ̛I @ LL$If D LL$LD$ LL$LD$f. LHt$(LL$LD$YLD$LL$Ht$(f D HLL$(LD$Ht$!Ht$LD$LL$(|. D H= Hʭ L\$H5ƭ 聝L\$IG @ ; ,HvH I~H E1E1E1ɻ 3; L\$LD$I f ; I(B E1 @ LD$LD$H: f D E1E1M 5; k[I H=y IE @ < 4f MWMMGII I/ fInfInLǺ flHt$PL\$ LT$LD$)D$PYLT$LD$L\$ II*]LLL$ L\$LD$LL$ L\$LD$2fMCMGMSI II+] fInfInL flHt$PLD$ LL$LT$)D$PLD$ LT$LL$II(LLL$LT$LL$LT$ @ E1Mӻ < E1E1Mǻ 8; MpM.MxIII( fInfInHt$PLflǺ LL$ )D$PI.LL$ ILLL$ lLL$ E1E1ɻ M; -D D.H5 H= 1kIHk HI// /< E1E1 L< H5R H=3 1IH& HPI/ E1E1 a; E1E1{~; L; D D.ME1E1; uLL\$ LT$LD$4LD$LT$L\$ LLL$ LT$LD$ LD$LT$LL$ xLLL$ LL$ )L E1/< E1LE1ɻ +< E1E1E1ɻ ]; jLljt$L\$yL\$t$E1VE1E1E1E1: AWH AVAUATUSHH L= L5 HD$PH- HD$XH HD$`H-( H|$HD$0 HD$hHD$p L|$8L|$@Lt$HH L4Ha H! IHcHHFHD$HHFHD$@LnH.IL$Ll$8Hl$0H H H H H HD$@Ll$8Lt$HH$HE IE M9R L% Lt$XHD$P I|$H;= tH5 S IT$B Ht$XHZE1 H=5v LD$Ht$Ht$LD$u@LIM Hu H H5
v H8f. H
b- E1H= S ID$Ht$X t%H@8IHtL1ɺ I L SIMtID$H5 LH H IM.
L;W L; j M9a LLT$lLT$ I*H H H@H9f @ HQ H H L= M IBLT$LH5 H HQ LT$IIHMO IH ICH5 H H H=9t L\$Ht$L\$ 1LHt$HHL\$ I+ H+o ID$H5 LH H HH H[ H9G LOM L_IIH/^ LHt$P LL$PLL$L\$mLL$L\$HI) H I+
I,$
IH. H
H9H5 H Hm H H z H HCH5ޱ HH HS IHHMN HH
L LL\$L\$HIT I+ L; L;i u M9 I* l HM H
H9H; H Hf H L M ICL\$LH5 H HV L\$IIHM) IHo Lֺ LLT$LT$HHs I*w H; H; ~ u L9 H+ i Hb H
H9Hp H H H H H( H5 H螿IHg H+{ L LL\$L\$HI I+ L; L; M9 LLT$LT$ I* HD$HE1L HL LH IARHT$LT$ HXZHLT$ A<. A f HuLH~PM\$H- M 1 @ HI9 I;luIHp HD$HHHl Hl$0 I*L3f D H |H H L<$LnH.Ll$8Hl$0HE IE M9HE I/ H* H H Hm t IHwf Hv LvLt$HHFH$HD$@w HD$HE1H LL LH IARHT$LT$8 _AXHLT$H I* L9<$H HII,$ H+o @ Ht Hm Im - HĈ L[]A\A]A^A_ H.HIHl$01 HIH] LLH $>HD$0HH H $HH.L<$MHl$0i @ LLT$LT$FA- A
17 f H
A L
k HHQ H H5r SH81XX- ZH
Y H=6y E1fHɫ LLH $ZH $HI
HD$8HH H LLH $"H $HE HD$@H LHr HIH2 D LL\$L\$ MD$2f D Ap- A 1I*u"E1LL $L $Mt
I+z DDH
< A H=x KI,$0 HH+HL9u M9u L HIH H;ӊ L;- u M9) Im ; k MHL$H\$IL4$ H9 HL$0HT$PILL
] Lm, L n- H
H=v #I,$A z1Lh HXk LHy HL\$3L\$f LHD$LT$f L HE0HL$E1HD$ L4$MMH\$HLf. MlL92 H H9CI9E
{ A} HSI;U IEHsH9@H@t
H DS EM DD@@8u{A A H{HA@HE|$ A Iu0IHA@IDDA6
A DDE9u&HtHHf D HI9MH\$L4$f. MHL$H\$IL4$KHHɌ H
AHOL
EH LOOD@ f. I< H Lj HD$@Hl$0Lt$HH$ IH5e LIH H;5 L; L; $ LL $JL $ I+
H5 LIH( H;Æ H; M9 LL $L $
I+
I. HH H
1 H9H H HV H L M ICL $LH5 H H L $IIHM IH He I9@L LHt$X L$HD$P H\$XL$IMM I) IBL$LH5 H H L$IIHMV IH H5D LϺ L $L $HID I) L; L; M9 LL$0L$A I* E&IHC I9F Ht$X LHD$P H\$XyMIM
I) I,$pL LIL\$LL$LL$L\$fLq HD$HE1L HL LH IASHT$L\$X Y^HL\$H I+L3 f D H
IA A. 1.fL 1LL\$L\$HH=A A- 1 D D, f D DF A
A- H= HR H5S ~Hf D LL\$CL\$Sf H=9 贁H @ I IA- 1A
fLLT$LT$zf A
A- 1 D L| Ht$X1H|$HD$P H|$HIf D LL$lL$ H߉D$TD$J LL$MAx/ A Ay/ IH\ H
H9H Hl H| H L X MY H5 LL\$蓧L\$HI! I+ Lֺ LLT$úLT$HI I*| L; w L; w u M9l LL\$L\$ I+ ] HD$E1LHL LH IQ ASHT$L\$ ^_HL\$HxA A. 1f. S. H= H; H5< xI{H=x uIgLHD$NL\$AX. A AA AU. 1LLLLL$L$L$LL$IA AZ. 1
LHD$ѸLT$\LHD$貸LT$ H H
* H9H H H H L M H5 LLT$HLT$HI\ I* L LL\$xL\$HI I+r L;u L;\u
M9 LLT$諻LT$= I* HD$E1 LHL LH IASARHT$LT$ HXZHLT$EA. A n1A. A [H=V sIfH=B Hӄ H5Ԅ ?vID1A A~. :LA. A 1LHD$϶L\$mA A. 1LHD$襶L\$^LHD$莶LT$w1A. A A A. 1 . H=X rI{H=D HŃ H5ƃ AuIYA A. 12Ho H
x H9H H_ H H L K M H53 LL\$覢L\$HIb I+A Lֺ LLT$ֵLT$HI I* L; r L; r M9 LL\$ L\$ I+ HD$ LHL LH IAPE1ASHT$L\$ AYAZHL\$HA A/ 1L貴{LHD$蘴L\$#MA A A. 11A/ A hLHD$MLT$A A/ 1\ . H=* pI:H= Hw H5x sI1A. A 1A A. H=Γ IpI/ A GL1 A A/ 1EH=z L9 ID$ t H;o upL
IM H=G Ht$XL\$XH L $HD$P !L $HItQI+tAL'I.t ]/ LjILm ]/ LVA AX/ 1m V/ L*A1/ A 1 jLHD$LT$A A// 1 LHD$ӰL\$1A,/ A 1A A*/ H= 'mIFH= H} H5} oI$ff. fAWAVAUATUHHH rIH HE H H
S H9Hi H: H H L5& M5 IFH5 LH Ho IIHIM7 H L讴IHb IEL M H=M 貮 LHLAIֲM} Im tfI.tPHm t9I,$t"HL]A\A]A^A_ÐL(m Lf D Hf D Lf D LI.uH I.Ao Im D E1H
$q H=u 9D @ LHL貳IHtIm zf. HBIILl$H$ HD$ t'L/IH E1 1LLLPtH$H@ uH4k Hft H5K E1H819 @ Ao D H= Hʀ H5ˀ lIf D Ao HLq @ CI H= iIF @ Ao s D L(lH$j H5K H8譭6L 9ff. AWAVAUATUHHH IH HE H* H
H9Hi H H H L5 M5 IFH5: LH Ho IIHIM7 H L>IHb IEL M H=J B LHLAIfM} Im tfI.tPHm t9I,$t"HL]A\A]A^A_ÐL踫m L訫f D H蘫f D L舫f D LxI.u苮H I.AYo Im D E1H
m H=q ɼD @ LHLBIHtIm zf. HBIILl$H$ HD$ t'L迯IH E1 1LLLtH$H@ uHg Hq H5vH E1H81ɯ @ ARo D H= HJ} H5K} FiIf D ATo HL @ ӯI H=9 lfIF @ AWo s D L踩lHf H5-H H8=6L萩9ff. ATUHH= Hk| H9G HR| H H H->| H HEH5ڃ HH H HM HQHU Ht4HtH]A\ HHD$HD$H]A\f D Gn H H
Bk H=\ RH1]A\ L% IT$LHH~ H-s{ H@Hp{ Ht[HE $En f H= dH @ f D Ht$ t$I +HuLdHf D AWH AVAUATUSHHHHD$( HD$0HD$8 HH HL4HP H L.HILl$(H H} H=z H9x Hrz H H H-^z HM L%d L9 HELHH H( I$LHm HHD$HD$HH[]A\A]A^A_f. HH%d Hwm H5J SL
%i A H
Ii H81Xn ZH
i H=Z )1HH[]A\A]A^A_ HuL.Ll$( D LyL- 1Mr HL9 L;luM,Ll$(MT IOH H
xh n H=hY 胷1U @ H=) Hx H5x dH`f D IE0E1HD$ @ JtI9 Hkc I9EH9F
A} * ~ P IUH;V HFI}H9AHAt
H EU DN DD@@8 A - I}HA@HE|$A LV0HHA@IEDA A DDE9u2H LD$E1H蜦LD$A IM9 f D L%a M9uuL9uuL LD$腤HHt^H;a LD$H;=wa 4 L9+ LD$H|$ħLD$H|$AH/ E\Ey'HD$( Hn
f D O,w H= `H. @ Hz H H}H9&HX H HqH~ 1 H;THH9uHu` HJH5ZF HWH81|Hm H
ye n H=iV 脴1V D D HL$(HT$0ILL
Zi H號Q Ll$( H
e n HD$H=U HD$N @ HXR LD$FLD$_ @ LLD$Ht$覠Ht$LD$@ HLD$Ht$vHt$LD$ HvH I}HDDDDH^ H5c H8/~H H H93HuH;_ !-f n f D AWH AVAUATIUSHHhL
f L-^ HD$@H HD$HHD$P LL$0Ll$8H HLH H0 HO HH-c IH
c Hgg HIHH] I?SIH5fD H8L
c A1XcL ZH
b H=T E1HhL[]A\A]A^A_ D H HL H\MHI$ It$ H= A HE Hvy HH, AUj RPj RLPj5O q IHE HPM% HHE XH觟KfoLvLY)D$0Mn LL$0\ @ LYMHHԁ LHL\$L$ L$L\$HI IHD$0M~~HML52 H 1 D HH9 L;tuM4M Lt$8IRLvLt$8LLL$0f. LLYLL$0MLt$8 D M HHE H
a Y L H=R
IF0L\$E1HD$ L$Ld$IHH\$LM D O|L9 H[ H9CI9G { K A X HSI;W IGHsH9@H@t
H { E_ D@@8 @ HsH@HHE|$ A Iw0IHA@IDDA A D D>E9u*H H4 f D IL9LL$H\$Ld$ D L9uuM9uuL HIHtH;GZ L;=
Z M9 LaI/ oLL\$L$MH\$Ld$y;L$yL$Ht8ML f D LL\$L$MH\$Ld$O4&f D HL$0HT$@ILL
b Hx%LL$0< HQ ?RL Tf D LD$,贛D$,$ H Lx IwH H{HLT$L $qL $LT$HFL D D>D D>ff. AWHw} AVAUATIUSHHhL
6 L-oX HD$@H HD$HHD$P LL$0Ll$8H HLH H0 HO HH\ IH
\ Ha HIHHW I?SIH56> H8L
] A1蹟X) ZH
\ H=N E1ǫHhL[]A\A]A^A_ D H HL H\MHI$ It$HH=" A HE HFs HH~ AUj RPj RLPj5 | A IHE HPM% HHE XHwKfoLvLY)D$0Mn LL$0\ @ LYMHH{ LHL\$L$ФL$L\$HI IHD$0M~~HML5| H 1 D HH9 L;tuM4M Lt$8IRLvLt$8LLL$0f. LLYLL$0MLt$8 D M HHE H
Z : ) H=L ݩ IF0L\$E1HD$ L$Ld$IHH\$LM D O|L9 HU H9CI9G { K A X HSI;W IGHsH9@H@t
H { E_ D@@8 @ HsH@HHE|$ A Iw0IHA@IDDA A D D>E9u*H H f D IL9LL$H\$Ld$ D L9uuM9uuL HIHtH;T L;=S M9 L1I/ oLL\$L$MH\$Ld$y;L$IL$Ht8) f D LL\$L$MH\$Ld$O4&f D HL$0HT$@ILL
] H蹒x%LL$0< H谕Q ?) Tf D LD$,脕D$,$ H Lؓx IwH H{HLT$L $AL $LT$H|) D D>D D>ff. AWHx AVAUIATUSHHHHD$( HD$0HD$8 Hu IL4H H H.LAHl$(M HEH G u H LR H9 H;\Q L`pM I|$ 1ΕIH HHAT$I.IZ M L5jk M9Q HQ I9D$I9F A|$ G A~ T IT$I;V ID$INH9@H@t
H A|$ Av 8m @ b @IL$0MD$HIDH@ 4 IN0IH@IDHȃ DA9 HU E1H֔AI,$\ E7 HHO HRY H5_6 SL
T A H
U H81ؗX% ZH
T 7 H=VF E1HHL[]A\A]A^A_ @ HuH.Hl$( D H5l H! H5w H=ey 1&~IH% HbI,$m 8& ; D H
0T H=E E1BW D LyH-=u 1M HL9 I;luI,Hl$(Ha MGH5u H! 8HE E1HEH5m HH H
IM
ID$L5v H HK H=D/ W 1LLI-M I,$ HM I9F LPf. J
I.x AEXHEHH5 m H H
IM
IFL%#v H HK H=. OW 1LLIuM I.R ID$ g ID$HPHM H3 HY LHcЉH9 / I,$ I}A]PHH5-s HGH H
ЅG
HL H IHm MI/L+f D H@hH H@H 1HI
H
qL I9uuI9 I,$uLH5t H=*v 1zIHL H'I,$s & LT$t$rt$T$ D HX
LLHL$苎IH, H;K AH;}K D HL$I9 LˑI/A E%A& r E11I,$A E1E1 HEL I$ AF D LeI$fI,$K 蠑IH HEH9' H;xJ LppMtAI~ t:1IH HHAVI/Iu8L .f. H@hHs H@Hf 1HIM3 H5lg LL衑 I. ڐIH HEH9 H;I L LxpMtKI tD *HR HD$HHAWLL$II)u;LHD$7LD$'H@hH> H@H1 HIM< A& v D I$E11HI$uC D LLD$ˋMLD$u'+ I,$
1E1E1u A& I.tLMtI(t1H
N DE1H={? H E1 D LPf D LLD$;LD$ @ HEL0IMLd LZ LD$D$o HE0E1HD$ @ KtH9 HH H9EH9F
} 3 ~ Y HEH;F HVHMH9@H@t
H D] DV DD8 A p H}HA@HE|$A H HN0HHA@HEʃ. DA9u1H LL$HLL$ IM9 f D H
G H9uuH9uuH HL$LL$踉HHt^H;F LL$H;=F / HL$H9! LL$H|$LL$H|$H/f Vy"HD$( HK% K,o HEL@I H5f LLLD$荍LD$ I(6 HEH9 H;E D HXpH/ H{ $ IH\ HHSI/I Mu H5i LLLD$LD$c I( H5k LLό I. HuH8 H LE1f D LuI L蘇 L與 Ht+AT$HEf D LX 1f H@hH H@H HI @ I/E2L 蛈IH HH脇I/ILHD$誆LD$E11A& u H HC H5& H8 膉H H
H s & H=C: ֗H5k H=m 1[rIH H藆I,$q v& :k D HEL@I HL$(HT$0ILL
}L L衂 Hl$() L1L車IH A ' | H
G r & E1H=M9 LE I g L ~ '' H
G H=9 E1蘖 L L1LIH I.uL貄H
*G } ' H=8 5+AD$ AT$H H HHcЉH9f AD$ AT$H H HcЉH9 @ LE(I 11Ҿ HwIH, H5 a HLY$ I/ 11Ҿ H6IH H5S` HL I/~ I$MLkf D L舃 [Ik | ' S1IHHHF D D$GD$HI.uL
H
E | ' E1H=6 芔 D l "& A& v E11A& v D$LL$蚂D$LL$~ @ } ' kf KI HLL$Ht$Ht$LL$5 HLL$Ht$螀Ht$LL$ A ' | HH> H5a H8q @ HvH H}H A& v 蛄 f D 19IHHH"@ D L^ LF CHZH> H5 H8褁? A& u E1 D IvH I|$HDA& v LHD$蝀LD$[LE1w & pl (& D{ IHt_HHDOL-AL uD'E1A& v % E1A& v Lx & LA& Mx E1Ly & LA& My E1A ' } H@`HtH HtsLIHtfH= I9Fu+f. LmI.L$|LH5TD 0mIHu1A& r HxH,< H5@ H8m]H9JH
-A m 4& H=2 8MA& u E11E1H
@ q r& H=k2 LQ~H
@ u & H=<2 ϏL"~ff. fAWHc AVAUIATUSHH HD$@ H$ HDŽ$ H HL4H H L&HILd$@H HD$H LHD$P HD$X HD$` HD$h HD$p HD$x HD$H' HT I|$H9t:HX H HqH 1 D HH9 H;TuH H5NY LHq HH|$HHk HGH5a H H HD$PH|$HH H/ H|$PH : HD$H H-9 H9H9 H;=9 x #Aƅ H|$PH/ HD$P EO I|$HR H9 H H5|[ LH HH|$PH H5Fa H9 HGH;9 HGH E1Hi H/3 HD$P E H5^ LohHD$PHHR% H9H9 H;=8 Å% H|$PH/ HD$P k H8 HD$I9 ID$H5^ HD$ID$H H LHH|$PH 111"vHD$HH H|$PH/ H|$HL5Q8 HD$P L9w HoHEHn Ht%HcGHHcHEHH H|$HH/8 ID$H5 V LHD$H H H HH|$HH HGH5W H H HD$PH|$HH H/ HD$H H|$PL9w LgID$H Mt%HcGIHcHEII H|$PH/ HO H ~K HD$P H9Xo H\K H H H=HK H|$PH HGH5U H H HD$HLT$PH I*8 HD$P LzHD$PH! o{HD$XIH HD$PHD$P IG|HD$PH
HN H J H9X HrJ Hm H H ^J H HCH5U HH HO IL|$`M H+ HT$`H5S H|$P| H|$`H/ HT$PHt$XHD$` H|$HdHD$`IH H|$HH/; HD$H H|$XH/7 HD$X H|$PH/ HD$P L|$`HD$` L;|$ I H5hS Mw rHH I H5-S rHD$PHH ! HD$X H4 H9G! HGHD$XH! HWH HH|$PHT$PH/0 HD$XH|$P H$ H$ H|$XHD$`HtH/` HD$`HD$X H ! H|$PH/V HD$P H|$`H/4 HD$` :uHL$xHT$pH Ht$h/xHL$HI H Hl$IE ILH\$ Ll$HL|$(If D LH] HD$HT$LH,LHxLLHrxLLLdxL+l$IuH\$ L|$(HD$H8 HD$`H HD$` H|$hHt
H/M HD$h H|$pHt
H/: HD$p H|$xHt
H/' H5Z 1HHD$x 7aHD$xH+ H\$xHC" H+ HD$x HD$H ( f HH1 Hl; H5o SL
6 A H
7 H81yXe ZH
6 H=( 1HĘ []A\A]A^A_ D HuL&Ld$@ D LyL%%Y 1M
HL9 L;duM$Ld$@M
IO;D s1H/
HD$P H|J I|$H96 H5V L`HD$XIH* H5X H9 H@H;1 p 1I I/7 HD$X H5R L`HD$XIH H5yX HuÅ! H|$XH/W HD$X % H5N L_HD$XIH$ H5V H_HD$PH$ H|$XH/& HH H D HD$X H9X% H^D Hq& H L=JD L|$XME& H5R L%_HD$`IH& H|$XH/# H\$PHl$`HD$X H+0 HD$P H|$`H/ HD$` H@H HPH9 H;C g$ HC H% H L=C L|$`Mi# H5VV Ln^HD$PHH% H|$`H/ HD$` uHD$`IH% HV H5dT H v HT$`H5 X H|$PN]HD$XIH$ H|$PH/s" HD$P H|$`H/" HD$` H|$XH/u" HD$X H G H B H9X# HnB H`# H L=ZB L|$`M# H5eL LU]HD$PH" H|$`H/ H51W LHD$` HD$`IH(# H|$PH-#- 1HD$H A H9o " fHnfInL$ flI4L)$ 9yH|$HHD$XHt
H/ HD$H H|$`H/& HD$` L|$XMp! H|$PH/ I H5K HD$P L|$XHD$X (jHH{" I H56K jHD$PHk" HD$` H9h$" HPHT$`H" H@HLA H H|$PHD$PH/a HD$`H|$PLHH$ xH|$`HD$XHtH/d HD$XHD$` H # H|$PH/H HD$P H|$XH/ HD$X KmHL$hHT$pH Ht$xHD$;pHl$HH I HL IH9 11HLOiHD$XHH~ H5W+ L/lV H|$XH/ 11HLHD$X iHD$XHHZ LLe H|$XH/ LHLHD$X Ve! H/H|$xHt
H/K" HD$x H|$pHt
H/" HD$p H|$hHt
H/" H5R 1HHD$h YHD$hH+I" H\$hH*" H+! HD$h H-* HD$ H D H H9HuH;$* rf D HX Ht,HqH~K1 HH9t7H;Tu H H9HuH;) pf D HqB H = H9X H= H
H L== L|$`M LLllà H|$`H/ HD$` d HA H
C= H9H H*= H8 H L== L|$`M} H5P L1XHD$PH H|$`H/$ HD$` mHD$`IH HP H HP HD$`HPI|$H59J WHD$XIH& H@H;( IHD$XHD$HHL H|$XH/p HD$HHL$`HD$X HpP H @Y
HA HJ HD$H H HD$`HD$(HH{J HC(pIHe D$ H HAF IV0INH@HDHT$1\$ E1HLd$0Ld$(Ll$8I> @ Hr0HzH@HD;D$ I1LLkIII" KTz
HjHtHH)I9 J uHrH+if D A+f A 1E1H|$HH H/LT$P Mt
I* H|$XHt
H/ Ht
H+ H|$`Ht
H/| H
$+ DDH= 3z1M1I/'LHD$qhHD$ [hLT$P_LHh` H8hs +hzf D hGf D ID$0E1Lt$MHD$ ILLl$M D MdM9 H% I9EI9D$ A} Z A|$ c IUI;T$ ID$IuH9@H@t
H EU EL$ DD@@8u}A I}HA@HE|$ A It$0IHA@IDDA A;
DDE9u'H Hh HL9 f D L
1$ M9uuM9uuL LLL$fIHt\H;$ L;%# LL$M9 LjI,$ mILl$LMLt$y9HD$@ 0iHWe D ILl$LMLt$O$ @ H=IM H5L 1RHD$PHH =fH|$PH/tGHD$P H|$HARf A E11Hy%he"Ve1Ag A 2E1AH=
J !I D eif D ef D d#f D drf D D$ LHHHH|$g8 Ld gH H|$HH7HL$@ILHH$ L
1+ Na: Ld$@H|$`Ld$0Lt$HLl$8H/u-dHD$` fHD$`IH HD$HIGHIK H HT$`HD$H HB hHD$HHH H.I H5F h
HT$HHt$`H|$POHD$XIHG H|$PH/ HD$P H|$`H/ HD$` H|$HH/ HD$H H|$XH/ HD$X I H5?? ]IH@ I H5? ]HD$HHH{ HD$` H H9G HGHD$`H HWH HH|$HHT$HH/ HD$`H|$H H$ H$ kH|$`HD$XHtH/, HD$XHD$` H H|$HH/ HD$H H|$XH/ HD$X I aHL$xHT$pH Ht$hHdHl$HH HLf 11LHI$]HD$XH1 11HL]HD$HH
HT$XHLY H|$XH/ HT$HLLHD$X YY+ H|$HH/ HD$H HNH|$hHt
H/ HD$h H|$pHt
H/ HD$p H|$xHt
H/X H5F 1LHD$x MHD$xI/" L|$xMh I/
H! H 9cH H|$PILfHLT$PA;f A E11WH57 Ld)Af A 1E1
@ H`H|$HAf A mLeH
e)A=f A BLT$PAf A a_A@f A 1E1_eIHHaI/HLf_LT$PAf A &eH+Af A 1E1H/ HD$P _!H H o GH H Af A GdHHT$(8]HT$(LI. HD$H LT$PA?i A& /LD$v^D$0h^^^T^L\ L\H|$HAf A cIHnH`I.IdL]WH== H/ H5/ HH+ H5 H8D^]#It$HyI}HUI I Dg GI I H=d= HAf A c'']HD$H H3 HA HX= HD$H H HD$`HHD$(H7= HA(NcIH!HD$ HH|$HAf A
\YH IHD$H\$LLL|$I IIMIf D LLջ HLH0H3I7H0HII)IuH\$L|$\\[H|$HAjf A XaH1Af A IFHHD$[Hv2 I|$HD$P [[H|$HAf A DDhH=e; HV- H5W- bHE1Af A ![[L
[Af A H=: xH`IH; [IHtAH9AH9D L;= LY^I/Ax Ep Alf A 1E1NH=3 H, H5, cIf1Ai A# #ZZAi A# 1E1YYYHYH=3 WIDDHYYA\i A+ 1E1vi H|$`Ht
H/ HD$` H|$HHt
H/ HD$H H|$PHt
H/ HD$P H|$XHt
H/ H
0 HD$X H=/
jHL$`HT$XHHt$H{J Ht$HHL$` 1HT$XH_HD$PHH 1LDI/HX H|$PH/? HD$P H H;- AH;- D H;- H \Hm A Ey9Ai H HL$x1E1HT$pHt$hA- }YAi Hl$HE Ht Hm HD$H H|$XHt
H/ HD$X H|$`Ht
H/ H HL$xHD$` HT$pHt$hXH H
Hm EeHMWCWHD$P 0WFYHG oH H HHi |LA?i A& VLT$PHD$H 1Af A VLXI&G DgH L HI
V9VLi Af A TH5,- LZAf A 1*f +Vi H|$HAsf A ~H|$HANf A hAf H+ A 11A i A% H=: H`' H5a' I6UAuf A 1E1eH$ 11Af nH|$HA i A% =UL0UH$ 1pe I/E
LT{Af A 1E11A)i A& 1A}i A- TcTAT 1A1i A& {TJHA H4 HD$H H HD$`HD$(HH4 HC(ZIHH?D$ H/H; W LPXZAf A 1E1H; ~ L#THHtFH;T H; H;-0 HjWHm
n Ag A 1E1`Ai I/! A- 1E1@LT$PA3i A& HA 1)SE1` f.G ADEX1AJi A% H$ 1YH$ 11HLR"Ai NLT$PAZi A+ NRApg A wR4wR mRcRYRAg A 1E1/LA- 1E1+R1Ag A
RqROHQ QAg A
1E1QHQQPAi QAi nHm l H{QqQgQ1f fA.GE1Aei A% $.Q$QLd$XLl$`SHLHLAi BHD$H HD$X HD$` Ah A H|$`Ht
H/H HD$` H|$HHt
H/5 HD$H H|$PHt
H/" HD$P H|$XHt
H/ H
DDHD$X H=} aH|$HL$`HT$PHt$XA Ht$XHL$` 1HT$PVHD$HHHt 1H)PH? HD$I,$aLNNHNvNlNbNXNNNDN:N_Ah A W1Ag A 1A$h A H|$HAg A
`1Ag A
HGHD$HHHWH HH|$PHT$PH/ HD$HL|$`1A H|$PH|$HA h A Ah A Ah A H=(2 H) H5* U IH=6- IH="- H H5 Iu1Ah A H$ E11A
h A A3h A A5h H+tCA 1H=p1 IH=, Hm H5n IHA 1QL=Ah A n1Ag A H|$HAg A 1Ag A
1Ag A
H=+ pIKKLKH; H5;" LkJLKKAh AIh 1Ag A GQK1GKD1A j A- Ah H KbL|$XK`H|$POJJJLt$`Ll$PMLAh HLL;HD$X HD$P HD$` "Ah A uH|J AWH( AVAUATIUSHHHL- HD$0HD$8 Ll$(HR ILIM
HH I9D$L $LH5E*
=L $IM
H I9EL $LH5)$
=L $IIE HM}
IE H9 H I9D$L $LH5) s
d=L $IMo
H I9FL $LH5& b
0=L $IIHMW
IH HN I9D$L $LH5" K
@'f L>$ & I.u LT$4$@4$T$f. H
h H=r }QI$LE1HHHt Hm kH?^ ?ڐH?H- z @ L?L Lp?2 % $ H
H= PM{` D EIQ & $ @ ?I^ I$LHPI$% @ LL $>L $ I/+L$>$ ' $ E1E11I) Mt
I/ Mt Im M H|H+rH߉T$4$S>T$4$H
H= OW @ L< LL $ >L $V>L $HfH
q I9u H9u LϺ HL$LD$L $>HHL9L $LD$H;= HL$H9 LD$LL$H<$6ALD$LL$H<$H/ 6f D HL9&f D LT$4$=T$4$ D LωT$4$L $HIH H5 H8;L $' $ RfH5 H=Z" 1'IH HW;Im . % TLt$$:$t$9 % - kH= H H5 I2f D Du @ LD$D$L $6:LD$D$L $ @ H= I @ LLD$Ht$L $r8L $Ht$LD$ % - 1E1E1I.LLL$T$4$94$T$LL$ HLD$LL$H4$7H4$LL$LD$dO HvH IyH L$%9$ D 9I[ 3 3% 9L $ImE13 5% 6D9L $IrM1E17% 3 D BQ9L $IE13 :% .9L $I1۾<% 3 4 G% 8L $II% 4 dD S% 3 IM$ . % ff. AWH_ AVAUIATUSHHHL%F HD$0HD$8 Ld$(H HLE9u2H H L IL9LH\$Ld$ f L9uuM9uuL HnIHtH; L L;=^ M9 L Lc I/ aLLL$H\$MLd$y- Ht6U j @ LLL$H\$MLd$KT f HL$0HT$@ILL
R HAxHD$0 ]U f D L LD$, D$,L + @ HpLq @ LPLQ ya @ IwH H{HLL$ LL$L HzU DD D>D D>ff. AWH AVIAUATIUSH L HD$PHHD$XH HD$`HX HD$0 HD$8 HD$@ HD$hHD$p LT$HH= L HC H8 HJcH @ HFHD$HHFHD$@HFLEHD$8HHD$0I I5 M MI H M 1 HL9K H;\uIHD$8H HUIL- H 1f D HCH9 HL;luIHD$@H IM H LHL\$LD$^#L\$L* H LD$HD$HIM~VHL$0HT$PMLL
p HWu LL$0HL$8HD$@HT$HL &fIuMgLL$0HL$8HD$@HT$HI HIvHH=6 A HE ARj5 Pj5 QHj5 v IHE HPMB HHE HĈ L[]A\A]A^A_ H& H IH
H AHMEIHH HQ H5! ATL
H81X2C ZH
H=, E1'[ H G HVHT$HHFoHNLHD$@)D$0HLAHD$0@ LAHU LHLD$L\$H!HD$0H LD$L}L\$L I
@ LqIE0LD$1L\$HD$ HLLd$IIH M|L9 H H9EI9G } K A ` HUI;W IGHuH9@H@t
H } E_ D@@8 @ O H}HA Iw0IHA@IDDA A D D>E9uFHt HDL u)f LD$L\$HLLd$I fHCI9 H L9uuM9uuL HIHt^H;G L8 L;= u M9F I/ tLD$L\$HLLd$_f. HD$@ rHi HH H
H5 jL
A H H81Y^C @ L HC0LD$1HD$ L\$Ld$ILIHf. MlM9 H I9GI9E] U A F A} W IWI;U IEIwH9@H@t
H A EM D@@8u{@
IHA ) Iu0IHA@IDDA! A1 DD.E9u0H. HLC D HH9HD$8 H HH A H5D jL
H
H8HS 1_C AXf D M9uuM9uzL LbIHkH; L L;-N u M9 Im x LLD$L\$HLd$ f LLD$L\$HLd$IRfHHE tH
p hC H=n ! @ LL @ HuH@HHE|$ LL 1IwH@HHE|$ Ht C C C @ LD$,L= D$,# @ H L! , @ L L @ IwH LD$,LD$,L lL
L L
L iL\$L\$HfC IuHD D>DD.D D>gDD.H
A H(B QAWH AVAUIATIUSHHHD$( HD$0HD$8 H HL4H H H>LAH|$(Mf H H9G LIGH MJ HcGIHcHEIIb LIoHHIHHIEH5 LH H IM IHN H.HH H5k HL0 Hm H H ? H9XM
H& H
H H- H
HEH5V HH H
IM
Hm H5 LL Im IFH- H H H=
LHLIM
I. I,$ IEH5 LH Ho
HHq
Im H H9] LuM LeII$Hm Lt$0Ht$0 H HD$8ID$ H@8IH 1LIMt
I. M I,$] IEH5z LH H IIE HIE M H I9^ MnM
MfIE I$I.m Ht$0 LLl$0VIm H H I,$ HEHXpH H{ L` IH H= HHI,$I M LHSIm HU HJHf HM HuoHH$1
H$] HHm H$ H5 ATL
l A H
H81_XV0 ZH
` $ H= p1HH[]A\A]A^A_ HuH>H|$( D f D HY1H
H f HH9 H;LuIHL$0HT$PILL
k H?yW HuM D HD$HLl$0H\$8Hl$@HD$H` L( h E111HA LAIHl H8 H L( h E111HA HAIHw H8 M H L( h E111HA HAIH H8
AFA;D$ H H H9P H HQ H L- M IEH5
LH H7 HH Im ^ H/ H=H H9xm H/ H H H- Hk HEH5 HH H HHE HHE H H H H H9P H Hj H L M I@HL$LLD$H5 H H
LD$HL$IM I( H̸ I9C LHt$X HL$L\$HD$P Ld$XLt$`L\$HL$ILM Hm Hh H9A HHt$X LD$XLD$HL$HD$P L|$`HL$LD$IHI(e M Hm H H9C Ht$X HHD$P Ll$X0IHIm H I( H;-% H;- u
H;- DHm EG ID$H5 LH H
HH H H= H9x} H{ H H L-g M IEH5S LH H HHf Im Hȶ H9C` LkMS LCIE I H+ fHnfInLǺ flHt$PLD$)D$PIm LD$HD$ Hm W H|$ I(B HD$H; o I,$2 IFH5J LH H HH HJ H=3 H9x H H H L- M IEH5 LH H IIE HM IE H
Hm H9C
HkH
LKHE IH+ fInfHnLϺ flHt$PLD$(LL$ )D$PpHm LL$ HD$LD$(H I( H|$ . I)^ HD$H;B w I.O IGH5 LH HB HH H H H9P H H H L- M IEH5 LH H HH Im H H9C LcM LCI$I H+[ fHnfInLǺ flHt$PLD$ )D$P I,$LD$ I Hm r Mx I( L;- I/ H$HH= H Hp HE HL
j5S AUj5 t$HjLD$PHT$H HD$@H@Hf Hm H<$MڿLt$Ld$HH D$~ E11D$Z r f. H. H HH
H AHMEIHH H| H59 SL
H81XW ZH
H= E1HĈ L[]A\A]A^A_ H1 HFHD$HD$HHnoH^L.Hl$@)L$0 @ HLAHD$0p LAHM LHLD$M HD$0H LD$LuIN D HD$|f D L` HHL$KHL$H8 A;GLIH
HHHd HHH ID H9 H$LH HHL$HL$HI& HHL$HD$L\$HL$HH9 HtL\$HL$HI H4$HE1H=| jA 5^ H Pj5 Sj5 ASHT$XL\$hHL$` HD$PHPHHL$L\$ H) I+ H+ Im H<$購HH I,$tjI.Itw I/tBH $H`HHD$HHKHp> H` LPf D 1LI;MtI.uL(Mu뇐ID$0LD$1HD$H\$LMI̐NlM9 H˯ I9FI9EU M A~ A} IVI;U IEIvH9@H@t
H EV EM DD@@8urA 8 I~HA Iu0IHA@IDDAZ A DDE9u'H H II9HD$@ H HH H
! H5 jL
A H H81Y^W ? L;5 uuL;- urL LIHcH;ϭ L;- u
L;- Im # LD$H\$L @ LD$H\$LI"f. M ID$0LD$1HD$H\$LMI̐NlM9 Hk I9FI9EU M A~ A} IVI;U IEIvH9@H@t
H EV EM DD@@8urA I~HA Iu0IHA@IDDA A DDE9u'H H IL9HD$8 HB HH A H5, jL
H
H8HN 1_W AXf D L;5 uuL;- urL LBIHcH;o L;-5 u
L;-O Im LD$H\$L @ LD$H\$LIzf. H$ E1E11D$` E11D$1X E1E1Ht
H+ Mt Im Ht Hm Mt
I( MtI+t9T$t$H
i H=K ~MI,$E1fLf D HL\$ LD$L\$ LD$\ LL\$ LD$vL\$ LD$D HL\$ LD$NL\$ LD$, LL\$+L\$ H$ E11E1D$a 1D$@X f LHL$L\$HL$L\$ H$ 1E11D$b D$OX \ @ L HHL$LD$~HL$LD$ L0= H AŅH$ E11D$s D$PY I~HA@HE|$ D L=I~HA@HE|$LLHLD$LD$-H= HL$6HL$ILLD$LD$7LLD$uLD$Ht$X HLD$XLD$ HD$P LD$ IHD$NW W LLD$LD$Zf H LD$ D$ L/ L@ L( H# IuHE H$ 11D$s D$X H=Y Hڹ H5۹ VI(f D L O H4 L HL\$L\$H$ 1D$s D$X yH= DI @ H LD$ D$ LLtHW H=J H H5 GHH$ E1D$s D$Y IuH L*HLD$LD$DDH= IH H=H
D$Y E1D$s HH $|H $H?
E1E1H) H$ HL\$ LD$@LD$L\$ H=: H HL$H5 2HL$ID$s E1D$Y E1D$s D$ Y HL$LD$ID$s ID$ Y MkMIkIE HE I+ fInfInHt$PHflº HL$Lt$`)D$PIm HL$ILHL$LD$6HL$LD$DD^DD(HH$ 1E11D$f D$pX LLL$ LL$ HH$ 1E11D$h D$X JfHH$ 1E11D$g D$zX D$s HD$5Y LIMHiIHE H) fInfInHt$PHflú LL$LD$L|$`)D$P^LL$LD$II)LLD$LD$H5I H=* 1HH+ H'Hm 5 H$ 1E11D$k D$X L`LSHt$X HHD$P Hl$XIHD$LKM4LCII H+0 fInfInLǺ flHt$PLL$LD$)D$P?LL$LD$HI)LLD$LD$H$ E1LD$s D$LY 6D$m E11D$X rHLL$ LD$RLD$LL$ D$X E1D$n I+Lf D H5 H= 1CHH HHm H$ 1E11D$t D$_Y xD$X D$o {DDHLL$(LD$ LL$(LD$ H
ؤ A HW H$ 1E1D$v D$qY HL!HLD$ LD$ wD$X D$l LhLrH$ 1D$v D$sY oD$q E11D$X UH= H H5 裠I|HLD$ nLD$ H$ D$v D$uY "HgH=C 辝I'H #H$ 1E1LD$v D$Y LLD$ LD$ DHLd$H$ 1E1D$w D$Y aH5r H
zHl$H$ E11D$v D$Y #Ht$X HHD$P Hl$XIIH=I H H5 FIpLd$H$ 1D$w D$Y LHL$HL$YH= gI!Ld$D$w E1LD$Y I Ld$1E1LH$ D$w D$Y 0HLL$LD$fLD$LL$5HO%HH5 HrLd$Hl$E11H$ D$w D$Y Ld$Lt$1E1H$ D$x D$Y HLD$LL$LL$LD$H= H H5 賝I@Ld$H$ 1D$x Lt$D$Y H=k ILd$H$ D$x Lt$D$Y HH)Ld$Lt$1LH$ D$x D$Y H5 LB\Ld$LLt$E1H$ 1D$x D$Y SLd$MLt$E1D$y 1D$Y ,H$ E11D$k D$X
H$ E11D$t D$[Y H$ E1E11H$ E11E1D$s E1D$Y AWH AVAUATIUSHHHL-V HD$0HD$8 Ll$(Ht~HL4H Hu{HHIHT$(H I$ It$ H=W MHE H IHE M HHE H@ H H HH H
{ HIHHl H?L
Z HLIL@HH5 SH H5 H81L$ ( o HnLq)$ M L$ HD$x LHDŽ$ HDŽ$ IH HV H( h E1ɹ A Hƺ LHD$HD$xHi H$ H H|$xH/ H$ H L HD$x HDŽ$ HD$H H9XW H H H H HD$HD$xHM HH@H5M H H IL$ H|$xM H/ Hi H5 HD$x H9p Hp HC H H\ HD$(HH HGH5 H H IM H\$(HHD$HHP Hy I9F HD$ LMH$ HDŽ$ H$ H H$ HD$HD$xH|$ + I/
H$ H H9G HD$xH$ HDŽ$ H$ +H$ H|$xH/
H$ HD$x HD$H@ H$ H/
H$ H;= HDŽ$ H;= s L9j Å H$ H/9
HDŽ$ U HD$HXL9k HD$ H HLxM9t M HPHuL0H@HD$MtIMtIHD$HtH H H5 H9p H H+ H H= H$ Hh HGH5 H H HD$xL$ H I) H|$x 1HDŽ$ H
H$ H9O fHnfHnfl)$ 9H$ H$ HtH/z H$ H|$xd HDŽ$ H H/ HD$x L(HD$xH HD$H$ H ~$ HDŽ$ HDŽ$ D$xHD$x @Mt
I. Mt
I/ Ht$HtHHD$ HH H3 H5< H9p H# Hg H L= L|$xM IGH5 LH HD IL$ H|$xM6 H/h
H H HD$x H9Pg H H< H L=r L|$xM` IGH5Y LH H IH|$xM H/ H$ 1HD$x H
H$ H9O fHnL$ D$)$ H|$xH$ Ht
H/v HD$x I.e L$ M1 H$ H/ H$ HDŽ$ H L$ HD$8IFAvHDŽ$ I~ HD$ H& H- HD$@HD$0HL MoLHD$(H H@H Ha H|$(LLHD$(H HD$0L=h H LLmL*HH H@H Hi LHH$ HH H@H; g HoHZ HGHE H H$ H$ H/ H$ H$ H$ H$ Hm ~ H$ H H$ H/ H$ HDŽ$ H/~ HDŽ$ H|$@ HD$` J Lt$hL|$ E1HD$HLHHHD$PLHHD$X @ M HD$0fE1HhH BHT$B T$CIXM9u
+ ^It HD$PJ 8L D f HfY@H9uHD$XI9tHL$ LHYML|$HL9l$@BLt$hH|$`KH\$(H5 1HUIHHD$HHX MD I/ HD$8HT$H HHD$HHv I.H\$8H\$ HT$HHD$HHV HT$8HHHD$HHHkf D HiL=] 1He f HH9c M;|uMLqL$ MIL$H- H 1 HH9 I;luI,H H$ If D H8 +&f D H bf D L sf D f D IG0LT$E1HD$H\$LILMf D NtL9 Hs H9EI9F
} ; A~ E HUI;V IFHuH9@H@t
H DU EN DD@@8u{A H}HA@HE|$A
Iv0IHA@IDDA A DDE9u&H E1HA IM9H\$ f L9uuM9uuH LHHtH;τ H;= L9 H|$ H|$ AH/ ElLLT$IMH\$EyOHDŽ$ H
3 A L
% Hb @ LLT$IH\$MOHּHD$(H E11A?d
E1AAd H|$xE1 HD$( Ade ACd HD$( AHd a#WH|$xE1E1 HD$( Ac HD$8 HD$ lHAd f AWH AVAUIATUHSHHH ft HD$0HD$8 H\$(H IL4H2 H HHIHT$(H HIuHIE1I H=w, HE HSj SSj SSj S IHE HPM HHE H3 f D H H HH{x H
kx HIHH\x H?L
Jy HLIL@HH%s UH} H5Y H81,X;* ZH
-x @ H=k E1:HHL[]A\A]A^A_ LyM H HHT$( La 1 M;D HL9uI@0E1HD$ KtI9Z Hr I9@H9F Ax ~ IPH;V HFIxH9AHAt
H EX DV DD@@8 A IxHA@HE|$A m L^0HHA@IEDAh Ak DD E9V L$H` LL$HLL$L$ 0 H HT$0HL$(ILL
z L諰HT$(-* @ HHE t&H
v f q* H=vi @ Hhf D I9u H9uuzLǺ LL$L$脳HH@H;p L$H;=sp LL$uwH9trLL$LD$H<$迶LL$LD$H<$H/tS IM9f D KHHT$(IO D If D$LL$L$vD$LL$L$ LLL$Ht$L$ʰL$Ht$LL$RG HLL$LD$H4$蒰H4$LD$LL$$ HvH IxHpDD DD (* AWH AVAUIATUHSHHH o HD$0HD$8 H\$(H IL4H2 H HHIHT$(H HIuHIE1I H=& HE HSj SSj SSj S IHE HPM HHE H f D H H HH+s H
s HIHH s H?L
s HLIL@HHm UHw H5NT H81ܵX}? ZH
r h H=f E1HHL[]A\A]A^A_ LyM H HHT$( L 1 M;D HL9uI@0E1HD$ KtI9Z Hm I9@H9F Ax ~ IPH;V HFIxH9AHAt
H EX DV DD@@8 A IxHA@HE|$A m L^0HHA@IEDAh Ak DD E9V L$H` LL$HǰLL$L$ 0 賱H HT$0HL$(ILL
u L[HT$(o? @ HHE t&H
p ? H=^d ɿ @ Hf D I9u H9uuzLǺ LL$L$4HH@H;ak L$H;=#k LL$uwH9trLL$LD$H<$oLL$LD$H<$H/tS IM9f D KHHT$(IO D If D$LL$L$&D$LL$L$ LLL$Ht$L$zL$Ht$LL$RG HLL$LD$H4$BH4$LD$LL$$ HvH IxHpDD DD j? AWHg AVAUATIUSHHHL-i HD$0HD$8 Ll$(H HL4HB H HHIHT$(H I$ HIt$HE1H=0 HE HL HL
AUj PAQj PAQj PM IHE HPM HHE H胫 f D H H HHm H
m HIHHm H?L
n HLIL@HHuh SH}r H5N H81|XAE ZH
}m H=Ra E1芼HHL[]A\A]A^A_ LyM L HHT$( L 1 L;D HL9uI@0E1HD$ JtI9Z H;h I9@H9F Ax ~ IPH;V HFIxH9AHAt
H EX DV DD@@8 A IxHA@HE|$A m L^0HHA@IEDAh Ak DD E9V L$H` LL$HgLL$L$ 0 SH HT$0HL$(ILL
sp HHT$( 3E @ HHE t&H
^k b wE H=._ i @ H踨f D M9u L9uuzLǺ LL$L$ԨHH@H;f L$H;=e LL$uwL9trLL$LD$H<$LL$LD$H<$H/tS IM9f D KHHT$(IO D If D$LL$L$ƧD$LL$L$ LLL$Ht$L$L$Ht$LL$RG HLL$LD$H4$H4$LD$LL$$ HvH IxHpDD DD .E AWH AVAUATUHSHHhL-fd HD$PHD$X Ll$0H IL~Hm L\$LD$LL$IJ I+ M L;WO L; O k M9b LLL$LD$LT$bLT$LD$LL$I*= s+ I LLLE11A ʒDD H|$HMHD$8 H^HA E1E11DD E11+ A |1Lf+ YHt$8 Ht
H. HD$8 H|$@Ht
H/( HD$@ H|$HHt
H/) I LLLHD$H M̑I*wLLL$LD$(LL$LD$HM H5. H8裐* LL$LD$LL$LD$яLL$LD$LLL$LT$LD$諏LL$LT$LD$HLL$ L\$LD$HD${LL$ LT$L\$LD$LL$LD$SLL$LD$LL$LD$5LL$LD$HLL$LD$LL$LD$^j+ o+ H\$HLl$@LL$LD$Ht$蓑Ht$HLHǻ{+ LD$LL$HD$8 HD$@ HD$H ''+ g
, !E1 , A
E1E1%+ A @ AWHWk AVfHnAUATUHH H SfHnHflHxL5K H<$HD$0 HD$`HD$h Lt$8Lt$@)D$PHP L ` H I/ H+q H<$H5m HGH H IM H 5I I9] LHH H@L
p H9C HUH HBH EHHcHcHDHIM Hm K L $蝍L $HHU I$fInfInfl@H HT$H5m HH$耏L $ Hmh H5nf L^L $:
IGH H H=( L $~L $ LHLI蟍ML $ I/
Hm I) I,$ Im L݉z H HFL&HMHD$@HFLd$0HD$8H
Ld$0 D H H H HHK H
K AHOL
K EHL LOOD f H
X H9H HX H
H L
X M{ IALL$LH5m H H(
LL$HIHHF
IHb H=a H5e HGH H IMLL$ 訌LL$HI H5 g LH5LL$
IAH-^ H HE H=& LL$HL$GLL$H LL$ HLHL$LHHD$XHLL$
I)
I/ HD H9Cg HD$Ht$X HHD$P HD$XHn HD$`IHHL$HHD$HH H I)
Hm I$I. Hl H H l I,$ MI^ HML-e 1H HH9 L;luM$Ld$0M HHs H
!I A L
J HHC H N H5c* SH81X > ZH
H H=&= E1HxL[]A\A]A^A_ @ HQc LHHL$HL$HI
HD$8HH LEL%i M 1f D HI9 L;duIH HD$@HLt$ML&Ld$0 HFHD$HD$@LnLl$8 I/A> I)
E11ۺe Lω$Y$HtH+t[MtI/t`HtHm tdDH
G E1H=; 軖M"I,$L
f. H߉$$L$Մ$H$ń$H踄 LnHHMLl$8HD$0f D IE LL
i 1 @ A? I/LL $\L $ HD$@Ld$0HD$ @ b A> ID$0HL$E1HD$ L|$ILH\$LM OlL9 HA H9CI9E
{ k A} x HSI;U IEHsH9@H@t
H D[ EU DD@@8 A H{HA@HE|$ A Iu0IHA@IDDA A
DD E9u*H H f D IL9LH\$L|$ L9uuM9uuL HނIHtH;@ L;-? M9 L)Im vLHL$H\$ML|$y2HH > D LHL$H\$ML|$KfLt$Lf D IE0L|$E1IHD$H\$HLNlL9 H? H9EI9E
} A} ( HUI;U IEHuH9@H@t
H DU EM DD@@8 A % H}HA@HE|$A Iu0IHA@IDDA At DDE9u*H HĂ f D IM9H\$~ @ L9uuM9uuL H趀IHtH;= L;-= M9 LIm tLHL|$H\$yNHD$0 H
`B A L
RB H?= `f LHL|$H\$O$ HL $L $ L b A> ' Lh: HX LH H8 L(h HL$0HT$PILL
F H{Z > v H=c HrN H5sN =Hwf D ` A> |O LLHIHIf D b A> H=Ic :IX @ H=)c :H @ H E1` A> D A> b ۃH b A> L}
L} Z Ai> I) P=HLL$}LL$%f LMIr} D L`}$ HP} L@} A ? D L } HL $ }L $ LL $|L $ e A> 諂I6 A> I/ L|e ^f D LD$,|D$,5 Y AX> S D H;!9 3 LH{ILLHLL$LL$HHD$Z Aj> f苁LL$Hf D IuHr H{HH E1Y AZ> D LD$ T{D$ % HL$^~HL$H"= f D I LMML}IIHm fInH@b fInLflHt$P LL$HD$`)D$P&LL$HI)Lz Hy SI 1E1Z Ae> Lx H# H HC`LHIA? K D IuH
H}H |A> b HvH6 H5A $H8Nz$ULHL~L $HIfA
? D Z Ag> DD \DDL{MLKIIH+L H` fInLHt$PD$ LL$HD$`)D$PiI/LL$HiLLL$xLL$RL $Aj> {L $Z HH5 H5) LL$$H81y$LL$DD xE1L˺Y A> DDo{L $HHC5 H5 A
? H8xL $} EH H } EH H HHLL$wLL$HLL$wLL$H XEyIe d @ AWHG[ AVAUATUHSHHHHD$( HD$0HD$8 H IL4H H L&LALd$(MV HEH5Y HH H HH H4 H9E LmM LuIE IHm fInfInHt$0 fl)D$0IF 6 H@8IH% 1LIMt Im C M I. I,$ H3 H HH[]A\A]A^A_ HH3 H= H5 SL
8 A H
8 H81x{X! ZH
y8 H=, 艇HH1[]A\A]A^A_ HuL&Ld$( D Ly1H
[Y M HL9 I;LuM$Ld$(Md MG2L}ILXu LHu H8u_ HD$0 H53 Ld$8H}H9t
]z HUB Ll$8HZE1 uLeH=C t LLII+xM@wHuH1 H5" H82ufI.C! H
6 H=^+ HH1[]A\A]A^A_ IHt$8 E1 L0t /! 렐yH HA0E1HD$ @ KtH9 H1 H9AH9F y S ~ HQH;V HFHyH9AHAt
H DY DV DD@@8 A f HyHA@HE|$A > L^0HHA@IEDA9 AD DD E9u;H $H LL$E1HtLL$H $A @ IM9 f D L%90 L9uuL9uuHϺ LL$H $rHHtbH;
0 H $H;=/ LL$uxL9tsLL$HL$H<$vLL$HL$H<$AH/ ETEy'HD$( 1uH f D O$g DfHL$(HT$0ILL
R9 Ln Ld$(y L4$q4$ D LL$H $qLL$H $G @ HLL$Ht$H $oH $Ht$LL$ HLL$HL$H4$oH4$HL$LL$S HvH HyHDD IBDD ff. AWHQ fAVfHnAUATUHH0H SHH H$ H+ )D$`fHnflH|$HDŽ$ HD$p)$ H L,H*
HS Hh HLEHD$`ML%Q M 1f D HL9
L;duID HD$hH MxM~yHML%R HL 1
HH9S L;duID H& HD$pMG+ H HFLEHD$pHFHD$hHHD$`MG H|$`U Ht;Ht,HH
1 H1 AHMEI D HFHD$po&H>)d$`H, H9G LIGHx Mt HcGIHcHEII Ld$hHV HD$H HD$P Hl$pHD$X H( h E1ɹ 1HA LHD$HHHT HD$PH H|$HH/D HD$H Ll$PHD$P Au HBV I} MuH5O LH$Hú Lt$U B HtHsL`U f/@{
L%+ L9 lHD$ H
HLpM9t M HPHuHL`HL$Ht HD$H MtIMtI$HC H
g> H9H HN> H H H=:> H|$PH HGH5!J H H HD$HLL$PH I)Z H|$H 1HD$P H
) H$ H9O fHnfHnfl)$ uH|$PHD$XHtH/ HD$XHD$P H|$H2a HB H/ HD$H H<$mHD$HH nHD$PHH ~D$XHL$HD$X HD$P D$HHD$H @HtHHD$ HH Mt
I. Mt I,$r HA H
< H9H H< H H L5< Lt$XM IFH5NP LH H HD$HHr H|$XH/ HD$X mHD$XIH HHD$XHXnHD$PIH Hf( H5F How Hl$HHT$PLd$XHEL M H= HT$i HT$LHAImM? H|$HH/ HD$H H|$XH/ HD$X H|$PH/ IFAvHD$P I~ IHD$0H(R f H=I I*H|Q HD$ H $Ht
HHHHD$HD$H5E H Ht$ HUHHT$(CmHt$ HI' H@HT$(H Ha LHIH HD$H5!E H Ht$ HUHHT$(lHt$ HH^ H@HT$(H H HHD$PHHy H@HD$X H;% HGHD$XH HWH HH|$PHT$PH/ HD$XH|$P H$ H$ qH|$XHHt
H/E HD$X H! H|$PH/ HD$P Hm lH|$ HD$ HD$1Lt$(Ll$8ILH`HH H$HHHD$HD$0Ld$0Ld$IH\$L @ L$LILLHI Lt$L;l$uLt$(Ld$0H\$Ll$8H|$ zfH5CM 1LSI,$H H Hm IIm ' I.M H+ M I. Lf f D ff D LEH
F LHL$^rL$HHD$` L}I H
( A HH# H- H5:
SL
) H81kX_ ZH
( H=V E1wHĨ L[]A\A]A^A_f Hf HFL}HD$hHHD$`)f D hH I+f D H<$wgHD$PIHe LhHD$XHH HD$X HD$PHD$P HC HL`HL$Hf D ID$0L$E1HD$ H\$LM @ NdM9
H" I9GI9D$\ T A 9 A|$ IWI;T$ ID$IwH9@H@t
H EW EL$ DD@@8uuA
IHA r It$0IHA@IDDA A DDE9u)H H3f D II9HD$h gH
HH1! H
A& H5 jL
)' A HS+ H81#iY^q_ ^ L
!! M9uuM9usL LLL$cIH_H; L;% uLL$M9| I,$f
L$H\$ L$H\$KD . D bf D H9 ID$H9t;HX H HqH2 1f D HH9 H;TuH9 H
3 H9H H3 HK H H 3 H\$HH HCH5? HH H ILt$XH|$HM H/ ID$H5= LHD$H H H HH\$HH H|$XH H9G H8 fHnfH$ flź H$ )$ kHD$PH|$HH/ HD$H L\$PM H|$XH/= H|$PH- HD$X L= H9L9z
H;= m
dAƅ H|$PH/) HD$P Ed H5< LMHD$PIH H5 HaHD$XIHR H|$PH/d HD$P H|$XH9L9 H;= 4dAƅ~ H|$XH/ HD$X E H5D LMHD$PIHi HD$H H I9F? IFHD$HH- IVH A L$ HH|$PHT$PH/ HD$HH|$PLLH$ iH|$HHD$XHHtH/ H\$XHD$H H|$PH H/ H5D H|$X1HD$P _HD$PIH H|$XH/4 HD$X H|$PH9L9 H;= bÅ H|$PH/ HD$P tAHB H L%B ? D H H9HuH;D f D HqB H L%fB H=E H$ H HDŽ$ L$ gHD$PIHw H^H|$PH/ HD$P E111$ H|$HE1E1A` 7 H|$Ha H H/LL$P HD$H Mt
I) HD$P H|$XHt
H/ H
HD$X H= oH|$ HL$XHT$HHt$PN
Hu H9Ex HE H<$^IH HD$(_L\$(HI LXHHHD$(\LL$(HH Hm Y I)B H|$PHt H/u\HD$P H|$HHt H/u\HD$H H|$XHt H/u~\HD$ Ht$LLHD$X H ] @ LH\ ID$0L|$E1MHD$ H $H @ NdM9 H I9GI9D$ A A|$ IWI;T$ ID$IwH@H9@t
H EW EL$ DD@@8u}A IHA@HE|$ A It$0IHA@IDDA A
DDE9u'H H!] IL9H $ f. L
a M9uuM9uuL LLL$[IHtH;3 L;% & LL$M9 LH^I,$7 eL|$H $y!s]HR x_ L|$H $KD D #Zf D _HH'H \Hm ILHY? @ $ H|$PE1A_ E1E1E1E11 D Ht
H/ H|$XHt
H/ Ht Hm Mt
I+ Mt
I) $H
DH=s jMtIm E1MtI.t0MtI,$tHf D LYE1 LXf D LL$L\$XLL$L\$)fLL$L\$XLL$L\$ fHLL$L\$XLL$L\$
LLL${XLL$LhX 1LISXf D I I OZI H5> H=? 1KDHD$PIH HXH|$PH/ HD$P A_ $ H|$HE1E111E1E1HtH/t
H|$P LL$L\$WH|$PLL$L\$ D $ A` f [Wf D KWIf D ;W!f D +Wf D Aa $ E1E11H|$HE1E1C HL$`ILHH$ L
q S}_ { @ LZzIHA@HE|$ )D GI I LVHxVLL$(f D HXV,D GI I I8VP.V
H=26 Ho_ L V LUa HUB I$f D LD$UD$ L(T $ E1E11H|$HE1Aa f D H=y5 H& H5& vIf D HH|$Pf. LSC Uf D H UIt$HLE1LH ZIH$ E1E11H|$HE1Aa H=4 1IR$ H|$PAa ]Z_sTH=4 H% H5% tHZ$ E1E11H|$HE1Aa r%TLL$PNLTY TlH=e4 HSY a $ E1E11H|$HE1Aa DHGHD$PHHWH HH|$HHT$HH/I HD$PH|$H H$ f LHSDDLD$*SD$LL$P6a ELQ!
LuQH|$H8a It$HIHa$ Aa H|$HE1E11E1Aa $ E1E11A^a HD$ Ht$LLLL$1E1E1H L\$SH|$HL\$LL$=R DDH H8 HFLyHD$@HFHD$8HHD$0M LL$0HD$8HT$@H
i I HIvHH={ A HE QHj 54% 50 j5& Pj5U% 73 IHE HPMc HHE 5 HxL[]A\A]A^A_ H H HVH
HT$@oHFL)T$0F LHLT$LyH$ VLT$HHD$0 HUIU D H
I
A HH Hc H5 ATL
H81PX( ZH
H= E1%\ HH
H AHMEI @ H
H
f H8J LML-5- M 1 HI9 L;luIH HD$@L{HFHHYHD$8HT$0{f D E1IE0JtHD$ I94 f D Hy I9EH9F# A} P ~ ~ IUH;V HFIMH9@H@t
H A} D^ D8 @ v I}HA H HN0HHA@HEȃ5 D A9u9HtQLL$HLT$JLT$LL$ D IAL9 IJtI9K f H
I9uuH9uuL HL$LL$LT${HHHtMH; LT$H;=m LL$uHL$H9; H/ NdHD$8 JH_ HH H
H5~ jL
A H2 H81LY^( f. IE0E1HD$( @ N|M9" H+ I9EI9G
A} A IUI;W IGIMH9@H@t
H A} Aw 8 @ IMH@HHE|$(@ IO0IH@IDHȃ D>A9ufLL$Ht2L\$HLT$\HLT$L\$LL$u2f K/ H
I9uu I9utIM9 D L LLT$HL$ L\$LL$ FLT$HItwH;H LL$L;= L\$1 HL$ I9# LL\$LL$LT$DIL\$LL$LT$I/ L D LT$^HLT$HtD( f. HHE H
) H=J V{HL$0HT$PMLL
{ HA( LL$LT$H|$tHLL$LT$H|$IMH@HHE|$ yHsD\f D ( f D LL$D$LT$=DLL$D$LT$Df. LLL$Ht$LT$BLT$Ht$LL$ D HLL$LT$Ht$QBHt$LT$LL$T D HvHD LD$ L\$LL$LT$CD$ L\$LL$LT$
LL\$LL$LT$ALT$LL$L\$LL\$LL$LT$ALT$LL$L\$IwHmI}HHD EHu*H
: A D>JD>>( f D AWHW fAVfHnIHP AUHP ATIUSHxHD$`H )D$0fHnflHD$@HD$h )D$PHi HLH H H HLyHD$0LL- H 1 @ HCH9 HL;luIHD$8H I_H LL$0HT$@H
) N H> HFLyHD$@HFHD$8HHD$0M LL$0HD$8HT$@H
I HIv H=[ A HE QHj 5 5^& j5 Pj 5% ( IHE HPMc HHE 5 HxL[]A\A]A^A_ H H HVH
9 HT$@oHFL)T$0F LHLT$LyH %LLT$HHD$0 HUIU D H
A HH H H5 ATL
H81EXF ZH
H=u E1Q HH
L HN AHMEI @ H
I H
f H? LML-" M 1 HI9 L;luIH HD$@L{HFHHYHD$8HT$0{f D E1IE0JtHD$ I94 f D H I9EH9F# A} P ~ ~ IUH;V HFIMH9@H@t
H A} D^ D8 @ v I}HA H HN0HHA@HEȃ5 D A9u9HtQLL$HLT$-@LT$LL$ D IAL9 IJtI9K f H
Q I9uuH9uuL HL$LL$LT$=HHtMH; LT$H;= LL$uHL$H9; H/ NdHD$8 X@H_ HHt H
H5 jL
l A H H81fBY^F f. IE0E1HD$( @ N|M9" H I9EI9G
A} A IUI;W IGIMH9@H@t
H A} Aw 8 @ IMH@HHE|$(@ IO0IH@IDHȃ D>A9ufLL$Ht2L\$HLT$=LT$L\$LL$u2f K/ H
I9uu I9utIM9 D L LLT$HL$ L\$LL$;LT$HItwH; LL$L;=y L\$1 HL$ I9# LL\$LL$LT$>L\$LL$LT$I/ L D LT$=LT$HtDF f. HHE H
, F H= L{HL$0HT$PMLL
H17F LL$LT$H|$=LL$LT$H|$IMH@HHE|$ yH9\f D F f D LL$D$LT$9LL$D$LT$Df. LLL$Ht$LT$7LT$Ht$LL$ D HLL$LT$Ht$7Ht$LT$LL$T D HvHD LD$ L\$LL$LT$8D$ L\$LL$LT$
LL\$LL$LT$A7LT$LL$L\$LL\$LL$LT$7LT$LL$L\$IwHmI}HHD o;Hu*H
A D>JD>>F f D AWHw fAVfHnAUIATUSHHH H H$ H )D$pfHnflH$ HDŽ$ )$ H HL4H H H HHIHD$pIL% M 1HL9 L;duM$Ld$xM LyM Ll$pL$ Lf D H HFHIH$ HFHD$xHHD$pHM Ll$pLd$xL$ H HD$@ HD$H HD$P H( HD$X HD$` HD$h h E111HA LHD$@HH HD$HH H|$@H/- HD$H HD$@ HD$H HD$hHZ L( h E111HA LAHD$HIH HD$@H H|$HH/ HD$H HD$@HD$@ HD$u p H5 H|$ < . H5 H|$ L- M9 H H=u H9x H\ H; H L=H L|$HM IGH5 LH H IL|$PM H|$HH/ H H|$PHD$H H$ HD$ H1H9OW fHnfInH flH$ )$ =H|$HHD$@IHtH/ L|$@HD$H M H|$PH/ HD$@HD$PH H|$@H/ L|$PE1HD$@ HD$P H2 AwI L HL$LHD$HT$ 1A HH HD$HL9 Mt I,$ HEH5@ HHD$H H H HH|$HH L HD$PHC H|$HH/ HD$H H|$PH/p L H5 HD$P MuHt$(L6Ht$(HI
H@H HM LLLIH L H5 MuHt$(Lh6Ht$(HH H@H H LLHD$HHH H@HD$@ H;D$ " HGHD$@HW HWH HH|$HHT$HH/N HD$@H|$H H$ H$ L;H|$@HD$PHtH// HD$PHD$@ A>R HN H|$HH/H HD$H H|$PH/& HD$P E1Lk`*6H|$ HD$ HC L|$(H\$Ld$MMI D H0 LLL0 H@ H0 H8 H0 H6 H0 1IMHE &efH( H0 HH@(H;}}AHH@HHt̀8 H( HHI8HcI H0 ;}|IL98Ld$L|$(H|$ |/H5E 1L HD$hI,$ H|$hHO H/ HD$h I? LG Hm = fH\$HHD$HH H|$ H\$HHD$HH H/ H H LvL$ o LfL.)\$p HIH LHHL$
;HL$HHD$p L}H D H
A HHp H H5 AUL
h H81o4XP ZH
p
H= E1}@Hĸ L[]A\A]A^A_ HH
H AHMEInf L5 @ HH0H;0 . HHH0HH0 H0 ~HD$ H|$HA0Q A}
HD$ E1fHt H/u.H|$PHt
H/ H
t DDH= ?Mt
I/ E1HtHm uH-H|$ @ y2 HF( HJ( H)0 HLcJ4LN(L;( }INL(HJ( H0 tf D H@0 HH@(HH( H+0 H0 A -f D ,0f D L0f.X: D$ IE MeID$HC
I
Iw
L/IIv H= D$ / fH= I* \ L- M9
H H=< H9x H# HM H L= L|$HM IGH5 LH H= IL|$PM H|$HH/
H H|$PHD$H H$ HD$ H1H9O fHnfInH flH$ )$ 4H|$HHD$@IHtH/
L|$@1A
HD$H AS MH|$PH/y HD$@HD$PH H|$@H/R L|$PH HD$@ HD$P AwI L L- HD$(IGIVLHD$8HHT$0`.HHU H@HT$0H HQ HLHH_ L L-A IVLHHT$0.HHq H@HT$0H H4 LHD$@HH H@HD$H H;D$ HGHD$HH HWH HH|$@HT$@H/ HD$HH|$@ H$ H$ 2H|$HHD$PHtH/w HD$PHD$H AS H H|$@H/ HD$@ H|$PH/ HD$P Ls`E1H -H|$( HD$ ~LHl$0Hl$(L|$(MIH\$8 D$LLL贱 JIL9uHl$0L|$(H|$ 'H5 1HHD$hHm Hl$hH Hm ' HD$h I?
H\$HHD$HHb @ H|$.(Cf LEL%% M 1 HI9 L;duIH H$ IOf D 1LI'f D LfHLyLd$xHD$ppf D ID$0HL$E1HD$(H\$LLl$ILM OdL9 H+ H9CI9D$\ T { 0 A|$ 9 HSI;T$ ID$HsH9@H@t
H D[ ET$ DD@@8uvA n H{HA It$0IHA@IDDA
A
DD E9u*H0 Hl( f D II9HD$x M)H HHi A H5 jL
b H
c H8Ha 1[+_P AXf D LY L9uuM9usL HLT$ %IH_H;# L;% uLT$ M9! I,$4 LHL$H\$MLl$ LHL$H\$MLl$O$f. %
ID$0E1L|$HD$(MH\$LLl$ILf D OdL9 H H9CI9D$ { P A|$ HCI;D$ IT$HsH9@H@t
H D[ ET$ DD@@8u~A H{HA@HE|$(A ~ It$0IHA@IDDA
A DD E9u(H H% @ IL9LH\$Ll$ f L L9uuM9uuL HLT$ #IHtH; L;% LT$ M9 L&I,$l ]MLL|$H\$Ll$y1&Hg P @ MLL|$H\$Ll$K"HD$ H|$@1APQ A
HH/t
H|$Hc {"t"lj"EMIcEIHcHEIH
HT$ 1Ht$ IH5 HD$PL9
Hr H=+ HD$P H9x
H H
H H= H|$@HM
HGH5 H H
IL|$HH|$@M
H/ H5C LHD$@ ZH|$HHD$@HU
H` HT$ H9W
H$ H H$ HDŽ$ H$ |*HD$PH|$@H/% H|$P H|$HHD$@
H/S HD$PHD$HH H|$PH/@ HD$P L|$HHD$H dHL$pMLHH$ L
U P [L$H{HA@HE|$(. $ H t L t 1E1H
H=u AQ A
T1HD$P H|$@HP 8Lv I$HH|$HT J AzQ A
1E1LD$ & D$ Ee AEI I Ee AEI I IiHj LU AQ A
1E1
It$H { }H? A*R H8 HD$H I,$A
L? H H5L IHP H H5 HD$HHH$ HD$@ H H9G HGHD$@H HWH HH|$HHT$HH/ HD$@H|$H H$ H$ &H|$@HD$PHtH/ HD$PHD$@ HW H|$HH/ HD$H H|$PH/ HD$P " HL$XHT$`H Ht$hHD$ HS`H{ LD$ܥ H HD$PHHL HD$ HL$XHD$P HT$`Ht$hH * 1LHl$XH5 HD$`I/ L|$`M>
I/B HD$` L|$XHD$X LI H=M Hn H5o JIH|$@1AQ A
nHE !I1AQ A
8H= dIHH|$@DD :LD$ D$ H=a H
L徦 A R A
-H|$@HD$H 1A
AQ :HHGHD$HHHWH HH|$PHT$PH/T HD$HH|$P H$ [ HAR A
1E1 D LUL#
It$HH{HeH5D H Hl$H= HH|$@AR A
AR A
1E1D HuHh H5 H8$ HH IpAR A
6AR A
1E1 H A(R A
H8 Hq LAS H8HD$@ Hm A
1DD } H H
A H:H|$@1AS A
DD +H$ 11sH= H H5 IH|$HH$ 1H= 9I1AS A
i I|rHGHD$HHHWH HH|$PHT$PH/ HD$HH|$P H$ H LA
AS H8!TDD
H$ 11UAR A
%H|$@H$ 10kIHA
1wH|$HLAQ A
4H=b Hs H5t _HjH5 H Ld$P
H= H5LAQ A
L\LAQ A
1 I!A7T A
LwMaHGIH H|$HHD$HH/\ HD$@H|$HH$ L$ H$ H H$ HD$PI.1L0$L#LAQ A
AS I/tKA
1E1 H H. LT$HH I* H H9E H$ H HDŽ$ L$ IHD$0H|$0 I) Im ~ HD$(H; H@ HH# HL$(Hl$(HH@HIFH5 LH HR IMT LLD$LD$HI I(
I H|$0H5 HGH HQ IMS LLD$6LD$HH I(j Hp H5 H= 1HH H
Hm A\ o HD$ 1E11HD$ E1HD$ HD$ y f D Ht]@H H HFo&LnH HD$(HD$p)d$`f H HF HD$@H$ HFHD$8HD$x D LLD$s LD$f HA H9HX H HqH+ 1 HH9 H;Tu H o&LnH HD$()d$` LqH LHzHD$`H LEI~ H
A HH Hq H5Z SL
H81
Xm[ ZH
H=. E1H L[]A\A]A^A_f H H9HuH; f D HD$(H f. HL$`ILHH$ L
U[ SHD$ 1E1E1HD$ A\ o HD$ HD$ Mt
I+ Ht
H) DH
E1H=) Mt I,$T HL$(HtHHD$8HHE Ht Hm E H\$HtHHD$(HH H|$HtHHD$HH HT$HtHHD$HH HL$ HtHHD$HH Mt
I/ I. H\$0HHD$HHHVLH
H8LD$f D H - ?f D H K HZ L H H LI..L!f H LHL$8sHL$8f LHD$SLD$LL$ @ L8y L(H+HL" Lu LZ ID$0Lt$E1MHD$ H\$L NdM9
H I9FI9D$ A~ A|$
IVI;T$ ID$IvH9@H@t
H EV EL$ DD@@8 A _ I~HA@HE|$ A 7 It$0IHA@IDDAM Ax DDE9uMHtHu7 D Lt$H\$KE D L;5 uu
L;% u2t.IL9H\$HfP[ @ L LIHtH; L;% u
L;% I,$ tLt$H\$xJ Lt$E1IID$0H\$LOdLHD$ L9- fH H9CI9D$* " { 0 A|$ < HSI;T$ ID$HsH9@H@t
H DS EL$ DD@@8u|A H{HA@HE|$ A j It$0IHA@IDDA] A DDE9u&Ht;H f D II9 OdL9LH\$Lt$O,o H; uuL;%ܾ uuL HIHtPH; L;% u
L;% ! I,$ [LH\$Lt$nHD$h H$ HH H
$ H5 jL
A H H81Y^;[ !f. Ll$0I1E1HD$ E11E1HD$ A[ ` HD$ HD$ HD$( f D L @HH
w Hy AHMEOD@X HD$ I11HD$ E1E1E1Ll$0E1` A[ HD$ HD$ HD$( MtI)tuMtI(t:MI*LHL$@L\$8eHL$@L\$8f D LHL$HL\$@LT$89HL$HL\$@LT$8 LLD$PHL$HL\$@LT$8LD$PHL$HL\$@LT$8V Ll$0I1E1HD$ E1E11HD$ A[ ` HD$ HD$ HD$( f D H= H H5 薽Ikf D Ll$0I1E1HD$ E11A[ HD$ c HD$ HD$ HD$( f L H|$0H5 HGH H IMX 111LLD$ LD$HI I(3 H5e H|$0LL$~LL$HI 11Ҿ HLL$HD$LD$LL$HI I(a LLϺ LT$LL$xLL$LT$HI I) I* H W L; I9o L;` b LLD$ LD$X I( 4IFH5a LH H IML 111LLD$LD$HI I( H|$0LT$H5 HGH H LT$IMl 111LLT$LD$ZLD$LT$HI I(j
LL LL$LT$LT$LL$HI= I*
I)
L; I9 L; LLD$4LD$ I( H|$(HWHBpHz H@Hm H5 HH H H9E H} H5 LH 111HHD$$LL$HI I)f HU HEHHH9 H9 I HULHHEI( H5 H|$JHD$HH HR H9Fn LnMa LVIE IHHD$HHn fHnfInL flH$ LT$)$ IIm LT$I9 M# I* H5 LLL$LL$HIW I) H5E LLT$`LT$H: 111HLT$HD$LL$LT$HHD$ I) H1 I9B! MjM MBIE I I*b Hd LǺ H$ LD$H$ HD$L$ H$ %Im LD$HD$q Ht$HHD$HHA H|$ C I( H5 H|$0OIHR H H5U H9pw H< H H L ( M H5 LLT$ L\$L\$LT$ HHD$ I+ H I9B MjM MBIE I I*C fInLǺ LD$D$H$ )$ Im LD$I Ht$HHD$HH M I(. HL$0HHD$HH I$H% I9D$ H$ LL$ LL$HDŽ$ L LL$MIM- I* I@H;۳ M IPH I@HD$I@ HD$I@(HD$ HD$H HD$H HD$ H I( H|$8 LL$0H5 DLL$0* A 3 H H H9X H H H L M H5 LLL$8LD$0LD$0LL$8HIs I(N H H h H9X HO H H L ; M H5 LLT$@LL$8L\$0LL\$0LL$8HLT$@HR I+ H@ H9AG HD$HϺ H$ LT$@LL$8HL$0HDŽ$ H$ YHL$0LL$8LT$@IIM Im H5 LLT$@LL$8LD$0 LD$0LL$8HLT$@I4 I(E Ht$ LLT$@LL$8L\$0L\$0LL$8HLT$@I I+ HE I9B HD$L H$ LL$@L$ LD$8LT$0HDŽ$ H$ VLT$0LD$8LL$@IMI( M4 Im H\$HHD$0HH LLLL$8L\$0L\$0LL$8HHD$n I+ HLL$0ELL$0HH# H|$LL$8HHL$0H5 HGH H# HL$0LL$8 H) HD$LL$0H I 1IHD$(HHD$ 1E11E1A\ f HD$ HD$ HD$ D H= Iq @ Ll$0I1E1HD$ E1E1E1HD$ A[ c HD$ HD$ HD$( } D LL$H9f D L LHD$ 1E11HD$ E1E1A\ HD$ n HD$
HY D 3 Ll$0I1E1HD$ E11A[ HD$ c HD$ HD$ HD$( L}MzLUIIHm fHnfInL flH$ LT$)$ LI/LT$IPLLT$LT$9 Ll$01E1E1HD$ 1A[ d HD$ HD$ HD$ HD$( @ H=i Hj H5k fIf D Ll$01E1E1HD$ A[ d HD$ HD$ HD$ HD$( df D H= lI @ LT$Hf D LHD$LT$WLl$01E1E1HD$ E1E11HD$ A[ d HD$ HD$ HD$( f D L}MkLMIIHm fInfInLϺ flH$ LL$)$ dI/LL$HD$0ALLL$LL$*f I HD$ 1E11E1Ac\ l HD$ HD$ HD$ fLHD$cLT$LL$z @ LD$(DD$(> SHI[ LD$(D$( Ae\ l HD$ 1E11HD$ E1E1HD$ HD$ 2 LLL$HD$LD$LL$ LLD$LD$L L HU L= H5 H= 1KHH HAu\ m |Hm HAu\ m f It$Hf D I~H LH It$Hf D H{Hs ;I HD$ 1E11E1A\ n HD$ HD$ HD$ f+HSB[ A\ n Ll$0I1E1HD$ E1E11HD$ E1A[ ` HD$ HD$ HD$( DDDDLHD$dLL$HLT$MLT$7LHD$6LD$HD$ 1E11E1A\ p HD$ HD$ HD$ iI`LLL$HD$LT$LL$~LHH HRw H5Ԍ A\ H81VHD$ 1E11E1A\ p HD$ HD$ HD$ LLT$HD$7LD$LT$ LLD$LD$HHD$IHu;I1E1E1E11A\ w HD$ HD$ HD$ ,Hm HLHD$ 1E11E1A\ p HD$ HD$ HD$ CLT$I;DDDDqHLL$/LL$L l3H
s A Hb1[ LLL$LL$&HD$ 1E11E1A\ p HD$ HD$ HD$ HLT$LT${LHD$wLT$HD$ 1E11E1A\ p HD$ HD$ HD$ HD$ 1E1E1HD$ A=\ h HD$ HD$ HD$( eLHLD$*LD$WHD$ x 1A] HD$ E1E1E1HD$ HD$ LLT$LL${LT$LL$A\ p _LLT$OLT$ HLD$8LD$H5 H= 1YHH HA\ q Hm HA\ q LZLl$H$ HDŽ$ H$ L MILLD$LD$HD$ 1E11E1A\ n HD$ HD$ HD$ ITLLD$"LD$xHD$ 1E1E1HD$ A\ x HD$ HD$ WHD$ 1E11HD$ E1E1A\ HD$ n HD$ HD$ 1E1E1E1A ] x HD$ HD$ HD$ HLD$ LL$JLD$ LL$LLT$.LT$HHLL$LL$LLL$ LL$Hg L H$ LT$H$ HD$HDŽ$ H$ $LT$HD$MHD$ 1E11E1A\ n HD$ HD$ HD$ LLD$WLD$1E1E1A
] HD$ y HD$ HD$ HD$ 1E11E1A\ n HD$ HD$ HD$ M IGH5 LH Hm IIHMB IH
M9ng Ht$8 LMHD$0 Ld$8IM I/
I,$
HEL$HH5& H H L$IM M9o IoH MgHE I$I/ fInfHnHt$0Lflź L$)D$0DHm L$I M I,$ I) IMHPIufLH$L $/ I)uLjHӗ H H9X
H H*
H L
o M IAL $LH5< H HQ
L $IIHM
IH_ ID$H5 LH H: IM 111LL $L $HI^ I)
L$0L$HI7 LPH$L $HId H H u H9X H\ H H L5H M IFLT$LL $H5x H H L $LT$HH I.
H5 LHLL$L$L$LL$
H+`
LLLLT$L $«L $LT$HI I/
I)f
I*O
H5 H0HHa L9h
LhM
LPIE IH( fInfInL flHt$0L$)D$0MIm L$I} M I* I/ LLHH I,$M IM I/Lnf HA0E1HD$ @ KtH9 H| H9AH9F y ~ HQH;V HFHyH9AHAt
H DY DV DD@@8 A HyHA@HE|$A L^0HHA@IEDA AL DD E9u;H $H
LL$1HJLL$H $ f D IM9 f D H z H9uuH9uuHϺ LL$H $)HHtgH;Zz H $H;= z LL$ H9 LL$HL$H<$`LL$HL$H<$H/ Ny*HD$( |HSj f K H( L LL$L$y L) LL$ܻL$ H Ht$8 LHD$0 Ld$8MHNL荻>L耻LL $oL $f D LPE1AyA1E1Xl A| f. I/tJM ! @ L " LL$L$ Lغ LLT$L $迺LT$L $ @ H診 1LI蓺f D HL$(HT$0MLL
m LY= H\$(a E1Ao pk D H=A H H5 >yIf D E1Ak k B D H= Hb H5c xIef D 諿I H=ə DvIw @ Ao rk M1ME1E1f. [I/ MAk E1k ]f. H=Y uI @ M~MRMNIII. fHnfInLϺ flHt$0L $)D$0\I/L $I(LL $ϸL $f D 1E1E1Ao k E1Ak ,k 1E1 M~M^MVIII. fHnfInL flHt$0L$)D$0I/L$I4LL$L$ f D I)LAp k %軽I Al :k 蛽I7E1Al Nk 1E1E1ҽk Ap hLL$H $zLL$H $HLL$Ht$H $ֵH $Ht$LL$-HLL$HL$H4$襵H4$HL$LL$H5 H=D 15IHO HqI/ E1Aq k HvH=HyHE1At k zIM*L肶LLH$qL$DD H;ts t LϺ L $荶L $HHtVH;s H;s H;=s LL$H<$ʹH<$LL$AH/q EAt k LLT$L $躵LT$L $LL$蠵L$LLT$L $膵LT$L $LL$lL$fLL$WL$LL $BL $$HLT$L $(LT$L $DD LRLLL$L$LִLT$L $eHLT$L $跴LT$L $LL$蝴L$4LL$舴L$H= HɆ H5ʆ sIOAv k E1A| Ql H=C Hd H5e @sIH=! pI1E1E1ҽk Av ǹIA| Sl H=ؓ SpI薹L $IL袳L蕳Ht$8 LMLT$8L$HD$0 ټL$IHL$QL$BMqMMQIII) fInfInL flHt$0L$H\$@)D$0gI.L$I]LL$ڲL$HLAq E1k 軲Av k 1E1E1ҽVl A| niIH/D L $jL $}MAv k QLL$BL$n1E1[l A| j ZHt$8 HHD$0 Lt$8jII$1E1`l A| 1X fA.A DAcgl A| E1L$I^MAx l H= H H5 LT$L $}pLT$L $I,1۽bl A| H=C LT$L $mL $LT$Idl A| ߶LT$L $H M1ME1E1ҽ/l Ax Aw k H=ɐ H H5 oI1۽il A| lH= mIMAw Mk =I1E1E1ɽl Aw I^HM~HII. fInfHnHt$0Lflƺ )D$0eH+IjHL$ܯL$UMA} xl MA} l MA~ l Aq k LL$~L$PLmN AWH AVAUATIUSH H$ H` H$ H- H$ H- H$ Hl H|$H$ Hl HDŽ$ H$ Hel HDŽ$ H$ H0 LHC Hww IJcH HFH$ HFH$ HFH.M}H$ H$ Il IQ M\ I M H$ L$ L$ H$ HDŽ$ HDŽ$ HDŽ$ HDŽ$ HDŽ$ HDŽ$ HDŽ$ HE H$ H IH H5| H9p H| H H H | H$ H8 HCH5 HH Hz IH$ M H/ HDŽ$ įH$ HH HE Hh"H$ HHn H7j H5( H許 ID$H$ H$ L M H=J HT$身HT$2 HLAHܯH+4 H$ I,$P H$ H/. H$ HDŽ$ H/ H$ HDŽ$ Hm HD$h H|$hH5h HDŽ$ HGH H3 HH$ H2 H5 H9 HCH-Wi H9V4 E1H{ AH+ HDŽ$ E H5܊ H|$hJH$ HH 6 H5 H9- H@H92: HSHH?HH1H)Hu H- H+uHHDŽ$ H5 H=V 1H$ HH0 HKH$ H/ Z D$`
3 E1E11HD$ E1E1H$ HDŽ$ Hl$hE1A HD$8 HD$0 HD$( HD$H HD$X HD$P HD$ HD$ HD$@ HD$ f IuOM~SIMH-Z H 1 D HH9 I;luIH H$ IM H$ ` D H DH H L=f IHFH.H$ H$ -f. H LvL$ L~L$ @ f D H.LyH$ @ LyH LLLT$腴H$ HHy7 LT$Iu H.L=6f IH$ yf D H
j A L
k HHe Hp H5;L ATH81ǭX1 ZH
j H H=}` E1չH L[]A\A]A^A_H) LLLT$蹳LT$H2 H$ IM H LLLT$LT$H1 H$ IH+.* HDŽ$ 蕦H$ H$ H H$ H~H} H5v H9pb5 Hv H5 H H=sv H$ H2 H5k H$ Hc5 H$ H/k- H5 H|$hHDŽ$ ΓIHi5 Hc HD$ I9D$+1 I\$H 1 Ml$HIE I,$D/ H$ LH$ H$ H+]0 H$ H7 Im . H$ HD$ H9GI H$ H$ HDŽ$ H$ tH$ H$ H/Z. H$ H$ HDŽ$ I H/]. H$ H$ HDŽ$ HDŽ$ Ht
H/' H$ HDŽ$ Ht
H/' H$ HDŽ$ Ht
H/' H5 Hߺ HDŽ$ pH$ IHI H;b L;-[b u
L;-ub & Im !' HDŽ$ e H.{ H5s H9pN Hs HO H L-s L$ MM H5 LbH$ H$ IHO H/2 H$ HL$ 1HDŽ$ H$ H9OLQ H$ H$ H$ mH$ H$ IHtH/H L$ HDŽ$ MMQ H$ H/2 H5 H$ HDŽ$ H9 HGH;5a W 1H @H/ I HDŽ$ H5W H= 1yH$ IHO H譣H$ H/9f D$`2 E1E1H$ HD$ E1E1Hl$hHDŽ$ A E1HD$8 HD$0 HD$( HD$H HD$X HD$P HD$ HD$ HD$@ HD$
D H` H;-_ u L;5_ u L HvIH H;_ L;5i_ u
L;5_ }# I.+ 8 ML|$MLd$P LT$ޤLT$H~' L
i MLLH$ H$ {1 )H.` HDŽ$ L;5^ s LHHH Hw H5@p H9p& H'p HI H L-p L$ MH H5 LۍH$ H$ IHI H/+ H.w H5o HDŽ$ H9pJ Ho HeL H L%~o MJ H5| L^IHL I,$. Hv H59o H9pN H o HYP H L% o MBN H5|| LLL$LL$HI{P I,$uC H\ HD$ I9A R LϺ H$ LL$HDŽ$ L$ LL$H$ MIm C L$ M;R I,$D H$ H5q{ LH$ IHS H/D H$ HL$ 1HDŽ$ H$ H9O>T fHnfInfl)$ aH$ H$ Ht
H/WG HDŽ$ Im cD L$ M9T H$ H/aD I~H5]u HDŽ$ L$ HDŽ$ W Ht H52m H9pQi Hm Hg H Hm HD$H$ Hf H5{ HIH)i H$ H/fQ H5y LLL$HDŽ$ 躊LL$HHD$H$ k Ht$ A 1HDŽ$ I9q#v fHnL$ LHxt D$I4LLL$H$ )$ 躦H$ LL$H$ Ht
H/^ H$ HDŽ$ H/Q H$ HDŽ$ HD$Hr I)S H$ H;=]Z H;=#Z F H;=9Z F vH$ v H/[ HDŽ$ o Hr H5:k H9p} H!k H} H L
k M H5] LLL$LL$HHD$H$ 7 I)!n Hlr H5j H9p Hj HR H Hj HD$H$ H H5 x H蛈H$ IH H/t H5nw LLD$HDŽ$ ]LD$HHD$H$ % HD$ I9@ HD$LǺ H$ LD$HDŽ$ H$ 耤LD$IMH$ H/
p HDŽ$ M I+{ H5v LLL$谇LL$HHD$ I){ H$ HD$ H9G HD$H$ HDŽ$ H$ ѣH$ Ht$HHD$HHb{ H$ HD$HP H$ H/0{ HDŽ$ LIE H$ L$ 9IHJ H;fW AH;+W D&m L;
@W m LLL$uLL$A I)Ą E[z H$ H L$ H$ H/@{ H$ HDŽ$ H/{ L$ I<$ z L$ Im z HDŽ$ MHR L( h E111HA LAHD$H$ HZ H H$ H/C HDŽ$ I.wC HD$H;V [ H|$H5w LgaIH\ H5} H9EO H@H;V
b IPHH?HH1H)Hu HO I(uLH54~ H=} 1>HD$@H Lt$@LsIHD$HI{ Lt$Hl$hE1E1D$`4 E1E1H$ HD$ A HD$8 HD$0 HD$( HD$H HD$X HD$P HD$ HD$ HD$@ HD$ f. H(' f D f D L D$` 2 E1E11HD$ E1E1H$ HD$8 A HD$0 HD$( HD$H HD$X HD$P HD$ HD$ HD$@ HD$ f Ht
H/ Mt I,$ H$ Ht
H/ H$ Ht
H/ Mt
I) Mt
I( t$`DE1H
cX H= N xHt
H+i Mt Im i HL$HtHHD$`HHZ HT$@HtHHD$HHK HL$HtHHD$HH< Mt
I/= Ht$ HtHHD$HH. H$ Ht
H/7 H\$PHtHHD$HH( HT$XHtHHD$HH HL$HHtHHD$HH
Ht$(HtHHD$HH H\$0HtHHD$HH HT$8HtHHD$HH HL$HtHHD$HH Hm t7H$ HtH/t4MI.L @ Hf D f ۓf D Hȓ H踓 H訓 H蘓 H舓 Hx Hh% HX LH H8 H( H L H LD\$hD\$hf D\$xLL$pLD$h輒D\$xLL$pLD$hW LD\$xLL$pLD$h艒D\$xLL$pLD$h4 D D\$xLL$pLD$h\D\$xLL$pLD$h D\$xLL$pLD$h,D\$xLL$pLD$h LD\$pLD$hD\$pLD$h HE0L|$1IHD$ Ld$MMf. MtL9* HO H9EI9F=5} c A~ HUI;V IFHuH9@H@t
H DU EN DD@@8u{A y H}HA@HE|$ A Q Iv0IHA@IDDA AI4 DDE9u&Ht@H̒f D HI9MMLd$ ML|$MLd$IMHR H
R AHOL
R EHS LOOD@f D HD$ E1E1E1HD$8 E1A HD$0 HD$( HD$H HD$X HD$P HD$ HD$ HD$@ HD$ D$`1 mf D H=o H^ H5^ NH
f D HL襔H$ HHHD$ E1H$ E1HD$8 E1A HD$0 HD$( HD$H HD$X HD$P HD$ HD$ HD$@ HD$ D$`2 zf. 諔I~ H=n DKH3 @ HD$ E1E11HD$8 E1E1A HD$0 HD$( HD$H HD$X HD$P HD$ HD$ HD$@ HD$ D$`1 @ H$ L$ L$ HD$ E1E1E1HD$8 E1A HD$0 HD$( HD$H HD$X HD$P HD$ HD$ HD$@ HD$ D$`1 -f D IFHD$ E1E1H$ HD$8 E1E1A HD$0 HD$( HD$H HD$X HD$P HD$ HD$ HD$@ HD$ D$`1 f D E1H$ H;VJ
H5!J HDŽ$ HH5:J H95J @@t$` H H$ H5[ HD$@Hb H9pC HZ H'C H HZ HD$H$ HUB H5Hm HyHD$H$ HI H$ H/1 HDŽ$ 蚎HD$H$ H`K Ht$@HH$ HpIHL Hb H5 Z H9pN HZ HO H L
Y MM H5h LLD$ LL$IxLL$LD$ HHD$H$ RO I)%6 H$ H5g LLD$H$ LD$K H/9 H$ H$ LLD$HDŽ$ wLD$HHD$H$ P H$ H/; H$ HDŽ$ H/; HDŽ$ I(; H$ H$ H$ H/V; HG HDŽ$ HD$L;=G L;=G \ L;=G O Lύ9 L;5pG / H5[e LvHD$HXO HDŽ$ HHF HD$ H9F O HFH$ H1Q LFH I HHD$(HH8 H$ H$ LLD$(H$ 谒H$ LD$(HD$HH$ tH/[< H$ HD$H|$ HDŽ$ N I(
6 H$ 1ɺ HHDŽ$ H H$ IHIO HHOH$ HD$HP H/: HDŽ$ Hm : H5!j H|$GuH$ IHP HDŽ$ HD$ I9GJ IGH$ HJ IWH H$ HH$ H$ H/IE H$ H$ H$ HD$@H$ &H$ IHt
H/ G HDŽ$ H$ M}Z H/< H5i H|$HDŽ$ HtIH] HD$LD$HHD$ H$ <^ IH$ Lx=LD$HHD$ H$ ] H;i H5i HLD$跋LD$N H$ H$ LLD$rLD$HHD$ H$ We I(M H$ H/M H$ HDŽ$ H/L H$ H5T HDŽ$ HDŽ$ HD$ H\ H9po H|T H p H HhT HD$PH$ Ho H5` HrHD$PH$ H.r H$ H/N HDŽ$ MHD$PH$ Hh Ht$ HH$ Hp蝉HD$PH$ Hh HB H5` H!c H$ H$ H$ \qIH H$ H/Gc H$ HDŽ$ H/c H$ HDŽ$ H/b H5_ LLD$HDŽ$ qLD$HHD$PH$ I(b #IH HB LD$H I@~LD$HHD$PH$ x Hh H5_ HLD$LD$,q H$ H$ LLD$.pH$ LD$HHD$PH$ y H/p HDŽ$ I(k H$ H/gk Ht$ H$ HDŽ$ HHD$HH3p HDŽ$ Hl$ HD$8 HD$0 HD$( HD$H HD$X HD$P t$`a LT$ H5Y IzwD H5` LoHD$H$ H| HDŽ$ H5? H9ptj HH@H$ H\j HVH H$ A HH$ H$ H/\ ~$ H$ LHg )$ 貋H$ H$ Ht
H/b H$ HDŽ$ y H$ H/b Ht$ H$ HDŽ$ HHD$HH_b HDŽ$ Hl$ H5(a H|$hnH$ HEo H5f H1H$ Ņn H/J HDŽ$ J L$` I H5` H|$ 'nH$ H&{ H5f H1蕃H$ ŅO H/ HDŽ$ H HNW H5N H9pu HN Ht H L%N L$ Mt H5\ LmH$ H$ IHZt H/Mn HDŽ$ 苄H$ Hx H5+\ H|$h)mH$ IH0 H5\ H$ Hm H$ H/} H$ H5Mf HDŽ$ H$ lH$ IH H$ H/=} H$ HDŽ$ H/} H$ Ht$ HDŽ$ H|$hHDŽ$ HD$DH$ IH؆ H5U H|$H} H$ H/x HD$Hl$hHDŽ$ IH Hy< D$` HDŽ$ H HD$HMU H HBU HD$@Hd H H$ Hd H$ H/Y~O L@y L0L$ ŅjD$`2 E1E1H$ HD$ E1E1Hl$hHD$8 A E1HD$0 HD$( HD$H HD$X HD$P HD$ HD$ HD$@ HD$ \ @ L} }^f D }+f D }f D Hp}HDŽ$ {Hf D H+ HDŽ$ H5_ H|$hjH$ HHA
111H_xH$ HH ! H$ H/i H$ H; *b HDŽ$ HDŽ$ LHS H5K H9p) HK H+ H L-K L$ MP( H5y] LIiH$ IH$+ H$ H/<
H$ 1HDŽ$ H
!9 H$ H9O- H$ H$ H$ RH$ H$ IHtH/! L$ HDŽ$ H$ M, H/W H5` H$ HDŽ$ H9# HGH9g9 E1H AH/ HDŽ$ EH5Na H=b 1`gH$ IHP H{H$ H/D: D$`a3 E1E1H$ HD$ E1E1Hl$hHDŽ$ A E1HD$8 HD$0 HD$( HD$H HD$X HD$P HD$ HD$ HD$@ HD$ H=]Z HNI H5OI Z9I'1 HD$ E1E1H$ HD$8 E1E1Hl$hHD$0 E1A HD$( HD$H HD$X HD$P HD$ HD$ HD$@ HD$ D$` 3 6f D yf D D$`2 E1E11HD$ E1E1H$ HD$8 A HDŽ$ HD$0 HD$( HD$H HD$X HD$P HD$ HD$ HD$@ HD$ HD$ E1E1H$ HD$8 E1E1Hl$hHD$0 E1A HD$( HD$H HD$X HD$P HD$ HD$ HD$@ HD$ D$`2 f D #~Hp S{H( HD$ E1E1H$ HD$8 E1E1A HDŽ$ HD$0 HD$( HD$H HD$X HD$P HD$ HD$ HD$@ HD$ D$`2 4 @ wf D Lxw* kwf D [wf D LHw H;Y4 Hߺ vwHH&7 H;4 AH;h4 D H; }4 HzH+A E D$`2 E1E11HD$ E1E1H$ HD$8 Hl$hE1A HD$0 HD$( HD$H HD$X HD$P HD$ HD$ HD$@ HD$ D LD$(,vD$(; Htp H v LptpH LT$xLT$H}1 nf D IvH H}H H$ 1LMHDŽ$ ~H$ LT$xxLT$Hdv1 DD`.udHD$ E1E1H$ HD$8 E1E1Hl$hHD$0 E1A HD$( HD$H HD$X HD$P HD$ HD$ HD$@ HD$ D$`2 7H$ D$`-2 Ht.H/uwtHDŽ$ H$ Ht
H/ H$ HDŽ$ Ht
H/i L%[ H}XHDŽ$ I9 H ID$H HW @ A$ @ HX Hq HJH 1 HH9s L;dut$`H
5 H=+ H$ H$ HH$ d H59Y H=Z 1c_IH4 HsI,$A D$`2 f D H D\$pE1E1H$ H$ E11H$ H$ H;=f) HDŽ$ @H;= ) @- H;=4) w- qoŅQ H$ H/S> HDŽ$ \ HP LH HP H5F H$ 8XHD$H$ H\ Ht$ H9pO HhHO H@HE H H$ H$ H/DK H$ LH$ BtH$ Hm ?K H$ H$ HD$H` H/
K HDŽ$ H$ I.J H@ H58 HDŽ$ H9p^ H8 H] H H8 HD$H$ HW] H5=O HWHD$H$ H\ H$ H/LJ HDŽ$ lHD$H$ Hd_ Ht$@HH$ HpmIH!` HL' H5uE HHD$`nLD$*U H$ H$ LLD$(UH$ LD$(HHD$H$ 6` H/~U H$ HDŽ$ H/LU HDŽ$ I()U H$ H5J HDŽ$ HHD$PUIH r HDŽ$ HD$ I9Ga IGH$ Hta MwH II/ea M H$ LH$ Hcи H)I4qH$ H$ Ht
H/SV H$ HDŽ$ HD$Hp I/` H$ 1E1E1HDŽ$ HD$8 Ll$HD$X1H\$0HHl$(HH$ H$ 1gH$ IH!p H; % L;
$ dU L;
$ WU L4kAŅk H$ H/P` HDŽ$ Ekq H5sH H|$TIHp H$ H$ pmH$ IHkq HDŽ$ HD$ I9EIq IUH$ H4q IEHH Im _ IŸ ~$ PLH)Hc$ I4)$ oH$ H$ Ht
H/J_ H$ HDŽ$ H/h L$ HDŽ$ M i Im h H$ HD$HHt
H+_ H5BK H$ HDŽ$ fH$ IHp H;9# H;" O_ L;
# B_ LOiÅh H$ H/_ HDŽ$ ^ H; H 3 H9X2j Hh3 Hj H L-T3 M0j H5@ LQH$ IHdk Im Lk H$ HD$ H9Gj HD$(H$ HDŽ$ H$ nH$ L$ Mj H$ H/=| HDŽ$ L$ Ht Hm f 1ɺ HLHDŽ$ _H$ IH{ HLeH$ IH { H$ H/z HDŽ$ H$ Im z H5JF HHDŽ$ PH$ IH6z HfH$ IHy H\$HHH$ HXgIH7y HE H5@F H(hx H$ H$ LhOH$ H=x H$ H/!x H$ HDŽ$ H/w HDŽ$ Im w H$ Mt
I.z H"9 H50 HDŽ$ H9pkw H0 H| H L
0 L$ M| H5F LJOIH{ H$ H/{ HDŽ$ dH$ H{ HH$ HX0fH$ IHz Hu H5D Hfz H$ H$ LMH$ IH~y Im . H$ H/ H$ HDŽ$ H/.| H$ HDŽ$ HGH;p Z{ HWH~ HGH$ HG H$ H$ H H$ H H$ H/~ HDŽ$ H$ HD$pMt
I/u Ht$8L$ HDŽ$ HtHHD$xHH~ H5C LHDŽ$ lMH$ IHt HDŽ$ HD$ I9At IAH$ Ht IQH A HH$ H$ H/t H$ IcH$ H$ H)I4PiH$ H$ Ht
H/ ~ L$ H$ HDŽ$ Ms H/s H$ HDŽ$ H/Xs H5uC HHDŽ$ ILH$ IHr HDŽ$ HD$ I9A'r IAH$ Hr IQH A HH$ H$ H/q H$ H$ AVL$ HcH$ L)I4!hH$ H$ Ht
H/^s L$ H$ HDŽ$ Ml H/l HDŽ$ L$ H+l H5NA LHDŽ$ KH$ IH#l H$ H]H$ IHk H$ H/k HD$XHDŽ$ H@HXpHj H{ j H4 H$ H$ 'cIH*j HD$8H|$XLHSLL$8I)i H$ i H/ti H5V@ LHDŽ$ "JH$ IHh H$ H~\H$ IHWh H$ H/;h H$ H$ HDŽ$ H$ H/h L|$8H\$HHDŽ$ L|$pf. DDL{\LLL$i\LL$tLgM HGI$H H$ H$ H/ H$ H$ H$ L$ H$ ieH$ I,$L[ݵD$`]2 sHD$ E1E1H$ HD$8 E1E1Hl$hHD$0 E1A HD$( HD$H HD$X HD$P HD$ HD$ HD$@ HD$ D$`"3 5[+[KHD$ E1E1H$ HD$8 E1Hl$hE1HD$0 A HD$( HD$H HD$X HD$P HD$ HD$ HD$@ HD$ D$`2 7LZZ6E1f f.CADEخ]ZLPZ鐻FZH0 E1E1E1HD$ Hl$hA HD$8 H$ HD$0 HD$( HD$H HD$X HD$P HD$ HD$ D$`5 HD$D$`2 A N9>LL$ @HD$ E1E1H$ HD$8 E1Hl$hE1HD$0 A HD$( HD$H HD$X HD$P HD$ HD$ HD$@ D$`p4 @H=NH$ 页H E1HD$ E1HD$8 Hl$hA HD$0 H$ HD$( HD$H HD$X HD$P HD$ HD$ D$`5 HD$鞦H= Hh LD$H5d LD$IW<齙H5 H)A+Lt$Hl$hE1E1D$`4 E1E1H$ HD$ A HD$8 HD$0 HD$( HD$H HD$X HD$P HD$ HD$ HD$@ HD$ 齥 D HLD$(9Ht$@LD$(AHHD$HH- Ex I(E Ey @ Lt$Hl$hE1E1D$`4 A E1H$ HD$ HD$8 HD$0 HD$( HD$H HD$X HD$P HD$ HD$ HD$@ HD$ 闞H= H H5 HD$髖HD$ E1E1H$ HD$8 Hl$hE1A HD$0 HD$( HD$H HD$X HD$P HD$ HD$ HD$@ HD$ D$`3 B4
H54HD$ E1E1Hl$hHD$8 E1A HD$0 HD$( HD$H HD$X HD$P HD$ D$`6 醝L3LD$3LD$LD$3LD$mD$`6 E1E1H$ HD$ Hl$hE1A HD$8 HD$0 HD$( HD$H HD$X HD$P HD$ HD$ 鸜Lt$Hl$hE1E1HD$ E1H$ A HD$8 HD$0 HD$( HD$H HD$X HD$P HD$ HD$ HD$@ HD$ D$`4 'Lt$Hl$hE1E1HD$ E1H$ A HD$8 HD$0 HD$( HD$H HD$X HD$P HD$ HD$ HD$ D$`4 韛HD$ E1E1H$ HD$8 Hl$hE1A HD$0 HD$( HD$H HD$X HD$P HD$ HD$ HD$@ D$`3 H5 H= 1 HD$H$ HA H1H$ H// D$`6 Hl$hA HDŽ$ HD$ E1E1E1HD$8 HD$0 HD$( HD$H HD$X HD$P HD$ HD$ xH5R H|$ HD$HH$ H+ HDŽ$ H H9Fu H$ H/+ H$ H5 HDŽ$ HDŽ$ HT$@HGH|$ H H5 Ѕ2D$`M9 E1E1H$ HD$ E1E1Hl$hHD$8 A HD$0 HD$( HD$H HD$X HD$P HD$ 6@Lt$Hl$hE1E1D$`4 E1E1H$ HD$ A HD$8 HD$0 HD$( HD$H HD$X HD$P HD$ HD$ HD$@ HD$ 陗LLD$-LD$NL-ґL-HD$-LD$D$`6 HE1Hl$hHD$ E1E1A HD$8 E1HD$0 HD$( HD$H HD$X HD$P HD$ HD$ ܖ7-M--#--1f f.G@E閉HD$ E1E1Hl$hHD$8 E1A HD$0 HD$( HD$H HD$X HD$P HD$ D$`F6 9EH= H* H5+ IkH5 H= 1HD$@H$ H04 H|$@,H$ H/@$ Lt$Hl$hE1E1D$`4 E1E1H$ HD$ A HDŽ$ HD$8 HD$0 HD$( HD$H HD$X HD$P HD$ HD$ HD$@ HD$ 'Lt$Hl$hE1E1HD$ E1H$ A HD$8 HD$0 HD$( HD$H HD$X HD$P HD$ HD$ HD$@ HD$ D$`4 閔H*LL$L\$*LL$L\$؏HD$ E1E1H$ HD$8 Hl$hE1A HD$0 HD$( HD$H HD$X HD$P HD$ HD$ HD$@ D$`3 HD$ E1E1H$ HD$8 E1Hl$hE1HD$0 A HD$( HD$H HD$X HD$P HD$ HD$ HD$@ HD$ D$`]3 YHD$ E1H$ E1HD$8 Hl$hA HD$0 HD$( HD$H HD$X HD$P HD$ D$`T6 HD$ E1H$ E1HD$8 Hl$hA HD$0 HD$( HD$H HD$X HD$P D$`[6 醒HD$ Hl$hE1A HD$8 HD$0 HD$( HD$H HD$X HD$P D$`V6 KD$`6 HE1Hl$hHD$ E1E1A HD$8 E1HD$0 HD$( HD$H HD$X HD$P HD$ HD$ 鴑HD$ E1E1H$ HD$8 E1E1Hl$hHD$0 E1A HD$( HD$H HD$X HD$P HD$ HD$ HD$@ HD$ D$`2 "E1f f.GADEIAH$ HȉMaH I$I)t" H$ H$ M1A Ht$錉HD$ E1E1H$ HD$8 E1Hl$hE1HD$0 A HD$( HD$H HD$X HD$P HD$ D$`6 ?HD$&LD$D$`3 E1E1H$ HD$ E1E1Hl$hHD$8 A HD$0 HD$( HD$H HD$X HD$P HD$ HD$ HD$@ HD$ 霏HD$ E1E1Hl$hHD$8 E1A HD$0 HD$( HD$H HD$X HD$P HD$ D$`6 R%%z%p%HD$ E1E1H$ HD$8 Hl$hE1A HD$0 HD$( HD$H HD$X HD$P HD$ HD$ D$`6 鑎HD$ E1E1H$ HD$8 E1Hl$hE1HD$0 A HD$( HD$H HD$X HD$P HD$ D$`6 Lt$Hl$hE1E1HD$ E1H$ A HD$8 HD$0 HD$( HD$H HD$X HD$P HD$ HD$ HD$ D$`4 镍Lt$Hl$hE1E1HD$ E1H$ E1HD$8 A HD$0 HD$( HD$H HD$X HD$P HD$ HD$ HD$ D$`4
LgMHGI$H H$ H$ H/ H$ fInĺ H$ D$@)$ z,H$ I,$L"Lt$Hl$hE1E1HD$ E1H$ E1HD$8 A HD$0 HD$( HD$H HD$X HD$P HD$ HD$ HD$ D$`4 H5 H= 1HD$H$ H$ H"H$ H/$ D$`6 Hl$hA HDŽ$ !NL!bLD$!LD$ LD$!LD$לHD$!LD$饜D$`y6 E1E1H$ HD$ Hl$hE1A HD$8 HD$0 HD$( HD$H HD$X HD$P ۊHD$ E1H$ E1HD$8 Hl$hA HD$0 HD$( HD$H HD$X HD$P D$`^6 vHD$ E1E1H$ HD$8 E1Hl$hE1HD$0 A HD$( HD$H HD$X HD$P HD$ HD$ HD$@ HD$ D$`2 HD$ E1E1H$ HD$8 Hl$hE1A HD$0 HD$( HD$H HD$X HD$P HD$ HD$ D$`7 mH= H H5 IJ 鲴 骵L Hx 鴴n FHa 锝W \H=[ I;L6 , H$ H H$ I饅L [LLL$ LL$ ƄH 鑄H= TIwH= Hv H5w IUHt$@EHHD$HHH|$@LD$m LD$E1+ fA.@ADEL8 L+ ! ބ 鶄HD$ E1E1Hl$hHD$8 E1A HD$0 HD$( HD$H HD$X HD$P HD$ D$`47 hHD$ E1Hl$hE1HD$8 A HD$0 HD$( HD$H HD$X HD$P HD$ D$`6 HD$ E1Hl$hE1HD$8 A HD$0 HD$( HD$H HD$X D$`w6 鮆HD$ E1E1H$ HD$8 Hl$hE1A HD$0 HD$( HD$H HD$X D$`r6 0Lt$Hl$hE1E1D$`4 E1E1H$ HD$ A HD$8 HD$0 HD$( HD$H HD$X HD$P HD$ HD$ HD$@ HD$ 霅H|$@E1E1Lt$E1E1D$`4 Hl$hA HD$ H$ HD$8 HD$0 HD$( HD$H HD$X HD$P HD$ HD$ HD$@ HD$ Y3H=] I߭H|$1H$ HDŽ$ $H$ TLt$Hl$hE1E1HD$ E1H$ A HD$8 HD$0 HD$( HD$H HD$X HD$P HD$ HD$ HD$@ HD$ D$`5 "D$`:7 E1E1H$ HD$ E1E1Hl$hHD$8 A HD$0 HD$( HD$H HD$X HD$P HD$ HD$ 饃Lt$Hl$hE1E1HD$ E1H$ A HD$8 HD$0 HD$( HD$H HD$X HD$P HD$ HD$ HD$ D$` 5 HD$ E1E1Hl$hHD$8 E1E1A HD$0 HD$( HD$H HD$X HD$P HD$ D$`87 鱂HD$ E1E1H$ HD$8 E1Hl$hE1HD$0 A HD$( HD$H HD$X HD$P HD$ D$` 7 =HGH$ HūHWH HH$ H$ H/X H$ H$ 1A 邫H$ A ŕ-鏔L pLt$Hl$hE1E1HD$ E1H$ E1HD$8 A HD$0 HD$( HD$H HD$X HD$P HD$ HD$ HD$ D$`5 0H= HD$@ H= H H5 HD$@H5 H= 1HD$@H$ Hr) H|$@H$ H/? Lt$Hl$hE1E1D$`5 E1E1H$ HD$ A HDŽ$ HD$8 HD$0 HD$( HD$H HD$X HD$P HD$ HD$ HD$@ HD$ H=x H H5 uHD$PPHD$ E1E1H$ HD$8 Hl$hE1A HD$0 HD$( HD$H HD$X D$`m6 H= pHD$PۏHD$ E1E1H$ HD$8 Hl$hE1A HD$0 HD$( HD$H HD$X HD$P HD$ HD$ HD$@ D$`4 ~HD$ E1E1H$ HD$8 Hl$hE1A HD$0 HD$( HD$H HD$X HD$P HD$ HD$ HD$@ HD$ D$`4 g~L/{HD$ E1E1H$ HD$8 Hl$hE1A HD$0 HD$( HD$H HD$X HD$P HD$ D$` 7 }IA E1E1D$`7 Hl$hE1HD$ H$ HD$8 HD$0 HD$( HD$H HD$X HD$P HD$ HD$ l}LʪLD$LD$頪LD$LD$nHD$ E1E1H$ HD$8 Hl$hE1A HD$0 HD$( HD$H HD$X D$`o6 |H0HD$@H$ HDŽ$ H$ p H$ LD$LD$ D$`6 E1E1H$ HD$ Hl$hA HD$8 HD$0 HD$( HD$H HD$X HD$P |Hl$hE1E1E1D$`9 A
HD$ {HD$ Hl$hE1E1D$`9 A
{$^驑D鳪Hl$hE1E1E1D$`9 H$ A HD$ z{飩Lt$Hl$hE1E1HD$ E1H$ E1HD$8 A HD$0 HD$( HD$H HD$X HD$P HD$ HD$ HD$ D$`55 zMHl$hHD$ E1HD$8 A HD$0 HD$( HD$H HD$X HD$P HD$ HD$ HD$@ HD$ D$`%4 yzMPMjuMXIII(i# Lߺ LLT$H$ L$ L\$H$ LT$L\$II*IuLLL$L\$<LL$L\$(uHD$ E1Hl$hE1HD$8 A HD$0 HD$( HD$H HD$X HD$P HD$ HD$ HD$@ D$`4 tyLt$Hl$hE1E1D$`^5 E1E1H$ HD$ A HD$8 HD$0 HD$( HD$H HD$X HD$P HD$ HD$ HD$@ HD$ xHD$ E1E1Hl$hHD$8 E1A HD$0 HD$( HD$H HD$X HD$P HD$ D$`e7 wxH5 H=" 1HD$H$ H! H|$H$ H/v! D$`I7 E1E1H$ HD$ E1E1Hl$hHD$8 A HDŽ$ HD$0 HD$( HD$H HD$X HD$P HD$ HD$ wLt$Hl$hE1E1HD$ E1H$ E1HD$8 A HD$0 HD$( HD$H HD$X HD$P HD$ HD$ HD$ D$`\5 vH=f H H5 cHD$nqIE1Hl$hE1HD$ E1A HD$8 HD$0 HD$( HD$H HD$X HD$P HD$ D$`7 vIE1Hl$hE1HD$ E1H$ E1HD$8 A HD$0 HD$( HD$H HD$X HD$P HD$ D$`7 uH=_ HD$ H=I Hz H5{ FHD$HD$ Hl$hE1E1D$`9 A uHD$ Hl$hE1E1D$`9 A uH= RIH= H H5 IHD$ E1H$ E1HD$8 Hl$hA HD$0 HD$( HD$H HD$X D$`6 tLt$Hl$hE1E1HD$ E1H$ E1HD$8 A HD$0 HD$( HD$H HD$X HD$P HD$ HD$ HD$ D$`!5 QtHD$ E1Hl$hE1HD$8 A HD$0 HD$( HD$H HD$X D$`6 sIE1Hl$hE1HD$ E1H$ E1HD$8 A HD$0 HD$( HD$H HD$X HD$P HD$ D$`7 sHD$ E1E1Hl$hHD$8 E1E1A HD$0 HD$( HD$H HD$X HD$P HD$ D$`y7 sIE1Hl$hE1HD$ E1H$ A HD$8 HD$0 HD$( HD$H HD$X HD$P HD$ HD$ D$`7 rIE1Hl$hE1HD$ E1A HD$8 HD$0 HD$( HD$H HD$X HD$P HD$ D$`7 1rLGMmHGI H H$ H$ H/ fIn LLD$H$ D$)$ LD$H$ I(mLmHD$ Hl$hE1E1D$`9 A qD$`F4 E1E1H$ HD$ Hl$hE1A HD$8 HD$0 HD$( HD$H HD$X HD$P HD$ HD$ HD$@ HD$ pHD$ Hl$hE1E1D$`9 A pL" 1飞LM 鎞鬠馟LHD$HHD$HIŸ 1HؠH|$XE1A 1H$ 1H$ IH
H H|$(HK
H$ H//
HDŽ$ JȠ8!Hl$hE1E1E1D$`l9 H$ A oHD$ Hl$hE1E1D$`9 A
oHD$ E1E1H$ HD$8 E1Hl$hE1HD$0 A HD$( HD$H HD$X HD$P HD$ HD$ HD$@ D$`?4 nHD$ E1E1H$ HD$8 E1Hl$hE1HD$0 A HD$( HD$H HD$X HD$P HD$ HD$ HD$@ HD$ D$`P3 dnLwHD$ E1E1Hl$hHD$8 E1A HD$0 HD$( HD$H HD$X HD$P HD$ D$`(9 n?Z5Lt$Hl$hE1E1D$`95 E1E1H$ HD$ A HD$8 HD$0 HD$( HD$H HD$X HD$P HD$ HD$ HD$@ HD$ IH H$ H/ IELHDŽ$ L AH$ H[ LAH$ H3 LAH HD$pjLL$px"Im `L>S4ȃMLl$Hl$E1Hl$(D$`8 A H\$(H$ H\$0IL|$0MHD$ Hl$hE1HD$ pNH(MLl$Hl$Hl$(H\$(H\$0L|$0 Hޡ IE1E1 H5 LD$pH81D$`8 Hl$hE1HD$ LD$pA HD$ H$ MMLl$Hl$A Hl$(H\$(H\$0L|$0I( tXIA E1E1D$`8 Hl$hE1E1HD$ H$ HD$ eMHLD$LD$ IH LIH
H5 HEHĠ E1E1H81Hl$hE1E1D$`8 H$ A HD$ HD$ LL4 ME1Ll$Hl$Hl$(H\$(H\$0L|$0DLl$Hl$IE1Hl$(E1H\$(A H\$0D$`8 L|$0IE1H$ HD$ Hl$hHD$ =LHWHuAHGHH@H$ H$ WnLaŀW`Ll$Hl$Hl$(H\$(H\$0L|$0H H HHu IH
r H5e HEH: E1E1H81ZHl$hE1E1D$`}8 H$ A HD$ HD$ RKHځIA E1E1D$`}8 Hl$hE1E1HD$ H$ HD$ JH IE1E1 H5n H81Hl$hE1E1D$`}8 H$ A HD$ HD$ Jf. fUf(SH(-6 f/\ f(f\H,H*X:
6 \$^T$YYX
r6 Y\
n6 YX
j6 Y\
f6 YX
b6 Y\
^6 YX
Z6 Y\
V6 Yf(L$SL$X
=6 T$f(55 \$^f(\%6 f/YX
6 X\vIH~DH D \@ L$Hf(T$L$H9T$\uH(f([] f1ff. fHHH?Pf*Y6 Hff. HGH? H~CAUIATIUHS1Hf D H} UAD HI9uH[]A\A]f D H~SAUIATIUHS1Hf D I} AUf*YM6 AHH9uH[]A\A] AUIATL%2 UH-* SH " H(I} AUfHH HH*YL H9 IEI} AL$HcAT$\$L$D$f(fW%5 f(BT$L$f($YD$Xf/KH(f([]A\A]f. fWV5
3 H([]\A\A]f(f D HW AWIAVE1AUL- ATL% UHSHH( f. H L$HcLT$\$L$D$f(fW%4 f(>T$L$f($YD$Xf/ BL IL9tkI?AWfHH HH*AY I;D rIGM8LfW4
n2 \BL IL9uH([]A\A]A^A_ Lf(b ff. @ AVAUIATL% UH- SH HI} AUfɉ *YL 9 IEI} AL$HcAT$ \D$L$A(W-33 A(T$ L$(fA*Y2 YD$X/HH([]A\A]A^ @ f*Y2 W2
2 H[]\A\A]A^( AWAVAUATUSH(Ht$H, HHL%W E1L-M AH
5 L$McLBT$ \D$L$A(W-2 A(T$ L$(fA*Y1 YD$X/ BL IL9t$tpH;Sfɉ *@DAY A;D rHCL @.Lf*Y>1 Wo1
.1 \ @ H([]A\A]A^A_f Hh(VH~[AUIATIUHS1Hf D I} AUfW0 kfW0 AHH9uH[]A\A]f ff. @ H~sAUIATE1UHSHH D I} AUf*YM0 W~0 ZZWj0 BD IL9uH[]A\A] AWAVIAUL- ATL%& UH SH H( IFI> L$HcT$\$L$%,. D$Yf(Y=T$L$f($YD$Xf/wAI>AVfII LH!H*AYL tfW
A/ I94?H(f([]A\A]A^A_ @ IFI>fW/
j- I>Y $AVfW. e $fW. f(XYf/vX
.- A zfW
. m @ SHH0=8 D$f/ H;SHD$
t$T$\f/r>
D$f(^s\$f(f/rH0f([f D$ L$ \^D$=|$L$ D$f(Y\f(
k ^T$\$f(\f/ H0f([ff(\%, , Yd$(ff. Qf(^d$fHff(D$YX f/sf(L$H;YYD$SL$+ f(YYY \f/wbL$ D$D$%^ \d$f(L$ f(X* YD$(YYXf/D$(L$(YL$H0[f(m% H~CAUIATIUHS1Hf D LAD HH9uH[]A\A] D AWAVIAUATL% UH-
SH H D IFI> HcL$ \D$%* fAnfZAYAf(YL$ f(fA*Y/+ YD$XZf/wDI>AVfAA A*AYfA~t W + fA~D9l /HfAn[]A\A]A^A_ IFI>f*Y* W* 0
* I>YL$AVf*Yl* W* L$W* (XY/vX
G* A fA~RW
Z* fA~AH~CAUIATIUHS1Hf D LAD HH9uH[]A\A] D f. {&ff.{ 7 uf(f uif UHH .) D$u d$f.R =b) /|$%E) d$ H} UfH*YT$T$ z
) t$T$ \/r-
( D$ (^\$ /rH ]fD$( L$\^D$
|$L$D$ (Y\(
( ^LT$ \$\/#H ] D t$\5V( fN( Yt$ .; Q='( d$^|$ H f(D$YX' /s(L$H} YYD$ UL$' f(*YYD$YY ' \/w_L$D$D$ =i' \|$ (L$(X[' YD$ YYX/D$ D$ YD$ H ] @ H f]H ]P{%& ff. HHH?PHHff. HHH?PHff. HHH?PHHff. HGH? f. Euf.$ Duffff. H$L$YD$X$Hff. UHH0H?D$UH= fHH HH*Y H= H;sD$H0]Y @ HEH} H L$ HcT$(\D$L$ D$f(fW%^% f(T$(L$ f(D$YD$Xf/_Hf(D$H0]Y fW$ y
Q# \D$H0]Yff. fHHH?$L$PYD$X$H Hf.< {Bff.{ L$L$HYf D ufHYf uL$L$HY @ HL$ qYD$ Hf D UHH0 D$ f/L$( f/ f(t" f/vf/n @ H} UH} D$U
L ^L$ D$D$
- ^L$(D$D$XD$ f/rL$XL$ff/vf/J L$H0]^f(f D \$ f. | d$ ff. D$ HJf(\$(f. {ht$(ff. D$(HL$L$X^H0f(]f D ~H2\$(f. f(zuHL$L$H?U\$ H f(D$(XYfHnf/wf} D Pfaf f D$5f(D$^L$ L$L$f(^T$(T$ f(_\\$f(L$3\$T$ D$\f(XD$L$H0]\f(HY f. {*ff.{HXfufH D uHXUHH H $Yf. f( ff.{sHL$ L$f(XYY
f.
C } ff.{;f(HT$T$XY$H]^f( @ ufuf eL$L$f(Xm @ }HT$T$X UHHHD$L$H]^f(ÐUHH0H?D$UH= fHH HH*Y H=r H;s ^L$H0f(]h HEH} H6 L$ HcT$(\D$L$ D$f(fW- f(T$(L$ f(D$YD$Xf/WH{f(FffW 1
\$UfHH0f.zu H0f(]f
H} ^L$UH=P fL$HH HH*YH=$ H; HEH} H L$(Hc T$\$ \D$T$D$f(fW- f(d\$ T$f(D$L$(YD$Xf/wHL$:L$f(H0f(]ffWf L$\ff. fHD$~
) fW ~
fW
^L$H=ff. fSHH$L$
ff/wFH;Sf/ r
N \\f(L$Y$H[\ @ XYD$X$H[ff. AVfI~SHHL$ H;S f( \f/vofW bL$H[YfInA^\ SHH$L$ D H;Sff/v
h \^YD$X$H[fH$L$\YD$X$H UHH0H?D$UH=E fHH HH*Y H=" H;s,Xff. QD$H0]Yf D HEH} H L$ HcT$(\D$L$ D$f(fW% f(=T$(L$ f(D$YD$Xf/GHf(6ffWV
\f(Gf(ff. UHH D$L$Y
W f.
f({qff.{_f(Hl$\$L$)L$\$l$f(f.wtQYf.wKQf(H ^] D uf(uHL$D$L$\$ff(f(L$UL$f(f(l$d$\$.l$d$\$f(Z AWf(AVAUATUSHHHf/ D$ f. z uE1HHL[]A\A]A^A_f D D$fW E1:
: D$f. IL$H;SL$Yf/L$w @ ff(f.> Qf(f(L$1}L$Y
X
D$0 Yf(L$ \
\- f( \= ^
f(|$8XfI~X fI~ ^\fI~f D H;SH;f(\ T$ST$
D$f(fT" \fIn^L$XD$ YXD$X bL$f/
L,\$rfInf/0M_= f/v
f/Gf(L$(D$fInL$(t$8D$D$ Y^X߿T$XT$ID$fI*YL$0\f\L$H*f. Eńu3f. Du!L$T$WL$T$\f/}@D$
f(D$ff. UHH x f(f.\^{>ff.{,HT$T$YHH] ufuT$#T$ff. AWfAVH*AUIATIUSHH $ t
H9r Me$ AE f(\A}|$Pf/t$H# L$PT$Yf(fD$HAEX\$AM(f(L$\$Y\$HH,fL$T$f.Im0f(\$h Qf(Yl \$HY f % -^ \f(fTf.0 5x d$PXf(t$(fD(D$AE8ffA(H*XX Xf(Am@$ A\f(\$xA]P Y|$8^f(A}H\X fD(\$@A]Xf(\^f(YXYf(Yl$H\\$`^A]`Yf(XYfA(AXXL$pAMhAYf(D$AEpfA(^D^Xf(D$XAExfA(XD$ A Ml$LH)H$ fH;Sd$ H;Yd$Sd$f/d$f(V f/d$" t$l$@fH* \YT$0f(^XXD$8\X\$(fT ^\f/L$[FL$T$0L,MI)LH?HL1H)H~#D$hYD$(fH*\f/ fd$P^d$HI*YI94 f(j f/$ M)f/L$(MGH []LA\A]A^A_ D f.8 ADEf/d$Xwcd$0D$r^D$`XD$8QL,MSEJd$0\d$L$ YYL$`d$0D$\$x^D$p\f(L,M9EL$d$0\d$X YYL$pqf D HEI9 IVf( ff(H*H^\YH9uIFH9HU ff(H*H^\^H9uWf(^ t$hHX HHf(XYX ^^XT$(YfH*^f(T$0\$ĸ\$T$0f(f(\f/Xd$0f/IFfEfEL*HEfEL*LfL*$ L)HH*fE(D$ EYfA(fA(D$ A^fE(D$ AYEYfD(l$DYD$ $ D$ D$ ηD$ $ D$ fA(^D$衷T$HD$ $ t$Yt$PAYf(^j=j
5j
L$ -^
H)f(f(D$ D$ ^d$0D$ DY$ D$ D$ D$ D$ \f(^\ fD(^D\D^
f(A\fEL*DX\$(DY$ A^D EXfEM*AYDXf(A^A^AXfD(D\f(E^A\fD(A^D\f(E^A\fD(A^A^Xf(A^A^D\f(E^\A^A\fD(A^\A^D\f(E^\A^A\A^\^L$A^A^XXf/ f($ YT$\XHL,~f D H,ffUH*f(fT\fVf( f(t$P\l$H f(
f.Bhf/B]J8rz Hj0L$J@Yt$P5 $ JH|$HL$8JPYt$(L$xJXL$@J`L$`Jh\$hL$pJpL$JxL$X L$
D$hT$L$˸T$L$Ff. AUIATIUSHH8D$t
H9rW d$- fMeI*AE \AeAm f($l$耳$Y±d$$L$f(AEfYYAeXX
f. Q- f(YXf/a H,Im0 $H;S $1f/f(vp @ HH9}) $H;S $f/ 1f(HH9|Lf\H)HH*YT$YfH*YT$^f/wH8[]A\A]Ðf.Bf/Bz ZHj0|$9H81[]A\A]f(d$(\$ T$ $Ӷd$(T$-W $\$ YXf/f(l$ d$ $舶 $d$l$ f( YXH,ff. H f. Eurr fUHH*f/r Y f/rM]O \\ Yf/f(r&!IH]L)f D 1 D ]Bf;IH]L)UHH$f(L$ L$ff. $f/ \ Yf. ff. H $d $XD$H $ $ff(f.% QXD$YXH] D HYfHH*X$Y H$ fHnf. ff.{RHHX]Ð9HD$ G @ $Y} f.Ż {kff.zufKf D H $ $XD$f ]HrXf t$f(讳$f(UHH0$f(L$T$ެv T$ff.
<$f/ \% f(Yf. ff. H\$ d$T$UXT$d$\$ D$(H\$ d$T$T$fd$\$ f(f. QXYXT$( @ % H\$Yd$f(\fd$\$HH*X$Yf.Y ff. H\$d$od$\$f(X!f x %8 l$YYf.{Dff.{2f(HT$T$XY$H0]^f( ufuHT$ T$X @ KHD$( s @ % $ ո Yf.{sff.f.f D H\$ d$T$ Hzd$\$f(Xu\$d$D$f(\$ d$蕰\$ d$L$f(f. f(f(SHXf(H ^L$\$l$\$L$Y
f(YYYf(YXff.w\Q\YT$\$H;XT$S\$T$f(f(X^f/s Y^f(H f([f(\$T$蒯\$T$f(UHH@D$8f(L$è f/D$ f/D$s |$f/
- ft$Yl$YXf. Qf(XL$f(Xf.J Q\T$f(f(X^f(YXXL$^L$0&f(^賩XD$L$ \f/D$sH} UY \$0H} f(YXXL$f(L$^\d$(YL$ UL$ f(| \Y\f/D$\H} UD$D$(ĩf( f/D$vfW XT$8
J f(fTN T$X t$T$\ f/vfWI H@] H} UX\մ Y H@] f ^D$f. QD$HYD$
XD$8f/vX f/` q\r d D =H f(|$|$^Xf|$D$0(~D$qf(L$ dL$ f(f(Ll$f(hff. fSHH0D$ fW
腧D$(H;Sf/D$ D$ H;SYD$(֨T$f(fW Yf/~ f(T$\$\$D$f(ܦL$^" X豪L,MaT$ff.EEH0L[ f/A rA @ H HH?D$\ $PL$ $ f(f/v f(f D YHXf/wHÐHD$a~ T$$fWf(~ $f(fW f(^4 f(fTf.v3H,ff(% fUH*fTXfVf(f/ HsH,H D Hf/t Ir_ H?D$\ $APL$ $ f(f/f(v YHXf/wHf D$5~ } L$$fWf(~ ] $f(fW h f( ^f(fTf.w*f/ HtH,H H,ff(% fUH*fTXfVf(ff. AVSHH(\V f(D$4 ףD$H;SH;D$S% \d$fI~
^L$f(蔣=l f( fTf.v;H,f=ͯ H*f(fT\
fUf(fVf/ ]5 f/Kf(L$T$^XT$l$f(fInYf(\ A ^Yf(\ - ^f/H(H,[A^f. f(f(H8H\\T$H?L$D$(f(d$^l$ 4$P4$d$L$T$f/r;l$ \$(Yf(Yff.wPQXH8f( f(\
X \fYYf.w*Q\H8f(f( $苦 $f(f($r$f( 1H ATIIUHI SHLHI LHL IIL III LH I ĸH9w f D H;SD!H9r[]A\ D H;SL!H9sH;SL!H9rf. ff. @ AWAVAUATIUSHHttHHH?IIH9wqHE AE DjAME9v,D1AAA9s H} UAME9wI IHL[]A\A]A^A_ @ HEH EuQLbIHHI9v+L1HIIH9sf D H} UIHI9wHL$ D HEH} L!I9rL$o D HEH} D!D9wL$O D ЉI> @ I0f D AWAVAUATAUSHteHGIH? AEu`JL$ Dl$ AME9v%1AAA9sI>AVAME9wI AHD[]A\A]A^A_ @ IFI>D!9rD$f. Af AWAVAUATUSHt$H\$Pf A։IAMfA AE EF- DD$ H?AUDD$ A$ 3EAfA9v^AAƙAAf9r&I D 3A$xA<$3AfA9v%uI} AUA$ 3AfA9wD$H[]A\A]A^A_ +A$PA$D!f9s!uI} AUA$ D!f9rfD$H[]A\A]A^A_fuDH?AUA$ D$fH[]A\A]A^A_ @ +AxA9 +A)ff. @ AWAVAUATUSHt$ H\$P A։IAMA AE E~ H?AU A$ 3D@A8v^AEAƙAA8r#Ff3A$xDA<$3@A8v%uI} AUDA$ 3@A8wD$ fH[]A\A]A^A_f+A$PA$D!@8s!uI} AUA$ D!@8rD$ H[]A\A]A^A_ uDH?AUA$ D$ H[]A\A]A^A_ D +AxA9 +A)ff. @ USHHl$ tAHL˅tm A)E H[]f D H?QE AWAVAUATIULSH(HL$HujH~OHH HfInLHHL HH9uHt$HHtLd H([]A\A]A^A_ IHH9 E H|$ ~DrE1Dt$D$ f I} AUt$I9s$D$ 19s @ I} AUI9wH LJL IL9|$uLf. H E E1HLrH|$ H\$fI} AUIHHL9s-HD$1IHH9s I} AUIHH9wHLJD IL9|$ufH|$ 1fI} AULHD HH9\$uf D H|$ n1f. I} AULHD HH9\$uBIII LHI LHI LHI LHI LH I H|$ E1f D I} AUL!H9rLJD IL9|$u III LHI LHI LHI LHI H|$ E1I} AUD!9wLJD IL9|$u[1OfAWAVAUATMUHSHt$ H~pHAH HfnLHfp HL HH9uHH@t,t$HHH A4H9~HAtH9~AtH[]A\A]A^A_ @ IӃ E DrE1Dt$\$ H~f. I} AUt$I9v$D$ 19s @ I} AUI9wH L$C IL9uH[]A\A]A^A_fIII LHI LHI LHI LHA HE1I} AUD!9rD$CIL9uH[]A\A]A^A_ÐH1 D I} AUD$AHH9uH[]A\A]A^A_1zAWAVAUATUSLHf H HAHC HfnLHfaHfp Lʐ HH9uHHt\Hxf4CH H9~KHxftH9~=HxftH9~/HxftH9~!HxftH9~Hft
H9}ft H[]A\A]A^A_ D IAfH E H~DrII1H$A1D$ uf I?AW fD9s@D$ Af9s1t 1fA9vI?AWȉfA9wۿ HDfKH; $2t1뒐AHHH HHH HHH HH HM4I11 t @ 1!fA9sI?AW!fA9r DHfSL9uH[]A\A]A^A_ @ HI,IHDfCH9mI?AWAT fHSH9uP1 D AWAVIAUATUSH@t$ uVH~ff.{,HT$FT$YH;H[ ufuHT$H8PH fHn\f(}T$fW f D UHHWt9OG HG HL$L$H]^f( Ef(ȅtEE HE H^]f(f D AVUHSH ň D$f/L$ f/ D HE H8PHE fI~H8P
^L$fH~fIn|
b ^L$$fHn{X$=@ f/rf/z d $H []^A^f(f D T$f. T$ff. D$Hbf(\$f. ȇ T$ff. D$H $# $XH []A^^f(f vHE H8Pf(\ \z\$f. E f(fW
qkHE $H8Pf( \z $fWT a H9fL$HHNfMHMfI)H*I9HD$8LI*LOfIH*fI*L)|$f(^f(YXU D$fH*ID$Y% \YfH*Y^X f.! f(Qf(IGfIY T$0M)X L$(\$XD$ fH*HD$8HH*YfI*^yL,fID$H*誥HD$8D$fL)HH*芥L\$L)HXfHH*\$_XD$KD&Lt$@D$fH*;d$L9|$8L$(T$0Xd$H Y
D$ N % X Xf(fTf. ]T$0f D H;SH;D$SL$|$\z YD$ ^XD$f/wf/D$0s?xML,fID$M)H*aHD$8D$(fL)HH*Ad$(IFXfH*d$( XD$(HD$@JD D$(fH*XD$(T$HL$\ \Y\ f/s=f(T$\Yf/ f(nsT$Xf/L;l$PMOM)L9MOffH*fI~ D H,f5o fUH*f(fT\fVf(H\$Xf(T$ \$wT$ \$f(ff. [ff. ff. f/ Ir f D HH?D$APfW rL$$~ \>r$^f( wHH,f[ff. SHH@D$8f(L$ p+ w ;~ f/D$ o |$ f/ ~ fl$D$^XD$0, f(^{qXD$L$\f/D$s}H;SY q\$0H;f(YXXL$f(L$ ^\d$(YL$SL$f(F \Y\f/D$^H;SD$D$(qf( f/D$vfWc XT$8
f(fT} T$X p|$T$\ f/w,H@[f D H;SX\| Y H@[fW H@[f
p -x| ft$Yl$YXf.w[Qf(XL$f(Xf.wTQ\T$ f(f(X^f(YXXL$^L$0@f(Zt|$f(f(L$?tL$f( SHH05{ D$ \f(MoD$(H;Sf/D$ D$ H;SYD$(nm n{ T$\f(Yf/r~f(T$\$n\$D$f(nL$^{ XrL,MaT$ff.EEH0L[ f/A rA HH %.200s() keywords must be strings %s() got an unexpected keyword argument '%U' while calling a Python object NULL result without error in PyObject_Call __int__ returned non-int (type %.200s). The ability to return an instance of a strict subclass of int is deprecated, and may be removed in a future version of Python. __%.4s__ returned non-%.4s (type %.200s) value too large to convert to int %.200s does not export expected C variable %.200s C variable %.200s.%.200s has wrong signature (expected %.500s, got %.500s) %.200s does not export expected C function %.200s C function %.200s.%.200s has wrong signature (expected %.500s, got %.500s) Interpreter change detected - this module can only be loaded into one interpreter per process. %.200s.%.200s is not a type object %.200s.%.200s size changed, may indicate binary incompatibility. Expected %zd from C header, got %zd from PyObject %s.%s size changed, may indicate binary incompatibility. Expected %zd from C header, got %zd from PyObject '%.200s' object is unsliceable %s() got multiple values for keyword argument '%U' calling %R should have returned an instance of BaseException, not %R raise: exception class must be a subclass of BaseException invalid vtable found for imported type Cannot convert %.200s to %.200s '%.200s' object has no attribute '%U' numpy/random/mtrand.cpython-39-x86_64-linux-gnu.so.p/numpy/random/mtrand.pyx.c %.200s() takes %.8s %zd positional argument%.1s (%zd given) numpy.random.mtrand.RandomState.random numpy.random.mtrand.RandomState.__getstate__ numpy.random.mtrand.RandomState.__str__ numpy.random.mtrand.RandomState._initialize_bit_generator cannot fit '%.200s' into an index-sized integer '%.200s' object is not subscriptable too many values to unpack (expected %zd) need more than %zd value%.1s to unpack numpy.random.mtrand.RandomState.__reduce__ numpy.random.mtrand.RandomState.noncentral_chisquare numpy.random.mtrand.RandomState.f numpy.random.mtrand.RandomState.wald numpy.random.mtrand.RandomState.rand numpy.random.mtrand.RandomState.randn numpy.random.mtrand.RandomState.__repr__ numpy.random.mtrand.RandomState.pareto numpy.random.mtrand.RandomState.weibull numpy.random.mtrand.RandomState.chisquare numpy.random.mtrand.RandomState.standard_gamma numpy.random.mtrand.RandomState.standard_t numpy.random.mtrand.RandomState.power numpy.random.mtrand.RandomState.normal numpy.random.mtrand.RandomState.logistic numpy.random.mtrand.RandomState.lognormal numpy.random.mtrand.RandomState.laplace numpy.random.mtrand.RandomState.gumbel numpy.random.mtrand.RandomState.gamma numpy.random.mtrand.RandomState.__init__ hasattr(): attribute name must be string numpy.random.mtrand.int64_to_long numpy.random.mtrand.RandomState.logseries numpy.random.mtrand.RandomState.geometric numpy.random.mtrand.RandomState.zipf numpy.random.mtrand.RandomState.negative_binomial numpy.random.mtrand.RandomState.triangular numpy.random.mtrand.RandomState.uniform numpy.random.mtrand.RandomState.randint Module 'mtrand' has already been imported. Re-initialisation is not supported. compile time version %s of module '%.100s' does not match runtime version %s base class '%.200s' is not a heap type extension type '%.200s' has no __dict__ slot, but base type '%.200s' has: either add 'cdef dict __dict__' to the extension type or add '__slots__ = [...]' to the base type multiple bases have vtable conflict: '%.200s' and '%.200s' numpy.random._bounded_integers PyObject *(PyObject *, PyObject *, PyObject *, int, int, bitgen_t *, PyObject *) int (double, PyObject *, __pyx_t_5numpy_6random_7_common_constraint_type) int (PyArrayObject *, PyObject *, __pyx_t_5numpy_6random_7_common_constraint_type) PyObject *(void *, bitgen_t *, PyObject *, PyObject *, PyObject *) PyObject *(PyObject *, PyArrayObject *) PyObject *(void *, void *, PyObject *, PyObject *, int, PyObject *, PyObject *, __pyx_t_5numpy_6random_7_common_constraint_type, PyObject *, PyObject *, __pyx_t_5numpy_6random_7_common_constraint_type, PyObject *, PyObject *, __pyx_t_5numpy_6random_7_common_constraint_type, PyObject *) PyObject *(void *, void *, PyObject *, PyObject *, int, int, PyObject *, PyObject *, __pyx_t_5numpy_6random_7_common_constraint_type, PyObject *, PyObject *, __pyx_t_5numpy_6random_7_common_constraint_type, PyObject *, PyObject *, __pyx_t_5numpy_6random_7_common_constraint_type) PyObject *(void *, void *, PyObject *, PyObject *, PyArrayObject *, PyObject *, __pyx_t_5numpy_6random_7_common_constraint_type, PyArrayObject *, PyObject *, __pyx_t_5numpy_6random_7_common_constraint_type, PyArrayObject *, PyObject *, __pyx_t_5numpy_6random_7_common_constraint_type) _ARRAY_API is not PyCapsule object module compiled against ABI version 0x%x but this version of numpy is 0x%x module compiled against API version 0x%x but this version of numpy is 0x%x . Check the section C-API incompatibility at the Troubleshooting ImportError section at https://numpy.org/devdocs/user/troubleshooting-importerror.html#c-api-incompatibility for indications on how to solve this problem . FATAL: module compiled as unknown endian FATAL: module compiled as little endian, but detected different endianness at runtime numpy.random.mtrand.get_bit_generator numpy.random.mtrand.set_bit_generator numpy.random.mtrand.RandomState.rayleigh numpy.random.mtrand.RandomState.exponential numpy.random.mtrand.RandomState.set_state numpy.random.mtrand.RandomState.shuffle join() result is too long for a Python string numpy.random.mtrand.RandomState.get_state numpy.random.mtrand.RandomState.seed numpy.random.mtrand.RandomState.poisson numpy.random.mtrand.RandomState.noncentral_f numpy.random.mtrand.RandomState.bytes numpy.random.mtrand.RandomState.hypergeometric numpy.random.mtrand.RandomState.random_sample numpy.random.mtrand.RandomState.dirichlet numpy.random.mtrand.RandomState.standard_exponential numpy.random.mtrand.RandomState.standard_normal numpy.random.mtrand.RandomState.standard_cauchy numpy.random.mtrand.RandomState.tomaxint numpy.random.mtrand.RandomState.random_integers numpy.random.mtrand.RandomState.__setstate__ numpy.random.mtrand.RandomState.multinomial numpy.random.mtrand.RandomState.beta numpy.random.mtrand.RandomState.vonmises numpy.random.mtrand.RandomState.binomial numpy.random.mtrand.RandomState.multivariate_normal numpy.random.mtrand.RandomState.permutation numpy.random.mtrand.RandomState.choice '%.200s' object does not support slice %.10s numpy.random.mtrand.RandomState
RandomState(seed=None)
Container for the slow Mersenne Twister pseudo-random number generator.
Consider using a different BitGenerator with the Generator container
instead.
`RandomState` and `Generator` expose a number of methods for generating
random numbers drawn from a variety of probability distributions. In
addition to the distribution-specific arguments, each method takes a
keyword argument `size` that defaults to ``None``. If `size` is ``None``,
then a single value is generated and returned. If `size` is an integer,
then a 1-D array filled with generated values is returned. If `size` is a
tuple, then an array with that shape is filled and returned.
**Compatibility Guarantee**
A fixed bit generator using a fixed seed and a fixed series of calls to
'RandomState' methods using the same parameters will always produce the
same results up to roundoff error except when the values were incorrect.
`RandomState` is effectively frozen and will only receive updates that
are required by changes in the internals of Numpy. More substantial
changes, including algorithmic improvements, are reserved for
`Generator`.
Parameters
----------
seed : {None, int, array_like, BitGenerator}, optional
Random seed used to initialize the pseudo-random number generator or
an instantized BitGenerator. If an integer or array, used as a seed for
the MT19937 BitGenerator. Values can be any integer between 0 and
2**32 - 1 inclusive, an array (or other sequence) of such integers,
or ``None`` (the default). If `seed` is ``None``, then the `MT19937`
BitGenerator is initialized by reading data from ``/dev/urandom``
(or the Windows analogue) if available or seed from the clock
otherwise.
Notes
-----
The Python stdlib module "random" also contains a Mersenne Twister
pseudo-random number generator with a number of methods that are similar
to the ones available in `RandomState`. `RandomState`, besides being
NumPy-aware, has the advantage that it provides a much larger number
of probability distributions to choose from.
See Also
--------
Generator
MT19937
numpy.random.BitGenerator
an integer is required __pyx_capi__ name __loader__ loader __file__ origin __package__ parent __path__ submodule_search_locations Missing type object cannot import name %S %s (%s:%d) at least at most random numpy/random/mtrand.pyx exactly __getstate__ BitGenerator __reduce__ noncentral_chisquare wald randn pareto weibull standard_gamma standard_t power logistic lognormal laplace gumbel name '%U' is not defined __init__ logseries zipf negative_binomial triangular uniform randint builtins cython_runtime __builtins__ %d.%d 4294967296 complex numpy dtype flatiter broadcast ndarray generic number unsignedinteger inexact complexfloating flexible character ufunc numpy.random.bit_generator SeedSequence SeedlessSequence numpy.random._common double LEGACY_POISSON_LAM_MAX uint64_t MAXSIZE _rand_uint64 _rand_uint32 _rand_uint16 _rand_uint8 _rand_bool _rand_int64 _rand_int32 _rand_int16 _rand_int8 check_constraint check_array_constraint double (double *, npy_intp) kahan_sum double_fill validate_output_shape cont disc cont_broadcast_3 discrete_broadcast_iii numpy.core._multiarray_umath _ARRAY_API _ARRAY_API not found _ARRAY_API is NULL pointer numpy/__init__.cython-30.pxd numpy.import_array init numpy.random.mtrand numpy.random.mtrand.ranf numpy.random.mtrand.sample set_bit_generator rayleigh set_state shuffle get_state numpy.random.mtrand.seed poisson noncentral_f bytes hypergeometric random_sample dirichlet standard_exponential standard_normal standard_cauchy tomaxint random_integers __setstate__ multinomial beta vonmises numpy.PyArray_MultiIterNew2 numpy.PyArray_MultiIterNew3 multivariate_normal permutation assignment deletion choice __repr__ get_bit_generator x0`0&&&gg^^^!! BB877. (''''l.(Z(((D,
This is an alias of `random_sample`. See `random_sample` for the complete
documentation.
This is an alias of `random_sample`. See `random_sample` for the complete
documentation.
Sets the singleton RandomState's bit generator
Parameters
----------
bitgen
A bit generator instance
Notes
-----
The singleton RandomState provides the random variate generators in the
``numpy.random``namespace. This function, and its counterpart get method,
provides a path to hot-swap the default MT19937 bit generator with a
user provided alternative. These function are intended to provide
a continuous path where a single underlying bit generator can be
used both with an instance of ``Generator`` and with the singleton
instance of RandomState.
See Also
--------
get_bit_generator
numpy.random.Generator
Returns the singleton RandomState's bit generator
Returns
-------
BitGenerator
The bit generator that underlies the singleton RandomState instance
Notes
-----
The singleton RandomState provides the random variate generators in the
``numpy.random`` namespace. This function, and its counterpart set method,
provides a path to hot-swap the default MT19937 bit generator with a
user provided alternative. These function are intended to provide
a continuous path where a single underlying bit generator can be
used both with an instance of ``Generator`` and with the singleton
instance of RandomState.
See Also
--------
set_bit_generator
numpy.random.Generator
seed(seed=None)
Reseed the singleton RandomState instance.
Notes
-----
This is a convenience, legacy function that exists to support
older code that uses the singleton RandomState. Best practice
is to use a dedicated ``Generator`` instance rather than
the random variate generation methods exposed directly in
the random module.
See Also
--------
numpy.random.Generator
permutation(x)
Randomly permute a sequence, or return a permuted range.
If `x` is a multi-dimensional array, it is only shuffled along its
first index.
.. note::
New code should use the
`~numpy.random.Generator.permutation`
method of a `~numpy.random.Generator` instance instead;
please see the :ref:`random-quick-start`.
Parameters
----------
x : int or array_like
If `x` is an integer, randomly permute ``np.arange(x)``.
If `x` is an array, make a copy and shuffle the elements
randomly.
Returns
-------
out : ndarray
Permuted sequence or array range.
See Also
--------
random.Generator.permutation: which should be used for new code.
Examples
--------
>>> np.random.permutation(10)
array([1, 7, 4, 3, 0, 9, 2, 5, 8, 6]) # random
>>> np.random.permutation([1, 4, 9, 12, 15])
array([15, 1, 9, 4, 12]) # random
>>> arr = np.arange(9).reshape((3, 3))
>>> np.random.permutation(arr)
array([[6, 7, 8], # random
[0, 1, 2],
[3, 4, 5]])
shuffle(x)
Modify a sequence in-place by shuffling its contents.
This function only shuffles the array along the first axis of a
multi-dimensional array. The order of sub-arrays is changed but
their contents remains the same.
.. note::
New code should use the `~numpy.random.Generator.shuffle`
method of a `~numpy.random.Generator` instance instead;
please see the :ref:`random-quick-start`.
Parameters
----------
x : ndarray or MutableSequence
The array, list or mutable sequence to be shuffled.
Returns
-------
None
See Also
--------
random.Generator.shuffle: which should be used for new code.
Examples
--------
>>> arr = np.arange(10)
>>> np.random.shuffle(arr)
>>> arr
[1 7 5 2 9 4 3 6 0 8] # random
Multi-dimensional arrays are only shuffled along the first axis:
>>> arr = np.arange(9).reshape((3, 3))
>>> np.random.shuffle(arr)
>>> arr
array([[3, 4, 5], # random
[6, 7, 8],
[0, 1, 2]])
dirichlet(alpha, size=None)
Draw samples from the Dirichlet distribution.
Draw `size` samples of dimension k from a Dirichlet distribution. A
Dirichlet-distributed random variable can be seen as a multivariate
generalization of a Beta distribution. The Dirichlet distribution
is a conjugate prior of a multinomial distribution in Bayesian
inference.
.. note::
New code should use the `~numpy.random.Generator.dirichlet`
method of a `~numpy.random.Generator` instance instead;
please see the :ref:`random-quick-start`.
Parameters
----------
alpha : sequence of floats, length k
Parameter of the distribution (length ``k`` for sample of
length ``k``).
size : int or tuple of ints, optional
Output shape. If the given shape is, e.g., ``(m, n)``, then
``m * n * k`` samples are drawn. Default is None, in which case a
vector of length ``k`` is returned.
Returns
-------
samples : ndarray,
The drawn samples, of shape ``(size, k)``.
Raises
------
ValueError
If any value in ``alpha`` is less than or equal to zero
See Also
--------
random.Generator.dirichlet: which should be used for new code.
Notes
-----
The Dirichlet distribution is a distribution over vectors
:math:`x` that fulfil the conditions :math:`x_i>0` and
:math:`\sum_{i=1}^k x_i = 1`.
The probability density function :math:`p` of a
Dirichlet-distributed random vector :math:`X` is
proportional to
.. math:: p(x) \propto \prod_{i=1}^{k}{x^{\alpha_i-1}_i},
where :math:`\alpha` is a vector containing the positive
concentration parameters.
The method uses the following property for computation: let :math:`Y`
be a random vector which has components that follow a standard gamma
distribution, then :math:`X = \frac{1}{\sum_{i=1}^k{Y_i}} Y`
is Dirichlet-distributed
References
----------
.. [1] David McKay, "Information Theory, Inference and Learning
Algorithms," chapter 23,
http://www.inference.org.uk/mackay/itila/
.. [2] Wikipedia, "Dirichlet distribution",
https://en.wikipedia.org/wiki/Dirichlet_distribution
Examples
--------
Taking an example cited in Wikipedia, this distribution can be used if
one wanted to cut strings (each of initial length 1.0) into K pieces
with different lengths, where each piece had, on average, a designated
average length, but allowing some variation in the relative sizes of
the pieces.
>>> s = np.random.dirichlet((10, 5, 3), 20).transpose()
>>> import matplotlib.pyplot as plt
>>> plt.barh(range(20), s[0])
>>> plt.barh(range(20), s[1], left=s[0], color='g')
>>> plt.barh(range(20), s[2], left=s[0]+s[1], color='r')
>>> plt.title("Lengths of Strings")
multinomial(n, pvals, size=None)
Draw samples from a multinomial distribution.
The multinomial distribution is a multivariate generalization of the
binomial distribution. Take an experiment with one of ``p``
possible outcomes. An example of such an experiment is throwing a dice,
where the outcome can be 1 through 6. Each sample drawn from the
distribution represents `n` such experiments. Its values,
``X_i = [X_0, X_1, ..., X_p]``, represent the number of times the
outcome was ``i``.
.. note::
New code should use the `~numpy.random.Generator.multinomial`
method of a `~numpy.random.Generator` instance instead;
please see the :ref:`random-quick-start`.
Parameters
----------
n : int
Number of experiments.
pvals : sequence of floats, length p
Probabilities of each of the ``p`` different outcomes. These
must sum to 1 (however, the last element is always assumed to
account for the remaining probability, as long as
``sum(pvals[:-1]) <= 1)``.
size : int or tuple of ints, optional
Output shape. If the given shape is, e.g., ``(m, n, k)``, then
``m * n * k`` samples are drawn. Default is None, in which case a
single value is returned.
Returns
-------
out : ndarray
The drawn samples, of shape *size*, if that was provided. If not,
the shape is ``(N,)``.
In other words, each entry ``out[i,j,...,:]`` is an N-dimensional
value drawn from the distribution.
See Also
--------
random.Generator.multinomial: which should be used for new code.
Examples
--------
Throw a dice 20 times:
>>> np.random.multinomial(20, [1/6.]*6, size=1)
array([[4, 1, 7, 5, 2, 1]]) # random
It landed 4 times on 1, once on 2, etc.
Now, throw the dice 20 times, and 20 times again:
>>> np.random.multinomial(20, [1/6.]*6, size=2)
array([[3, 4, 3, 3, 4, 3], # random
[2, 4, 3, 4, 0, 7]])
For the first run, we threw 3 times 1, 4 times 2, etc. For the second,
we threw 2 times 1, 4 times 2, etc.
A loaded die is more likely to land on number 6:
>>> np.random.multinomial(100, [1/7.]*5 + [2/7.])
array([11, 16, 14, 17, 16, 26]) # random
The probability inputs should be normalized. As an implementation
detail, the value of the last entry is ignored and assumed to take
up any leftover probability mass, but this should not be relied on.
A biased coin which has twice as much weight on one side as on the
other should be sampled like so:
>>> np.random.multinomial(100, [1.0 / 3, 2.0 / 3]) # RIGHT
array([38, 62]) # random
not like:
>>> np.random.multinomial(100, [1.0, 2.0]) # WRONG
Traceback (most recent call last):
ValueError: pvals < 0, pvals > 1 or pvals contains NaNs
multivariate_normal(mean, cov, size=None, check_valid='warn', tol=1e-8)
Draw random samples from a multivariate normal distribution.
The multivariate normal, multinormal or Gaussian distribution is a
generalization of the one-dimensional normal distribution to higher
dimensions. Such a distribution is specified by its mean and
covariance matrix. These parameters are analogous to the mean
(average or "center") and variance (standard deviation, or "width,"
squared) of the one-dimensional normal distribution.
.. note::
New code should use the
`~numpy.random.Generator.multivariate_normal`
method of a `~numpy.random.Generator` instance instead;
please see the :ref:`random-quick-start`.
Parameters
----------
mean : 1-D array_like, of length N
Mean of the N-dimensional distribution.
cov : 2-D array_like, of shape (N, N)
Covariance matrix of the distribution. It must be symmetric and
positive-semidefinite for proper sampling.
size : int or tuple of ints, optional
Given a shape of, for example, ``(m,n,k)``, ``m*n*k`` samples are
generated, and packed in an `m`-by-`n`-by-`k` arrangement. Because
each sample is `N`-dimensional, the output shape is ``(m,n,k,N)``.
If no shape is specified, a single (`N`-D) sample is returned.
check_valid : { 'warn', 'raise', 'ignore' }, optional
Behavior when the covariance matrix is not positive semidefinite.
tol : float, optional
Tolerance when checking the singular values in covariance matrix.
cov is cast to double before the check.
Returns
-------
out : ndarray
The drawn samples, of shape *size*, if that was provided. If not,
the shape is ``(N,)``.
In other words, each entry ``out[i,j,...,:]`` is an N-dimensional
value drawn from the distribution.
See Also
--------
random.Generator.multivariate_normal: which should be used for new code.
Notes
-----
The mean is a coordinate in N-dimensional space, which represents the
location where samples are most likely to be generated. This is
analogous to the peak of the bell curve for the one-dimensional or
univariate normal distribution.
Covariance indicates the level to which two variables vary together.
From the multivariate normal distribution, we draw N-dimensional
samples, :math:`X = [x_1, x_2, ... x_N]`. The covariance matrix
element :math:`C_{ij}` is the covariance of :math:`x_i` and :math:`x_j`.
The element :math:`C_{ii}` is the variance of :math:`x_i` (i.e. its
"spread").
Instead of specifying the full covariance matrix, popular
approximations include:
- Spherical covariance (`cov` is a multiple of the identity matrix)
- Diagonal covariance (`cov` has non-negative elements, and only on
the diagonal)
This geometrical property can be seen in two dimensions by plotting
generated data-points:
>>> mean = [0, 0]
>>> cov = [[1, 0], [0, 100]] # diagonal covariance
Diagonal covariance means that points are oriented along x or y-axis:
>>> import matplotlib.pyplot as plt
>>> x, y = np.random.multivariate_normal(mean, cov, 5000).T
>>> plt.plot(x, y, 'x')
>>> plt.axis('equal')
>>> plt.show()
Note that the covariance matrix must be positive semidefinite (a.k.a.
nonnegative-definite). Otherwise, the behavior of this method is
undefined and backwards compatibility is not guaranteed.
References
----------
.. [1] Papoulis, A., "Probability, Random Variables, and Stochastic
Processes," 3rd ed., New York: McGraw-Hill, 1991.
.. [2] Duda, R. O., Hart, P. E., and Stork, D. G., "Pattern
Classification," 2nd ed., New York: Wiley, 2001.
Examples
--------
>>> mean = (1, 2)
>>> cov = [[1, 0], [0, 1]]
>>> x = np.random.multivariate_normal(mean, cov, (3, 3))
>>> x.shape
(3, 3, 2)
Here we generate 800 samples from the bivariate normal distribution
with mean [0, 0] and covariance matrix [[6, -3], [-3, 3.5]]. The
expected variances of the first and second components of the sample
are 6 and 3.5, respectively, and the expected correlation
coefficient is -3/sqrt(6*3.5) ≈ -0.65465.
>>> cov = np.array([[6, -3], [-3, 3.5]])
>>> pts = np.random.multivariate_normal([0, 0], cov, size=800)
Check that the mean, covariance, and correlation coefficient of the
sample are close to the expected values:
>>> pts.mean(axis=0)
array([ 0.0326911 , -0.01280782]) # may vary
>>> np.cov(pts.T)
array([[ 5.96202397, -2.85602287],
[-2.85602287, 3.47613949]]) # may vary
>>> np.corrcoef(pts.T)[0, 1]
-0.6273591314603949 # may vary
We can visualize this data with a scatter plot. The orientation
of the point cloud illustrates the negative correlation of the
components of this sample.
>>> import matplotlib.pyplot as plt
>>> plt.plot(pts[:, 0], pts[:, 1], '.', alpha=0.5)
>>> plt.axis('equal')
>>> plt.grid()
>>> plt.show()
logseries(p, size=None)
Draw samples from a logarithmic series distribution.
Samples are drawn from a log series distribution with specified
shape parameter, 0 <= ``p`` < 1.
.. note::
New code should use the `~numpy.random.Generator.logseries`
method of a `~numpy.random.Generator` instance instead;
please see the :ref:`random-quick-start`.
Parameters
----------
p : float or array_like of floats
Shape parameter for the distribution. Must be in the range [0, 1).
size : int or tuple of ints, optional
Output shape. If the given shape is, e.g., ``(m, n, k)``, then
``m * n * k`` samples are drawn. If size is ``None`` (default),
a single value is returned if ``p`` is a scalar. Otherwise,
``np.array(p).size`` samples are drawn.
Returns
-------
out : ndarray or scalar
Drawn samples from the parameterized logarithmic series distribution.
See Also
--------
scipy.stats.logser : probability density function, distribution or
cumulative density function, etc.
random.Generator.logseries: which should be used for new code.
Notes
-----
The probability density for the Log Series distribution is
.. math:: P(k) = \frac{-p^k}{k \ln(1-p)},
where p = probability.
The log series distribution is frequently used to represent species
richness and occurrence, first proposed by Fisher, Corbet, and
Williams in 1943 [2]. It may also be used to model the numbers of
occupants seen in cars [3].
References
----------
.. [1] Buzas, Martin A.; Culver, Stephen J., Understanding regional
species diversity through the log series distribution of
occurrences: BIODIVERSITY RESEARCH Diversity & Distributions,
Volume 5, Number 5, September 1999 , pp. 187-195(9).
.. [2] Fisher, R.A,, A.S. Corbet, and C.B. Williams. 1943. The
relation between the number of species and the number of
individuals in a random sample of an animal population.
Journal of Animal Ecology, 12:42-58.
.. [3] D. J. Hand, F. Daly, D. Lunn, E. Ostrowski, A Handbook of Small
Data Sets, CRC Press, 1994.
.. [4] Wikipedia, "Logarithmic distribution",
https://en.wikipedia.org/wiki/Logarithmic_distribution
Examples
--------
Draw samples from the distribution:
>>> a = .6
>>> s = np.random.logseries(a, 10000)
>>> import matplotlib.pyplot as plt
>>> count, bins, ignored = plt.hist(s)
# plot against distribution
>>> def logseries(k, p):
... return -p**k/(k*np.log(1-p))
>>> plt.plot(bins, logseries(bins, a)*count.max()/
... logseries(bins, a).max(), 'r')
>>> plt.show()
hypergeometric(ngood, nbad, nsample, size=None)
Draw samples from a Hypergeometric distribution.
Samples are drawn from a hypergeometric distribution with specified
parameters, `ngood` (ways to make a good selection), `nbad` (ways to make
a bad selection), and `nsample` (number of items sampled, which is less
than or equal to the sum ``ngood + nbad``).
.. note::
New code should use the
`~numpy.random.Generator.hypergeometric`
method of a `~numpy.random.Generator` instance instead;
please see the :ref:`random-quick-start`.
Parameters
----------
ngood : int or array_like of ints
Number of ways to make a good selection. Must be nonnegative.
nbad : int or array_like of ints
Number of ways to make a bad selection. Must be nonnegative.
nsample : int or array_like of ints
Number of items sampled. Must be at least 1 and at most
``ngood + nbad``.
size : int or tuple of ints, optional
Output shape. If the given shape is, e.g., ``(m, n, k)``, then
``m * n * k`` samples are drawn. If size is ``None`` (default),
a single value is returned if `ngood`, `nbad`, and `nsample`
are all scalars. Otherwise, ``np.broadcast(ngood, nbad, nsample).size``
samples are drawn.
Returns
-------
out : ndarray or scalar
Drawn samples from the parameterized hypergeometric distribution. Each
sample is the number of good items within a randomly selected subset of
size `nsample` taken from a set of `ngood` good items and `nbad` bad items.
See Also
--------
scipy.stats.hypergeom : probability density function, distribution or
cumulative density function, etc.
random.Generator.hypergeometric: which should be used for new code.
Notes
-----
The probability density for the Hypergeometric distribution is
.. math:: P(x) = \frac{\binom{g}{x}\binom{b}{n-x}}{\binom{g+b}{n}},
where :math:`0 \le x \le n` and :math:`n-b \le x \le g`
for P(x) the probability of ``x`` good results in the drawn sample,
g = `ngood`, b = `nbad`, and n = `nsample`.
Consider an urn with black and white marbles in it, `ngood` of them
are black and `nbad` are white. If you draw `nsample` balls without
replacement, then the hypergeometric distribution describes the
distribution of black balls in the drawn sample.
Note that this distribution is very similar to the binomial
distribution, except that in this case, samples are drawn without
replacement, whereas in the Binomial case samples are drawn with
replacement (or the sample space is infinite). As the sample space
becomes large, this distribution approaches the binomial.
References
----------
.. [1] Lentner, Marvin, "Elementary Applied Statistics", Bogden
and Quigley, 1972.
.. [2] Weisstein, Eric W. "Hypergeometric Distribution." From
MathWorld--A Wolfram Web Resource.
http://mathworld.wolfram.com/HypergeometricDistribution.html
.. [3] Wikipedia, "Hypergeometric distribution",
https://en.wikipedia.org/wiki/Hypergeometric_distribution
Examples
--------
Draw samples from the distribution:
>>> ngood, nbad, nsamp = 100, 2, 10
# number of good, number of bad, and number of samples
>>> s = np.random.hypergeometric(ngood, nbad, nsamp, 1000)
>>> from matplotlib.pyplot import hist
>>> hist(s)
# note that it is very unlikely to grab both bad items
Suppose you have an urn with 15 white and 15 black marbles.
If you pull 15 marbles at random, how likely is it that
12 or more of them are one color?
>>> s = np.random.hypergeometric(15, 15, 15, 100000)
>>> sum(s>=12)/100000. + sum(s<=3)/100000.
# answer = 0.003 ... pretty unlikely!
geometric(p, size=None)
Draw samples from the geometric distribution.
Bernoulli trials are experiments with one of two outcomes:
success or failure (an example of such an experiment is flipping
a coin). The geometric distribution models the number of trials
that must be run in order to achieve success. It is therefore
supported on the positive integers, ``k = 1, 2, ...``.
The probability mass function of the geometric distribution is
.. math:: f(k) = (1 - p)^{k - 1} p
where `p` is the probability of success of an individual trial.
.. note::
New code should use the `~numpy.random.Generator.geometric`
method of a `~numpy.random.Generator` instance instead;
please see the :ref:`random-quick-start`.
Parameters
----------
p : float or array_like of floats
The probability of success of an individual trial.
size : int or tuple of ints, optional
Output shape. If the given shape is, e.g., ``(m, n, k)``, then
``m * n * k`` samples are drawn. If size is ``None`` (default),
a single value is returned if ``p`` is a scalar. Otherwise,
``np.array(p).size`` samples are drawn.
Returns
-------
out : ndarray or scalar
Drawn samples from the parameterized geometric distribution.
See Also
--------
random.Generator.geometric: which should be used for new code.
Examples
--------
Draw ten thousand values from the geometric distribution,
with the probability of an individual success equal to 0.35:
>>> z = np.random.geometric(p=0.35, size=10000)
How many trials succeeded after a single run?
>>> (z == 1).sum() / 10000.
0.34889999999999999 #random
zipf(a, size=None)
Draw samples from a Zipf distribution.
Samples are drawn from a Zipf distribution with specified parameter
`a` > 1.
The Zipf distribution (also known as the zeta distribution) is a
discrete probability distribution that satisfies Zipf's law: the
frequency of an item is inversely proportional to its rank in a
frequency table.
.. note::
New code should use the `~numpy.random.Generator.zipf`
method of a `~numpy.random.Generator` instance instead;
please see the :ref:`random-quick-start`.
Parameters
----------
a : float or array_like of floats
Distribution parameter. Must be greater than 1.
size : int or tuple of ints, optional
Output shape. If the given shape is, e.g., ``(m, n, k)``, then
``m * n * k`` samples are drawn. If size is ``None`` (default),
a single value is returned if ``a`` is a scalar. Otherwise,
``np.array(a).size`` samples are drawn.
Returns
-------
out : ndarray or scalar
Drawn samples from the parameterized Zipf distribution.
See Also
--------
scipy.stats.zipf : probability density function, distribution, or
cumulative density function, etc.
random.Generator.zipf: which should be used for new code.
Notes
-----
The probability density for the Zipf distribution is
.. math:: p(k) = \frac{k^{-a}}{\zeta(a)},
for integers :math:`k \geq 1`, where :math:`\zeta` is the Riemann Zeta
function.
It is named for the American linguist George Kingsley Zipf, who noted
that the frequency of any word in a sample of a language is inversely
proportional to its rank in the frequency table.
References
----------
.. [1] Zipf, G. K., "Selected Studies of the Principle of Relative
Frequency in Language," Cambridge, MA: Harvard Univ. Press,
1932.
Examples
--------
Draw samples from the distribution:
>>> a = 4.0
>>> n = 20000
>>> s = np.random.zipf(a, n)
Display the histogram of the samples, along with
the expected histogram based on the probability
density function:
>>> import matplotlib.pyplot as plt
>>> from scipy.special import zeta # doctest: +SKIP
`bincount` provides a fast histogram for small integers.
>>> count = np.bincount(s)
>>> k = np.arange(1, s.max() + 1)
>>> plt.bar(k, count[1:], alpha=0.5, label='sample count')
>>> plt.plot(k, n*(k**-a)/zeta(a), 'k.-', alpha=0.5,
... label='expected count') # doctest: +SKIP
>>> plt.semilogy()
>>> plt.grid(alpha=0.4)
>>> plt.legend()
>>> plt.title(f'Zipf sample, a={a}, size={n}')
>>> plt.show()
poisson(lam=1.0, size=None)
Draw samples from a Poisson distribution.
The Poisson distribution is the limit of the binomial distribution
for large N.
.. note::
New code should use the `~numpy.random.Generator.poisson`
method of a `~numpy.random.Generator` instance instead;
please see the :ref:`random-quick-start`.
Parameters
----------
lam : float or array_like of floats
Expected number of events occurring in a fixed-time interval,
must be >= 0. A sequence must be broadcastable over the requested
size.
size : int or tuple of ints, optional
Output shape. If the given shape is, e.g., ``(m, n, k)``, then
``m * n * k`` samples are drawn. If size is ``None`` (default),
a single value is returned if ``lam`` is a scalar. Otherwise,
``np.array(lam).size`` samples are drawn.
Returns
-------
out : ndarray or scalar
Drawn samples from the parameterized Poisson distribution.
See Also
--------
random.Generator.poisson: which should be used for new code.
Notes
-----
The Poisson distribution
.. math:: f(k; \lambda)=\frac{\lambda^k e^{-\lambda}}{k!}
For events with an expected separation :math:`\lambda` the Poisson
distribution :math:`f(k; \lambda)` describes the probability of
:math:`k` events occurring within the observed
interval :math:`\lambda`.
Because the output is limited to the range of the C int64 type, a
ValueError is raised when `lam` is within 10 sigma of the maximum
representable value.
References
----------
.. [1] Weisstein, Eric W. "Poisson Distribution."
From MathWorld--A Wolfram Web Resource.
http://mathworld.wolfram.com/PoissonDistribution.html
.. [2] Wikipedia, "Poisson distribution",
https://en.wikipedia.org/wiki/Poisson_distribution
Examples
--------
Draw samples from the distribution:
>>> import numpy as np
>>> s = np.random.poisson(5, 10000)
Display histogram of the sample:
>>> import matplotlib.pyplot as plt
>>> count, bins, ignored = plt.hist(s, 14, density=True)
>>> plt.show()
Draw each 100 values for lambda 100 and 500:
>>> s = np.random.poisson(lam=(100., 500.), size=(100, 2))
negative_binomial(n, p, size=None)
Draw samples from a negative binomial distribution.
Samples are drawn from a negative binomial distribution with specified
parameters, `n` successes and `p` probability of success where `n`
is > 0 and `p` is in the interval [0, 1].
.. note::
New code should use the
`~numpy.random.Generator.negative_binomial`
method of a `~numpy.random.Generator` instance instead;
please see the :ref:`random-quick-start`.
Parameters
----------
n : float or array_like of floats
Parameter of the distribution, > 0.
p : float or array_like of floats
Parameter of the distribution, >= 0 and <=1.
size : int or tuple of ints, optional
Output shape. If the given shape is, e.g., ``(m, n, k)``, then
``m * n * k`` samples are drawn. If size is ``None`` (default),
a single value is returned if ``n`` and ``p`` are both scalars.
Otherwise, ``np.broadcast(n, p).size`` samples are drawn.
Returns
-------
out : ndarray or scalar
Drawn samples from the parameterized negative binomial distribution,
where each sample is equal to N, the number of failures that
occurred before a total of n successes was reached.
See Also
--------
random.Generator.negative_binomial: which should be used for new code.
Notes
-----
The probability mass function of the negative binomial distribution is
.. math:: P(N;n,p) = \frac{\Gamma(N+n)}{N!\Gamma(n)}p^{n}(1-p)^{N},
where :math:`n` is the number of successes, :math:`p` is the
probability of success, :math:`N+n` is the number of trials, and
:math:`\Gamma` is the gamma function. When :math:`n` is an integer,
:math:`\frac{\Gamma(N+n)}{N!\Gamma(n)} = \binom{N+n-1}{N}`, which is
the more common form of this term in the pmf. The negative
binomial distribution gives the probability of N failures given n
successes, with a success on the last trial.
If one throws a die repeatedly until the third time a "1" appears,
then the probability distribution of the number of non-"1"s that
appear before the third "1" is a negative binomial distribution.
References
----------
.. [1] Weisstein, Eric W. "Negative Binomial Distribution." From
MathWorld--A Wolfram Web Resource.
http://mathworld.wolfram.com/NegativeBinomialDistribution.html
.. [2] Wikipedia, "Negative binomial distribution",
https://en.wikipedia.org/wiki/Negative_binomial_distribution
Examples
--------
Draw samples from the distribution:
A real world example. A company drills wild-cat oil
exploration wells, each with an estimated probability of
success of 0.1. What is the probability of having one success
for each successive well, that is what is the probability of a
single success after drilling 5 wells, after 6 wells, etc.?
>>> s = np.random.negative_binomial(1, 0.1, 100000)
>>> for i in range(1, 11): # doctest: +SKIP
... probability = sum(s>> n, p = 10, .5 # number of trials, probability of each trial
>>> s = np.random.binomial(n, p, 1000)
# result of flipping a coin 10 times, tested 1000 times.
A real world example. A company drills 9 wild-cat oil exploration
wells, each with an estimated probability of success of 0.1. All nine
wells fail. What is the probability of that happening?
Let's do 20,000 trials of the model, and count the number that
generate zero positive results.
>>> sum(np.random.binomial(9, 0.1, 20000) == 0)/20000.
# answer = 0.38885, or 38%.
triangular(left, mode, right, size=None)
Draw samples from the triangular distribution over the
interval ``[left, right]``.
The triangular distribution is a continuous probability
distribution with lower limit left, peak at mode, and upper
limit right. Unlike the other distributions, these parameters
directly define the shape of the pdf.
.. note::
New code should use the `~numpy.random.Generator.triangular`
method of a `~numpy.random.Generator` instance instead;
please see the :ref:`random-quick-start`.
Parameters
----------
left : float or array_like of floats
Lower limit.
mode : float or array_like of floats
The value where the peak of the distribution occurs.
The value must fulfill the condition ``left <= mode <= right``.
right : float or array_like of floats
Upper limit, must be larger than `left`.
size : int or tuple of ints, optional
Output shape. If the given shape is, e.g., ``(m, n, k)``, then
``m * n * k`` samples are drawn. If size is ``None`` (default),
a single value is returned if ``left``, ``mode``, and ``right``
are all scalars. Otherwise, ``np.broadcast(left, mode, right).size``
samples are drawn.
Returns
-------
out : ndarray or scalar
Drawn samples from the parameterized triangular distribution.
See Also
--------
random.Generator.triangular: which should be used for new code.
Notes
-----
The probability density function for the triangular distribution is
.. math:: P(x;l, m, r) = \begin{cases}
\frac{2(x-l)}{(r-l)(m-l)}& \text{for $l \leq x \leq m$},\\
\frac{2(r-x)}{(r-l)(r-m)}& \text{for $m \leq x \leq r$},\\
0& \text{otherwise}.
\end{cases}
The triangular distribution is often used in ill-defined
problems where the underlying distribution is not known, but
some knowledge of the limits and mode exists. Often it is used
in simulations.
References
----------
.. [1] Wikipedia, "Triangular distribution"
https://en.wikipedia.org/wiki/Triangular_distribution
Examples
--------
Draw values from the distribution and plot the histogram:
>>> import matplotlib.pyplot as plt
>>> h = plt.hist(np.random.triangular(-3, 0, 8, 100000), bins=200,
... density=True)
>>> plt.show()
wald(mean, scale, size=None)
Draw samples from a Wald, or inverse Gaussian, distribution.
As the scale approaches infinity, the distribution becomes more like a
Gaussian. Some references claim that the Wald is an inverse Gaussian
with mean equal to 1, but this is by no means universal.
The inverse Gaussian distribution was first studied in relationship to
Brownian motion. In 1956 M.C.K. Tweedie used the name inverse Gaussian
because there is an inverse relationship between the time to cover a
unit distance and distance covered in unit time.
.. note::
New code should use the `~numpy.random.Generator.wald`
method of a `~numpy.random.Generator` instance instead;
please see the :ref:`random-quick-start`.
Parameters
----------
mean : float or array_like of floats
Distribution mean, must be > 0.
scale : float or array_like of floats
Scale parameter, must be > 0.
size : int or tuple of ints, optional
Output shape. If the given shape is, e.g., ``(m, n, k)``, then
``m * n * k`` samples are drawn. If size is ``None`` (default),
a single value is returned if ``mean`` and ``scale`` are both scalars.
Otherwise, ``np.broadcast(mean, scale).size`` samples are drawn.
Returns
-------
out : ndarray or scalar
Drawn samples from the parameterized Wald distribution.
See Also
--------
random.Generator.wald: which should be used for new code.
Notes
-----
The probability density function for the Wald distribution is
.. math:: P(x;mean,scale) = \sqrt{\frac{scale}{2\pi x^3}}e^
\frac{-scale(x-mean)^2}{2\cdotp mean^2x}
As noted above the inverse Gaussian distribution first arise
from attempts to model Brownian motion. It is also a
competitor to the Weibull for use in reliability modeling and
modeling stock returns and interest rate processes.
References
----------
.. [1] Brighton Webs Ltd., Wald Distribution,
https://web.archive.org/web/20090423014010/http://www.brighton-webs.co.uk:80/distributions/wald.asp
.. [2] Chhikara, Raj S., and Folks, J. Leroy, "The Inverse Gaussian
Distribution: Theory : Methodology, and Applications", CRC Press,
1988.
.. [3] Wikipedia, "Inverse Gaussian distribution"
https://en.wikipedia.org/wiki/Inverse_Gaussian_distribution
Examples
--------
Draw values from the distribution and plot the histogram:
>>> import matplotlib.pyplot as plt
>>> h = plt.hist(np.random.wald(3, 2, 100000), bins=200, density=True)
>>> plt.show()
rayleigh(scale=1.0, size=None)
Draw samples from a Rayleigh distribution.
The :math:`\chi` and Weibull distributions are generalizations of the
Rayleigh.
.. note::
New code should use the `~numpy.random.Generator.rayleigh`
method of a `~numpy.random.Generator` instance instead;
please see the :ref:`random-quick-start`.
Parameters
----------
scale : float or array_like of floats, optional
Scale, also equals the mode. Must be non-negative. Default is 1.
size : int or tuple of ints, optional
Output shape. If the given shape is, e.g., ``(m, n, k)``, then
``m * n * k`` samples are drawn. If size is ``None`` (default),
a single value is returned if ``scale`` is a scalar. Otherwise,
``np.array(scale).size`` samples are drawn.
Returns
-------
out : ndarray or scalar
Drawn samples from the parameterized Rayleigh distribution.
See Also
--------
random.Generator.rayleigh: which should be used for new code.
Notes
-----
The probability density function for the Rayleigh distribution is
.. math:: P(x;scale) = \frac{x}{scale^2}e^{\frac{-x^2}{2 \cdotp scale^2}}
The Rayleigh distribution would arise, for example, if the East
and North components of the wind velocity had identical zero-mean
Gaussian distributions. Then the wind speed would have a Rayleigh
distribution.
References
----------
.. [1] Brighton Webs Ltd., "Rayleigh Distribution,"
https://web.archive.org/web/20090514091424/http://brighton-webs.co.uk:80/distributions/rayleigh.asp
.. [2] Wikipedia, "Rayleigh distribution"
https://en.wikipedia.org/wiki/Rayleigh_distribution
Examples
--------
Draw values from the distribution and plot the histogram
>>> from matplotlib.pyplot import hist
>>> values = hist(np.random.rayleigh(3, 100000), bins=200, density=True)
Wave heights tend to follow a Rayleigh distribution. If the mean wave
height is 1 meter, what fraction of waves are likely to be larger than 3
meters?
>>> meanvalue = 1
>>> modevalue = np.sqrt(2 / np.pi) * meanvalue
>>> s = np.random.rayleigh(modevalue, 1000000)
The percentage of waves larger than 3 meters is:
>>> 100.*sum(s>3)/1000000.
0.087300000000000003 # random
lognormal(mean=0.0, sigma=1.0, size=None)
Draw samples from a log-normal distribution.
Draw samples from a log-normal distribution with specified mean,
standard deviation, and array shape. Note that the mean and standard
deviation are not the values for the distribution itself, but of the
underlying normal distribution it is derived from.
.. note::
New code should use the `~numpy.random.Generator.lognormal`
method of a `~numpy.random.Generator` instance instead;
please see the :ref:`random-quick-start`.
Parameters
----------
mean : float or array_like of floats, optional
Mean value of the underlying normal distribution. Default is 0.
sigma : float or array_like of floats, optional
Standard deviation of the underlying normal distribution. Must be
non-negative. Default is 1.
size : int or tuple of ints, optional
Output shape. If the given shape is, e.g., ``(m, n, k)``, then
``m * n * k`` samples are drawn. If size is ``None`` (default),
a single value is returned if ``mean`` and ``sigma`` are both scalars.
Otherwise, ``np.broadcast(mean, sigma).size`` samples are drawn.
Returns
-------
out : ndarray or scalar
Drawn samples from the parameterized log-normal distribution.
See Also
--------
scipy.stats.lognorm : probability density function, distribution,
cumulative density function, etc.
random.Generator.lognormal: which should be used for new code.
Notes
-----
A variable `x` has a log-normal distribution if `log(x)` is normally
distributed. The probability density function for the log-normal
distribution is:
.. math:: p(x) = \frac{1}{\sigma x \sqrt{2\pi}}
e^{(-\frac{(ln(x)-\mu)^2}{2\sigma^2})}
where :math:`\mu` is the mean and :math:`\sigma` is the standard
deviation of the normally distributed logarithm of the variable.
A log-normal distribution results if a random variable is the *product*
of a large number of independent, identically-distributed variables in
the same way that a normal distribution results if the variable is the
*sum* of a large number of independent, identically-distributed
variables.
References
----------
.. [1] Limpert, E., Stahel, W. A., and Abbt, M., "Log-normal
Distributions across the Sciences: Keys and Clues,"
BioScience, Vol. 51, No. 5, May, 2001.
https://stat.ethz.ch/~stahel/lognormal/bioscience.pdf
.. [2] Reiss, R.D. and Thomas, M., "Statistical Analysis of Extreme
Values," Basel: Birkhauser Verlag, 2001, pp. 31-32.
Examples
--------
Draw samples from the distribution:
>>> mu, sigma = 3., 1. # mean and standard deviation
>>> s = np.random.lognormal(mu, sigma, 1000)
Display the histogram of the samples, along with
the probability density function:
>>> import matplotlib.pyplot as plt
>>> count, bins, ignored = plt.hist(s, 100, density=True, align='mid')
>>> x = np.linspace(min(bins), max(bins), 10000)
>>> pdf = (np.exp(-(np.log(x) - mu)**2 / (2 * sigma**2))
... / (x * sigma * np.sqrt(2 * np.pi)))
>>> plt.plot(x, pdf, linewidth=2, color='r')
>>> plt.axis('tight')
>>> plt.show()
Demonstrate that taking the products of random samples from a uniform
distribution can be fit well by a log-normal probability density
function.
>>> # Generate a thousand samples: each is the product of 100 random
>>> # values, drawn from a normal distribution.
>>> b = []
>>> for i in range(1000):
... a = 10. + np.random.standard_normal(100)
... b.append(np.prod(a))
>>> b = np.array(b) / np.min(b) # scale values to be positive
>>> count, bins, ignored = plt.hist(b, 100, density=True, align='mid')
>>> sigma = np.std(np.log(b))
>>> mu = np.mean(np.log(b))
>>> x = np.linspace(min(bins), max(bins), 10000)
>>> pdf = (np.exp(-(np.log(x) - mu)**2 / (2 * sigma**2))
... / (x * sigma * np.sqrt(2 * np.pi)))
>>> plt.plot(x, pdf, color='r', linewidth=2)
>>> plt.show()
logistic(loc=0.0, scale=1.0, size=None)
Draw samples from a logistic distribution.
Samples are drawn from a logistic distribution with specified
parameters, loc (location or mean, also median), and scale (>0).
.. note::
New code should use the `~numpy.random.Generator.logistic`
method of a `~numpy.random.Generator` instance instead;
please see the :ref:`random-quick-start`.
Parameters
----------
loc : float or array_like of floats, optional
Parameter of the distribution. Default is 0.
scale : float or array_like of floats, optional
Parameter of the distribution. Must be non-negative.
Default is 1.
size : int or tuple of ints, optional
Output shape. If the given shape is, e.g., ``(m, n, k)``, then
``m * n * k`` samples are drawn. If size is ``None`` (default),
a single value is returned if ``loc`` and ``scale`` are both scalars.
Otherwise, ``np.broadcast(loc, scale).size`` samples are drawn.
Returns
-------
out : ndarray or scalar
Drawn samples from the parameterized logistic distribution.
See Also
--------
scipy.stats.logistic : probability density function, distribution or
cumulative density function, etc.
random.Generator.logistic: which should be used for new code.
Notes
-----
The probability density for the Logistic distribution is
.. math:: P(x) = P(x) = \frac{e^{-(x-\mu)/s}}{s(1+e^{-(x-\mu)/s})^2},
where :math:`\mu` = location and :math:`s` = scale.
The Logistic distribution is used in Extreme Value problems where it
can act as a mixture of Gumbel distributions, in Epidemiology, and by
the World Chess Federation (FIDE) where it is used in the Elo ranking
system, assuming the performance of each player is a logistically
distributed random variable.
References
----------
.. [1] Reiss, R.-D. and Thomas M. (2001), "Statistical Analysis of
Extreme Values, from Insurance, Finance, Hydrology and Other
Fields," Birkhauser Verlag, Basel, pp 132-133.
.. [2] Weisstein, Eric W. "Logistic Distribution." From
MathWorld--A Wolfram Web Resource.
http://mathworld.wolfram.com/LogisticDistribution.html
.. [3] Wikipedia, "Logistic-distribution",
https://en.wikipedia.org/wiki/Logistic_distribution
Examples
--------
Draw samples from the distribution:
>>> loc, scale = 10, 1
>>> s = np.random.logistic(loc, scale, 10000)
>>> import matplotlib.pyplot as plt
>>> count, bins, ignored = plt.hist(s, bins=50)
# plot against distribution
>>> def logist(x, loc, scale):
... return np.exp((loc-x)/scale)/(scale*(1+np.exp((loc-x)/scale))**2)
>>> lgst_val = logist(bins, loc, scale)
>>> plt.plot(bins, lgst_val * count.max() / lgst_val.max())
>>> plt.show()
gumbel(loc=0.0, scale=1.0, size=None)
Draw samples from a Gumbel distribution.
Draw samples from a Gumbel distribution with specified location and
scale. For more information on the Gumbel distribution, see
Notes and References below.
.. note::
New code should use the `~numpy.random.Generator.gumbel`
method of a `~numpy.random.Generator` instance instead;
please see the :ref:`random-quick-start`.
Parameters
----------
loc : float or array_like of floats, optional
The location of the mode of the distribution. Default is 0.
scale : float or array_like of floats, optional
The scale parameter of the distribution. Default is 1. Must be non-
negative.
size : int or tuple of ints, optional
Output shape. If the given shape is, e.g., ``(m, n, k)``, then
``m * n * k`` samples are drawn. If size is ``None`` (default),
a single value is returned if ``loc`` and ``scale`` are both scalars.
Otherwise, ``np.broadcast(loc, scale).size`` samples are drawn.
Returns
-------
out : ndarray or scalar
Drawn samples from the parameterized Gumbel distribution.
See Also
--------
scipy.stats.gumbel_l
scipy.stats.gumbel_r
scipy.stats.genextreme
weibull
random.Generator.gumbel: which should be used for new code.
Notes
-----
The Gumbel (or Smallest Extreme Value (SEV) or the Smallest Extreme
Value Type I) distribution is one of a class of Generalized Extreme
Value (GEV) distributions used in modeling extreme value problems.
The Gumbel is a special case of the Extreme Value Type I distribution
for maximums from distributions with "exponential-like" tails.
The probability density for the Gumbel distribution is
.. math:: p(x) = \frac{e^{-(x - \mu)/ \beta}}{\beta} e^{ -e^{-(x - \mu)/
\beta}},
where :math:`\mu` is the mode, a location parameter, and
:math:`\beta` is the scale parameter.
The Gumbel (named for German mathematician Emil Julius Gumbel) was used
very early in the hydrology literature, for modeling the occurrence of
flood events. It is also used for modeling maximum wind speed and
rainfall rates. It is a "fat-tailed" distribution - the probability of
an event in the tail of the distribution is larger than if one used a
Gaussian, hence the surprisingly frequent occurrence of 100-year
floods. Floods were initially modeled as a Gaussian process, which
underestimated the frequency of extreme events.
It is one of a class of extreme value distributions, the Generalized
Extreme Value (GEV) distributions, which also includes the Weibull and
Frechet.
The function has a mean of :math:`\mu + 0.57721\beta` and a variance
of :math:`\frac{\pi^2}{6}\beta^2`.
References
----------
.. [1] Gumbel, E. J., "Statistics of Extremes,"
New York: Columbia University Press, 1958.
.. [2] Reiss, R.-D. and Thomas, M., "Statistical Analysis of Extreme
Values from Insurance, Finance, Hydrology and Other Fields,"
Basel: Birkhauser Verlag, 2001.
Examples
--------
Draw samples from the distribution:
>>> mu, beta = 0, 0.1 # location and scale
>>> s = np.random.gumbel(mu, beta, 1000)
Display the histogram of the samples, along with
the probability density function:
>>> import matplotlib.pyplot as plt
>>> count, bins, ignored = plt.hist(s, 30, density=True)
>>> plt.plot(bins, (1/beta)*np.exp(-(bins - mu)/beta)
... * np.exp( -np.exp( -(bins - mu) /beta) ),
... linewidth=2, color='r')
>>> plt.show()
Show how an extreme value distribution can arise from a Gaussian process
and compare to a Gaussian:
>>> means = []
>>> maxima = []
>>> for i in range(0,1000) :
... a = np.random.normal(mu, beta, 1000)
... means.append(a.mean())
... maxima.append(a.max())
>>> count, bins, ignored = plt.hist(maxima, 30, density=True)
>>> beta = np.std(maxima) * np.sqrt(6) / np.pi
>>> mu = np.mean(maxima) - 0.57721*beta
>>> plt.plot(bins, (1/beta)*np.exp(-(bins - mu)/beta)
... * np.exp(-np.exp(-(bins - mu)/beta)),
... linewidth=2, color='r')
>>> plt.plot(bins, 1/(beta * np.sqrt(2 * np.pi))
... * np.exp(-(bins - mu)**2 / (2 * beta**2)),
... linewidth=2, color='g')
>>> plt.show()
laplace(loc=0.0, scale=1.0, size=None)
Draw samples from the Laplace or double exponential distribution with
specified location (or mean) and scale (decay).
The Laplace distribution is similar to the Gaussian/normal distribution,
but is sharper at the peak and has fatter tails. It represents the
difference between two independent, identically distributed exponential
random variables.
.. note::
New code should use the `~numpy.random.Generator.laplace`
method of a `~numpy.random.Generator` instance instead;
please see the :ref:`random-quick-start`.
Parameters
----------
loc : float or array_like of floats, optional
The position, :math:`\mu`, of the distribution peak. Default is 0.
scale : float or array_like of floats, optional
:math:`\lambda`, the exponential decay. Default is 1. Must be non-
negative.
size : int or tuple of ints, optional
Output shape. If the given shape is, e.g., ``(m, n, k)``, then
``m * n * k`` samples are drawn. If size is ``None`` (default),
a single value is returned if ``loc`` and ``scale`` are both scalars.
Otherwise, ``np.broadcast(loc, scale).size`` samples are drawn.
Returns
-------
out : ndarray or scalar
Drawn samples from the parameterized Laplace distribution.
See Also
--------
random.Generator.laplace: which should be used for new code.
Notes
-----
It has the probability density function
.. math:: f(x; \mu, \lambda) = \frac{1}{2\lambda}
\exp\left(-\frac{|x - \mu|}{\lambda}\right).
The first law of Laplace, from 1774, states that the frequency
of an error can be expressed as an exponential function of the
absolute magnitude of the error, which leads to the Laplace
distribution. For many problems in economics and health
sciences, this distribution seems to model the data better
than the standard Gaussian distribution.
References
----------
.. [1] Abramowitz, M. and Stegun, I. A. (Eds.). "Handbook of
Mathematical Functions with Formulas, Graphs, and Mathematical
Tables, 9th printing," New York: Dover, 1972.
.. [2] Kotz, Samuel, et. al. "The Laplace Distribution and
Generalizations, " Birkhauser, 2001.
.. [3] Weisstein, Eric W. "Laplace Distribution."
From MathWorld--A Wolfram Web Resource.
http://mathworld.wolfram.com/LaplaceDistribution.html
.. [4] Wikipedia, "Laplace distribution",
https://en.wikipedia.org/wiki/Laplace_distribution
Examples
--------
Draw samples from the distribution
>>> loc, scale = 0., 1.
>>> s = np.random.laplace(loc, scale, 1000)
Display the histogram of the samples, along with
the probability density function:
>>> import matplotlib.pyplot as plt
>>> count, bins, ignored = plt.hist(s, 30, density=True)
>>> x = np.arange(-8., 8., .01)
>>> pdf = np.exp(-abs(x-loc)/scale)/(2.*scale)
>>> plt.plot(x, pdf)
Plot Gaussian for comparison:
>>> g = (1/(scale * np.sqrt(2 * np.pi)) *
... np.exp(-(x - loc)**2 / (2 * scale**2)))
>>> plt.plot(x,g)
power(a, size=None)
Draws samples in [0, 1] from a power distribution with positive
exponent a - 1.
Also known as the power function distribution.
.. note::
New code should use the `~numpy.random.Generator.power`
method of a `~numpy.random.Generator` instance instead;
please see the :ref:`random-quick-start`.
Parameters
----------
a : float or array_like of floats
Parameter of the distribution. Must be non-negative.
size : int or tuple of ints, optional
Output shape. If the given shape is, e.g., ``(m, n, k)``, then
``m * n * k`` samples are drawn. If size is ``None`` (default),
a single value is returned if ``a`` is a scalar. Otherwise,
``np.array(a).size`` samples are drawn.
Returns
-------
out : ndarray or scalar
Drawn samples from the parameterized power distribution.
Raises
------
ValueError
If a <= 0.
See Also
--------
random.Generator.power: which should be used for new code.
Notes
-----
The probability density function is
.. math:: P(x; a) = ax^{a-1}, 0 \le x \le 1, a>0.
The power function distribution is just the inverse of the Pareto
distribution. It may also be seen as a special case of the Beta
distribution.
It is used, for example, in modeling the over-reporting of insurance
claims.
References
----------
.. [1] Christian Kleiber, Samuel Kotz, "Statistical size distributions
in economics and actuarial sciences", Wiley, 2003.
.. [2] Heckert, N. A. and Filliben, James J. "NIST Handbook 148:
Dataplot Reference Manual, Volume 2: Let Subcommands and Library
Functions", National Institute of Standards and Technology
Handbook Series, June 2003.
https://www.itl.nist.gov/div898/software/dataplot/refman2/auxillar/powpdf.pdf
Examples
--------
Draw samples from the distribution:
>>> a = 5. # shape
>>> samples = 1000
>>> s = np.random.power(a, samples)
Display the histogram of the samples, along with
the probability density function:
>>> import matplotlib.pyplot as plt
>>> count, bins, ignored = plt.hist(s, bins=30)
>>> x = np.linspace(0, 1, 100)
>>> y = a*x**(a-1.)
>>> normed_y = samples*np.diff(bins)[0]*y
>>> plt.plot(x, normed_y)
>>> plt.show()
Compare the power function distribution to the inverse of the Pareto.
>>> from scipy import stats # doctest: +SKIP
>>> rvs = np.random.power(5, 1000000)
>>> rvsp = np.random.pareto(5, 1000000)
>>> xx = np.linspace(0,1,100)
>>> powpdf = stats.powerlaw.pdf(xx,5) # doctest: +SKIP
>>> plt.figure()
>>> plt.hist(rvs, bins=50, density=True)
>>> plt.plot(xx,powpdf,'r-') # doctest: +SKIP
>>> plt.title('np.random.power(5)')
>>> plt.figure()
>>> plt.hist(1./(1.+rvsp), bins=50, density=True)
>>> plt.plot(xx,powpdf,'r-') # doctest: +SKIP
>>> plt.title('inverse of 1 + np.random.pareto(5)')
>>> plt.figure()
>>> plt.hist(1./(1.+rvsp), bins=50, density=True)
>>> plt.plot(xx,powpdf,'r-') # doctest: +SKIP
>>> plt.title('inverse of stats.pareto(5)')
weibull(a, size=None)
Draw samples from a Weibull distribution.
Draw samples from a 1-parameter Weibull distribution with the given
shape parameter `a`.
.. math:: X = (-ln(U))^{1/a}
Here, U is drawn from the uniform distribution over (0,1].
The more common 2-parameter Weibull, including a scale parameter
:math:`\lambda` is just :math:`X = \lambda(-ln(U))^{1/a}`.
.. note::
New code should use the `~numpy.random.Generator.weibull`
method of a `~numpy.random.Generator` instance instead;
please see the :ref:`random-quick-start`.
Parameters
----------
a : float or array_like of floats
Shape parameter of the distribution. Must be nonnegative.
size : int or tuple of ints, optional
Output shape. If the given shape is, e.g., ``(m, n, k)``, then
``m * n * k`` samples are drawn. If size is ``None`` (default),
a single value is returned if ``a`` is a scalar. Otherwise,
``np.array(a).size`` samples are drawn.
Returns
-------
out : ndarray or scalar
Drawn samples from the parameterized Weibull distribution.
See Also
--------
scipy.stats.weibull_max
scipy.stats.weibull_min
scipy.stats.genextreme
gumbel
random.Generator.weibull: which should be used for new code.
Notes
-----
The Weibull (or Type III asymptotic extreme value distribution
for smallest values, SEV Type III, or Rosin-Rammler
distribution) is one of a class of Generalized Extreme Value
(GEV) distributions used in modeling extreme value problems.
This class includes the Gumbel and Frechet distributions.
The probability density for the Weibull distribution is
.. math:: p(x) = \frac{a}
{\lambda}(\frac{x}{\lambda})^{a-1}e^{-(x/\lambda)^a},
where :math:`a` is the shape and :math:`\lambda` the scale.
The function has its peak (the mode) at
:math:`\lambda(\frac{a-1}{a})^{1/a}`.
When ``a = 1``, the Weibull distribution reduces to the exponential
distribution.
References
----------
.. [1] Waloddi Weibull, Royal Technical University, Stockholm,
1939 "A Statistical Theory Of The Strength Of Materials",
Ingeniorsvetenskapsakademiens Handlingar Nr 151, 1939,
Generalstabens Litografiska Anstalts Forlag, Stockholm.
.. [2] Waloddi Weibull, "A Statistical Distribution Function of
Wide Applicability", Journal Of Applied Mechanics ASME Paper
1951.
.. [3] Wikipedia, "Weibull distribution",
https://en.wikipedia.org/wiki/Weibull_distribution
Examples
--------
Draw samples from the distribution:
>>> a = 5. # shape
>>> s = np.random.weibull(a, 1000)
Display the histogram of the samples, along with
the probability density function:
>>> import matplotlib.pyplot as plt
>>> x = np.arange(1,100.)/50.
>>> def weib(x,n,a):
... return (a / n) * (x / n)**(a - 1) * np.exp(-(x / n)**a)
>>> count, bins, ignored = plt.hist(np.random.weibull(5.,1000))
>>> x = np.arange(1,100.)/50.
>>> scale = count.max()/weib(x, 1., 5.).max()
>>> plt.plot(x, weib(x, 1., 5.)*scale)
>>> plt.show()
pareto(a, size=None)
Draw samples from a Pareto II or Lomax distribution with
specified shape.
The Lomax or Pareto II distribution is a shifted Pareto
distribution. The classical Pareto distribution can be
obtained from the Lomax distribution by adding 1 and
multiplying by the scale parameter ``m`` (see Notes). The
smallest value of the Lomax distribution is zero while for the
classical Pareto distribution it is ``mu``, where the standard
Pareto distribution has location ``mu = 1``. Lomax can also
be considered as a simplified version of the Generalized
Pareto distribution (available in SciPy), with the scale set
to one and the location set to zero.
The Pareto distribution must be greater than zero, and is
unbounded above. It is also known as the "80-20 rule". In
this distribution, 80 percent of the weights are in the lowest
20 percent of the range, while the other 20 percent fill the
remaining 80 percent of the range.
.. note::
New code should use the `~numpy.random.Generator.pareto`
method of a `~numpy.random.Generator` instance instead;
please see the :ref:`random-quick-start`.
Parameters
----------
a : float or array_like of floats
Shape of the distribution. Must be positive.
size : int or tuple of ints, optional
Output shape. If the given shape is, e.g., ``(m, n, k)``, then
``m * n * k`` samples are drawn. If size is ``None`` (default),
a single value is returned if ``a`` is a scalar. Otherwise,
``np.array(a).size`` samples are drawn.
Returns
-------
out : ndarray or scalar
Drawn samples from the parameterized Pareto distribution.
See Also
--------
scipy.stats.lomax : probability density function, distribution or
cumulative density function, etc.
scipy.stats.genpareto : probability density function, distribution or
cumulative density function, etc.
random.Generator.pareto: which should be used for new code.
Notes
-----
The probability density for the Pareto distribution is
.. math:: p(x) = \frac{am^a}{x^{a+1}}
where :math:`a` is the shape and :math:`m` the scale.
The Pareto distribution, named after the Italian economist
Vilfredo Pareto, is a power law probability distribution
useful in many real world problems. Outside the field of
economics it is generally referred to as the Bradford
distribution. Pareto developed the distribution to describe
the distribution of wealth in an economy. It has also found
use in insurance, web page access statistics, oil field sizes,
and many other problems, including the download frequency for
projects in Sourceforge [1]_. It is one of the so-called
"fat-tailed" distributions.
References
----------
.. [1] Francis Hunt and Paul Johnson, On the Pareto Distribution of
Sourceforge projects.
.. [2] Pareto, V. (1896). Course of Political Economy. Lausanne.
.. [3] Reiss, R.D., Thomas, M.(2001), Statistical Analysis of Extreme
Values, Birkhauser Verlag, Basel, pp 23-30.
.. [4] Wikipedia, "Pareto distribution",
https://en.wikipedia.org/wiki/Pareto_distribution
Examples
--------
Draw samples from the distribution:
>>> a, m = 3., 2. # shape and mode
>>> s = (np.random.pareto(a, 1000) + 1) * m
Display the histogram of the samples, along with the probability
density function:
>>> import matplotlib.pyplot as plt
>>> count, bins, _ = plt.hist(s, 100, density=True)
>>> fit = a*m**a / bins**(a+1)
>>> plt.plot(bins, max(count)*fit/max(fit), linewidth=2, color='r')
>>> plt.show()
vonmises(mu, kappa, size=None)
Draw samples from a von Mises distribution.
Samples are drawn from a von Mises distribution with specified mode
(mu) and dispersion (kappa), on the interval [-pi, pi].
The von Mises distribution (also known as the circular normal
distribution) is a continuous probability distribution on the unit
circle. It may be thought of as the circular analogue of the normal
distribution.
.. note::
New code should use the `~numpy.random.Generator.vonmises`
method of a `~numpy.random.Generator` instance instead;
please see the :ref:`random-quick-start`.
Parameters
----------
mu : float or array_like of floats
Mode ("center") of the distribution.
kappa : float or array_like of floats
Dispersion of the distribution, has to be >=0.
size : int or tuple of ints, optional
Output shape. If the given shape is, e.g., ``(m, n, k)``, then
``m * n * k`` samples are drawn. If size is ``None`` (default),
a single value is returned if ``mu`` and ``kappa`` are both scalars.
Otherwise, ``np.broadcast(mu, kappa).size`` samples are drawn.
Returns
-------
out : ndarray or scalar
Drawn samples from the parameterized von Mises distribution.
See Also
--------
scipy.stats.vonmises : probability density function, distribution, or
cumulative density function, etc.
random.Generator.vonmises: which should be used for new code.
Notes
-----
The probability density for the von Mises distribution is
.. math:: p(x) = \frac{e^{\kappa cos(x-\mu)}}{2\pi I_0(\kappa)},
where :math:`\mu` is the mode and :math:`\kappa` the dispersion,
and :math:`I_0(\kappa)` is the modified Bessel function of order 0.
The von Mises is named for Richard Edler von Mises, who was born in
Austria-Hungary, in what is now the Ukraine. He fled to the United
States in 1939 and became a professor at Harvard. He worked in
probability theory, aerodynamics, fluid mechanics, and philosophy of
science.
References
----------
.. [1] Abramowitz, M. and Stegun, I. A. (Eds.). "Handbook of
Mathematical Functions with Formulas, Graphs, and Mathematical
Tables, 9th printing," New York: Dover, 1972.
.. [2] von Mises, R., "Mathematical Theory of Probability
and Statistics", New York: Academic Press, 1964.
Examples
--------
Draw samples from the distribution:
>>> mu, kappa = 0.0, 4.0 # mean and dispersion
>>> s = np.random.vonmises(mu, kappa, 1000)
Display the histogram of the samples, along with
the probability density function:
>>> import matplotlib.pyplot as plt
>>> from scipy.special import i0 # doctest: +SKIP
>>> plt.hist(s, 50, density=True)
>>> x = np.linspace(-np.pi, np.pi, num=51)
>>> y = np.exp(kappa*np.cos(x-mu))/(2*np.pi*i0(kappa)) # doctest: +SKIP
>>> plt.plot(x, y, linewidth=2, color='r') # doctest: +SKIP
>>> plt.show()
standard_t(df, size=None)
Draw samples from a standard Student's t distribution with `df` degrees
of freedom.
A special case of the hyperbolic distribution. As `df` gets
large, the result resembles that of the standard normal
distribution (`standard_normal`).
.. note::
New code should use the `~numpy.random.Generator.standard_t`
method of a `~numpy.random.Generator` instance instead;
please see the :ref:`random-quick-start`.
Parameters
----------
df : float or array_like of floats
Degrees of freedom, must be > 0.
size : int or tuple of ints, optional
Output shape. If the given shape is, e.g., ``(m, n, k)``, then
``m * n * k`` samples are drawn. If size is ``None`` (default),
a single value is returned if ``df`` is a scalar. Otherwise,
``np.array(df).size`` samples are drawn.
Returns
-------
out : ndarray or scalar
Drawn samples from the parameterized standard Student's t distribution.
See Also
--------
random.Generator.standard_t: which should be used for new code.
Notes
-----
The probability density function for the t distribution is
.. math:: P(x, df) = \frac{\Gamma(\frac{df+1}{2})}{\sqrt{\pi df}
\Gamma(\frac{df}{2})}\Bigl( 1+\frac{x^2}{df} \Bigr)^{-(df+1)/2}
The t test is based on an assumption that the data come from a
Normal distribution. The t test provides a way to test whether
the sample mean (that is the mean calculated from the data) is
a good estimate of the true mean.
The derivation of the t-distribution was first published in
1908 by William Gosset while working for the Guinness Brewery
in Dublin. Due to proprietary issues, he had to publish under
a pseudonym, and so he used the name Student.
References
----------
.. [1] Dalgaard, Peter, "Introductory Statistics With R",
Springer, 2002.
.. [2] Wikipedia, "Student's t-distribution"
https://en.wikipedia.org/wiki/Student's_t-distribution
Examples
--------
From Dalgaard page 83 [1]_, suppose the daily energy intake for 11
women in kilojoules (kJ) is:
>>> intake = np.array([5260., 5470, 5640, 6180, 6390, 6515, 6805, 7515, \
... 7515, 8230, 8770])
Does their energy intake deviate systematically from the recommended
value of 7725 kJ? Our null hypothesis will be the absence of deviation,
and the alternate hypothesis will be the presence of an effect that could be
either positive or negative, hence making our test 2-tailed.
Because we are estimating the mean and we have N=11 values in our sample,
we have N-1=10 degrees of freedom. We set our significance level to 95% and
compute the t statistic using the empirical mean and empirical standard
deviation of our intake. We use a ddof of 1 to base the computation of our
empirical standard deviation on an unbiased estimate of the variance (note:
the final estimate is not unbiased due to the concave nature of the square
root).
>>> np.mean(intake)
6753.636363636364
>>> intake.std(ddof=1)
1142.1232221373727
>>> t = (np.mean(intake)-7725)/(intake.std(ddof=1)/np.sqrt(len(intake)))
>>> t
-2.8207540608310198
We draw 1000000 samples from Student's t distribution with the adequate
degrees of freedom.
>>> import matplotlib.pyplot as plt
>>> s = np.random.standard_t(10, size=1000000)
>>> h = plt.hist(s, bins=100, density=True)
Does our t statistic land in one of the two critical regions found at
both tails of the distribution?
>>> np.sum(np.abs(t) < np.abs(s)) / float(len(s))
0.018318 #random < 0.05, statistic is in critical region
The probability value for this 2-tailed test is about 1.83%, which is
lower than the 5% pre-determined significance threshold.
Therefore, the probability of observing values as extreme as our intake
conditionally on the null hypothesis being true is too low, and we reject
the null hypothesis of no deviation.
standard_cauchy(size=None)
Draw samples from a standard Cauchy distribution with mode = 0.
Also known as the Lorentz distribution.
.. note::
New code should use the
`~numpy.random.Generator.standard_cauchy`
method of a `~numpy.random.Generator` instance instead;
please see the :ref:`random-quick-start`.
Parameters
----------
size : int or tuple of ints, optional
Output shape. If the given shape is, e.g., ``(m, n, k)``, then
``m * n * k`` samples are drawn. Default is None, in which case a
single value is returned.
Returns
-------
samples : ndarray or scalar
The drawn samples.
See Also
--------
random.Generator.standard_cauchy: which should be used for new code.
Notes
-----
The probability density function for the full Cauchy distribution is
.. math:: P(x; x_0, \gamma) = \frac{1}{\pi \gamma \bigl[ 1+
(\frac{x-x_0}{\gamma})^2 \bigr] }
and the Standard Cauchy distribution just sets :math:`x_0=0` and
:math:`\gamma=1`
The Cauchy distribution arises in the solution to the driven harmonic
oscillator problem, and also describes spectral line broadening. It
also describes the distribution of values at which a line tilted at
a random angle will cut the x axis.
When studying hypothesis tests that assume normality, seeing how the
tests perform on data from a Cauchy distribution is a good indicator of
their sensitivity to a heavy-tailed distribution, since the Cauchy looks
very much like a Gaussian distribution, but with heavier tails.
References
----------
.. [1] NIST/SEMATECH e-Handbook of Statistical Methods, "Cauchy
Distribution",
https://www.itl.nist.gov/div898/handbook/eda/section3/eda3663.htm
.. [2] Weisstein, Eric W. "Cauchy Distribution." From MathWorld--A
Wolfram Web Resource.
http://mathworld.wolfram.com/CauchyDistribution.html
.. [3] Wikipedia, "Cauchy distribution"
https://en.wikipedia.org/wiki/Cauchy_distribution
Examples
--------
Draw samples and plot the distribution:
>>> import matplotlib.pyplot as plt
>>> s = np.random.standard_cauchy(1000000)
>>> s = s[(s>-25) & (s<25)] # truncate distribution so it plots well
>>> plt.hist(s, bins=100)
>>> plt.show()
noncentral_chisquare(df, nonc, size=None)
Draw samples from a noncentral chi-square distribution.
The noncentral :math:`\chi^2` distribution is a generalization of
the :math:`\chi^2` distribution.
.. note::
New code should use the
`~numpy.random.Generator.noncentral_chisquare`
method of a `~numpy.random.Generator` instance instead;
please see the :ref:`random-quick-start`.
Parameters
----------
df : float or array_like of floats
Degrees of freedom, must be > 0.
.. versionchanged:: 1.10.0
Earlier NumPy versions required dfnum > 1.
nonc : float or array_like of floats
Non-centrality, must be non-negative.
size : int or tuple of ints, optional
Output shape. If the given shape is, e.g., ``(m, n, k)``, then
``m * n * k`` samples are drawn. If size is ``None`` (default),
a single value is returned if ``df`` and ``nonc`` are both scalars.
Otherwise, ``np.broadcast(df, nonc).size`` samples are drawn.
Returns
-------
out : ndarray or scalar
Drawn samples from the parameterized noncentral chi-square distribution.
See Also
--------
random.Generator.noncentral_chisquare: which should be used for new code.
Notes
-----
The probability density function for the noncentral Chi-square
distribution is
.. math:: P(x;df,nonc) = \sum^{\infty}_{i=0}
\frac{e^{-nonc/2}(nonc/2)^{i}}{i!}
P_{Y_{df+2i}}(x),
where :math:`Y_{q}` is the Chi-square with q degrees of freedom.
References
----------
.. [1] Wikipedia, "Noncentral chi-squared distribution"
https://en.wikipedia.org/wiki/Noncentral_chi-squared_distribution
Examples
--------
Draw values from the distribution and plot the histogram
>>> import matplotlib.pyplot as plt
>>> values = plt.hist(np.random.noncentral_chisquare(3, 20, 100000),
... bins=200, density=True)
>>> plt.show()
Draw values from a noncentral chisquare with very small noncentrality,
and compare to a chisquare.
>>> plt.figure()
>>> values = plt.hist(np.random.noncentral_chisquare(3, .0000001, 100000),
... bins=np.arange(0., 25, .1), density=True)
>>> values2 = plt.hist(np.random.chisquare(3, 100000),
... bins=np.arange(0., 25, .1), density=True)
>>> plt.plot(values[1][0:-1], values[0]-values2[0], 'ob')
>>> plt.show()
Demonstrate how large values of non-centrality lead to a more symmetric
distribution.
>>> plt.figure()
>>> values = plt.hist(np.random.noncentral_chisquare(3, 20, 100000),
... bins=200, density=True)
>>> plt.show()
chisquare(df, size=None)
Draw samples from a chi-square distribution.
When `df` independent random variables, each with standard normal
distributions (mean 0, variance 1), are squared and summed, the
resulting distribution is chi-square (see Notes). This distribution
is often used in hypothesis testing.
.. note::
New code should use the `~numpy.random.Generator.chisquare`
method of a `~numpy.random.Generator` instance instead;
please see the :ref:`random-quick-start`.
Parameters
----------
df : float or array_like of floats
Number of degrees of freedom, must be > 0.
size : int or tuple of ints, optional
Output shape. If the given shape is, e.g., ``(m, n, k)``, then
``m * n * k`` samples are drawn. If size is ``None`` (default),
a single value is returned if ``df`` is a scalar. Otherwise,
``np.array(df).size`` samples are drawn.
Returns
-------
out : ndarray or scalar
Drawn samples from the parameterized chi-square distribution.
Raises
------
ValueError
When `df` <= 0 or when an inappropriate `size` (e.g. ``size=-1``)
is given.
See Also
--------
random.Generator.chisquare: which should be used for new code.
Notes
-----
The variable obtained by summing the squares of `df` independent,
standard normally distributed random variables:
.. math:: Q = \sum_{i=0}^{\mathtt{df}} X^2_i
is chi-square distributed, denoted
.. math:: Q \sim \chi^2_k.
The probability density function of the chi-squared distribution is
.. math:: p(x) = \frac{(1/2)^{k/2}}{\Gamma(k/2)}
x^{k/2 - 1} e^{-x/2},
where :math:`\Gamma` is the gamma function,
.. math:: \Gamma(x) = \int_0^{-\infty} t^{x - 1} e^{-t} dt.
References
----------
.. [1] NIST "Engineering Statistics Handbook"
https://www.itl.nist.gov/div898/handbook/eda/section3/eda3666.htm
Examples
--------
>>> np.random.chisquare(2,4)
array([ 1.89920014, 9.00867716, 3.13710533, 5.62318272]) # random
noncentral_f(dfnum, dfden, nonc, size=None)
Draw samples from the noncentral F distribution.
Samples are drawn from an F distribution with specified parameters,
`dfnum` (degrees of freedom in numerator) and `dfden` (degrees of
freedom in denominator), where both parameters > 1.
`nonc` is the non-centrality parameter.
.. note::
New code should use the
`~numpy.random.Generator.noncentral_f`
method of a `~numpy.random.Generator` instance instead;
please see the :ref:`random-quick-start`.
Parameters
----------
dfnum : float or array_like of floats
Numerator degrees of freedom, must be > 0.
.. versionchanged:: 1.14.0
Earlier NumPy versions required dfnum > 1.
dfden : float or array_like of floats
Denominator degrees of freedom, must be > 0.
nonc : float or array_like of floats
Non-centrality parameter, the sum of the squares of the numerator
means, must be >= 0.
size : int or tuple of ints, optional
Output shape. If the given shape is, e.g., ``(m, n, k)``, then
``m * n * k`` samples are drawn. If size is ``None`` (default),
a single value is returned if ``dfnum``, ``dfden``, and ``nonc``
are all scalars. Otherwise, ``np.broadcast(dfnum, dfden, nonc).size``
samples are drawn.
Returns
-------
out : ndarray or scalar
Drawn samples from the parameterized noncentral Fisher distribution.
See Also
--------
random.Generator.noncentral_f: which should be used for new code.
Notes
-----
When calculating the power of an experiment (power = probability of
rejecting the null hypothesis when a specific alternative is true) the
non-central F statistic becomes important. When the null hypothesis is
true, the F statistic follows a central F distribution. When the null
hypothesis is not true, then it follows a non-central F statistic.
References
----------
.. [1] Weisstein, Eric W. "Noncentral F-Distribution."
From MathWorld--A Wolfram Web Resource.
http://mathworld.wolfram.com/NoncentralF-Distribution.html
.. [2] Wikipedia, "Noncentral F-distribution",
https://en.wikipedia.org/wiki/Noncentral_F-distribution
Examples
--------
In a study, testing for a specific alternative to the null hypothesis
requires use of the Noncentral F distribution. We need to calculate the
area in the tail of the distribution that exceeds the value of the F
distribution for the null hypothesis. We'll plot the two probability
distributions for comparison.
>>> dfnum = 3 # between group deg of freedom
>>> dfden = 20 # within groups degrees of freedom
>>> nonc = 3.0
>>> nc_vals = np.random.noncentral_f(dfnum, dfden, nonc, 1000000)
>>> NF = np.histogram(nc_vals, bins=50, density=True)
>>> c_vals = np.random.f(dfnum, dfden, 1000000)
>>> F = np.histogram(c_vals, bins=50, density=True)
>>> import matplotlib.pyplot as plt
>>> plt.plot(F[1][1:], F[0])
>>> plt.plot(NF[1][1:], NF[0])
>>> plt.show()
f(dfnum, dfden, size=None)
Draw samples from an F distribution.
Samples are drawn from an F distribution with specified parameters,
`dfnum` (degrees of freedom in numerator) and `dfden` (degrees of
freedom in denominator), where both parameters must be greater than
zero.
The random variate of the F distribution (also known as the
Fisher distribution) is a continuous probability distribution
that arises in ANOVA tests, and is the ratio of two chi-square
variates.
.. note::
New code should use the `~numpy.random.Generator.f`
method of a `~numpy.random.Generator` instance instead;
please see the :ref:`random-quick-start`.
Parameters
----------
dfnum : float or array_like of floats
Degrees of freedom in numerator, must be > 0.
dfden : float or array_like of float
Degrees of freedom in denominator, must be > 0.
size : int or tuple of ints, optional
Output shape. If the given shape is, e.g., ``(m, n, k)``, then
``m * n * k`` samples are drawn. If size is ``None`` (default),
a single value is returned if ``dfnum`` and ``dfden`` are both scalars.
Otherwise, ``np.broadcast(dfnum, dfden).size`` samples are drawn.
Returns
-------
out : ndarray or scalar
Drawn samples from the parameterized Fisher distribution.
See Also
--------
scipy.stats.f : probability density function, distribution or
cumulative density function, etc.
random.Generator.f: which should be used for new code.
Notes
-----
The F statistic is used to compare in-group variances to between-group
variances. Calculating the distribution depends on the sampling, and
so it is a function of the respective degrees of freedom in the
problem. The variable `dfnum` is the number of samples minus one, the
between-groups degrees of freedom, while `dfden` is the within-groups
degrees of freedom, the sum of the number of samples in each group
minus the number of groups.
References
----------
.. [1] Glantz, Stanton A. "Primer of Biostatistics.", McGraw-Hill,
Fifth Edition, 2002.
.. [2] Wikipedia, "F-distribution",
https://en.wikipedia.org/wiki/F-distribution
Examples
--------
An example from Glantz[1], pp 47-40:
Two groups, children of diabetics (25 people) and children from people
without diabetes (25 controls). Fasting blood glucose was measured,
case group had a mean value of 86.1, controls had a mean value of
82.2. Standard deviations were 2.09 and 2.49 respectively. Are these
data consistent with the null hypothesis that the parents diabetic
status does not affect their children's blood glucose levels?
Calculating the F statistic from the data gives a value of 36.01.
Draw samples from the distribution:
>>> dfnum = 1. # between group degrees of freedom
>>> dfden = 48. # within groups degrees of freedom
>>> s = np.random.f(dfnum, dfden, 1000)
The lower bound for the top 1% of the samples is :
>>> np.sort(s)[-10]
7.61988120985 # random
So there is about a 1% chance that the F statistic will exceed 7.62,
the measured value is 36, so the null hypothesis is rejected at the 1%
level.
gamma(shape, scale=1.0, size=None)
Draw samples from a Gamma distribution.
Samples are drawn from a Gamma distribution with specified parameters,
`shape` (sometimes designated "k") and `scale` (sometimes designated
"theta"), where both parameters are > 0.
.. note::
New code should use the `~numpy.random.Generator.gamma`
method of a `~numpy.random.Generator` instance instead;
please see the :ref:`random-quick-start`.
Parameters
----------
shape : float or array_like of floats
The shape of the gamma distribution. Must be non-negative.
scale : float or array_like of floats, optional
The scale of the gamma distribution. Must be non-negative.
Default is equal to 1.
size : int or tuple of ints, optional
Output shape. If the given shape is, e.g., ``(m, n, k)``, then
``m * n * k`` samples are drawn. If size is ``None`` (default),
a single value is returned if ``shape`` and ``scale`` are both scalars.
Otherwise, ``np.broadcast(shape, scale).size`` samples are drawn.
Returns
-------
out : ndarray or scalar
Drawn samples from the parameterized gamma distribution.
See Also
--------
scipy.stats.gamma : probability density function, distribution or
cumulative density function, etc.
random.Generator.gamma: which should be used for new code.
Notes
-----
The probability density for the Gamma distribution is
.. math:: p(x) = x^{k-1}\frac{e^{-x/\theta}}{\theta^k\Gamma(k)},
where :math:`k` is the shape and :math:`\theta` the scale,
and :math:`\Gamma` is the Gamma function.
The Gamma distribution is often used to model the times to failure of
electronic components, and arises naturally in processes for which the
waiting times between Poisson distributed events are relevant.
References
----------
.. [1] Weisstein, Eric W. "Gamma Distribution." From MathWorld--A
Wolfram Web Resource.
http://mathworld.wolfram.com/GammaDistribution.html
.. [2] Wikipedia, "Gamma distribution",
https://en.wikipedia.org/wiki/Gamma_distribution
Examples
--------
Draw samples from the distribution:
>>> shape, scale = 2., 2. # mean=4, std=2*sqrt(2)
>>> s = np.random.gamma(shape, scale, 1000)
Display the histogram of the samples, along with
the probability density function:
>>> import matplotlib.pyplot as plt
>>> import scipy.special as sps # doctest: +SKIP
>>> count, bins, ignored = plt.hist(s, 50, density=True)
>>> y = bins**(shape-1)*(np.exp(-bins/scale) / # doctest: +SKIP
... (sps.gamma(shape)*scale**shape))
>>> plt.plot(bins, y, linewidth=2, color='r') # doctest: +SKIP
>>> plt.show()
standard_gamma(shape, size=None)
Draw samples from a standard Gamma distribution.
Samples are drawn from a Gamma distribution with specified parameters,
shape (sometimes designated "k") and scale=1.
.. note::
New code should use the
`~numpy.random.Generator.standard_gamma`
method of a `~numpy.random.Generator` instance instead;
please see the :ref:`random-quick-start`.
Parameters
----------
shape : float or array_like of floats
Parameter, must be non-negative.
size : int or tuple of ints, optional
Output shape. If the given shape is, e.g., ``(m, n, k)``, then
``m * n * k`` samples are drawn. If size is ``None`` (default),
a single value is returned if ``shape`` is a scalar. Otherwise,
``np.array(shape).size`` samples are drawn.
Returns
-------
out : ndarray or scalar
Drawn samples from the parameterized standard gamma distribution.
See Also
--------
scipy.stats.gamma : probability density function, distribution or
cumulative density function, etc.
random.Generator.standard_gamma: which should be used for new code.
Notes
-----
The probability density for the Gamma distribution is
.. math:: p(x) = x^{k-1}\frac{e^{-x/\theta}}{\theta^k\Gamma(k)},
where :math:`k` is the shape and :math:`\theta` the scale,
and :math:`\Gamma` is the Gamma function.
The Gamma distribution is often used to model the times to failure of
electronic components, and arises naturally in processes for which the
waiting times between Poisson distributed events are relevant.
References
----------
.. [1] Weisstein, Eric W. "Gamma Distribution." From MathWorld--A
Wolfram Web Resource.
http://mathworld.wolfram.com/GammaDistribution.html
.. [2] Wikipedia, "Gamma distribution",
https://en.wikipedia.org/wiki/Gamma_distribution
Examples
--------
Draw samples from the distribution:
>>> shape, scale = 2., 1. # mean and width
>>> s = np.random.standard_gamma(shape, 1000000)
Display the histogram of the samples, along with
the probability density function:
>>> import matplotlib.pyplot as plt
>>> import scipy.special as sps # doctest: +SKIP
>>> count, bins, ignored = plt.hist(s, 50, density=True)
>>> y = bins**(shape-1) * ((np.exp(-bins/scale))/ # doctest: +SKIP
... (sps.gamma(shape) * scale**shape))
>>> plt.plot(bins, y, linewidth=2, color='r') # doctest: +SKIP
>>> plt.show()
normal(loc=0.0, scale=1.0, size=None)
Draw random samples from a normal (Gaussian) distribution.
The probability density function of the normal distribution, first
derived by De Moivre and 200 years later by both Gauss and Laplace
independently [2]_, is often called the bell curve because of
its characteristic shape (see the example below).
The normal distributions occurs often in nature. For example, it
describes the commonly occurring distribution of samples influenced
by a large number of tiny, random disturbances, each with its own
unique distribution [2]_.
.. note::
New code should use the `~numpy.random.Generator.normal`
method of a `~numpy.random.Generator` instance instead;
please see the :ref:`random-quick-start`.
Parameters
----------
loc : float or array_like of floats
Mean ("centre") of the distribution.
scale : float or array_like of floats
Standard deviation (spread or "width") of the distribution. Must be
non-negative.
size : int or tuple of ints, optional
Output shape. If the given shape is, e.g., ``(m, n, k)``, then
``m * n * k`` samples are drawn. If size is ``None`` (default),
a single value is returned if ``loc`` and ``scale`` are both scalars.
Otherwise, ``np.broadcast(loc, scale).size`` samples are drawn.
Returns
-------
out : ndarray or scalar
Drawn samples from the parameterized normal distribution.
See Also
--------
scipy.stats.norm : probability density function, distribution or
cumulative density function, etc.
random.Generator.normal: which should be used for new code.
Notes
-----
The probability density for the Gaussian distribution is
.. math:: p(x) = \frac{1}{\sqrt{ 2 \pi \sigma^2 }}
e^{ - \frac{ (x - \mu)^2 } {2 \sigma^2} },
where :math:`\mu` is the mean and :math:`\sigma` the standard
deviation. The square of the standard deviation, :math:`\sigma^2`,
is called the variance.
The function has its peak at the mean, and its "spread" increases with
the standard deviation (the function reaches 0.607 times its maximum at
:math:`x + \sigma` and :math:`x - \sigma` [2]_). This implies that
normal is more likely to return samples lying close to the mean, rather
than those far away.
References
----------
.. [1] Wikipedia, "Normal distribution",
https://en.wikipedia.org/wiki/Normal_distribution
.. [2] P. R. Peebles Jr., "Central Limit Theorem" in "Probability,
Random Variables and Random Signal Principles", 4th ed., 2001,
pp. 51, 51, 125.
Examples
--------
Draw samples from the distribution:
>>> mu, sigma = 0, 0.1 # mean and standard deviation
>>> s = np.random.normal(mu, sigma, 1000)
Verify the mean and the variance:
>>> abs(mu - np.mean(s))
0.0 # may vary
>>> abs(sigma - np.std(s, ddof=1))
0.1 # may vary
Display the histogram of the samples, along with
the probability density function:
>>> import matplotlib.pyplot as plt
>>> count, bins, ignored = plt.hist(s, 30, density=True)
>>> plt.plot(bins, 1/(sigma * np.sqrt(2 * np.pi)) *
... np.exp( - (bins - mu)**2 / (2 * sigma**2) ),
... linewidth=2, color='r')
>>> plt.show()
Two-by-four array of samples from the normal distribution with
mean 3 and standard deviation 2.5:
>>> np.random.normal(3, 2.5, size=(2, 4))
array([[-4.49401501, 4.00950034, -1.81814867, 7.29718677], # random
[ 0.39924804, 4.68456316, 4.99394529, 4.84057254]]) # random
standard_normal(size=None)
Draw samples from a standard Normal distribution (mean=0, stdev=1).
.. note::
New code should use the
`~numpy.random.Generator.standard_normal`
method of a `~numpy.random.Generator` instance instead;
please see the :ref:`random-quick-start`.
Parameters
----------
size : int or tuple of ints, optional
Output shape. If the given shape is, e.g., ``(m, n, k)``, then
``m * n * k`` samples are drawn. Default is None, in which case a
single value is returned.
Returns
-------
out : float or ndarray
A floating-point array of shape ``size`` of drawn samples, or a
single sample if ``size`` was not specified.
See Also
--------
normal :
Equivalent function with additional ``loc`` and ``scale`` arguments
for setting the mean and standard deviation.
random.Generator.standard_normal: which should be used for new code.
Notes
-----
For random samples from the normal distribution with mean ``mu`` and
standard deviation ``sigma``, use one of::
mu + sigma * np.random.standard_normal(size=...)
np.random.normal(mu, sigma, size=...)
Examples
--------
>>> np.random.standard_normal()
2.1923875335537315 #random
>>> s = np.random.standard_normal(8000)
>>> s
array([ 0.6888893 , 0.78096262, -0.89086505, ..., 0.49876311, # random
-0.38672696, -0.4685006 ]) # random
>>> s.shape
(8000,)
>>> s = np.random.standard_normal(size=(3, 4, 2))
>>> s.shape
(3, 4, 2)
Two-by-four array of samples from the normal distribution with
mean 3 and standard deviation 2.5:
>>> 3 + 2.5 * np.random.standard_normal(size=(2, 4))
array([[-4.49401501, 4.00950034, -1.81814867, 7.29718677], # random
[ 0.39924804, 4.68456316, 4.99394529, 4.84057254]]) # random
random_integers(low, high=None, size=None)
Random integers of type `np.int_` between `low` and `high`, inclusive.
Return random integers of type `np.int_` from the "discrete uniform"
distribution in the closed interval [`low`, `high`]. If `high` is
None (the default), then results are from [1, `low`]. The `np.int_`
type translates to the C long integer type and its precision
is platform dependent.
This function has been deprecated. Use randint instead.
.. deprecated:: 1.11.0
Parameters
----------
low : int
Lowest (signed) integer to be drawn from the distribution (unless
``high=None``, in which case this parameter is the *highest* such
integer).
high : int, optional
If provided, the largest (signed) integer to be drawn from the
distribution (see above for behavior if ``high=None``).
size : int or tuple of ints, optional
Output shape. If the given shape is, e.g., ``(m, n, k)``, then
``m * n * k`` samples are drawn. Default is None, in which case a
single value is returned.
Returns
-------
out : int or ndarray of ints
`size`-shaped array of random integers from the appropriate
distribution, or a single such random int if `size` not provided.
See Also
--------
randint : Similar to `random_integers`, only for the half-open
interval [`low`, `high`), and 0 is the lowest value if `high` is
omitted.
Notes
-----
To sample from N evenly spaced floating-point numbers between a and b,
use::
a + (b - a) * (np.random.random_integers(N) - 1) / (N - 1.)
Examples
--------
>>> np.random.random_integers(5)
4 # random
>>> type(np.random.random_integers(5))
>>> np.random.random_integers(5, size=(3,2))
array([[5, 4], # random
[3, 3],
[4, 5]])
Choose five random numbers from the set of five evenly-spaced
numbers between 0 and 2.5, inclusive (*i.e.*, from the set
:math:`{0, 5/8, 10/8, 15/8, 20/8}`):
>>> 2.5 * (np.random.random_integers(5, size=(5,)) - 1) / 4.
array([ 0.625, 1.25 , 0.625, 0.625, 2.5 ]) # random
Roll two six sided dice 1000 times and sum the results:
>>> d1 = np.random.random_integers(1, 6, 1000)
>>> d2 = np.random.random_integers(1, 6, 1000)
>>> dsums = d1 + d2
Display results as a histogram:
>>> import matplotlib.pyplot as plt
>>> count, bins, ignored = plt.hist(dsums, 11, density=True)
>>> plt.show()
randn(d0, d1, ..., dn)
Return a sample (or samples) from the "standard normal" distribution.
.. note::
This is a convenience function for users porting code from Matlab,
and wraps `standard_normal`. That function takes a
tuple to specify the size of the output, which is consistent with
other NumPy functions like `numpy.zeros` and `numpy.ones`.
.. note::
New code should use the
`~numpy.random.Generator.standard_normal`
method of a `~numpy.random.Generator` instance instead;
please see the :ref:`random-quick-start`.
If positive int_like arguments are provided, `randn` generates an array
of shape ``(d0, d1, ..., dn)``, filled
with random floats sampled from a univariate "normal" (Gaussian)
distribution of mean 0 and variance 1. A single float randomly sampled
from the distribution is returned if no argument is provided.
Parameters
----------
d0, d1, ..., dn : int, optional
The dimensions of the returned array, must be non-negative.
If no argument is given a single Python float is returned.
Returns
-------
Z : ndarray or float
A ``(d0, d1, ..., dn)``-shaped array of floating-point samples from
the standard normal distribution, or a single such float if
no parameters were supplied.
See Also
--------
standard_normal : Similar, but takes a tuple as its argument.
normal : Also accepts mu and sigma arguments.
random.Generator.standard_normal: which should be used for new code.
Notes
-----
For random samples from the normal distribution with mean ``mu`` and
standard deviation ``sigma``, use::
sigma * np.random.randn(...) + mu
Examples
--------
>>> np.random.randn()
2.1923875335537315 # random
Two-by-four array of samples from the normal distribution with
mean 3 and standard deviation 2.5:
>>> 3 + 2.5 * np.random.randn(2, 4)
array([[-4.49401501, 4.00950034, -1.81814867, 7.29718677], # random
[ 0.39924804, 4.68456316, 4.99394529, 4.84057254]]) # random
rand(d0, d1, ..., dn)
Random values in a given shape.
.. note::
This is a convenience function for users porting code from Matlab,
and wraps `random_sample`. That function takes a
tuple to specify the size of the output, which is consistent with
other NumPy functions like `numpy.zeros` and `numpy.ones`.
Create an array of the given shape and populate it with
random samples from a uniform distribution
over ``[0, 1)``.
Parameters
----------
d0, d1, ..., dn : int, optional
The dimensions of the returned array, must be non-negative.
If no argument is given a single Python float is returned.
Returns
-------
out : ndarray, shape ``(d0, d1, ..., dn)``
Random values.
See Also
--------
random
Examples
--------
>>> np.random.rand(3,2)
array([[ 0.14022471, 0.96360618], #random
[ 0.37601032, 0.25528411], #random
[ 0.49313049, 0.94909878]]) #random
uniform(low=0.0, high=1.0, size=None)
Draw samples from a uniform distribution.
Samples are uniformly distributed over the half-open interval
``[low, high)`` (includes low, but excludes high). In other words,
any value within the given interval is equally likely to be drawn
by `uniform`.
.. note::
New code should use the `~numpy.random.Generator.uniform`
method of a `~numpy.random.Generator` instance instead;
please see the :ref:`random-quick-start`.
Parameters
----------
low : float or array_like of floats, optional
Lower boundary of the output interval. All values generated will be
greater than or equal to low. The default value is 0.
high : float or array_like of floats
Upper boundary of the output interval. All values generated will be
less than or equal to high. The high limit may be included in the
returned array of floats due to floating-point rounding in the
equation ``low + (high-low) * random_sample()``. The default value
is 1.0.
size : int or tuple of ints, optional
Output shape. If the given shape is, e.g., ``(m, n, k)``, then
``m * n * k`` samples are drawn. If size is ``None`` (default),
a single value is returned if ``low`` and ``high`` are both scalars.
Otherwise, ``np.broadcast(low, high).size`` samples are drawn.
Returns
-------
out : ndarray or scalar
Drawn samples from the parameterized uniform distribution.
See Also
--------
randint : Discrete uniform distribution, yielding integers.
random_integers : Discrete uniform distribution over the closed
interval ``[low, high]``.
random_sample : Floats uniformly distributed over ``[0, 1)``.
random : Alias for `random_sample`.
rand : Convenience function that accepts dimensions as input, e.g.,
``rand(2,2)`` would generate a 2-by-2 array of floats,
uniformly distributed over ``[0, 1)``.
random.Generator.uniform: which should be used for new code.
Notes
-----
The probability density function of the uniform distribution is
.. math:: p(x) = \frac{1}{b - a}
anywhere within the interval ``[a, b)``, and zero elsewhere.
When ``high`` == ``low``, values of ``low`` will be returned.
If ``high`` < ``low``, the results are officially undefined
and may eventually raise an error, i.e. do not rely on this
function to behave when passed arguments satisfying that
inequality condition. The ``high`` limit may be included in the
returned array of floats due to floating-point rounding in the
equation ``low + (high-low) * random_sample()``. For example:
>>> x = np.float32(5*0.99999999)
>>> x
5.0
Examples
--------
Draw samples from the distribution:
>>> s = np.random.uniform(-1,0,1000)
All values are within the given interval:
>>> np.all(s >= -1)
True
>>> np.all(s < 0)
True
Display the histogram of the samples, along with the
probability density function:
>>> import matplotlib.pyplot as plt
>>> count, bins, ignored = plt.hist(s, 15, density=True)
>>> plt.plot(bins, np.ones_like(bins), linewidth=2, color='r')
>>> plt.show()
choice(a, size=None, replace=True, p=None)
Generates a random sample from a given 1-D array
.. versionadded:: 1.7.0
.. note::
New code should use the `~numpy.random.Generator.choice`
method of a `~numpy.random.Generator` instance instead;
please see the :ref:`random-quick-start`.
Parameters
----------
a : 1-D array-like or int
If an ndarray, a random sample is generated from its elements.
If an int, the random sample is generated as if it were ``np.arange(a)``
size : int or tuple of ints, optional
Output shape. If the given shape is, e.g., ``(m, n, k)``, then
``m * n * k`` samples are drawn. Default is None, in which case a
single value is returned.
replace : boolean, optional
Whether the sample is with or without replacement. Default is True,
meaning that a value of ``a`` can be selected multiple times.
p : 1-D array-like, optional
The probabilities associated with each entry in a.
If not given, the sample assumes a uniform distribution over all
entries in ``a``.
Returns
-------
samples : single item or ndarray
The generated random samples
Raises
------
ValueError
If a is an int and less than zero, if a or p are not 1-dimensional,
if a is an array-like of size 0, if p is not a vector of
probabilities, if a and p have different lengths, or if
replace=False and the sample size is greater than the population
size
See Also
--------
randint, shuffle, permutation
random.Generator.choice: which should be used in new code
Notes
-----
Setting user-specified probabilities through ``p`` uses a more general but less
efficient sampler than the default. The general sampler produces a different sample
than the optimized sampler even if each element of ``p`` is 1 / len(a).
Sampling random rows from a 2-D array is not possible with this function,
but is possible with `Generator.choice` through its ``axis`` keyword.
Examples
--------
Generate a uniform random sample from np.arange(5) of size 3:
>>> np.random.choice(5, 3)
array([0, 3, 4]) # random
>>> #This is equivalent to np.random.randint(0,5,3)
Generate a non-uniform random sample from np.arange(5) of size 3:
>>> np.random.choice(5, 3, p=[0.1, 0, 0.3, 0.6, 0])
array([3, 3, 0]) # random
Generate a uniform random sample from np.arange(5) of size 3 without
replacement:
>>> np.random.choice(5, 3, replace=False)
array([3,1,0]) # random
>>> #This is equivalent to np.random.permutation(np.arange(5))[:3]
Generate a non-uniform random sample from np.arange(5) of size
3 without replacement:
>>> np.random.choice(5, 3, replace=False, p=[0.1, 0, 0.3, 0.6, 0])
array([2, 3, 0]) # random
Any of the above can be repeated with an arbitrary array-like
instead of just integers. For instance:
>>> aa_milne_arr = ['pooh', 'rabbit', 'piglet', 'Christopher']
>>> np.random.choice(aa_milne_arr, 5, p=[0.5, 0.1, 0.1, 0.3])
array(['pooh', 'pooh', 'pooh', 'Christopher', 'piglet'], # random
dtype='>> np.random.bytes(10)
b' eh\x85\x022SZ\xbf\xa4' #random
randint(low, high=None, size=None, dtype=int)
Return random integers from `low` (inclusive) to `high` (exclusive).
Return random integers from the "discrete uniform" distribution of
the specified dtype in the "half-open" interval [`low`, `high`). If
`high` is None (the default), then results are from [0, `low`).
.. note::
New code should use the `~numpy.random.Generator.integers`
method of a `~numpy.random.Generator` instance instead;
please see the :ref:`random-quick-start`.
Parameters
----------
low : int or array-like of ints
Lowest (signed) integers to be drawn from the distribution (unless
``high=None``, in which case this parameter is one above the
*highest* such integer).
high : int or array-like of ints, optional
If provided, one above the largest (signed) integer to be drawn
from the distribution (see above for behavior if ``high=None``).
If array-like, must contain integer values
size : int or tuple of ints, optional
Output shape. If the given shape is, e.g., ``(m, n, k)``, then
``m * n * k`` samples are drawn. Default is None, in which case a
single value is returned.
dtype : dtype, optional
Desired dtype of the result. Byteorder must be native.
The default value is int.
.. versionadded:: 1.11.0
Returns
-------
out : int or ndarray of ints
`size`-shaped array of random integers from the appropriate
distribution, or a single such random int if `size` not provided.
See Also
--------
random_integers : similar to `randint`, only for the closed
interval [`low`, `high`], and 1 is the lowest value if `high` is
omitted.
random.Generator.integers: which should be used for new code.
Examples
--------
>>> np.random.randint(2, size=10)
array([1, 0, 0, 0, 1, 1, 0, 0, 1, 0]) # random
>>> np.random.randint(1, size=10)
array([0, 0, 0, 0, 0, 0, 0, 0, 0, 0])
Generate a 2 x 4 array of ints between 0 and 4, inclusive:
>>> np.random.randint(5, size=(2, 4))
array([[4, 0, 2, 1], # random
[3, 2, 2, 0]])
Generate a 1 x 3 array with 3 different upper bounds
>>> np.random.randint(1, [3, 5, 10])
array([2, 2, 9]) # random
Generate a 1 by 3 array with 3 different lower bounds
>>> np.random.randint([1, 5, 7], 10)
array([9, 8, 7]) # random
Generate a 2 by 4 array using broadcasting with dtype of uint8
>>> np.random.randint([1, 3, 5, 7], [[10], [20]], dtype=np.uint8)
array([[ 8, 6, 9, 7], # random
[ 1, 16, 9, 12]], dtype=uint8)
tomaxint(size=None)
Return a sample of uniformly distributed random integers in the interval
[0, ``np.iinfo(np.int_).max``]. The `np.int_` type translates to the C long
integer type and its precision is platform dependent.
Parameters
----------
size : int or tuple of ints, optional
Output shape. If the given shape is, e.g., ``(m, n, k)``, then
``m * n * k`` samples are drawn. Default is None, in which case a
single value is returned.
Returns
-------
out : ndarray
Drawn samples, with shape `size`.
See Also
--------
randint : Uniform sampling over a given half-open interval of integers.
random_integers : Uniform sampling over a given closed interval of
integers.
Examples
--------
>>> rs = np.random.RandomState() # need a RandomState object
>>> rs.tomaxint((2,2,2))
array([[[1170048599, 1600360186], # random
[ 739731006, 1947757578]],
[[1871712945, 752307660],
[1601631370, 1479324245]]])
>>> rs.tomaxint((2,2,2)) < np.iinfo(np.int_).max
array([[[ True, True],
[ True, True]],
[[ True, True],
[ True, True]]])
standard_exponential(size=None)
Draw samples from the standard exponential distribution.
`standard_exponential` is identical to the exponential distribution
with a scale parameter of 1.
.. note::
New code should use the
`~numpy.random.Generator.standard_exponential`
method of a `~numpy.random.Generator` instance instead;
please see the :ref:`random-quick-start`.
Parameters
----------
size : int or tuple of ints, optional
Output shape. If the given shape is, e.g., ``(m, n, k)``, then
``m * n * k`` samples are drawn. Default is None, in which case a
single value is returned.
Returns
-------
out : float or ndarray
Drawn samples.
See Also
--------
random.Generator.standard_exponential: which should be used for new code.
Examples
--------
Output a 3x8000 array:
>>> n = np.random.standard_exponential((3, 8000))
exponential(scale=1.0, size=None)
Draw samples from an exponential distribution.
Its probability density function is
.. math:: f(x; \frac{1}{\beta}) = \frac{1}{\beta} \exp(-\frac{x}{\beta}),
for ``x > 0`` and 0 elsewhere. :math:`\beta` is the scale parameter,
which is the inverse of the rate parameter :math:`\lambda = 1/\beta`.
The rate parameter is an alternative, widely used parameterization
of the exponential distribution [3]_.
The exponential distribution is a continuous analogue of the
geometric distribution. It describes many common situations, such as
the size of raindrops measured over many rainstorms [1]_, or the time
between page requests to Wikipedia [2]_.
.. note::
New code should use the `~numpy.random.Generator.exponential`
method of a `~numpy.random.Generator` instance instead;
please see the :ref:`random-quick-start`.
Parameters
----------
scale : float or array_like of floats
The scale parameter, :math:`\beta = 1/\lambda`. Must be
non-negative.
size : int or tuple of ints, optional
Output shape. If the given shape is, e.g., ``(m, n, k)``, then
``m * n * k`` samples are drawn. If size is ``None`` (default),
a single value is returned if ``scale`` is a scalar. Otherwise,
``np.array(scale).size`` samples are drawn.
Returns
-------
out : ndarray or scalar
Drawn samples from the parameterized exponential distribution.
Examples
--------
A real world example: Assume a company has 10000 customer support
agents and the average time between customer calls is 4 minutes.
>>> n = 10000
>>> time_between_calls = np.random.default_rng().exponential(scale=4, size=n)
What is the probability that a customer will call in the next
4 to 5 minutes?
>>> x = ((time_between_calls < 5).sum())/n
>>> y = ((time_between_calls < 4).sum())/n
>>> x-y
0.08 # may vary
See Also
--------
random.Generator.exponential: which should be used for new code.
References
----------
.. [1] Peyton Z. Peebles Jr., "Probability, Random Variables and
Random Signal Principles", 4th ed, 2001, p. 57.
.. [2] Wikipedia, "Poisson process",
https://en.wikipedia.org/wiki/Poisson_process
.. [3] Wikipedia, "Exponential distribution",
https://en.wikipedia.org/wiki/Exponential_distribution
beta(a, b, size=None)
Draw samples from a Beta distribution.
The Beta distribution is a special case of the Dirichlet distribution,
and is related to the Gamma distribution. It has the probability
distribution function
.. math:: f(x; a,b) = \frac{1}{B(\alpha, \beta)} x^{\alpha - 1}
(1 - x)^{\beta - 1},
where the normalization, B, is the beta function,
.. math:: B(\alpha, \beta) = \int_0^1 t^{\alpha - 1}
(1 - t)^{\beta - 1} dt.
It is often seen in Bayesian inference and order statistics.
.. note::
New code should use the `~numpy.random.Generator.beta`
method of a `~numpy.random.Generator` instance instead;
please see the :ref:`random-quick-start`.
Parameters
----------
a : float or array_like of floats
Alpha, positive (>0).
b : float or array_like of floats
Beta, positive (>0).
size : int or tuple of ints, optional
Output shape. If the given shape is, e.g., ``(m, n, k)``, then
``m * n * k`` samples are drawn. If size is ``None`` (default),
a single value is returned if ``a`` and ``b`` are both scalars.
Otherwise, ``np.broadcast(a, b).size`` samples are drawn.
Returns
-------
out : ndarray or scalar
Drawn samples from the parameterized beta distribution.
See Also
--------
random.Generator.beta: which should be used for new code.
random(size=None)
Return random floats in the half-open interval [0.0, 1.0). Alias for
`random_sample` to ease forward-porting to the new random API.
random_sample(size=None)
Return random floats in the half-open interval [0.0, 1.0).
Results are from the "continuous uniform" distribution over the
stated interval. To sample :math:`Unif[a, b), b > a` multiply
the output of `random_sample` by `(b-a)` and add `a`::
(b - a) * random_sample() + a
.. note::
New code should use the `~numpy.random.Generator.random`
method of a `~numpy.random.Generator` instance instead;
please see the :ref:`random-quick-start`.
Parameters
----------
size : int or tuple of ints, optional
Output shape. If the given shape is, e.g., ``(m, n, k)``, then
``m * n * k`` samples are drawn. Default is None, in which case a
single value is returned.
Returns
-------
out : float or ndarray of floats
Array of random floats of shape `size` (unless ``size=None``, in which
case a single float is returned).
See Also
--------
random.Generator.random: which should be used for new code.
Examples
--------
>>> np.random.random_sample()
0.47108547995356098 # random
>>> type(np.random.random_sample())
>>> np.random.random_sample((5,))
array([ 0.30220482, 0.86820401, 0.1654503 , 0.11659149, 0.54323428]) # random
Three-by-two array of random numbers from [-5, 0):
>>> 5 * np.random.random_sample((3, 2)) - 5
array([[-3.99149989, -0.52338984], # random
[-2.99091858, -0.79479508],
[-1.23204345, -1.75224494]])
set_state(state)
Set the internal state of the generator from a tuple.
For use if one has reason to manually (re-)set the internal state of
the bit generator used by the RandomState instance. By default,
RandomState uses the "Mersenne Twister"[1]_ pseudo-random number
generating algorithm.
Parameters
----------
state : {tuple(str, ndarray of 624 uints, int, int, float), dict}
The `state` tuple has the following items:
1. the string 'MT19937', specifying the Mersenne Twister algorithm.
2. a 1-D array of 624 unsigned integers ``keys``.
3. an integer ``pos``.
4. an integer ``has_gauss``.
5. a float ``cached_gaussian``.
If state is a dictionary, it is directly set using the BitGenerators
`state` property.
Returns
-------
out : None
Returns 'None' on success.
See Also
--------
get_state
Notes
-----
`set_state` and `get_state` are not needed to work with any of the
random distributions in NumPy. If the internal state is manually altered,
the user should know exactly what he/she is doing.
For backwards compatibility, the form (str, array of 624 uints, int) is
also accepted although it is missing some information about the cached
Gaussian value: ``state = ('MT19937', keys, pos)``.
References
----------
.. [1] M. Matsumoto and T. Nishimura, "Mersenne Twister: A
623-dimensionally equidistributed uniform pseudorandom number
generator," *ACM Trans. on Modeling and Computer Simulation*,
Vol. 8, No. 1, pp. 3-30, Jan. 1998.
get_state(legacy=True)
Return a tuple representing the internal state of the generator.
For more details, see `set_state`.
Parameters
----------
legacy : bool, optional
Flag indicating to return a legacy tuple state when the BitGenerator
is MT19937, instead of a dict. Raises ValueError if the underlying
bit generator is not an instance of MT19937.
Returns
-------
out : {tuple(str, ndarray of 624 uints, int, int, float), dict}
If legacy is True, the returned tuple has the following items:
1. the string 'MT19937'.
2. a 1-D array of 624 unsigned integer keys.
3. an integer ``pos``.
4. an integer ``has_gauss``.
5. a float ``cached_gaussian``.
If `legacy` is False, or the BitGenerator is not MT19937, then
state is returned as a dictionary.
See Also
--------
set_state
Notes
-----
`set_state` and `get_state` are not needed to work with any of the
random distributions in NumPy. If the internal state is manually altered,
the user should know exactly what he/she is doing.
seed(seed=None)
Reseed a legacy MT19937 BitGenerator
Notes
-----
This is a convenience, legacy function.
The best practice is to **not** reseed a BitGenerator, rather to
recreate a new one. This method is here for legacy reasons.
This example demonstrates best practice.
>>> from numpy.random import MT19937
>>> from numpy.random import RandomState, SeedSequence
>>> rs = RandomState(MT19937(SeedSequence(123456789)))
# Later, you want to restart the stream
>>> rs = RandomState(MT19937(SeedSequence(987654321)))
This function is deprecated. Please call randint({low}, {high} + 1) instead x must be an integer or at least 1-dimensional probabilities are not non-negative numpy.core.umath failed to import mean and cov must have same length legacy can only be True when the underlyign bitgenerator is an instance of MT19937. get_state and legacy can only be used with the MT19937 BitGenerator. To silence this warning, set `legacy` to False. covariance is not symmetric positive-semidefinite. cov must be 2 dimensional and square check_valid must equal 'warn', 'raise', or 'ignore' can only re-seed a MT19937 BitGenerator a must be 1-dimensional or an integer This function is deprecated. Please call randint(1, {low} + 1) instead Shuffling a one dimensional array subclass containing objects gives incorrect results for most array subclasses. Please use the new random number API instead: https://numpy.org/doc/stable/reference/random/index.html
The new API fixes this issue. This version will not be fixed due to stability guarantees of the API. RandomState.triangular (line 3243) RandomState.standard_t (line 2149) RandomState.standard_normal (line 1384) RandomState.standard_exponential (line 576) RandomState.standard_cauchy (line 2074) RandomState.random_sample (line 384) RandomState.random_integers (line 1288) RandomState.permutation (line 4667) RandomState.noncentral_f (line 1822) RandomState.noncentral_chisquare (line 1985) RandomState.negative_binomial (line 3504) RandomState.multinomial (line 4256) RandomState.exponential (line 499) Providing a dtype with a non-native byteorder is not supported. If you require platform-independent byteorder, call byteswap when required.
In future version, providing byteorder will raise a ValueError Negative dimensions are not allowed Invalid bit generator. The bit generator must be instantized. Fewer non-zero entries in p than size Cannot take a larger sample than population when 'replace=False'
zipf(a, size=None)
Draw samples from a Zipf distribution.
Samples are drawn from a Zipf distribution with specified parameter
`a` > 1.
The Zipf distribution (also known as the zeta distribution) is a
discrete probability distribution that satisfies Zipf's law: the
frequency of an item is inversely proportional to its rank in a
frequency table.
.. note::
New code should use the `~numpy.random.Generator.zipf`
method of a `~numpy.random.Generator` instance instead;
please see the :ref:`random-quick-start`.
Parameters
----------
a : float or array_like of floats
Distribution parameter. Must be greater than 1.
size : int or tuple of ints, optional
Output shape. If the given shape is, e.g., ``(m, n, k)``, then
``m * n * k`` samples are drawn. If size is ``None`` (default),
a single value is returned if ``a`` is a scalar. Otherwise,
``np.array(a).size`` samples are drawn.
Returns
-------
out : ndarray or scalar
Drawn samples from the parameterized Zipf distribution.
See Also
--------
scipy.stats.zipf : probability density function, distribution, or
cumulative density function, etc.
random.Generator.zipf: which should be used for new code.
Notes
-----
The probability density for the Zipf distribution is
.. math:: p(k) = \frac{k^{-a}}{\zeta(a)},
for integers :math:`k \geq 1`, where :math:`\zeta` is the Riemann Zeta
function.
It is named for the American linguist George Kingsley Zipf, who noted
that the frequency of any word in a sample of a language is inversely
proportional to its rank in the frequency table.
References
----------
.. [1] Zipf, G. K., "Selected Studies of the Principle of Relative
Frequency in Language," Cambridge, MA: Harvard Univ. Press,
1932.
Examples
--------
Draw samples from the distribution:
>>> a = 4.0
>>> n = 20000
>>> s = np.random.zipf(a, n)
Display the histogram of the samples, along with
the expected histogram based on the probability
density function:
>>> import matplotlib.pyplot as plt
>>> from scipy.special import zeta # doctest: +SKIP
`bincount` provides a fast histogram for small integers.
>>> count = np.bincount(s)
>>> k = np.arange(1, s.max() + 1)
>>> plt.bar(k, count[1:], alpha=0.5, label='sample count')
>>> plt.plot(k, n*(k**-a)/zeta(a), 'k.-', alpha=0.5,
... label='expected count') # doctest: +SKIP
>>> plt.semilogy()
>>> plt.grid(alpha=0.4)
>>> plt.legend()
>>> plt.title(f'Zipf sample, a={a}, size={n}')
>>> plt.show()
weibull(a, size=None)
Draw samples from a Weibull distribution.
Draw samples from a 1-parameter Weibull distribution with the given
shape parameter `a`.
.. math:: X = (-ln(U))^{1/a}
Here, U is drawn from the uniform distribution over (0,1].
The more common 2-parameter Weibull, including a scale parameter
:math:`\lambda` is just :math:`X = \lambda(-ln(U))^{1/a}`.
.. note::
New code should use the `~numpy.random.Generator.weibull`
method of a `~numpy.random.Generator` instance instead;
please see the :ref:`random-quick-start`.
Parameters
----------
a : float or array_like of floats
Shape parameter of the distribution. Must be nonnegative.
size : int or tuple of ints, optional
Output shape. If the given shape is, e.g., ``(m, n, k)``, then
``m * n * k`` samples are drawn. If size is ``None`` (default),
a single value is returned if ``a`` is a scalar. Otherwise,
``np.array(a).size`` samples are drawn.
Returns
-------
out : ndarray or scalar
Drawn samples from the parameterized Weibull distribution.
See Also
--------
scipy.stats.weibull_max
scipy.stats.weibull_min
scipy.stats.genextreme
gumbel
random.Generator.weibull: which should be used for new code.
Notes
-----
The Weibull (or Type III asymptotic extreme value distribution
for smallest values, SEV Type III, or Rosin-Rammler
distribution) is one of a class of Generalized Extreme Value
(GEV) distributions used in modeling extreme value problems.
This class includes the Gumbel and Frechet distributions.
The probability density for the Weibull distribution is
.. math:: p(x) = \frac{a}
{\lambda}(\frac{x}{\lambda})^{a-1}e^{-(x/\lambda)^a},
where :math:`a` is the shape and :math:`\lambda` the scale.
The function has its peak (the mode) at
:math:`\lambda(\frac{a-1}{a})^{1/a}`.
When ``a = 1``, the Weibull distribution reduces to the exponential
distribution.
References
----------
.. [1] Waloddi Weibull, Royal Technical University, Stockholm,
1939 "A Statistical Theory Of The Strength Of Materials",
Ingeniorsvetenskapsakademiens Handlingar Nr 151, 1939,
Generalstabens Litografiska Anstalts Forlag, Stockholm.
.. [2] Waloddi Weibull, "A Statistical Distribution Function of
Wide Applicability", Journal Of Applied Mechanics ASME Paper
1951.
.. [3] Wikipedia, "Weibull distribution",
https://en.wikipedia.org/wiki/Weibull_distribution
Examples
--------
Draw samples from the distribution:
>>> a = 5. # shape
>>> s = np.random.weibull(a, 1000)
Display the histogram of the samples, along with
the probability density function:
>>> import matplotlib.pyplot as plt
>>> x = np.arange(1,100.)/50.
>>> def weib(x,n,a):
... return (a / n) * (x / n)**(a - 1) * np.exp(-(x / n)**a)
>>> count, bins, ignored = plt.hist(np.random.weibull(5.,1000))
>>> x = np.arange(1,100.)/50.
>>> scale = count.max()/weib(x, 1., 5.).max()
>>> plt.plot(x, weib(x, 1., 5.)*scale)
>>> plt.show()
vonmises(mu, kappa, size=None)
Draw samples from a von Mises distribution.
Samples are drawn from a von Mises distribution with specified mode
(mu) and dispersion (kappa), on the interval [-pi, pi].
The von Mises distribution (also known as the circular normal
distribution) is a continuous probability distribution on the unit
circle. It may be thought of as the circular analogue of the normal
distribution.
.. note::
New code should use the `~numpy.random.Generator.vonmises`
method of a `~numpy.random.Generator` instance instead;
please see the :ref:`random-quick-start`.
Parameters
----------
mu : float or array_like of floats
Mode ("center") of the distribution.
kappa : float or array_like of floats
Dispersion of the distribution, has to be >=0.
size : int or tuple of ints, optional
Output shape. If the given shape is, e.g., ``(m, n, k)``, then
``m * n * k`` samples are drawn. If size is ``None`` (default),
a single value is returned if ``mu`` and ``kappa`` are both scalars.
Otherwise, ``np.broadcast(mu, kappa).size`` samples are drawn.
Returns
-------
out : ndarray or scalar
Drawn samples from the parameterized von Mises distribution.
See Also
--------
scipy.stats.vonmises : probability density function, distribution, or
cumulative density function, etc.
random.Generator.vonmises: which should be used for new code.
Notes
-----
The probability density for the von Mises distribution is
.. math:: p(x) = \frac{e^{\kappa cos(x-\mu)}}{2\pi I_0(\kappa)},
where :math:`\mu` is the mode and :math:`\kappa` the dispersion,
and :math:`I_0(\kappa)` is the modified Bessel function of order 0.
The von Mises is named for Richard Edler von Mises, who was born in
Austria-Hungary, in what is now the Ukraine. He fled to the United
States in 1939 and became a professor at Harvard. He worked in
probability theory, aerodynamics, fluid mechanics, and philosophy of
science.
References
----------
.. [1] Abramowitz, M. and Stegun, I. A. (Eds.). "Handbook of
Mathematical Functions with Formulas, Graphs, and Mathematical
Tables, 9th printing," New York: Dover, 1972.
.. [2] von Mises, R., "Mathematical Theory of Probability
and Statistics", New York: Academic Press, 1964.
Examples
--------
Draw samples from the distribution:
>>> mu, kappa = 0.0, 4.0 # mean and dispersion
>>> s = np.random.vonmises(mu, kappa, 1000)
Display the histogram of the samples, along with
the probability density function:
>>> import matplotlib.pyplot as plt
>>> from scipy.special import i0 # doctest: +SKIP
>>> plt.hist(s, 50, density=True)
>>> x = np.linspace(-np.pi, np.pi, num=51)
>>> y = np.exp(kappa*np.cos(x-mu))/(2*np.pi*i0(kappa)) # doctest: +SKIP
>>> plt.plot(x, y, linewidth=2, color='r') # doctest: +SKIP
>>> plt.show()
uniform(low=0.0, high=1.0, size=None)
Draw samples from a uniform distribution.
Samples are uniformly distributed over the half-open interval
``[low, high)`` (includes low, but excludes high). In other words,
any value within the given interval is equally likely to be drawn
by `uniform`.
.. note::
New code should use the `~numpy.random.Generator.uniform`
method of a `~numpy.random.Generator` instance instead;
please see the :ref:`random-quick-start`.
Parameters
----------
low : float or array_like of floats, optional
Lower boundary of the output interval. All values generated will be
greater than or equal to low. The default value is 0.
high : float or array_like of floats
Upper boundary of the output interval. All values generated will be
less than or equal to high. The high limit may be included in the
returned array of floats due to floating-point rounding in the
equation ``low + (high-low) * random_sample()``. The default value
is 1.0.
size : int or tuple of ints, optional
Output shape. If the given shape is, e.g., ``(m, n, k)``, then
``m * n * k`` samples are drawn. If size is ``None`` (default),
a single value is returned if ``low`` and ``high`` are both scalars.
Otherwise, ``np.broadcast(low, high).size`` samples are drawn.
Returns
-------
out : ndarray or scalar
Drawn samples from the parameterized uniform distribution.
See Also
--------
randint : Discrete uniform distribution, yielding integers.
random_integers : Discrete uniform distribution over the closed
interval ``[low, high]``.
random_sample : Floats uniformly distributed over ``[0, 1)``.
random : Alias for `random_sample`.
rand : Convenience function that accepts dimensions as input, e.g.,
``rand(2,2)`` would generate a 2-by-2 array of floats,
uniformly distributed over ``[0, 1)``.
random.Generator.uniform: which should be used for new code.
Notes
-----
The probability density function of the uniform distribution is
.. math:: p(x) = \frac{1}{b - a}
anywhere within the interval ``[a, b)``, and zero elsewhere.
When ``high`` == ``low``, values of ``low`` will be returned.
If ``high`` < ``low``, the results are officially undefined
and may eventually raise an error, i.e. do not rely on this
function to behave when passed arguments satisfying that
inequality condition. The ``high`` limit may be included in the
returned array of floats due to floating-point rounding in the
equation ``low + (high-low) * random_sample()``. For example:
>>> x = np.float32(5*0.99999999)
>>> x
5.0
Examples
--------
Draw samples from the distribution:
>>> s = np.random.uniform(-1,0,1000)
All values are within the given interval:
>>> np.all(s >= -1)
True
>>> np.all(s < 0)
True
Display the histogram of the samples, along with the
probability density function:
>>> import matplotlib.pyplot as plt
>>> count, bins, ignored = plt.hist(s, 15, density=True)
>>> plt.plot(bins, np.ones_like(bins), linewidth=2, color='r')
>>> plt.show()
triangular(left, mode, right, size=None)
Draw samples from the triangular distribution over the
interval ``[left, right]``.
The triangular distribution is a continuous probability
distribution with lower limit left, peak at mode, and upper
limit right. Unlike the other distributions, these parameters
directly define the shape of the pdf.
.. note::
New code should use the `~numpy.random.Generator.triangular`
method of a `~numpy.random.Generator` instance instead;
please see the :ref:`random-quick-start`.
Parameters
----------
left : float or array_like of floats
Lower limit.
mode : float or array_like of floats
The value where the peak of the distribution occurs.
The value must fulfill the condition ``left <= mode <= right``.
right : float or array_like of floats
Upper limit, must be larger than `left`.
size : int or tuple of ints, optional
Output shape. If the given shape is, e.g., ``(m, n, k)``, then
``m * n * k`` samples are drawn. If size is ``None`` (default),
a single value is returned if ``left``, ``mode``, and ``right``
are all scalars. Otherwise, ``np.broadcast(left, mode, right).size``
samples are drawn.
Returns
-------
out : ndarray or scalar
Drawn samples from the parameterized triangular distribution.
See Also
--------
random.Generator.triangular: which should be used for new code.
Notes
-----
The probability density function for the triangular distribution is
.. math:: P(x;l, m, r) = \begin{cases}
\frac{2(x-l)}{(r-l)(m-l)}& \text{for $l \leq x \leq m$},\\
\frac{2(r-x)}{(r-l)(r-m)}& \text{for $m \leq x \leq r$},\\
0& \text{otherwise}.
\end{cases}
The triangular distribution is often used in ill-defined
problems where the underlying distribution is not known, but
some knowledge of the limits and mode exists. Often it is used
in simulations.
References
----------
.. [1] Wikipedia, "Triangular distribution"
https://en.wikipedia.org/wiki/Triangular_distribution
Examples
--------
Draw values from the distribution and plot the histogram:
>>> import matplotlib.pyplot as plt
>>> h = plt.hist(np.random.triangular(-3, 0, 8, 100000), bins=200,
... density=True)
>>> plt.show()
tomaxint(size=None)
Return a sample of uniformly distributed random integers in the interval
[0, ``np.iinfo(np.int_).max``]. The `np.int_` type translates to the C long
integer type and its precision is platform dependent.
Parameters
----------
size : int or tuple of ints, optional
Output shape. If the given shape is, e.g., ``(m, n, k)``, then
``m * n * k`` samples are drawn. Default is None, in which case a
single value is returned.
Returns
-------
out : ndarray
Drawn samples, with shape `size`.
See Also
--------
randint : Uniform sampling over a given half-open interval of integers.
random_integers : Uniform sampling over a given closed interval of
integers.
Examples
--------
>>> rs = np.random.RandomState() # need a RandomState object
>>> rs.tomaxint((2,2,2))
array([[[1170048599, 1600360186], # random
[ 739731006, 1947757578]],
[[1871712945, 752307660],
[1601631370, 1479324245]]])
>>> rs.tomaxint((2,2,2)) < np.iinfo(np.int_).max
array([[[ True, True],
[ True, True]],
[[ True, True],
[ True, True]]])
sum(pvals[:-1].astype(np.float64)) > 1.0. The pvals array is cast to 64-bit floating point prior to checking the sum. Precision changes when casting may cause problems even if the sum of the original pvals is valid. state must be a dict or a tuple.
standard_t(df, size=None)
Draw samples from a standard Student's t distribution with `df` degrees
of freedom.
A special case of the hyperbolic distribution. As `df` gets
large, the result resembles that of the standard normal
distribution (`standard_normal`).
.. note::
New code should use the `~numpy.random.Generator.standard_t`
method of a `~numpy.random.Generator` instance instead;
please see the :ref:`random-quick-start`.
Parameters
----------
df : float or array_like of floats
Degrees of freedom, must be > 0.
size : int or tuple of ints, optional
Output shape. If the given shape is, e.g., ``(m, n, k)``, then
``m * n * k`` samples are drawn. If size is ``None`` (default),
a single value is returned if ``df`` is a scalar. Otherwise,
``np.array(df).size`` samples are drawn.
Returns
-------
out : ndarray or scalar
Drawn samples from the parameterized standard Student's t distribution.
See Also
--------
random.Generator.standard_t: which should be used for new code.
Notes
-----
The probability density function for the t distribution is
.. math:: P(x, df) = \frac{\Gamma(\frac{df+1}{2})}{\sqrt{\pi df}
\Gamma(\frac{df}{2})}\Bigl( 1+\frac{x^2}{df} \Bigr)^{-(df+1)/2}
The t test is based on an assumption that the data come from a
Normal distribution. The t test provides a way to test whether
the sample mean (that is the mean calculated from the data) is
a good estimate of the true mean.
The derivation of the t-distribution was first published in
1908 by William Gosset while working for the Guinness Brewery
in Dublin. Due to proprietary issues, he had to publish under
a pseudonym, and so he used the name Student.
References
----------
.. [1] Dalgaard, Peter, "Introductory Statistics With R",
Springer, 2002.
.. [2] Wikipedia, "Student's t-distribution"
https://en.wikipedia.org/wiki/Student's_t-distribution
Examples
--------
From Dalgaard page 83 [1]_, suppose the daily energy intake for 11
women in kilojoules (kJ) is:
>>> intake = np.array([5260., 5470, 5640, 6180, 6390, 6515, 6805, 7515, \
... 7515, 8230, 8770])
Does their energy intake deviate systematically from the recommended
value of 7725 kJ? Our null hypothesis will be the absence of deviation,
and the alternate hypothesis will be the presence of an effect that could be
either positive or negative, hence making our test 2-tailed.
Because we are estimating the mean and we have N=11 values in our sample,
we have N-1=10 degrees of freedom. We set our significance level to 95% and
compute the t statistic using the empirical mean and empirical standard
deviation of our intake. We use a ddof of 1 to base the computation of our
empirical standard deviation on an unbiased estimate of the variance (note:
the final estimate is not unbiased due to the concave nature of the square
root).
>>> np.mean(intake)
6753.636363636364
>>> intake.std(ddof=1)
1142.1232221373727
>>> t = (np.mean(intake)-7725)/(intake.std(ddof=1)/np.sqrt(len(intake)))
>>> t
-2.8207540608310198
We draw 1000000 samples from Student's t distribution with the adequate
degrees of freedom.
>>> import matplotlib.pyplot as plt
>>> s = np.random.standard_t(10, size=1000000)
>>> h = plt.hist(s, bins=100, density=True)
Does our t statistic land in one of the two critical regions found at
both tails of the distribution?
>>> np.sum(np.abs(t) < np.abs(s)) / float(len(s))
0.018318 #random < 0.05, statistic is in critical region
The probability value for this 2-tailed test is about 1.83%, which is
lower than the 5% pre-determined significance threshold.
Therefore, the probability of observing values as extreme as our intake
conditionally on the null hypothesis being true is too low, and we reject
the null hypothesis of no deviation.
set_state can only be used with legacy MT19937state instances.
rayleigh(scale=1.0, size=None)
Draw samples from a Rayleigh distribution.
The :math:`\chi` and Weibull distributions are generalizations of the
Rayleigh.
.. note::
New code should use the `~numpy.random.Generator.rayleigh`
method of a `~numpy.random.Generator` instance instead;
please see the :ref:`random-quick-start`.
Parameters
----------
scale : float or array_like of floats, optional
Scale, also equals the mode. Must be non-negative. Default is 1.
size : int or tuple of ints, optional
Output shape. If the given shape is, e.g., ``(m, n, k)``, then
``m * n * k`` samples are drawn. If size is ``None`` (default),
a single value is returned if ``scale`` is a scalar. Otherwise,
``np.array(scale).size`` samples are drawn.
Returns
-------
out : ndarray or scalar
Drawn samples from the parameterized Rayleigh distribution.
See Also
--------
random.Generator.rayleigh: which should be used for new code.
Notes
-----
The probability density function for the Rayleigh distribution is
.. math:: P(x;scale) = \frac{x}{scale^2}e^{\frac{-x^2}{2 \cdotp scale^2}}
The Rayleigh distribution would arise, for example, if the East
and North components of the wind velocity had identical zero-mean
Gaussian distributions. Then the wind speed would have a Rayleigh
distribution.
References
----------
.. [1] Brighton Webs Ltd., "Rayleigh Distribution,"
https://web.archive.org/web/20090514091424/http://brighton-webs.co.uk:80/distributions/rayleigh.asp
.. [2] Wikipedia, "Rayleigh distribution"
https://en.wikipedia.org/wiki/Rayleigh_distribution
Examples
--------
Draw values from the distribution and plot the histogram
>>> from matplotlib.pyplot import hist
>>> values = hist(np.random.rayleigh(3, 100000), bins=200, density=True)
Wave heights tend to follow a Rayleigh distribution. If the mean wave
height is 1 meter, what fraction of waves are likely to be larger than 3
meters?
>>> meanvalue = 1
>>> modevalue = np.sqrt(2 / np.pi) * meanvalue
>>> s = np.random.rayleigh(modevalue, 1000000)
The percentage of waves larger than 3 meters is:
>>> 100.*sum(s>3)/1000000.
0.087300000000000003 # random
random_integers(low, high=None, size=None)
Random integers of type `np.int_` between `low` and `high`, inclusive.
Return random integers of type `np.int_` from the "discrete uniform"
distribution in the closed interval [`low`, `high`]. If `high` is
None (the default), then results are from [1, `low`]. The `np.int_`
type translates to the C long integer type and its precision
is platform dependent.
This function has been deprecated. Use randint instead.
.. deprecated:: 1.11.0
Parameters
----------
low : int
Lowest (signed) integer to be drawn from the distribution (unless
``high=None``, in which case this parameter is the *highest* such
integer).
high : int, optional
If provided, the largest (signed) integer to be drawn from the
distribution (see above for behavior if ``high=None``).
size : int or tuple of ints, optional
Output shape. If the given shape is, e.g., ``(m, n, k)``, then
``m * n * k`` samples are drawn. Default is None, in which case a
single value is returned.
Returns
-------
out : int or ndarray of ints
`size`-shaped array of random integers from the appropriate
distribution, or a single such random int if `size` not provided.
See Also
--------
randint : Similar to `random_integers`, only for the half-open
interval [`low`, `high`), and 0 is the lowest value if `high` is
omitted.
Notes
-----
To sample from N evenly spaced floating-point numbers between a and b,
use::
a + (b - a) * (np.random.random_integers(N) - 1) / (N - 1.)
Examples
--------
>>> np.random.random_integers(5)
4 # random
>>> type(np.random.random_integers(5))
>>> np.random.random_integers(5, size=(3,2))
array([[5, 4], # random
[3, 3],
[4, 5]])
Choose five random numbers from the set of five evenly-spaced
numbers between 0 and 2.5, inclusive (*i.e.*, from the set
:math:`{0, 5/8, 10/8, 15/8, 20/8}`):
>>> 2.5 * (np.random.random_integers(5, size=(5,)) - 1) / 4.
array([ 0.625, 1.25 , 0.625, 0.625, 2.5 ]) # random
Roll two six sided dice 1000 times and sum the results:
>>> d1 = np.random.random_integers(1, 6, 1000)
>>> d2 = np.random.random_integers(1, 6, 1000)
>>> dsums = d1 + d2
Display results as a histogram:
>>> import matplotlib.pyplot as plt
>>> count, bins, ignored = plt.hist(dsums, 11, density=True)
>>> plt.show()
randint(low, high=None, size=None, dtype=int)
Return random integers from `low` (inclusive) to `high` (exclusive).
Return random integers from the "discrete uniform" distribution of
the specified dtype in the "half-open" interval [`low`, `high`). If
`high` is None (the default), then results are from [0, `low`).
.. note::
New code should use the `~numpy.random.Generator.integers`
method of a `~numpy.random.Generator` instance instead;
please see the :ref:`random-quick-start`.
Parameters
----------
low : int or array-like of ints
Lowest (signed) integers to be drawn from the distribution (unless
``high=None``, in which case this parameter is one above the
*highest* such integer).
high : int or array-like of ints, optional
If provided, one above the largest (signed) integer to be drawn
from the distribution (see above for behavior if ``high=None``).
If array-like, must contain integer values
size : int or tuple of ints, optional
Output shape. If the given shape is, e.g., ``(m, n, k)``, then
``m * n * k`` samples are drawn. Default is None, in which case a
single value is returned.
dtype : dtype, optional
Desired dtype of the result. Byteorder must be native.
The default value is int.
.. versionadded:: 1.11.0
Returns
-------
out : int or ndarray of ints
`size`-shaped array of random integers from the appropriate
distribution, or a single such random int if `size` not provided.
See Also
--------
random_integers : similar to `randint`, only for the closed
interval [`low`, `high`], and 1 is the lowest value if `high` is
omitted.
random.Generator.integers: which should be used for new code.
Examples
--------
>>> np.random.randint(2, size=10)
array([1, 0, 0, 0, 1, 1, 0, 0, 1, 0]) # random
>>> np.random.randint(1, size=10)
array([0, 0, 0, 0, 0, 0, 0, 0, 0, 0])
Generate a 2 x 4 array of ints between 0 and 4, inclusive:
>>> np.random.randint(5, size=(2, 4))
array([[4, 0, 2, 1], # random
[3, 2, 2, 0]])
Generate a 1 x 3 array with 3 different upper bounds
>>> np.random.randint(1, [3, 5, 10])
array([2, 2, 9]) # random
Generate a 1 by 3 array with 3 different lower bounds
>>> np.random.randint([1, 5, 7], 10)
array([9, 8, 7]) # random
Generate a 2 by 4 array using broadcasting with dtype of uint8
>>> np.random.randint([1, 3, 5, 7], [[10], [20]], dtype=np.uint8)
array([[ 8, 6, 9, 7], # random
[ 1, 16, 9, 12]], dtype=uint8)
power(a, size=None)
Draws samples in [0, 1] from a power distribution with positive
exponent a - 1.
Also known as the power function distribution.
.. note::
New code should use the `~numpy.random.Generator.power`
method of a `~numpy.random.Generator` instance instead;
please see the :ref:`random-quick-start`.
Parameters
----------
a : float or array_like of floats
Parameter of the distribution. Must be non-negative.
size : int or tuple of ints, optional
Output shape. If the given shape is, e.g., ``(m, n, k)``, then
``m * n * k`` samples are drawn. If size is ``None`` (default),
a single value is returned if ``a`` is a scalar. Otherwise,
``np.array(a).size`` samples are drawn.
Returns
-------
out : ndarray or scalar
Drawn samples from the parameterized power distribution.
Raises
------
ValueError
If a <= 0.
See Also
--------
random.Generator.power: which should be used for new code.
Notes
-----
The probability density function is
.. math:: P(x; a) = ax^{a-1}, 0 \le x \le 1, a>0.
The power function distribution is just the inverse of the Pareto
distribution. It may also be seen as a special case of the Beta
distribution.
It is used, for example, in modeling the over-reporting of insurance
claims.
References
----------
.. [1] Christian Kleiber, Samuel Kotz, "Statistical size distributions
in economics and actuarial sciences", Wiley, 2003.
.. [2] Heckert, N. A. and Filliben, James J. "NIST Handbook 148:
Dataplot Reference Manual, Volume 2: Let Subcommands and Library
Functions", National Institute of Standards and Technology
Handbook Series, June 2003.
https://www.itl.nist.gov/div898/software/dataplot/refman2/auxillar/powpdf.pdf
Examples
--------
Draw samples from the distribution:
>>> a = 5. # shape
>>> samples = 1000
>>> s = np.random.power(a, samples)
Display the histogram of the samples, along with
the probability density function:
>>> import matplotlib.pyplot as plt
>>> count, bins, ignored = plt.hist(s, bins=30)
>>> x = np.linspace(0, 1, 100)
>>> y = a*x**(a-1.)
>>> normed_y = samples*np.diff(bins)[0]*y
>>> plt.plot(x, normed_y)
>>> plt.show()
Compare the power function distribution to the inverse of the Pareto.
>>> from scipy import stats # doctest: +SKIP
>>> rvs = np.random.power(5, 1000000)
>>> rvsp = np.random.pareto(5, 1000000)
>>> xx = np.linspace(0,1,100)
>>> powpdf = stats.powerlaw.pdf(xx,5) # doctest: +SKIP
>>> plt.figure()
>>> plt.hist(rvs, bins=50, density=True)
>>> plt.plot(xx,powpdf,'r-') # doctest: +SKIP
>>> plt.title('np.random.power(5)')
>>> plt.figure()
>>> plt.hist(1./(1.+rvsp), bins=50, density=True)
>>> plt.plot(xx,powpdf,'r-') # doctest: +SKIP
>>> plt.title('inverse of 1 + np.random.pareto(5)')
>>> plt.figure()
>>> plt.hist(1./(1.+rvsp), bins=50, density=True)
>>> plt.plot(xx,powpdf,'r-') # doctest: +SKIP
>>> plt.title('inverse of stats.pareto(5)')
pareto(a, size=None)
Draw samples from a Pareto II or Lomax distribution with
specified shape.
The Lomax or Pareto II distribution is a shifted Pareto
distribution. The classical Pareto distribution can be
obtained from the Lomax distribution by adding 1 and
multiplying by the scale parameter ``m`` (see Notes). The
smallest value of the Lomax distribution is zero while for the
classical Pareto distribution it is ``mu``, where the standard
Pareto distribution has location ``mu = 1``. Lomax can also
be considered as a simplified version of the Generalized
Pareto distribution (available in SciPy), with the scale set
to one and the location set to zero.
The Pareto distribution must be greater than zero, and is
unbounded above. It is also known as the "80-20 rule". In
this distribution, 80 percent of the weights are in the lowest
20 percent of the range, while the other 20 percent fill the
remaining 80 percent of the range.
.. note::
New code should use the `~numpy.random.Generator.pareto`
method of a `~numpy.random.Generator` instance instead;
please see the :ref:`random-quick-start`.
Parameters
----------
a : float or array_like of floats
Shape of the distribution. Must be positive.
size : int or tuple of ints, optional
Output shape. If the given shape is, e.g., ``(m, n, k)``, then
``m * n * k`` samples are drawn. If size is ``None`` (default),
a single value is returned if ``a`` is a scalar. Otherwise,
``np.array(a).size`` samples are drawn.
Returns
-------
out : ndarray or scalar
Drawn samples from the parameterized Pareto distribution.
See Also
--------
scipy.stats.lomax : probability density function, distribution or
cumulative density function, etc.
scipy.stats.genpareto : probability density function, distribution or
cumulative density function, etc.
random.Generator.pareto: which should be used for new code.
Notes
-----
The probability density for the Pareto distribution is
.. math:: p(x) = \frac{am^a}{x^{a+1}}
where :math:`a` is the shape and :math:`m` the scale.
The Pareto distribution, named after the Italian economist
Vilfredo Pareto, is a power law probability distribution
useful in many real world problems. Outside the field of
economics it is generally referred to as the Bradford
distribution. Pareto developed the distribution to describe
the distribution of wealth in an economy. It has also found
use in insurance, web page access statistics, oil field sizes,
and many other problems, including the download frequency for
projects in Sourceforge [1]_. It is one of the so-called
"fat-tailed" distributions.
References
----------
.. [1] Francis Hunt and Paul Johnson, On the Pareto Distribution of
Sourceforge projects.
.. [2] Pareto, V. (1896). Course of Political Economy. Lausanne.
.. [3] Reiss, R.D., Thomas, M.(2001), Statistical Analysis of Extreme
Values, Birkhauser Verlag, Basel, pp 23-30.
.. [4] Wikipedia, "Pareto distribution",
https://en.wikipedia.org/wiki/Pareto_distribution
Examples
--------
Draw samples from the distribution:
>>> a, m = 3., 2. # shape and mode
>>> s = (np.random.pareto(a, 1000) + 1) * m
Display the histogram of the samples, along with the probability
density function:
>>> import matplotlib.pyplot as plt
>>> count, bins, _ = plt.hist(s, 100, density=True)
>>> fit = a*m**a / bins**(a+1)
>>> plt.plot(bins, max(count)*fit/max(fit), linewidth=2, color='r')
>>> plt.show()
numpy.core.multiarray failed to import
normal(loc=0.0, scale=1.0, size=None)
Draw random samples from a normal (Gaussian) distribution.
The probability density function of the normal distribution, first
derived by De Moivre and 200 years later by both Gauss and Laplace
independently [2]_, is often called the bell curve because of
its characteristic shape (see the example below).
The normal distributions occurs often in nature. For example, it
describes the commonly occurring distribution of samples influenced
by a large number of tiny, random disturbances, each with its own
unique distribution [2]_.
.. note::
New code should use the `~numpy.random.Generator.normal`
method of a `~numpy.random.Generator` instance instead;
please see the :ref:`random-quick-start`.
Parameters
----------
loc : float or array_like of floats
Mean ("centre") of the distribution.
scale : float or array_like of floats
Standard deviation (spread or "width") of the distribution. Must be
non-negative.
size : int or tuple of ints, optional
Output shape. If the given shape is, e.g., ``(m, n, k)``, then
``m * n * k`` samples are drawn. If size is ``None`` (default),
a single value is returned if ``loc`` and ``scale`` are both scalars.
Otherwise, ``np.broadcast(loc, scale).size`` samples are drawn.
Returns
-------
out : ndarray or scalar
Drawn samples from the parameterized normal distribution.
See Also
--------
scipy.stats.norm : probability density function, distribution or
cumulative density function, etc.
random.Generator.normal: which should be used for new code.
Notes
-----
The probability density for the Gaussian distribution is
.. math:: p(x) = \frac{1}{\sqrt{ 2 \pi \sigma^2 }}
e^{ - \frac{ (x - \mu)^2 } {2 \sigma^2} },
where :math:`\mu` is the mean and :math:`\sigma` the standard
deviation. The square of the standard deviation, :math:`\sigma^2`,
is called the variance.
The function has its peak at the mean, and its "spread" increases with
the standard deviation (the function reaches 0.607 times its maximum at
:math:`x + \sigma` and :math:`x - \sigma` [2]_). This implies that
normal is more likely to return samples lying close to the mean, rather
than those far away.
References
----------
.. [1] Wikipedia, "Normal distribution",
https://en.wikipedia.org/wiki/Normal_distribution
.. [2] P. R. Peebles Jr., "Central Limit Theorem" in "Probability,
Random Variables and Random Signal Principles", 4th ed., 2001,
pp. 51, 51, 125.
Examples
--------
Draw samples from the distribution:
>>> mu, sigma = 0, 0.1 # mean and standard deviation
>>> s = np.random.normal(mu, sigma, 1000)
Verify the mean and the variance:
>>> abs(mu - np.mean(s))
0.0 # may vary
>>> abs(sigma - np.std(s, ddof=1))
0.1 # may vary
Display the histogram of the samples, along with
the probability density function:
>>> import matplotlib.pyplot as plt
>>> count, bins, ignored = plt.hist(s, 30, density=True)
>>> plt.plot(bins, 1/(sigma * np.sqrt(2 * np.pi)) *
... np.exp( - (bins - mu)**2 / (2 * sigma**2) ),
... linewidth=2, color='r')
>>> plt.show()
Two-by-four array of samples from the normal distribution with
mean 3 and standard deviation 2.5:
>>> np.random.normal(3, 2.5, size=(2, 4))
array([[-4.49401501, 4.00950034, -1.81814867, 7.29718677], # random
[ 0.39924804, 4.68456316, 4.99394529, 4.84057254]]) # random
noncentral_f(dfnum, dfden, nonc, size=None)
Draw samples from the noncentral F distribution.
Samples are drawn from an F distribution with specified parameters,
`dfnum` (degrees of freedom in numerator) and `dfden` (degrees of
freedom in denominator), where both parameters > 1.
`nonc` is the non-centrality parameter.
.. note::
New code should use the
`~numpy.random.Generator.noncentral_f`
method of a `~numpy.random.Generator` instance instead;
please see the :ref:`random-quick-start`.
Parameters
----------
dfnum : float or array_like of floats
Numerator degrees of freedom, must be > 0.
.. versionchanged:: 1.14.0
Earlier NumPy versions required dfnum > 1.
dfden : float or array_like of floats
Denominator degrees of freedom, must be > 0.
nonc : float or array_like of floats
Non-centrality parameter, the sum of the squares of the numerator
means, must be >= 0.
size : int or tuple of ints, optional
Output shape. If the given shape is, e.g., ``(m, n, k)``, then
``m * n * k`` samples are drawn. If size is ``None`` (default),
a single value is returned if ``dfnum``, ``dfden``, and ``nonc``
are all scalars. Otherwise, ``np.broadcast(dfnum, dfden, nonc).size``
samples are drawn.
Returns
-------
out : ndarray or scalar
Drawn samples from the parameterized noncentral Fisher distribution.
See Also
--------
random.Generator.noncentral_f: which should be used for new code.
Notes
-----
When calculating the power of an experiment (power = probability of
rejecting the null hypothesis when a specific alternative is true) the
non-central F statistic becomes important. When the null hypothesis is
true, the F statistic follows a central F distribution. When the null
hypothesis is not true, then it follows a non-central F statistic.
References
----------
.. [1] Weisstein, Eric W. "Noncentral F-Distribution."
From MathWorld--A Wolfram Web Resource.
http://mathworld.wolfram.com/NoncentralF-Distribution.html
.. [2] Wikipedia, "Noncentral F-distribution",
https://en.wikipedia.org/wiki/Noncentral_F-distribution
Examples
--------
In a study, testing for a specific alternative to the null hypothesis
requires use of the Noncentral F distribution. We need to calculate the
area in the tail of the distribution that exceeds the value of the F
distribution for the null hypothesis. We'll plot the two probability
distributions for comparison.
>>> dfnum = 3 # between group deg of freedom
>>> dfden = 20 # within groups degrees of freedom
>>> nonc = 3.0
>>> nc_vals = np.random.noncentral_f(dfnum, dfden, nonc, 1000000)
>>> NF = np.histogram(nc_vals, bins=50, density=True)
>>> c_vals = np.random.f(dfnum, dfden, 1000000)
>>> F = np.histogram(c_vals, bins=50, density=True)
>>> import matplotlib.pyplot as plt
>>> plt.plot(F[1][1:], F[0])
>>> plt.plot(NF[1][1:], NF[0])
>>> plt.show()
noncentral_chisquare(df, nonc, size=None)
Draw samples from a noncentral chi-square distribution.
The noncentral :math:`\chi^2` distribution is a generalization of
the :math:`\chi^2` distribution.
.. note::
New code should use the
`~numpy.random.Generator.noncentral_chisquare`
method of a `~numpy.random.Generator` instance instead;
please see the :ref:`random-quick-start`.
Parameters
----------
df : float or array_like of floats
Degrees of freedom, must be > 0.
.. versionchanged:: 1.10.0
Earlier NumPy versions required dfnum > 1.
nonc : float or array_like of floats
Non-centrality, must be non-negative.
size : int or tuple of ints, optional
Output shape. If the given shape is, e.g., ``(m, n, k)``, then
``m * n * k`` samples are drawn. If size is ``None`` (default),
a single value is returned if ``df`` and ``nonc`` are both scalars.
Otherwise, ``np.broadcast(df, nonc).size`` samples are drawn.
Returns
-------
out : ndarray or scalar
Drawn samples from the parameterized noncentral chi-square distribution.
See Also
--------
random.Generator.noncentral_chisquare: which should be used for new code.
Notes
-----
The probability density function for the noncentral Chi-square
distribution is
.. math:: P(x;df,nonc) = \sum^{\infty}_{i=0}
\frac{e^{-nonc/2}(nonc/2)^{i}}{i!}
P_{Y_{df+2i}}(x),
where :math:`Y_{q}` is the Chi-square with q degrees of freedom.
References
----------
.. [1] Wikipedia, "Noncentral chi-squared distribution"
https://en.wikipedia.org/wiki/Noncentral_chi-squared_distribution
Examples
--------
Draw values from the distribution and plot the histogram
>>> import matplotlib.pyplot as plt
>>> values = plt.hist(np.random.noncentral_chisquare(3, 20, 100000),
... bins=200, density=True)
>>> plt.show()
Draw values from a noncentral chisquare with very small noncentrality,
and compare to a chisquare.
>>> plt.figure()
>>> values = plt.hist(np.random.noncentral_chisquare(3, .0000001, 100000),
... bins=np.arange(0., 25, .1), density=True)
>>> values2 = plt.hist(np.random.chisquare(3, 100000),
... bins=np.arange(0., 25, .1), density=True)
>>> plt.plot(values[1][0:-1], values[0]-values2[0], 'ob')
>>> plt.show()
Demonstrate how large values of non-centrality lead to a more symmetric
distribution.
>>> plt.figure()
>>> values = plt.hist(np.random.noncentral_chisquare(3, 20, 100000),
... bins=200, density=True)
>>> plt.show()
negative_binomial(n, p, size=None)
Draw samples from a negative binomial distribution.
Samples are drawn from a negative binomial distribution with specified
parameters, `n` successes and `p` probability of success where `n`
is > 0 and `p` is in the interval [0, 1].
.. note::
New code should use the
`~numpy.random.Generator.negative_binomial`
method of a `~numpy.random.Generator` instance instead;
please see the :ref:`random-quick-start`.
Parameters
----------
n : float or array_like of floats
Parameter of the distribution, > 0.
p : float or array_like of floats
Parameter of the distribution, >= 0 and <=1.
size : int or tuple of ints, optional
Output shape. If the given shape is, e.g., ``(m, n, k)``, then
``m * n * k`` samples are drawn. If size is ``None`` (default),
a single value is returned if ``n`` and ``p`` are both scalars.
Otherwise, ``np.broadcast(n, p).size`` samples are drawn.
Returns
-------
out : ndarray or scalar
Drawn samples from the parameterized negative binomial distribution,
where each sample is equal to N, the number of failures that
occurred before a total of n successes was reached.
See Also
--------
random.Generator.negative_binomial: which should be used for new code.
Notes
-----
The probability mass function of the negative binomial distribution is
.. math:: P(N;n,p) = \frac{\Gamma(N+n)}{N!\Gamma(n)}p^{n}(1-p)^{N},
where :math:`n` is the number of successes, :math:`p` is the
probability of success, :math:`N+n` is the number of trials, and
:math:`\Gamma` is the gamma function. When :math:`n` is an integer,
:math:`\frac{\Gamma(N+n)}{N!\Gamma(n)} = \binom{N+n-1}{N}`, which is
the more common form of this term in the pmf. The negative
binomial distribution gives the probability of N failures given n
successes, with a success on the last trial.
If one throws a die repeatedly until the third time a "1" appears,
then the probability distribution of the number of non-"1"s that
appear before the third "1" is a negative binomial distribution.
References
----------
.. [1] Weisstein, Eric W. "Negative Binomial Distribution." From
MathWorld--A Wolfram Web Resource.
http://mathworld.wolfram.com/NegativeBinomialDistribution.html
.. [2] Wikipedia, "Negative binomial distribution",
https://en.wikipedia.org/wiki/Negative_binomial_distribution
Examples
--------
Draw samples from the distribution:
A real world example. A company drills wild-cat oil
exploration wells, each with an estimated probability of
success of 0.1. What is the probability of having one success
for each successive well, that is what is the probability of a
single success after drilling 5 wells, after 6 wells, etc.?
>>> s = np.random.negative_binomial(1, 0.1, 100000)
>>> for i in range(1, 11): # doctest: +SKIP
... probability = sum(s>> mean = [0, 0]
>>> cov = [[1, 0], [0, 100]] # diagonal covariance
Diagonal covariance means that points are oriented along x or y-axis:
>>> import matplotlib.pyplot as plt
>>> x, y = np.random.multivariate_normal(mean, cov, 5000).T
>>> plt.plot(x, y, 'x')
>>> plt.axis('equal')
>>> plt.show()
Note that the covariance matrix must be positive semidefinite (a.k.a.
nonnegative-definite). Otherwise, the behavior of this method is
undefined and backwards compatibility is not guaranteed.
References
----------
.. [1] Papoulis, A., "Probability, Random Variables, and Stochastic
Processes," 3rd ed., New York: McGraw-Hill, 1991.
.. [2] Duda, R. O., Hart, P. E., and Stork, D. G., "Pattern
Classification," 2nd ed., New York: Wiley, 2001.
Examples
--------
>>> mean = (1, 2)
>>> cov = [[1, 0], [0, 1]]
>>> x = np.random.multivariate_normal(mean, cov, (3, 3))
>>> x.shape
(3, 3, 2)
Here we generate 800 samples from the bivariate normal distribution
with mean [0, 0] and covariance matrix [[6, -3], [-3, 3.5]]. The
expected variances of the first and second components of the sample
are 6 and 3.5, respectively, and the expected correlation
coefficient is -3/sqrt(6*3.5) ≈ -0.65465.
>>> cov = np.array([[6, -3], [-3, 3.5]])
>>> pts = np.random.multivariate_normal([0, 0], cov, size=800)
Check that the mean, covariance, and correlation coefficient of the
sample are close to the expected values:
>>> pts.mean(axis=0)
array([ 0.0326911 , -0.01280782]) # may vary
>>> np.cov(pts.T)
array([[ 5.96202397, -2.85602287],
[-2.85602287, 3.47613949]]) # may vary
>>> np.corrcoef(pts.T)[0, 1]
-0.6273591314603949 # may vary
We can visualize this data with a scatter plot. The orientation
of the point cloud illustrates the negative correlation of the
components of this sample.
>>> import matplotlib.pyplot as plt
>>> plt.plot(pts[:, 0], pts[:, 1], '.', alpha=0.5)
>>> plt.axis('equal')
>>> plt.grid()
>>> plt.show()
multinomial(n, pvals, size=None)
Draw samples from a multinomial distribution.
The multinomial distribution is a multivariate generalization of the
binomial distribution. Take an experiment with one of ``p``
possible outcomes. An example of such an experiment is throwing a dice,
where the outcome can be 1 through 6. Each sample drawn from the
distribution represents `n` such experiments. Its values,
``X_i = [X_0, X_1, ..., X_p]``, represent the number of times the
outcome was ``i``.
.. note::
New code should use the `~numpy.random.Generator.multinomial`
method of a `~numpy.random.Generator` instance instead;
please see the :ref:`random-quick-start`.
Parameters
----------
n : int
Number of experiments.
pvals : sequence of floats, length p
Probabilities of each of the ``p`` different outcomes. These
must sum to 1 (however, the last element is always assumed to
account for the remaining probability, as long as
``sum(pvals[:-1]) <= 1)``.
size : int or tuple of ints, optional
Output shape. If the given shape is, e.g., ``(m, n, k)``, then
``m * n * k`` samples are drawn. Default is None, in which case a
single value is returned.
Returns
-------
out : ndarray
The drawn samples, of shape *size*, if that was provided. If not,
the shape is ``(N,)``.
In other words, each entry ``out[i,j,...,:]`` is an N-dimensional
value drawn from the distribution.
See Also
--------
random.Generator.multinomial: which should be used for new code.
Examples
--------
Throw a dice 20 times:
>>> np.random.multinomial(20, [1/6.]*6, size=1)
array([[4, 1, 7, 5, 2, 1]]) # random
It landed 4 times on 1, once on 2, etc.
Now, throw the dice 20 times, and 20 times again:
>>> np.random.multinomial(20, [1/6.]*6, size=2)
array([[3, 4, 3, 3, 4, 3], # random
[2, 4, 3, 4, 0, 7]])
For the first run, we threw 3 times 1, 4 times 2, etc. For the second,
we threw 2 times 1, 4 times 2, etc.
A loaded die is more likely to land on number 6:
>>> np.random.multinomial(100, [1/7.]*5 + [2/7.])
array([11, 16, 14, 17, 16, 26]) # random
The probability inputs should be normalized. As an implementation
detail, the value of the last entry is ignored and assumed to take
up any leftover probability mass, but this should not be relied on.
A biased coin which has twice as much weight on one side as on the
other should be sampled like so:
>>> np.random.multinomial(100, [1.0 / 3, 2.0 / 3]) # RIGHT
array([38, 62]) # random
not like:
>>> np.random.multinomial(100, [1.0, 2.0]) # WRONG
Traceback (most recent call last):
ValueError: pvals < 0, pvals > 1 or pvals contains NaNs
logseries(p, size=None)
Draw samples from a logarithmic series distribution.
Samples are drawn from a log series distribution with specified
shape parameter, 0 <= ``p`` < 1.
.. note::
New code should use the `~numpy.random.Generator.logseries`
method of a `~numpy.random.Generator` instance instead;
please see the :ref:`random-quick-start`.
Parameters
----------
p : float or array_like of floats
Shape parameter for the distribution. Must be in the range [0, 1).
size : int or tuple of ints, optional
Output shape. If the given shape is, e.g., ``(m, n, k)``, then
``m * n * k`` samples are drawn. If size is ``None`` (default),
a single value is returned if ``p`` is a scalar. Otherwise,
``np.array(p).size`` samples are drawn.
Returns
-------
out : ndarray or scalar
Drawn samples from the parameterized logarithmic series distribution.
See Also
--------
scipy.stats.logser : probability density function, distribution or
cumulative density function, etc.
random.Generator.logseries: which should be used for new code.
Notes
-----
The probability density for the Log Series distribution is
.. math:: P(k) = \frac{-p^k}{k \ln(1-p)},
where p = probability.
The log series distribution is frequently used to represent species
richness and occurrence, first proposed by Fisher, Corbet, and
Williams in 1943 [2]. It may also be used to model the numbers of
occupants seen in cars [3].
References
----------
.. [1] Buzas, Martin A.; Culver, Stephen J., Understanding regional
species diversity through the log series distribution of
occurrences: BIODIVERSITY RESEARCH Diversity & Distributions,
Volume 5, Number 5, September 1999 , pp. 187-195(9).
.. [2] Fisher, R.A,, A.S. Corbet, and C.B. Williams. 1943. The
relation between the number of species and the number of
individuals in a random sample of an animal population.
Journal of Animal Ecology, 12:42-58.
.. [3] D. J. Hand, F. Daly, D. Lunn, E. Ostrowski, A Handbook of Small
Data Sets, CRC Press, 1994.
.. [4] Wikipedia, "Logarithmic distribution",
https://en.wikipedia.org/wiki/Logarithmic_distribution
Examples
--------
Draw samples from the distribution:
>>> a = .6
>>> s = np.random.logseries(a, 10000)
>>> import matplotlib.pyplot as plt
>>> count, bins, ignored = plt.hist(s)
# plot against distribution
>>> def logseries(k, p):
... return -p**k/(k*np.log(1-p))
>>> plt.plot(bins, logseries(bins, a)*count.max()/
... logseries(bins, a).max(), 'r')
>>> plt.show()
lognormal(mean=0.0, sigma=1.0, size=None)
Draw samples from a log-normal distribution.
Draw samples from a log-normal distribution with specified mean,
standard deviation, and array shape. Note that the mean and standard
deviation are not the values for the distribution itself, but of the
underlying normal distribution it is derived from.
.. note::
New code should use the `~numpy.random.Generator.lognormal`
method of a `~numpy.random.Generator` instance instead;
please see the :ref:`random-quick-start`.
Parameters
----------
mean : float or array_like of floats, optional
Mean value of the underlying normal distribution. Default is 0.
sigma : float or array_like of floats, optional
Standard deviation of the underlying normal distribution. Must be
non-negative. Default is 1.
size : int or tuple of ints, optional
Output shape. If the given shape is, e.g., ``(m, n, k)``, then
``m * n * k`` samples are drawn. If size is ``None`` (default),
a single value is returned if ``mean`` and ``sigma`` are both scalars.
Otherwise, ``np.broadcast(mean, sigma).size`` samples are drawn.
Returns
-------
out : ndarray or scalar
Drawn samples from the parameterized log-normal distribution.
See Also
--------
scipy.stats.lognorm : probability density function, distribution,
cumulative density function, etc.
random.Generator.lognormal: which should be used for new code.
Notes
-----
A variable `x` has a log-normal distribution if `log(x)` is normally
distributed. The probability density function for the log-normal
distribution is:
.. math:: p(x) = \frac{1}{\sigma x \sqrt{2\pi}}
e^{(-\frac{(ln(x)-\mu)^2}{2\sigma^2})}
where :math:`\mu` is the mean and :math:`\sigma` is the standard
deviation of the normally distributed logarithm of the variable.
A log-normal distribution results if a random variable is the *product*
of a large number of independent, identically-distributed variables in
the same way that a normal distribution results if the variable is the
*sum* of a large number of independent, identically-distributed
variables.
References
----------
.. [1] Limpert, E., Stahel, W. A., and Abbt, M., "Log-normal
Distributions across the Sciences: Keys and Clues,"
BioScience, Vol. 51, No. 5, May, 2001.
https://stat.ethz.ch/~stahel/lognormal/bioscience.pdf
.. [2] Reiss, R.D. and Thomas, M., "Statistical Analysis of Extreme
Values," Basel: Birkhauser Verlag, 2001, pp. 31-32.
Examples
--------
Draw samples from the distribution:
>>> mu, sigma = 3., 1. # mean and standard deviation
>>> s = np.random.lognormal(mu, sigma, 1000)
Display the histogram of the samples, along with
the probability density function:
>>> import matplotlib.pyplot as plt
>>> count, bins, ignored = plt.hist(s, 100, density=True, align='mid')
>>> x = np.linspace(min(bins), max(bins), 10000)
>>> pdf = (np.exp(-(np.log(x) - mu)**2 / (2 * sigma**2))
... / (x * sigma * np.sqrt(2 * np.pi)))
>>> plt.plot(x, pdf, linewidth=2, color='r')
>>> plt.axis('tight')
>>> plt.show()
Demonstrate that taking the products of random samples from a uniform
distribution can be fit well by a log-normal probability density
function.
>>> # Generate a thousand samples: each is the product of 100 random
>>> # values, drawn from a normal distribution.
>>> b = []
>>> for i in range(1000):
... a = 10. + np.random.standard_normal(100)
... b.append(np.prod(a))
>>> b = np.array(b) / np.min(b) # scale values to be positive
>>> count, bins, ignored = plt.hist(b, 100, density=True, align='mid')
>>> sigma = np.std(np.log(b))
>>> mu = np.mean(np.log(b))
>>> x = np.linspace(min(bins), max(bins), 10000)
>>> pdf = (np.exp(-(np.log(x) - mu)**2 / (2 * sigma**2))
... / (x * sigma * np.sqrt(2 * np.pi)))
>>> plt.plot(x, pdf, color='r', linewidth=2)
>>> plt.show()
logistic(loc=0.0, scale=1.0, size=None)
Draw samples from a logistic distribution.
Samples are drawn from a logistic distribution with specified
parameters, loc (location or mean, also median), and scale (>0).
.. note::
New code should use the `~numpy.random.Generator.logistic`
method of a `~numpy.random.Generator` instance instead;
please see the :ref:`random-quick-start`.
Parameters
----------
loc : float or array_like of floats, optional
Parameter of the distribution. Default is 0.
scale : float or array_like of floats, optional
Parameter of the distribution. Must be non-negative.
Default is 1.
size : int or tuple of ints, optional
Output shape. If the given shape is, e.g., ``(m, n, k)``, then
``m * n * k`` samples are drawn. If size is ``None`` (default),
a single value is returned if ``loc`` and ``scale`` are both scalars.
Otherwise, ``np.broadcast(loc, scale).size`` samples are drawn.
Returns
-------
out : ndarray or scalar
Drawn samples from the parameterized logistic distribution.
See Also
--------
scipy.stats.logistic : probability density function, distribution or
cumulative density function, etc.
random.Generator.logistic: which should be used for new code.
Notes
-----
The probability density for the Logistic distribution is
.. math:: P(x) = P(x) = \frac{e^{-(x-\mu)/s}}{s(1+e^{-(x-\mu)/s})^2},
where :math:`\mu` = location and :math:`s` = scale.
The Logistic distribution is used in Extreme Value problems where it
can act as a mixture of Gumbel distributions, in Epidemiology, and by
the World Chess Federation (FIDE) where it is used in the Elo ranking
system, assuming the performance of each player is a logistically
distributed random variable.
References
----------
.. [1] Reiss, R.-D. and Thomas M. (2001), "Statistical Analysis of
Extreme Values, from Insurance, Finance, Hydrology and Other
Fields," Birkhauser Verlag, Basel, pp 132-133.
.. [2] Weisstein, Eric W. "Logistic Distribution." From
MathWorld--A Wolfram Web Resource.
http://mathworld.wolfram.com/LogisticDistribution.html
.. [3] Wikipedia, "Logistic-distribution",
https://en.wikipedia.org/wiki/Logistic_distribution
Examples
--------
Draw samples from the distribution:
>>> loc, scale = 10, 1
>>> s = np.random.logistic(loc, scale, 10000)
>>> import matplotlib.pyplot as plt
>>> count, bins, ignored = plt.hist(s, bins=50)
# plot against distribution
>>> def logist(x, loc, scale):
... return np.exp((loc-x)/scale)/(scale*(1+np.exp((loc-x)/scale))**2)
>>> lgst_val = logist(bins, loc, scale)
>>> plt.plot(bins, lgst_val * count.max() / lgst_val.max())
>>> plt.show()
hypergeometric(ngood, nbad, nsample, size=None)
Draw samples from a Hypergeometric distribution.
Samples are drawn from a hypergeometric distribution with specified
parameters, `ngood` (ways to make a good selection), `nbad` (ways to make
a bad selection), and `nsample` (number of items sampled, which is less
than or equal to the sum ``ngood + nbad``).
.. note::
New code should use the
`~numpy.random.Generator.hypergeometric`
method of a `~numpy.random.Generator` instance instead;
please see the :ref:`random-quick-start`.
Parameters
----------
ngood : int or array_like of ints
Number of ways to make a good selection. Must be nonnegative.
nbad : int or array_like of ints
Number of ways to make a bad selection. Must be nonnegative.
nsample : int or array_like of ints
Number of items sampled. Must be at least 1 and at most
``ngood + nbad``.
size : int or tuple of ints, optional
Output shape. If the given shape is, e.g., ``(m, n, k)``, then
``m * n * k`` samples are drawn. If size is ``None`` (default),
a single value is returned if `ngood`, `nbad`, and `nsample`
are all scalars. Otherwise, ``np.broadcast(ngood, nbad, nsample).size``
samples are drawn.
Returns
-------
out : ndarray or scalar
Drawn samples from the parameterized hypergeometric distribution. Each
sample is the number of good items within a randomly selected subset of
size `nsample` taken from a set of `ngood` good items and `nbad` bad items.
See Also
--------
scipy.stats.hypergeom : probability density function, distribution or
cumulative density function, etc.
random.Generator.hypergeometric: which should be used for new code.
Notes
-----
The probability density for the Hypergeometric distribution is
.. math:: P(x) = \frac{\binom{g}{x}\binom{b}{n-x}}{\binom{g+b}{n}},
where :math:`0 \le x \le n` and :math:`n-b \le x \le g`
for P(x) the probability of ``x`` good results in the drawn sample,
g = `ngood`, b = `nbad`, and n = `nsample`.
Consider an urn with black and white marbles in it, `ngood` of them
are black and `nbad` are white. If you draw `nsample` balls without
replacement, then the hypergeometric distribution describes the
distribution of black balls in the drawn sample.
Note that this distribution is very similar to the binomial
distribution, except that in this case, samples are drawn without
replacement, whereas in the Binomial case samples are drawn with
replacement (or the sample space is infinite). As the sample space
becomes large, this distribution approaches the binomial.
References
----------
.. [1] Lentner, Marvin, "Elementary Applied Statistics", Bogden
and Quigley, 1972.
.. [2] Weisstein, Eric W. "Hypergeometric Distribution." From
MathWorld--A Wolfram Web Resource.
http://mathworld.wolfram.com/HypergeometricDistribution.html
.. [3] Wikipedia, "Hypergeometric distribution",
https://en.wikipedia.org/wiki/Hypergeometric_distribution
Examples
--------
Draw samples from the distribution:
>>> ngood, nbad, nsamp = 100, 2, 10
# number of good, number of bad, and number of samples
>>> s = np.random.hypergeometric(ngood, nbad, nsamp, 1000)
>>> from matplotlib.pyplot import hist
>>> hist(s)
# note that it is very unlikely to grab both bad items
Suppose you have an urn with 15 white and 15 black marbles.
If you pull 15 marbles at random, how likely is it that
12 or more of them are one color?
>>> s = np.random.hypergeometric(15, 15, 15, 100000)
>>> sum(s>=12)/100000. + sum(s<=3)/100000.
# answer = 0.003 ... pretty unlikely!
gumbel(loc=0.0, scale=1.0, size=None)
Draw samples from a Gumbel distribution.
Draw samples from a Gumbel distribution with specified location and
scale. For more information on the Gumbel distribution, see
Notes and References below.
.. note::
New code should use the `~numpy.random.Generator.gumbel`
method of a `~numpy.random.Generator` instance instead;
please see the :ref:`random-quick-start`.
Parameters
----------
loc : float or array_like of floats, optional
The location of the mode of the distribution. Default is 0.
scale : float or array_like of floats, optional
The scale parameter of the distribution. Default is 1. Must be non-
negative.
size : int or tuple of ints, optional
Output shape. If the given shape is, e.g., ``(m, n, k)``, then
``m * n * k`` samples are drawn. If size is ``None`` (default),
a single value is returned if ``loc`` and ``scale`` are both scalars.
Otherwise, ``np.broadcast(loc, scale).size`` samples are drawn.
Returns
-------
out : ndarray or scalar
Drawn samples from the parameterized Gumbel distribution.
See Also
--------
scipy.stats.gumbel_l
scipy.stats.gumbel_r
scipy.stats.genextreme
weibull
random.Generator.gumbel: which should be used for new code.
Notes
-----
The Gumbel (or Smallest Extreme Value (SEV) or the Smallest Extreme
Value Type I) distribution is one of a class of Generalized Extreme
Value (GEV) distributions used in modeling extreme value problems.
The Gumbel is a special case of the Extreme Value Type I distribution
for maximums from distributions with "exponential-like" tails.
The probability density for the Gumbel distribution is
.. math:: p(x) = \frac{e^{-(x - \mu)/ \beta}}{\beta} e^{ -e^{-(x - \mu)/
\beta}},
where :math:`\mu` is the mode, a location parameter, and
:math:`\beta` is the scale parameter.
The Gumbel (named for German mathematician Emil Julius Gumbel) was used
very early in the hydrology literature, for modeling the occurrence of
flood events. It is also used for modeling maximum wind speed and
rainfall rates. It is a "fat-tailed" distribution - the probability of
an event in the tail of the distribution is larger than if one used a
Gaussian, hence the surprisingly frequent occurrence of 100-year
floods. Floods were initially modeled as a Gaussian process, which
underestimated the frequency of extreme events.
It is one of a class of extreme value distributions, the Generalized
Extreme Value (GEV) distributions, which also includes the Weibull and
Frechet.
The function has a mean of :math:`\mu + 0.57721\beta` and a variance
of :math:`\frac{\pi^2}{6}\beta^2`.
References
----------
.. [1] Gumbel, E. J., "Statistics of Extremes,"
New York: Columbia University Press, 1958.
.. [2] Reiss, R.-D. and Thomas, M., "Statistical Analysis of Extreme
Values from Insurance, Finance, Hydrology and Other Fields,"
Basel: Birkhauser Verlag, 2001.
Examples
--------
Draw samples from the distribution:
>>> mu, beta = 0, 0.1 # location and scale
>>> s = np.random.gumbel(mu, beta, 1000)
Display the histogram of the samples, along with
the probability density function:
>>> import matplotlib.pyplot as plt
>>> count, bins, ignored = plt.hist(s, 30, density=True)
>>> plt.plot(bins, (1/beta)*np.exp(-(bins - mu)/beta)
... * np.exp( -np.exp( -(bins - mu) /beta) ),
... linewidth=2, color='r')
>>> plt.show()
Show how an extreme value distribution can arise from a Gaussian process
and compare to a Gaussian:
>>> means = []
>>> maxima = []
>>> for i in range(0,1000) :
... a = np.random.normal(mu, beta, 1000)
... means.append(a.mean())
... maxima.append(a.max())
>>> count, bins, ignored = plt.hist(maxima, 30, density=True)
>>> beta = np.std(maxima) * np.sqrt(6) / np.pi
>>> mu = np.mean(maxima) - 0.57721*beta
>>> plt.plot(bins, (1/beta)*np.exp(-(bins - mu)/beta)
... * np.exp(-np.exp(-(bins - mu)/beta)),
... linewidth=2, color='r')
>>> plt.plot(bins, 1/(beta * np.sqrt(2 * np.pi))
... * np.exp(-(bins - mu)**2 / (2 * beta**2)),
... linewidth=2, color='g')
>>> plt.show()
geometric(p, size=None)
Draw samples from the geometric distribution.
Bernoulli trials are experiments with one of two outcomes:
success or failure (an example of such an experiment is flipping
a coin). The geometric distribution models the number of trials
that must be run in order to achieve success. It is therefore
supported on the positive integers, ``k = 1, 2, ...``.
The probability mass function of the geometric distribution is
.. math:: f(k) = (1 - p)^{k - 1} p
where `p` is the probability of success of an individual trial.
.. note::
New code should use the `~numpy.random.Generator.geometric`
method of a `~numpy.random.Generator` instance instead;
please see the :ref:`random-quick-start`.
Parameters
----------
p : float or array_like of floats
The probability of success of an individual trial.
size : int or tuple of ints, optional
Output shape. If the given shape is, e.g., ``(m, n, k)``, then
``m * n * k`` samples are drawn. If size is ``None`` (default),
a single value is returned if ``p`` is a scalar. Otherwise,
``np.array(p).size`` samples are drawn.
Returns
-------
out : ndarray or scalar
Drawn samples from the parameterized geometric distribution.
See Also
--------
random.Generator.geometric: which should be used for new code.
Examples
--------
Draw ten thousand values from the geometric distribution,
with the probability of an individual success equal to 0.35:
>>> z = np.random.geometric(p=0.35, size=10000)
How many trials succeeded after a single run?
>>> (z == 1).sum() / 10000.
0.34889999999999999 #random
gamma(shape, scale=1.0, size=None)
Draw samples from a Gamma distribution.
Samples are drawn from a Gamma distribution with specified parameters,
`shape` (sometimes designated "k") and `scale` (sometimes designated
"theta"), where both parameters are > 0.
.. note::
New code should use the `~numpy.random.Generator.gamma`
method of a `~numpy.random.Generator` instance instead;
please see the :ref:`random-quick-start`.
Parameters
----------
shape : float or array_like of floats
The shape of the gamma distribution. Must be non-negative.
scale : float or array_like of floats, optional
The scale of the gamma distribution. Must be non-negative.
Default is equal to 1.
size : int or tuple of ints, optional
Output shape. If the given shape is, e.g., ``(m, n, k)``, then
``m * n * k`` samples are drawn. If size is ``None`` (default),
a single value is returned if ``shape`` and ``scale`` are both scalars.
Otherwise, ``np.broadcast(shape, scale).size`` samples are drawn.
Returns
-------
out : ndarray or scalar
Drawn samples from the parameterized gamma distribution.
See Also
--------
scipy.stats.gamma : probability density function, distribution or
cumulative density function, etc.
random.Generator.gamma: which should be used for new code.
Notes
-----
The probability density for the Gamma distribution is
.. math:: p(x) = x^{k-1}\frac{e^{-x/\theta}}{\theta^k\Gamma(k)},
where :math:`k` is the shape and :math:`\theta` the scale,
and :math:`\Gamma` is the Gamma function.
The Gamma distribution is often used to model the times to failure of
electronic components, and arises naturally in processes for which the
waiting times between Poisson distributed events are relevant.
References
----------
.. [1] Weisstein, Eric W. "Gamma Distribution." From MathWorld--A
Wolfram Web Resource.
http://mathworld.wolfram.com/GammaDistribution.html
.. [2] Wikipedia, "Gamma distribution",
https://en.wikipedia.org/wiki/Gamma_distribution
Examples
--------
Draw samples from the distribution:
>>> shape, scale = 2., 2. # mean=4, std=2*sqrt(2)
>>> s = np.random.gamma(shape, scale, 1000)
Display the histogram of the samples, along with
the probability density function:
>>> import matplotlib.pyplot as plt
>>> import scipy.special as sps # doctest: +SKIP
>>> count, bins, ignored = plt.hist(s, 50, density=True)
>>> y = bins**(shape-1)*(np.exp(-bins/scale) / # doctest: +SKIP
... (sps.gamma(shape)*scale**shape))
>>> plt.plot(bins, y, linewidth=2, color='r') # doctest: +SKIP
>>> plt.show()
f(dfnum, dfden, size=None)
Draw samples from an F distribution.
Samples are drawn from an F distribution with specified parameters,
`dfnum` (degrees of freedom in numerator) and `dfden` (degrees of
freedom in denominator), where both parameters must be greater than
zero.
The random variate of the F distribution (also known as the
Fisher distribution) is a continuous probability distribution
that arises in ANOVA tests, and is the ratio of two chi-square
variates.
.. note::
New code should use the `~numpy.random.Generator.f`
method of a `~numpy.random.Generator` instance instead;
please see the :ref:`random-quick-start`.
Parameters
----------
dfnum : float or array_like of floats
Degrees of freedom in numerator, must be > 0.
dfden : float or array_like of float
Degrees of freedom in denominator, must be > 0.
size : int or tuple of ints, optional
Output shape. If the given shape is, e.g., ``(m, n, k)``, then
``m * n * k`` samples are drawn. If size is ``None`` (default),
a single value is returned if ``dfnum`` and ``dfden`` are both scalars.
Otherwise, ``np.broadcast(dfnum, dfden).size`` samples are drawn.
Returns
-------
out : ndarray or scalar
Drawn samples from the parameterized Fisher distribution.
See Also
--------
scipy.stats.f : probability density function, distribution or
cumulative density function, etc.
random.Generator.f: which should be used for new code.
Notes
-----
The F statistic is used to compare in-group variances to between-group
variances. Calculating the distribution depends on the sampling, and
so it is a function of the respective degrees of freedom in the
problem. The variable `dfnum` is the number of samples minus one, the
between-groups degrees of freedom, while `dfden` is the within-groups
degrees of freedom, the sum of the number of samples in each group
minus the number of groups.
References
----------
.. [1] Glantz, Stanton A. "Primer of Biostatistics.", McGraw-Hill,
Fifth Edition, 2002.
.. [2] Wikipedia, "F-distribution",
https://en.wikipedia.org/wiki/F-distribution
Examples
--------
An example from Glantz[1], pp 47-40:
Two groups, children of diabetics (25 people) and children from people
without diabetes (25 controls). Fasting blood glucose was measured,
case group had a mean value of 86.1, controls had a mean value of
82.2. Standard deviations were 2.09 and 2.49 respectively. Are these
data consistent with the null hypothesis that the parents diabetic
status does not affect their children's blood glucose levels?
Calculating the F statistic from the data gives a value of 36.01.
Draw samples from the distribution:
>>> dfnum = 1. # between group degrees of freedom
>>> dfden = 48. # within groups degrees of freedom
>>> s = np.random.f(dfnum, dfden, 1000)
The lower bound for the top 1% of the samples is :
>>> np.sort(s)[-10]
7.61988120985 # random
So there is about a 1% chance that the F statistic will exceed 7.62,
the measured value is 36, so the null hypothesis is rejected at the 1%
level.
exponential(scale=1.0, size=None)
Draw samples from an exponential distribution.
Its probability density function is
.. math:: f(x; \frac{1}{\beta}) = \frac{1}{\beta} \exp(-\frac{x}{\beta}),
for ``x > 0`` and 0 elsewhere. :math:`\beta` is the scale parameter,
which is the inverse of the rate parameter :math:`\lambda = 1/\beta`.
The rate parameter is an alternative, widely used parameterization
of the exponential distribution [3]_.
The exponential distribution is a continuous analogue of the
geometric distribution. It describes many common situations, such as
the size of raindrops measured over many rainstorms [1]_, or the time
between page requests to Wikipedia [2]_.
.. note::
New code should use the `~numpy.random.Generator.exponential`
method of a `~numpy.random.Generator` instance instead;
please see the :ref:`random-quick-start`.
Parameters
----------
scale : float or array_like of floats
The scale parameter, :math:`\beta = 1/\lambda`. Must be
non-negative.
size : int or tuple of ints, optional
Output shape. If the given shape is, e.g., ``(m, n, k)``, then
``m * n * k`` samples are drawn. If size is ``None`` (default),
a single value is returned if ``scale`` is a scalar. Otherwise,
``np.array(scale).size`` samples are drawn.
Returns
-------
out : ndarray or scalar
Drawn samples from the parameterized exponential distribution.
Examples
--------
A real world example: Assume a company has 10000 customer support
agents and the average time between customer calls is 4 minutes.
>>> n = 10000
>>> time_between_calls = np.random.default_rng().exponential(scale=4, size=n)
What is the probability that a customer will call in the next
4 to 5 minutes?
>>> x = ((time_between_calls < 5).sum())/n
>>> y = ((time_between_calls < 4).sum())/n
>>> x-y
0.08 # may vary
See Also
--------
random.Generator.exponential: which should be used for new code.
References
----------
.. [1] Peyton Z. Peebles Jr., "Probability, Random Variables and
Random Signal Principles", 4th ed, 2001, p. 57.
.. [2] Wikipedia, "Poisson process",
https://en.wikipedia.org/wiki/Poisson_process
.. [3] Wikipedia, "Exponential distribution",
https://en.wikipedia.org/wiki/Exponential_distribution
choice(a, size=None, replace=True, p=None)
Generates a random sample from a given 1-D array
.. versionadded:: 1.7.0
.. note::
New code should use the `~numpy.random.Generator.choice`
method of a `~numpy.random.Generator` instance instead;
please see the :ref:`random-quick-start`.
Parameters
----------
a : 1-D array-like or int
If an ndarray, a random sample is generated from its elements.
If an int, the random sample is generated as if it were ``np.arange(a)``
size : int or tuple of ints, optional
Output shape. If the given shape is, e.g., ``(m, n, k)``, then
``m * n * k`` samples are drawn. Default is None, in which case a
single value is returned.
replace : boolean, optional
Whether the sample is with or without replacement. Default is True,
meaning that a value of ``a`` can be selected multiple times.
p : 1-D array-like, optional
The probabilities associated with each entry in a.
If not given, the sample assumes a uniform distribution over all
entries in ``a``.
Returns
-------
samples : single item or ndarray
The generated random samples
Raises
------
ValueError
If a is an int and less than zero, if a or p are not 1-dimensional,
if a is an array-like of size 0, if p is not a vector of
probabilities, if a and p have different lengths, or if
replace=False and the sample size is greater than the population
size
See Also
--------
randint, shuffle, permutation
random.Generator.choice: which should be used in new code
Notes
-----
Setting user-specified probabilities through ``p`` uses a more general but less
efficient sampler than the default. The general sampler produces a different sample
than the optimized sampler even if each element of ``p`` is 1 / len(a).
Sampling random rows from a 2-D array is not possible with this function,
but is possible with `Generator.choice` through its ``axis`` keyword.
Examples
--------
Generate a uniform random sample from np.arange(5) of size 3:
>>> np.random.choice(5, 3)
array([0, 3, 4]) # random
>>> #This is equivalent to np.random.randint(0,5,3)
Generate a non-uniform random sample from np.arange(5) of size 3:
>>> np.random.choice(5, 3, p=[0.1, 0, 0.3, 0.6, 0])
array([3, 3, 0]) # random
Generate a uniform random sample from np.arange(5) of size 3 without
replacement:
>>> np.random.choice(5, 3, replace=False)
array([3,1,0]) # random
>>> #This is equivalent to np.random.permutation(np.arange(5))[:3]
Generate a non-uniform random sample from np.arange(5) of size
3 without replacement:
>>> np.random.choice(5, 3, replace=False, p=[0.1, 0, 0.3, 0.6, 0])
array([2, 3, 0]) # random
Any of the above can be repeated with an arbitrary array-like
instead of just integers. For instance:
>>> aa_milne_arr = ['pooh', 'rabbit', 'piglet', 'Christopher']
>>> np.random.choice(aa_milne_arr, 5, p=[0.5, 0.1, 0.1, 0.3])
array(['pooh', 'pooh', 'pooh', 'Christopher', 'piglet'], # random
dtype=' 0.
size : int or tuple of ints, optional
Output shape. If the given shape is, e.g., ``(m, n, k)``, then
``m * n * k`` samples are drawn. If size is ``None`` (default),
a single value is returned if ``df`` is a scalar. Otherwise,
``np.array(df).size`` samples are drawn.
Returns
-------
out : ndarray or scalar
Drawn samples from the parameterized chi-square distribution.
Raises
------
ValueError
When `df` <= 0 or when an inappropriate `size` (e.g. ``size=-1``)
is given.
See Also
--------
random.Generator.chisquare: which should be used for new code.
Notes
-----
The variable obtained by summing the squares of `df` independent,
standard normally distributed random variables:
.. math:: Q = \sum_{i=0}^{\mathtt{df}} X^2_i
is chi-square distributed, denoted
.. math:: Q \sim \chi^2_k.
The probability density function of the chi-squared distribution is
.. math:: p(x) = \frac{(1/2)^{k/2}}{\Gamma(k/2)}
x^{k/2 - 1} e^{-x/2},
where :math:`\Gamma` is the gamma function,
.. math:: \Gamma(x) = \int_0^{-\infty} t^{x - 1} e^{-t} dt.
References
----------
.. [1] NIST "Engineering Statistics Handbook"
https://www.itl.nist.gov/div898/handbook/eda/section3/eda3666.htm
Examples
--------
>>> np.random.chisquare(2,4)
array([ 1.89920014, 9.00867716, 3.13710533, 5.62318272]) # random
bytes(length)
Return random bytes.
.. note::
New code should use the `~numpy.random.Generator.bytes`
method of a `~numpy.random.Generator` instance instead;
please see the :ref:`random-quick-start`.
Parameters
----------
length : int
Number of random bytes.
Returns
-------
out : bytes
String of length `length`.
See Also
--------
random.Generator.bytes: which should be used for new code.
Examples
--------
>>> np.random.bytes(10)
b' eh\x85\x022SZ\xbf\xa4' #random
binomial(n, p, size=None)
Draw samples from a binomial distribution.
Samples are drawn from a binomial distribution with specified
parameters, n trials and p probability of success where
n an integer >= 0 and p is in the interval [0,1]. (n may be
input as a float, but it is truncated to an integer in use)
.. note::
New code should use the `~numpy.random.Generator.binomial`
method of a `~numpy.random.Generator` instance instead;
please see the :ref:`random-quick-start`.
Parameters
----------
n : int or array_like of ints
Parameter of the distribution, >= 0. Floats are also accepted,
but they will be truncated to integers.
p : float or array_like of floats
Parameter of the distribution, >= 0 and <=1.
size : int or tuple of ints, optional
Output shape. If the given shape is, e.g., ``(m, n, k)``, then
``m * n * k`` samples are drawn. If size is ``None`` (default),
a single value is returned if ``n`` and ``p`` are both scalars.
Otherwise, ``np.broadcast(n, p).size`` samples are drawn.
Returns
-------
out : ndarray or scalar
Drawn samples from the parameterized binomial distribution, where
each sample is equal to the number of successes over the n trials.
See Also
--------
scipy.stats.binom : probability density function, distribution or
cumulative density function, etc.
random.Generator.binomial: which should be used for new code.
Notes
-----
The probability density for the binomial distribution is
.. math:: P(N) = \binom{n}{N}p^N(1-p)^{n-N},
where :math:`n` is the number of trials, :math:`p` is the probability
of success, and :math:`N` is the number of successes.
When estimating the standard error of a proportion in a population by
using a random sample, the normal distribution works well unless the
product p*n <=5, where p = population proportion estimate, and n =
number of samples, in which case the binomial distribution is used
instead. For example, a sample of 15 people shows 4 who are left
handed, and 11 who are right handed. Then p = 4/15 = 27%. 0.27*15 = 4,
so the binomial distribution should be used in this case.
References
----------
.. [1] Dalgaard, Peter, "Introductory Statistics with R",
Springer-Verlag, 2002.
.. [2] Glantz, Stanton A. "Primer of Biostatistics.", McGraw-Hill,
Fifth Edition, 2002.
.. [3] Lentner, Marvin, "Elementary Applied Statistics", Bogden
and Quigley, 1972.
.. [4] Weisstein, Eric W. "Binomial Distribution." From MathWorld--A
Wolfram Web Resource.
http://mathworld.wolfram.com/BinomialDistribution.html
.. [5] Wikipedia, "Binomial distribution",
https://en.wikipedia.org/wiki/Binomial_distribution
Examples
--------
Draw samples from the distribution:
>>> n, p = 10, .5 # number of trials, probability of each trial
>>> s = np.random.binomial(n, p, 1000)
# result of flipping a coin 10 times, tested 1000 times.
A real world example. A company drills 9 wild-cat oil exploration
wells, each with an estimated probability of success of 0.1. All nine
wells fail. What is the probability of that happening?
Let's do 20,000 trials of the model, and count the number that
generate zero positive results.
>>> sum(np.random.binomial(9, 0.1, 20000) == 0)/20000.
# answer = 0.38885, or 38%.
a must be greater than 0 unless no samples are taken 'a' cannot be empty unless no samples are taken Unsupported dtype %r for randint RandomState.standard_gamma (line 1562) RandomState.multivariate_normal (line 4057) RandomState.logseries (line 3968) RandomState.lognormal (line 2973) RandomState.hypergeometric (line 3833) RandomState.geometric (line 3771) RandomState.dirichlet (line 4393) RandomState.chisquare (line 1909)
wald(mean, scale, size=None)
Draw samples from a Wald, or inverse Gaussian, distribution.
As the scale approaches infinity, the distribution becomes more like a
Gaussian. Some references claim that the Wald is an inverse Gaussian
with mean equal to 1, but this is by no means universal.
The inverse Gaussian distribution was first studied in relationship to
Brownian motion. In 1956 M.C.K. Tweedie used the name inverse Gaussian
because there is an inverse relationship between the time to cover a
unit distance and distance covered in unit time.
.. note::
New code should use the `~numpy.random.Generator.wald`
method of a `~numpy.random.Generator` instance instead;
please see the :ref:`random-quick-start`.
Parameters
----------
mean : float or array_like of floats
Distribution mean, must be > 0.
scale : float or array_like of floats
Scale parameter, must be > 0.
size : int or tuple of ints, optional
Output shape. If the given shape is, e.g., ``(m, n, k)``, then
``m * n * k`` samples are drawn. If size is ``None`` (default),
a single value is returned if ``mean`` and ``scale`` are both scalars.
Otherwise, ``np.broadcast(mean, scale).size`` samples are drawn.
Returns
-------
out : ndarray or scalar
Drawn samples from the parameterized Wald distribution.
See Also
--------
random.Generator.wald: which should be used for new code.
Notes
-----
The probability density function for the Wald distribution is
.. math:: P(x;mean,scale) = \sqrt{\frac{scale}{2\pi x^3}}e^
\frac{-scale(x-mean)^2}{2\cdotp mean^2x}
As noted above the inverse Gaussian distribution first arise
from attempts to model Brownian motion. It is also a
competitor to the Weibull for use in reliability modeling and
modeling stock returns and interest rate processes.
References
----------
.. [1] Brighton Webs Ltd., Wald Distribution,
https://web.archive.org/web/20090423014010/http://www.brighton-webs.co.uk:80/distributions/wald.asp
.. [2] Chhikara, Raj S., and Folks, J. Leroy, "The Inverse Gaussian
Distribution: Theory : Methodology, and Applications", CRC Press,
1988.
.. [3] Wikipedia, "Inverse Gaussian distribution"
https://en.wikipedia.org/wiki/Inverse_Gaussian_distribution
Examples
--------
Draw values from the distribution and plot the histogram:
>>> import matplotlib.pyplot as plt
>>> h = plt.hist(np.random.wald(3, 2, 100000), bins=200, density=True)
>>> plt.show()
standard_normal(size=None)
Draw samples from a standard Normal distribution (mean=0, stdev=1).
.. note::
New code should use the
`~numpy.random.Generator.standard_normal`
method of a `~numpy.random.Generator` instance instead;
please see the :ref:`random-quick-start`.
Parameters
----------
size : int or tuple of ints, optional
Output shape. If the given shape is, e.g., ``(m, n, k)``, then
``m * n * k`` samples are drawn. Default is None, in which case a
single value is returned.
Returns
-------
out : float or ndarray
A floating-point array of shape ``size`` of drawn samples, or a
single sample if ``size`` was not specified.
See Also
--------
normal :
Equivalent function with additional ``loc`` and ``scale`` arguments
for setting the mean and standard deviation.
random.Generator.standard_normal: which should be used for new code.
Notes
-----
For random samples from the normal distribution with mean ``mu`` and
standard deviation ``sigma``, use one of::
mu + sigma * np.random.standard_normal(size=...)
np.random.normal(mu, sigma, size=...)
Examples
--------
>>> np.random.standard_normal()
2.1923875335537315 #random
>>> s = np.random.standard_normal(8000)
>>> s
array([ 0.6888893 , 0.78096262, -0.89086505, ..., 0.49876311, # random
-0.38672696, -0.4685006 ]) # random
>>> s.shape
(8000,)
>>> s = np.random.standard_normal(size=(3, 4, 2))
>>> s.shape
(3, 4, 2)
Two-by-four array of samples from the normal distribution with
mean 3 and standard deviation 2.5:
>>> 3 + 2.5 * np.random.standard_normal(size=(2, 4))
array([[-4.49401501, 4.00950034, -1.81814867, 7.29718677], # random
[ 0.39924804, 4.68456316, 4.99394529, 4.84057254]]) # random
standard_gamma(shape, size=None)
Draw samples from a standard Gamma distribution.
Samples are drawn from a Gamma distribution with specified parameters,
shape (sometimes designated "k") and scale=1.
.. note::
New code should use the
`~numpy.random.Generator.standard_gamma`
method of a `~numpy.random.Generator` instance instead;
please see the :ref:`random-quick-start`.
Parameters
----------
shape : float or array_like of floats
Parameter, must be non-negative.
size : int or tuple of ints, optional
Output shape. If the given shape is, e.g., ``(m, n, k)``, then
``m * n * k`` samples are drawn. If size is ``None`` (default),
a single value is returned if ``shape`` is a scalar. Otherwise,
``np.array(shape).size`` samples are drawn.
Returns
-------
out : ndarray or scalar
Drawn samples from the parameterized standard gamma distribution.
See Also
--------
scipy.stats.gamma : probability density function, distribution or
cumulative density function, etc.
random.Generator.standard_gamma: which should be used for new code.
Notes
-----
The probability density for the Gamma distribution is
.. math:: p(x) = x^{k-1}\frac{e^{-x/\theta}}{\theta^k\Gamma(k)},
where :math:`k` is the shape and :math:`\theta` the scale,
and :math:`\Gamma` is the Gamma function.
The Gamma distribution is often used to model the times to failure of
electronic components, and arises naturally in processes for which the
waiting times between Poisson distributed events are relevant.
References
----------
.. [1] Weisstein, Eric W. "Gamma Distribution." From MathWorld--A
Wolfram Web Resource.
http://mathworld.wolfram.com/GammaDistribution.html
.. [2] Wikipedia, "Gamma distribution",
https://en.wikipedia.org/wiki/Gamma_distribution
Examples
--------
Draw samples from the distribution:
>>> shape, scale = 2., 1. # mean and width
>>> s = np.random.standard_gamma(shape, 1000000)
Display the histogram of the samples, along with
the probability density function:
>>> import matplotlib.pyplot as plt
>>> import scipy.special as sps # doctest: +SKIP
>>> count, bins, ignored = plt.hist(s, 50, density=True)
>>> y = bins**(shape-1) * ((np.exp(-bins/scale))/ # doctest: +SKIP
... (sps.gamma(shape) * scale**shape))
>>> plt.plot(bins, y, linewidth=2, color='r') # doctest: +SKIP
>>> plt.show()
standard_exponential(size=None)
Draw samples from the standard exponential distribution.
`standard_exponential` is identical to the exponential distribution
with a scale parameter of 1.
.. note::
New code should use the
`~numpy.random.Generator.standard_exponential`
method of a `~numpy.random.Generator` instance instead;
please see the :ref:`random-quick-start`.
Parameters
----------
size : int or tuple of ints, optional
Output shape. If the given shape is, e.g., ``(m, n, k)``, then
``m * n * k`` samples are drawn. Default is None, in which case a
single value is returned.
Returns
-------
out : float or ndarray
Drawn samples.
See Also
--------
random.Generator.standard_exponential: which should be used for new code.
Examples
--------
Output a 3x8000 array:
>>> n = np.random.standard_exponential((3, 8000))
standard_cauchy(size=None)
Draw samples from a standard Cauchy distribution with mode = 0.
Also known as the Lorentz distribution.
.. note::
New code should use the
`~numpy.random.Generator.standard_cauchy`
method of a `~numpy.random.Generator` instance instead;
please see the :ref:`random-quick-start`.
Parameters
----------
size : int or tuple of ints, optional
Output shape. If the given shape is, e.g., ``(m, n, k)``, then
``m * n * k`` samples are drawn. Default is None, in which case a
single value is returned.
Returns
-------
samples : ndarray or scalar
The drawn samples.
See Also
--------
random.Generator.standard_cauchy: which should be used for new code.
Notes
-----
The probability density function for the full Cauchy distribution is
.. math:: P(x; x_0, \gamma) = \frac{1}{\pi \gamma \bigl[ 1+
(\frac{x-x_0}{\gamma})^2 \bigr] }
and the Standard Cauchy distribution just sets :math:`x_0=0` and
:math:`\gamma=1`
The Cauchy distribution arises in the solution to the driven harmonic
oscillator problem, and also describes spectral line broadening. It
also describes the distribution of values at which a line tilted at
a random angle will cut the x axis.
When studying hypothesis tests that assume normality, seeing how the
tests perform on data from a Cauchy distribution is a good indicator of
their sensitivity to a heavy-tailed distribution, since the Cauchy looks
very much like a Gaussian distribution, but with heavier tails.
References
----------
.. [1] NIST/SEMATECH e-Handbook of Statistical Methods, "Cauchy
Distribution",
https://www.itl.nist.gov/div898/handbook/eda/section3/eda3663.htm
.. [2] Weisstein, Eric W. "Cauchy Distribution." From MathWorld--A
Wolfram Web Resource.
http://mathworld.wolfram.com/CauchyDistribution.html
.. [3] Wikipedia, "Cauchy distribution"
https://en.wikipedia.org/wiki/Cauchy_distribution
Examples
--------
Draw samples and plot the distribution:
>>> import matplotlib.pyplot as plt
>>> s = np.random.standard_cauchy(1000000)
>>> s = s[(s>-25) & (s<25)] # truncate distribution so it plots well
>>> plt.hist(s, bins=100)
>>> plt.show()
shuffle(x)
Modify a sequence in-place by shuffling its contents.
This function only shuffles the array along the first axis of a
multi-dimensional array. The order of sub-arrays is changed but
their contents remains the same.
.. note::
New code should use the `~numpy.random.Generator.shuffle`
method of a `~numpy.random.Generator` instance instead;
please see the :ref:`random-quick-start`.
Parameters
----------
x : ndarray or MutableSequence
The array, list or mutable sequence to be shuffled.
Returns
-------
None
See Also
--------
random.Generator.shuffle: which should be used for new code.
Examples
--------
>>> arr = np.arange(10)
>>> np.random.shuffle(arr)
>>> arr
[1 7 5 2 9 4 3 6 0 8] # random
Multi-dimensional arrays are only shuffled along the first axis:
>>> arr = np.arange(9).reshape((3, 3))
>>> np.random.shuffle(arr)
>>> arr
array([[3, 4, 5], # random
[6, 7, 8],
[0, 1, 2]])
seed(seed=None)
Reseed a legacy MT19937 BitGenerator
Notes
-----
This is a convenience, legacy function.
The best practice is to **not** reseed a BitGenerator, rather to
recreate a new one. This method is here for legacy reasons.
This example demonstrates best practice.
>>> from numpy.random import MT19937
>>> from numpy.random import RandomState, SeedSequence
>>> rs = RandomState(MT19937(SeedSequence(123456789)))
# Later, you want to restart the stream
>>> rs = RandomState(MT19937(SeedSequence(987654321)))
random_sample(size=None)
Return random floats in the half-open interval [0.0, 1.0).
Results are from the "continuous uniform" distribution over the
stated interval. To sample :math:`Unif[a, b), b > a` multiply
the output of `random_sample` by `(b-a)` and add `a`::
(b - a) * random_sample() + a
.. note::
New code should use the `~numpy.random.Generator.random`
method of a `~numpy.random.Generator` instance instead;
please see the :ref:`random-quick-start`.
Parameters
----------
size : int or tuple of ints, optional
Output shape. If the given shape is, e.g., ``(m, n, k)``, then
``m * n * k`` samples are drawn. Default is None, in which case a
single value is returned.
Returns
-------
out : float or ndarray of floats
Array of random floats of shape `size` (unless ``size=None``, in which
case a single float is returned).
See Also
--------
random.Generator.random: which should be used for new code.
Examples
--------
>>> np.random.random_sample()
0.47108547995356098 # random
>>> type(np.random.random_sample())
>>> np.random.random_sample((5,))
array([ 0.30220482, 0.86820401, 0.1654503 , 0.11659149, 0.54323428]) # random
Three-by-two array of random numbers from [-5, 0):
>>> 5 * np.random.random_sample((3, 2)) - 5
array([[-3.99149989, -0.52338984], # random
[-2.99091858, -0.79479508],
[-1.23204345, -1.75224494]])
randn(d0, d1, ..., dn)
Return a sample (or samples) from the "standard normal" distribution.
.. note::
This is a convenience function for users porting code from Matlab,
and wraps `standard_normal`. That function takes a
tuple to specify the size of the output, which is consistent with
other NumPy functions like `numpy.zeros` and `numpy.ones`.
.. note::
New code should use the
`~numpy.random.Generator.standard_normal`
method of a `~numpy.random.Generator` instance instead;
please see the :ref:`random-quick-start`.
If positive int_like arguments are provided, `randn` generates an array
of shape ``(d0, d1, ..., dn)``, filled
with random floats sampled from a univariate "normal" (Gaussian)
distribution of mean 0 and variance 1. A single float randomly sampled
from the distribution is returned if no argument is provided.
Parameters
----------
d0, d1, ..., dn : int, optional
The dimensions of the returned array, must be non-negative.
If no argument is given a single Python float is returned.
Returns
-------
Z : ndarray or float
A ``(d0, d1, ..., dn)``-shaped array of floating-point samples from
the standard normal distribution, or a single such float if
no parameters were supplied.
See Also
--------
standard_normal : Similar, but takes a tuple as its argument.
normal : Also accepts mu and sigma arguments.
random.Generator.standard_normal: which should be used for new code.
Notes
-----
For random samples from the normal distribution with mean ``mu`` and
standard deviation ``sigma``, use::
sigma * np.random.randn(...) + mu
Examples
--------
>>> np.random.randn()
2.1923875335537315 # random
Two-by-four array of samples from the normal distribution with
mean 3 and standard deviation 2.5:
>>> 3 + 2.5 * np.random.randn(2, 4)
array([[-4.49401501, 4.00950034, -1.81814867, 7.29718677], # random
[ 0.39924804, 4.68456316, 4.99394529, 4.84057254]]) # random
rand(d0, d1, ..., dn)
Random values in a given shape.
.. note::
This is a convenience function for users porting code from Matlab,
and wraps `random_sample`. That function takes a
tuple to specify the size of the output, which is consistent with
other NumPy functions like `numpy.zeros` and `numpy.ones`.
Create an array of the given shape and populate it with
random samples from a uniform distribution
over ``[0, 1)``.
Parameters
----------
d0, d1, ..., dn : int, optional
The dimensions of the returned array, must be non-negative.
If no argument is given a single Python float is returned.
Returns
-------
out : ndarray, shape ``(d0, d1, ..., dn)``
Random values.
See Also
--------
random
Examples
--------
>>> np.random.rand(3,2)
array([[ 0.14022471, 0.96360618], #random
[ 0.37601032, 0.25528411], #random
[ 0.49313049, 0.94909878]]) #random
poisson(lam=1.0, size=None)
Draw samples from a Poisson distribution.
The Poisson distribution is the limit of the binomial distribution
for large N.
.. note::
New code should use the `~numpy.random.Generator.poisson`
method of a `~numpy.random.Generator` instance instead;
please see the :ref:`random-quick-start`.
Parameters
----------
lam : float or array_like of floats
Expected number of events occurring in a fixed-time interval,
must be >= 0. A sequence must be broadcastable over the requested
size.
size : int or tuple of ints, optional
Output shape. If the given shape is, e.g., ``(m, n, k)``, then
``m * n * k`` samples are drawn. If size is ``None`` (default),
a single value is returned if ``lam`` is a scalar. Otherwise,
``np.array(lam).size`` samples are drawn.
Returns
-------
out : ndarray or scalar
Drawn samples from the parameterized Poisson distribution.
See Also
--------
random.Generator.poisson: which should be used for new code.
Notes
-----
The Poisson distribution
.. math:: f(k; \lambda)=\frac{\lambda^k e^{-\lambda}}{k!}
For events with an expected separation :math:`\lambda` the Poisson
distribution :math:`f(k; \lambda)` describes the probability of
:math:`k` events occurring within the observed
interval :math:`\lambda`.
Because the output is limited to the range of the C int64 type, a
ValueError is raised when `lam` is within 10 sigma of the maximum
representable value.
References
----------
.. [1] Weisstein, Eric W. "Poisson Distribution."
From MathWorld--A Wolfram Web Resource.
http://mathworld.wolfram.com/PoissonDistribution.html
.. [2] Wikipedia, "Poisson distribution",
https://en.wikipedia.org/wiki/Poisson_distribution
Examples
--------
Draw samples from the distribution:
>>> import numpy as np
>>> s = np.random.poisson(5, 10000)
Display histogram of the sample:
>>> import matplotlib.pyplot as plt
>>> count, bins, ignored = plt.hist(s, 14, density=True)
>>> plt.show()
Draw each 100 values for lambda 100 and 500:
>>> s = np.random.poisson(lam=(100., 500.), size=(100, 2))
permutation(x)
Randomly permute a sequence, or return a permuted range.
If `x` is a multi-dimensional array, it is only shuffled along its
first index.
.. note::
New code should use the
`~numpy.random.Generator.permutation`
method of a `~numpy.random.Generator` instance instead;
please see the :ref:`random-quick-start`.
Parameters
----------
x : int or array_like
If `x` is an integer, randomly permute ``np.arange(x)``.
If `x` is an array, make a copy and shuffle the elements
randomly.
Returns
-------
out : ndarray
Permuted sequence or array range.
See Also
--------
random.Generator.permutation: which should be used for new code.
Examples
--------
>>> np.random.permutation(10)
array([1, 7, 4, 3, 0, 9, 2, 5, 8, 6]) # random
>>> np.random.permutation([1, 4, 9, 12, 15])
array([15, 1, 9, 4, 12]) # random
>>> arr = np.arange(9).reshape((3, 3))
>>> np.random.permutation(arr)
array([[6, 7, 8], # random
[0, 1, 2],
[3, 4, 5]])
' object which is not a subclass of 'Sequence'; `shuffle` is not guaranteed to behave correctly. E.g., non-numpy array/tensor objects with view semantics may contain duplicates after shuffling.
laplace(loc=0.0, scale=1.0, size=None)
Draw samples from the Laplace or double exponential distribution with
specified location (or mean) and scale (decay).
The Laplace distribution is similar to the Gaussian/normal distribution,
but is sharper at the peak and has fatter tails. It represents the
difference between two independent, identically distributed exponential
random variables.
.. note::
New code should use the `~numpy.random.Generator.laplace`
method of a `~numpy.random.Generator` instance instead;
please see the :ref:`random-quick-start`.
Parameters
----------
loc : float or array_like of floats, optional
The position, :math:`\mu`, of the distribution peak. Default is 0.
scale : float or array_like of floats, optional
:math:`\lambda`, the exponential decay. Default is 1. Must be non-
negative.
size : int or tuple of ints, optional
Output shape. If the given shape is, e.g., ``(m, n, k)``, then
``m * n * k`` samples are drawn. If size is ``None`` (default),
a single value is returned if ``loc`` and ``scale`` are both scalars.
Otherwise, ``np.broadcast(loc, scale).size`` samples are drawn.
Returns
-------
out : ndarray or scalar
Drawn samples from the parameterized Laplace distribution.
See Also
--------
random.Generator.laplace: which should be used for new code.
Notes
-----
It has the probability density function
.. math:: f(x; \mu, \lambda) = \frac{1}{2\lambda}
\exp\left(-\frac{|x - \mu|}{\lambda}\right).
The first law of Laplace, from 1774, states that the frequency
of an error can be expressed as an exponential function of the
absolute magnitude of the error, which leads to the Laplace
distribution. For many problems in economics and health
sciences, this distribution seems to model the data better
than the standard Gaussian distribution.
References
----------
.. [1] Abramowitz, M. and Stegun, I. A. (Eds.). "Handbook of
Mathematical Functions with Formulas, Graphs, and Mathematical
Tables, 9th printing," New York: Dover, 1972.
.. [2] Kotz, Samuel, et. al. "The Laplace Distribution and
Generalizations, " Birkhauser, 2001.
.. [3] Weisstein, Eric W. "Laplace Distribution."
From MathWorld--A Wolfram Web Resource.
http://mathworld.wolfram.com/LaplaceDistribution.html
.. [4] Wikipedia, "Laplace distribution",
https://en.wikipedia.org/wiki/Laplace_distribution
Examples
--------
Draw samples from the distribution
>>> loc, scale = 0., 1.
>>> s = np.random.laplace(loc, scale, 1000)
Display the histogram of the samples, along with
the probability density function:
>>> import matplotlib.pyplot as plt
>>> count, bins, ignored = plt.hist(s, 30, density=True)
>>> x = np.arange(-8., 8., .01)
>>> pdf = np.exp(-abs(x-loc)/scale)/(2.*scale)
>>> plt.plot(x, pdf)
Plot Gaussian for comparison:
>>> g = (1/(scale * np.sqrt(2 * np.pi)) *
... np.exp(-(x - loc)**2 / (2 * scale**2)))
>>> plt.plot(x,g)
dirichlet(alpha, size=None)
Draw samples from the Dirichlet distribution.
Draw `size` samples of dimension k from a Dirichlet distribution. A
Dirichlet-distributed random variable can be seen as a multivariate
generalization of a Beta distribution. The Dirichlet distribution
is a conjugate prior of a multinomial distribution in Bayesian
inference.
.. note::
New code should use the `~numpy.random.Generator.dirichlet`
method of a `~numpy.random.Generator` instance instead;
please see the :ref:`random-quick-start`.
Parameters
----------
alpha : sequence of floats, length k
Parameter of the distribution (length ``k`` for sample of
length ``k``).
size : int or tuple of ints, optional
Output shape. If the given shape is, e.g., ``(m, n)``, then
``m * n * k`` samples are drawn. Default is None, in which case a
vector of length ``k`` is returned.
Returns
-------
samples : ndarray,
The drawn samples, of shape ``(size, k)``.
Raises
------
ValueError
If any value in ``alpha`` is less than or equal to zero
See Also
--------
random.Generator.dirichlet: which should be used for new code.
Notes
-----
The Dirichlet distribution is a distribution over vectors
:math:`x` that fulfil the conditions :math:`x_i>0` and
:math:`\sum_{i=1}^k x_i = 1`.
The probability density function :math:`p` of a
Dirichlet-distributed random vector :math:`X` is
proportional to
.. math:: p(x) \propto \prod_{i=1}^{k}{x^{\alpha_i-1}_i},
where :math:`\alpha` is a vector containing the positive
concentration parameters.
The method uses the following property for computation: let :math:`Y`
be a random vector which has components that follow a standard gamma
distribution, then :math:`X = \frac{1}{\sum_{i=1}^k{Y_i}} Y`
is Dirichlet-distributed
References
----------
.. [1] David McKay, "Information Theory, Inference and Learning
Algorithms," chapter 23,
http://www.inference.org.uk/mackay/itila/
.. [2] Wikipedia, "Dirichlet distribution",
https://en.wikipedia.org/wiki/Dirichlet_distribution
Examples
--------
Taking an example cited in Wikipedia, this distribution can be used if
one wanted to cut strings (each of initial length 1.0) into K pieces
with different lengths, where each piece had, on average, a designated
average length, but allowing some variation in the relative sizes of
the pieces.
>>> s = np.random.dirichlet((10, 5, 3), 20).transpose()
>>> import matplotlib.pyplot as plt
>>> plt.barh(range(20), s[0])
>>> plt.barh(range(20), s[1], left=s[0], color='g')
>>> plt.barh(range(20), s[2], left=s[0]+s[1], color='r')
>>> plt.title("Lengths of Strings")
RandomState.vonmises (line 2264) RandomState.rayleigh (line 3089) RandomState.logistic (line 2887) RandomState.binomial (line 3352) state dictionary is not valid. probabilities do not sum to 1 RandomState.weibull (line 2456) RandomState.uniform (line 1049) RandomState.tomaxint (line 620) RandomState.shuffle (line 4542) RandomState.poisson (line 3592) RandomState.laplace (line 2669) pvals must be a 1-d sequence RandomState.randint (line 678) RandomState.pareto (line 2353) RandomState.normal (line 1453) RandomState.gumbel (line 2763) 'a' and 'p' must have same size RandomState.randn (line 1220) RandomState.power (line 2560) RandomState.gamma (line 1644) RandomState.choice (line 840) mean must be 1 dimensional Range exceeds valid bounds RandomState.zipf (line 3675) RandomState.wald (line 3166) RandomState.rand (line 1176) RandomState.bytes (line 804) probabilities contain NaN RandomState.seed (line 228) 'p' must be 1-dimensional numpy/random/mtrand.pyx a must be 1-dimensional RandomState.f (line 1728) standard_exponential noncentral_chisquare you are shuffling a ' numpy.random.mtrand multivariate_normal ngood + nbad < nsample cline_in_traceback array is read-only DeprecationWarning set_bit_generator negative_binomial get_bit_generator __randomstate_ctor may_share_memory sum(pvals[:-1]) > 1.0 standard_normal standard_cauchy random_integers _poisson_lam_max collections.abc _bit_generator standard_gamma _legacy_seeding hypergeometric RuntimeWarning random_sample count_nonzero __class_getitem__ bit_generator OverflowError searchsorted return_index numpy.linalg noncentral_f newbyteorder _initializing permutation multinomial exponential check_valid UserWarning RandomState ImportError triangular standard_t stacklevel __pyx_vtable__ mode > right logical_or less_equal left == right issubdtype empty_like ValueError IndexError writeable singleton set_state logseries lognormal left > mode isenabled has_gauss get_state geometric dirichlet chisquare TypeError MT19937 warnings vonmises subtract reversed reduce rayleigh operator logistic itemsize isscalar isnative isfinite binomial allclose Sequence weibull uniform tobytes strides shuffle reshape replace randint poisson nsample _mt19937 laplace greater float64 disable casting capsule bg_type at 0x{:X} asarray alpha <= 0 _MT19937 unsafe unique uint64 uint32 uint16 sample __reduce__ random _rand _pickle pareto object_ normal length legacy kwargs __import__ ignore gumbel format enable double cumsum choice bitgen astype arange zeros uint8 state sigma shape scale right ravel range randn raise pvals power numpy ngood kappa isnan int64 int32 int16 index gauss gamma flags finfo equal __enter__ empty dtype dfnum dfden __class__ bytes array alpha __all__ zipf warn wald type __test__ take sqrt __spec__ sort size side seed rtol ranf rand prod nonc ndim nbad __name__ mode mean __main__ lock less left item intp int8 high __exit__ copy bool_ beta atol args tol svd sum __str__ pos low loc lam key get eps dot cov any all add ? * qh ? ? ?/*p?3f?(_?xY?յS?N?J? F?DB?Qt??u+ ?A?Į?"?ʝ?G ? ?i>l>7>>*J>>>^>>F>>7P>>K{> >>u>;->>>|>eO>4(>8>L>N>ȿ>>>>·>ε>߳>>>0>U>~>|>ަ>Y>IP>w>ҟ>B>e>)>~>_>>C>{>>J>>X(>'>N>Í>x >b>x>>!>^}>;z>Хw>@t>wr>byl>i>g>Sd>3a>^>]\>&Y>z)W>T>P R>O>L>5~J>3H>E>n C>@>VK>>;>9>07>4>2>>0>p->+>s)>7'> %>"> >s >L >*>= >T>T>4>>y
>ϣ > >>L>>l>=+==0
=C==8==hp==0= =
=n= =|===;=ں=Z=o,=ް=ߗ=.W= ==%==r=W= C=4=M,=4*=D.=y8=H=~=x=3E3lM3FT3/[3b3i34p3fw3&~3[3B3ψ3g37!3>3T3d3n3r3Fq3j3_31P3r<3$3k 33ȸ3q3|{3P3#3C333dY3"3+3®3r35333x37333p3-33731b3 3l 44(4 4h4C44
4` 4M 47 44?4nB44L4 i4a4T044542` 4 4p. 4!4"4i$4%4@'4t(4>*4+4,4j.4/4'P1424):4454&)7484c :4;4$=4+>4@4A4K C4vD4B(F4G4:I4J4rTL4M4GuO4Q4R44T4U4EiW4Y4 Z4G\4]4_4:a4b4d4Bf4\g4ji4 bk4 m4n4p4\r4}"t4Yu4Hw4[y4X{46.}4 4q4a4]S4F4N<434,4+(4{%4$4o&4,*4'04m84
C4P4_4q474{4w4>ԕ44s4<4d444$4 (4a44lߢ4 $4l44x
4_444{4 4EP4±4{:4귴4);4nķ4S444<*4 տ44A4.44ע44f4RW4R4*Y4Fk44δ444444g44k4<444y44u4_4 5555@5ó
5 5]5^55 5q5v
5!5%5V*5s/5;S55:<5D5NO5 ^5Nv5QHq oM ֻa nj Do tTr ot ou $w 'x x ,jy y 7\z z { W{ S{ { .| 3| ]| ȃ| | | I| | } C0} F} Z} m} } S} (} } -} } "} } |} M} ~ i
~ ~ ~ B(~ o0~ C8~ ?~ F~ M~ T~ Z~ a~ f~ l~ r~ ]w~ v|~ `~ ~ ~ $~ m~ ~ ~ w~ :~ ަ~ f~ ѭ~ #~ Z~ y~ ~ q~ K~ ~ ~ ^~ ~ a~ ~ ~ `~ ~ ~ ~ ~ ~ ~ ~ f~ *~ ~ ~ -~ ~ J~ ~ =~ ~ ~ \~ ~ ~ $~ U~ }~ ~ ~ ~ ~ p H ` i
6 H
A ! B + m 5 X t t W 3 ` w K \
L
s
G { V~ ~ ~ d~ ~ x~ ~ K~ ~ ~ ~ ~ ~ ~ ~ ~ )~ ~ ~ a~ ~ ~ {~ ;~ ~ A~ ~ ~ m~ ~ z~ ~ ~ "~ k~ ]~ ~ ~ ԃ~ |~ s~ j~ Ua~ W~ K~ ?~ 2~ $~ ~ ~
} } } } } i} A} } | Q| D| { 3N{ z ey ww 7ms ?7E?P?'{{ ?*!?bv?mU?9U1T?/v?x]?&1$-?~ n?cK[!?I?\Omg?f?uLi=?sڂl?x ?Qf?ij?%ᨯC?+?Dܻ?z?cE#;?^E#?$O ?2m?P"K?>?{s?%; ?omo?3;? J9?+ +?*T[?};1s?HeC?$`?vE!=?ſ-r?MBц?K=?Q}6Ei?7u? ! ?z}k? ~?@?`x?*?8? Qi?oTC?_(4?ָ?@je?!u v ?7Zi ?{ ?I?]T?9]??}?8aD:?Yζi? Ɲҷ?r^sSw?ꍰ07?d>[?%۹?
Ə{?'HB>?vX #?l1& ?:l?磽!O?ލ? &?ڋ?ﾀ+ j?A1?N0Z?0H?}G?(V?5$1!?pB9 ?b"FS?)vEW(?vG}rO?~ / ? {^?Z? ?ބS?i"?lR?3Sn?>N?Ґ]b?,|y2?jG>?TLҫ?~>\O??@Y H?/֎@?9O"H?>?1 7?8?Ox?]4?5D9g?r|?>ܸ$8? [B/?I䠟?O?y%d ?bPޱ?c?PR?j?F}?9(Q1?c ?(ڦ^w?0U^Q?1j?T ξ?x.BTv?Imb.??6YJ?)ِ?\C}?%d?w?SN?эv?pa?,Q&?@oű?SuFe?PV?;?I?viׯ?4D ?.g?X1Iα?Jy ?!dJ?پz?j»?8G;?L|{ʎ?mwn?k9: 9??Ry?A&E?U?Ŗ< ?k&_?G??~ #? V#?_?S?Q| z?
Y&?$?htQz? 3Tݜ?pXP?N梚?H*g?gS(u?1c?w@rT?Q=I?QA?]1%? RD?lj?W'n?-BU؊?h?t4? n?boQ?qvi?_)N?]tQW}?6H#z? 67w?"Ηs?C@Wi=q?ḰXl?f?$ka?%> T+Y?
O?K 2 =?]d<A]X`<+M[Ij<[5q&<.8eG< h#ឪV
<;LC%K<ꆭh
N Ve Ι Vn 6n vK zic p%E tQ) 2U1 WQ9 Lin? 23F : L "3\LQ V f[ _ rWDd x h +*k 2=Ko :qr Mu \x ?A{ FS~ 8; b=Z V` bB tu 9= JE > X دGw dO 8cx A Fẙ i& zqV Yם Ρag 6 X 83:뇡 ko ɣ j_ۤ | M g^ ݧ t|Ψ _Γ Xp 2X^t tH 蟿 W;ޭ l ~$\ z[ ߁İ Pp : J+ N!X ɦ ֬ ᆴ X7(.
Ɉ ?5 }h . G{ t r &oya =c A/˺ DH0 ⤮ < )9O @ᣩ T rV j @?˷ ds I ^i@ (0߾ ta& ⊂l 1 EA1 T[n &m i# d) B}Q Jw t} B <
E Ovp c/ F< Ң "Ae
އ0 ~ R fq (*Q t H3D @ M `P} hwx% ƿ8 *J G+[ Eli PIw + E> ҙ 0 2y Ω 4A (N t.Ȱ - -̕ ^&܌ z#; ޖu ~g 6X .pmF 3 n
bH La EZ v pR (- x_ b˿ Ӱ dyQ Ӷ Vg <7 ܆u t7 $ MH l d" rqտ H)݄
/0 wپ }2} K D5z &R c M,}u c ? Ѡ p5 .b J3ʸ T[vv+ \[ U@ض Bi" 7oLe i Fγ >S R(D2 Z> B0$ y1 gW r-ެ
@樫 (a foe W - |&aY + M ?V#z?u?q?}n?k?Lh?e?Rc?`?Zw^?*+\?Y?RW?U?_S?XQ?߱O?M?3K?J?GH?F?jD?`C?(`A?j??>?x,>N>>q>>>j>>k>>Π>>F>>>'>\>#>u>J>*>_F>d>+>$>w> > >JK>y>|>iݿ>>I>;>ʾ>t>5<> ~>>>O>>>~3>T>ե>(>g~>ՠ>G/>>>F>J> >:n>bԓ>Q<>>x>~>>>^>Ј>D>l>1>>%>\D>@|>?y>Bv>Hs>Qp>#^m>mj>|g>md>a>^>$[>
Y>=3V>[S>P>M>J>~ H>UE>B>?>=>S:>7>"4>=22>T/>d,>m+*>m'>c$>N?">, > >m>t>F>>1*>
> >Y>>ʗ> >I=_={==^==&=_=g=='0===P6=˙=\= s==d=
=yo=/=6=.=fЍ=x=i'=܀=a1y=p=xIh=_==W=TO= G=>=N6=.=&= ==-H==<א<̀<<<.4V?4=3@4A4A4qB4C4D4udE4-CF4K"G4H4H41I4J4vK4\fL4HM4+N4aO4O4bP4ٽQ4R4ԊS4crT4ZU4CV4-W4ZX4Y4UY4Z4[4(\4_]4^4_4C`4va4alb40cc47[d4~Te4Of4Jg42Hh4Fi4Fj4Hk4Kl4MPm4Vn4^o48hp4sq4r4s4
t4u4 v4Cw4x4 z42{40S|4u}4~44v4@
4L4>4ق4v444lV44R4F44p4
I44"4_44Ќ4l4L4`4ԏ4坐4y4ݖ4%44r&4k44(44 44.4Q4N4t44\۶4H94̻4p44~X4w4p_4~444w E` m r u \zw 8x ky 5zz /
{ ԃ{ { 7| 3}| &| H| } C} g} ۇ} } a} g} ]} ~ ~ 4%~ 5~ C~ Q~ g^~ ij~ u~ >~ 2~ ~ r~ դ~ Ƭ~ N~ u~ C~ ~ ~ ~ k~ ~ ~ ~ ~ ~ t~ ~ ~ 6
< :# % ]( * .- z/ 1 3 5 7 9 ; = ? EA B D :F G NI J 8L M N LP Q R
T =U dV W X Y Z [ \ ] ^ ~_ _` ;a b b c od .e e f Lg g h ~ ~ 7~ ~ /~ 7~ ~
~
~ w~ G]~ >~ Y~ ,} 6} b} | O| 06{ x ?yjD?l[T?w'??o?Wp?xI?-3?x^j? ?N?R:e?4:>?l?*?%z?PՋt?4? e;?$"?zaWF}?GzB?Oq1?
OU?ߺH?7a?nV,? K?Xhw?հ<?Vp \?m?)?zP?ZcX?*;Q^?#*'g? U7?e&$ ?jJo?\Ȭ)?L&?FS?leZ&?g ?NIO??xRr!?P_hy?y6IJO?_5%?[X~?1>?bU? +À?PX?5:pɗ0?8d?;U?J?͓?)m?ېZ]G?/|!? ?iT??Wq?PF9 ?ߓ ^??ۮY?3 ???i?Z8o?
O5?ٸ?P?R9?igP?La;?L?!ވ?%o?{7=8?Ҁt ?DvC?6? =p\?;So&?mj?W?j?$O?z5Ѽ?Ҏ?C|P?yh|?%H?/ZM?f!w;??>ǭ? MAz? G?y?.?P9կ?TT}?g4K?#$O? Y?BM?6C;?B"_U?~t$?œ߉?52?Ҙl'?DɤT?<(i?qE8
?
Uī?OQM?o^?Sq͒?Gط5?zx?1zd}?:R!?Wg?~& ~k?=~-2?ZҿҶ?'|j_]?it?[?8R?uq b?#h?z|J?G~`?\!>?GF?vJ?l ?5hȩmE? 㭍?-l ?uG?1i%?調?M?e*|?zè?^V?4<%F?B}u?c-@c?n ? R=?Kr?*}T#?,"k>? R) ?K{o?vaӽ?命8?
t;I_? h?3xk?3Ӻ?b3?vZ9S?LJisk?M$a.?ftW?+ ?"@|?&#?p>_?1fҲ?
DE?} ?/?%,?0?5nl+,&?QG?b. ?,*(>?p_8?cU)?h*? 'wާ?dИۦ?ԭ<ڥ?]']ۤ?ݣ?=|?j ?.?ĥׁ?u? ̓0?"NR?
y? ڥ?d֔?^8
?0`4I?IrO*?O'?x
A?B?/)?7h`|?] ٨v? p?gC_e?T?yx;I< <[,L< Ŀk<4xV<=A[<'?}y<NG<~;[ xo6 xu{ f U Y> 9>{ pp CBw S( :5^ dܓ A N}8 ) Y fHq ն& |s f2 ,2Z tզ ޗ .n ZR' ӯB )[ l@u Pҍ ' T Ȉt (5w I' L/$; nXM ØT` OA r W , + jtȳ RfA Rnq ӊ< K Z W $eKs)
4 <=> )G 'Q A@Y .(5b X j z>lq {2Xx {~ JH҄ Cc` Qz %~ )Q \H srU b' Bk q-h nק
Ψ ;3K d)P ^٨ Tv $ Hx " $ 5. .& $ŗ :
٬ @r鷯?Q ?Q ?9v?(\@ffffff@ 0C.@ 4@x&? @ ?UUUUUU? a@ X@ `@ |@ @ MA >@ @-DT! @h㈵> .A-DT! -DT!@ C 3N@S i@ ?> Aޓ= ? 3?r?q? 0@;
ݯ
ڰ X\ ( ó , :- i/ g0% |4 P p4 l В 0 ДT h @P t ` 4
p @ | L
@
Ф
pT ` 4 `H p| P 08 P h L @ ` X 0 P P 08 @ P ` # *( P0 6@ 8 @\ PG Nt U @] pd g\ g q zD \! `! @" X# $ <& & `& ' |' ( ( )( p]L) p) py<* * $+ `+ L, - |- - 0d. . |/ / @0<0 070 Z<1 @e1 ot2 p2 T3 3 (4 T4 l4 4 4 p4 D5 5 05 @6 |6 6 7 p@7 |7 7 8 8 d8 |8 8 08 @8 8 8 9 89 \9 t9 p9 9 9 : 8: h: : `: : : P ; 0; T; ; `; < d< 0< 0< `< P= @= d= |= = = `= p> <> > @
> P?
?
? D@ @ pDA A PA XB |B B B B B C ` 4C LC 0 dC C !C $C ' D )$D )( BIG B(N0F8KdBFFBFABFQ[
8D0A(B BBBG VKF @ < PE BBE A(A0D@z
0D(A BBBD H Gt BHA D(G0s
(D ABBF N(D ABB T GD
BIB B(D0A8D`DhIpYhF`b
8D0A(B BBBE @ $ Q BBB E(A0D@
0D(B BBBC h 4Z BIB B(D0A8GORF_
8D0A(B BBBE KhBBBBEHFAS H` BIB B(D0A8GORF_
8D0A(B BBBE KhBBBBEHFAS \f BIB B(D0A8GORF_
8D0A(B BBBE KhBBBBEHFAS pl BMG R(D0A8D[FFBFABFATz
8D0A(B BBBI WRFW_A s BIB B(A0A8JeBBBBABTgVRFb
8D0A(B BBBA IBKHBABBAYW_AIV`G | y BIG B(A0D8ZrBAFBABBAMFMJFBABGARVRF_
8D0A(B BBBE 4 x( BIB B(A0A8J)_TAi_QBg
8D0A(B BBBI VKFZ_QA_RB_RBGQA8BTAERBjGQA ( 4 O a BBB B(A0A8Gz EFFAAAAACNnEFFAAAAAAKYEFFAAAAACNVEFFAAAAACNqEFFAAFAAAKS8A0A(B BBB @ `
AI ; % ; / Dj < (a vj < D i
K J
N x @< H D C X< $g \ ~ p< |Y D H < q De
G J
F l < H D |
A 4 < T AO
EC
AT z
EI = , AK@
AQ $= 8 AW0
EG H= ` t _ `= <] D g
U |= AK0
EH = AG C
AL $ = hz AG s
AL hEP = BAD D@
AAFK
AABR ; AAF @> J AG
AM d> H; D v ( |> p Ma
J n
J L
D A H > BBB E(A0D8G[
8D0A(B BBBA > ? ? n \ L 4? 4 H? AGP
AG ^
AA L
AC ? < AG@
DD P< <
P
o `
+
(5 H o o o , o (
6P FP VP fP vP P P P P P P P P Q Q &Q 6Q FQ VQ fQ vQ Q Q Q Q Q Q Q Q R R &R 6R FR VR fR vR R R R R R R R R S S &S 6S FS VS fS vS S S S S S S S S T T &T 6T FT VT fT vT T T T T T T T T U U &U 6U FU VU fU vU U U U U U U U U V V &V 6V FV VV fV vV V V V V V V V V W W &W 6W FW VW fW vW W W W W W W W W X X &X 6X FX VX fX vX X X X X X X X ^ ( h[ w
PB P pr D
< pE ` < < ? ` D o y P `9 `4 @- u & h Pl % @ 4 + ` ` { x pC s ` ` ` ` @ i @ @ I P ` @ 8 | s @ `g P ] 0 `K P @> p @. @ ` @ ` ` h P@ _ ` V p8 1 Q 1 0+ x Q h G $ \ A F @ 9 ! 0z - `( `# y ` p # ! GCC: (GNU) 10.2.1 20210130 (Red Hat 10.2.1-11) `< ; < E p <
< X 0: `( . @= H 0> \ > v ? ? Q @ @ - PB a C y C pE w E X Y Z ~ h[ ` . D 8: L F c \ F T s PI \ I K L | PM = N e R } ] y
E A
`V
E &
Y
"
Y
5
`E > ^
P\
n
Z
E $
8X
@D
X
`Q
! #
T
F
" n
S
` "
D #
@U
S
'
" O
S
t
'
R
Q
!
"
` " 9
C $ b
,
C *
@C -
C %
S
*
R
O
B $ x
`R
S
`T
R
`S
.
B ( W
@B %
P
!
T
@R
B (
A , A
' i
A (
@A #
R
A #
R
0
P
! W
@T
z
Q
T
T
W
[
? > 7
d_
A
`? G j
; L
Z
!
X
Y
<_
T_
R_
:_
$
P_
/
8_
;
b_
E
@S
i
` 0
U
? &
5
4_
0_
^
(
p[
9
^
G
@\
W
,_
c
"]
r
^
^
@V
8\
]
(\
^
`_
^
\
`[
D
(X
Z
W
r
]
^
]
`
> (
\
\
X
!
> 4 J
Z
\
6
]
@
]
X
V
W
^
X
5
(_
A
`> % j
> 3
]
M_
]
]
xZ
D
a
\
$_
\
-
]
;
]
I
Y
\
\
k
]
y
_
]
^
X
^_
]
]
*
\
:
\
I
]
W
`
]
J_
hZ
{
_
V
XZ
= u 3
[
C
\
R
q ! z
HZ
^
W
a n
G_
\
\
]
X
$
]
2
]
@
]
N
^
[
^
h
8Z
z
P[
]
@[
0[
Y
^
[
]
_
\
\_
_
+
[
;
@6
b
^
o
(Z
Y
\
@= T
W
\
^
xY
_
^
+
hY
>
[
O
T p w
Z
B
Z
6
_
^
W
^
*
= # S
S
v
^
XY
[
D_
X
`* Q
U
` 1
Z_
;
^
H
^
U
~^
b
V
|
X
}]
V
y^
U
4
xX
I
@ p
q
\
`
A_
[
w]
'
< " "
hX
7
U
S
U
s
\
`5
[
X_
T
\
X
/
`0
V
\
e
[
u
`&
pW
_
q]
< #
T
A
Q
g
t^
t
k]
R
HY
e]
o^
\
!
q
[
v C
_]
Q
( x
\
`W
W
V
j^
*
Y]
8
S]
F
Z
W
`
\
Z
[
[
XX
Z
M]
e^
!
|\
!
G]
!
HX
2!
`^
?!
`
w f!
V
!
Y
!
? !
A]
!
[
!
!
[^
"
;]
"
Y
,"
V^
9"
Q^
F"
H^
S"
>^
`"
8Y
s"
PW
"
@
A
"
`U
"
6 "
W
#
4#
@W
L#
` z s#
(Y
#
#
5]
#
Q
#
@ !
$
_
$
[
&$
Z
7$
^
C$
W
[$
` $
^
$
9^
$
0^
$
[
$
^
$
S $
Y
%
`{
(%
'^
5%
=_
@%
u\
O%
n\
^%
g\
m%
/]
{%
[
%
@m %
`\
%
Y\
%
Z
%
`
&
"^
&
k >&
^
K&
Z
\&
[
l&
R
&
Y
&
V_
&
@< / &
U
&
)]
'
^
'
@F 8' c O' pS l' T c ' pT ' U ' `V ' W
( W : ( Y . /( @Z \( `[ 1 ( J / ( ] ( ` [ ( b ( c ( ) *) : ;) Pl r) o ~ ) pr m ) u ) x C* h9 \* { s* u * @ ` * 9 + ` J+ ` + ` + @ + 0 ", p9 G, P 3, ` , p # , # , # (- # g- 0 # - ` # - ! - y . H U. H . ` H . H / H 7/ P ( m/ / t / D
/ $ / $ 0 $ 0 x$ ;0 h0 " 0 " 0 $ 0 9 0 0+ 41 1 i1 p8 1 P@ 1 @: 1 " 2 ! $2 ! :2 ! U2 ! k2 ! 2 ! 2 ! 2 ! 2 ! 2 ! 2 ! 3 9 J3 ` y 3 p! 3 h! 3 `! 3 X! 3 P! 3 H! 4 ! +4 x! F4 H9 b4 x ( 4 4 4 4 4 5 -5 C5 ^5 9 5 9 5 P 5 H 5 9 46 J6 e6 9 6 6 6 : 7 7 57 : m7 7 x 7 : 7 p 7 h 8 : >8 ` T8 X o8 9 8 `9 8 w a 8 X9 8 P9 9 @9 -9 89 F9 09 `9 @( 9 ` 9 9 9 9 ': 9 P: 9 : 9 : 9 : 9 ; 9 D; x9 {; ( ; ( ; ( ; ' ; ' ; ' < ' +< ' G< ' ^< ' z< ' < ' < ' < ' < ' < ' = ' *= ' F= ' ]= x' y= p' = h' = `' = X' = P' = H' > @' )> 8' E> 0' \> (' x> ' > ' > ' > ' > ' > & ? & (? & D? & [? & w? & ? & ? & ? & ? & ? & @ & '@ & C@ & Z@ & v@ & @ x& @ p& @ h& @ `& @ X& A P& &A H& BA @& YA 8& uA 0& A (& A & A & A & A & B & %B % AB % XB % tB % B % B % B % B % B %
C % $C % @C % WC % sC % C % C % C x% C p% C h% D `% #D X% ?D P% VD H% rD @% D 8% D 0% D (% D E 5E ` jE @ E E e E % E % F e =F % TF % pF p F $ F $ F G % G $
a
@. %b
@
^b
@
b
`
b
! c
p @c
{c
c
k c
'd
` ad
d
d
e
x { Ne
h n e
\ e
F f
9 Q Mf
- a f
`( f
`# g
h (g
` h Qg
g
g
! g ; g ; g <
h h
=h P< Ih
hh q }h
k
h
s
h
{
h
_
h
c
h
g
h
h
h
h 0{ P h
h
i
i i =i
Ki Zi I wi i i P J i 0 S i Ј i H i u i / j /j @ q @j @w p cj % pj 7 j p
j j 0 ` j ` B j s j ( m А j k 'k Ak { .k ` \k / xk N k k s Y k 0 Z k k l p l 3l H Cl C Pl ` jl @ & ~l y y l 8 l l l 3 l
l 0 l m p m r % 8m P 5 Fm ~i V Um p g dm v - m m m a m _ m m ` C m n } *n @n r Xn Y en $ sn ; n P n z n n t a n n p n @ o (
o y 4o @o To x a yo 0 ( o P j o p o @ o p i o r I o p I -p >p n Vp w op
p p p p 0 R p Ep Э 5 p } I q ] 8 ` , (5 P
P X
(
q ,q @q Qq \q mq q q q q q q q r r r -r u Ou ]u nu u u u v u u u v v "v 2v Fv Wv hv tv v v v v v v v w w )w ;w Ow bw uw w w w w w w w x x 2x Gx Yx gx {x x x x x x x x ; y y *y 5y Fy ^y jy vy y y y y y y y y z z .z Iz [z jz {z z z z z N z z z { { { 4{ @{ P{ l{ }{ { { { { { { { | "| 4| A| R| " n| P t| | | | | | | | } } __pyx_f_5numpy_6random_6mtrand_11RandomState__reset_gauss __pyx_tp_traverse_5numpy_6random_6mtrand_RandomState __pyx_getprop_5numpy_6random_6mtrand_11RandomState__bit_generator __pyx_tp_new_5numpy_6random_6mtrand_RandomState __pyx_vtabptr_5numpy_6random_6mtrand_RandomState __pyx_mstate_global_static __Pyx_CheckKeywordStrings __Pyx_PyObject_Call __Pyx_PyObject_GetAttrStr __pyx_f_5numpy_6random_6mtrand_11RandomState__shuffle_raw __pyx_setprop_5numpy_6random_6mtrand_11RandomState__bit_generator __Pyx_PyNumber_IntOrLongWrongResultType __Pyx_PyInt_As_int __pyx_tp_dealloc_5numpy_6random_6mtrand_RandomState __Pyx_ErrRestoreInState __Pyx__GetException __pyx_tp_clear_5numpy_6random_6mtrand_RandomState __Pyx_Import __Pyx_ImportVoidPtr_3_0_2 __Pyx_ImportFunction_3_0_2 __Pyx_copy_spec_to_module __pyx_pymod_create main_interpreter_id.0 __pyx_m __Pyx_IsSubtype __Pyx_PyUnicode_Equals __Pyx_PyDict_GetItem __Pyx_ImportType_3_0_2.constprop.0 __Pyx_SetItemInt_Fast.constprop.0 __Pyx_PyObject_GetSlice.constprop.0 __Pyx__PyObject_LookupSpecial.constprop.0 __Pyx_GetItemInt_Fast.constprop.0 __Pyx_ParseOptionalKeywords.constprop.0 __Pyx_Raise.constprop.0 __Pyx_CreateStringTabAndInitStrings __pyx_k_Cannot_take_a_larger_sample_than __pyx_k_DeprecationWarning __pyx_k_Fewer_non_zero_entries_in_p_than __pyx_k_ImportError __pyx_k_IndexError __pyx_k_Invalid_bit_generator_The_bit_ge __pyx_k_MT19937 __pyx_k_MT19937_2 __pyx_k_Negative_dimensions_are_not_allo __pyx_k_OverflowError __pyx_k_Providing_a_dtype_with_a_non_nat __pyx_k_RandomState __pyx_k_RandomState_binomial_line_3352 __pyx_k_RandomState_bytes_line_804 __pyx_k_RandomState_chisquare_line_1909 __pyx_k_RandomState_choice_line_840 __pyx_k_RandomState_dirichlet_line_4393 __pyx_k_RandomState_exponential_line_499 __pyx_k_RandomState_f_line_1728 __pyx_k_RandomState_gamma_line_1644 __pyx_k_RandomState_geometric_line_3771 __pyx_k_RandomState_gumbel_line_2763 __pyx_k_RandomState_hypergeometric_line __pyx_k_RandomState_laplace_line_2669 __pyx_k_RandomState_logistic_line_2887 __pyx_k_RandomState_lognormal_line_2973 __pyx_k_RandomState_logseries_line_3968 __pyx_k_RandomState_multinomial_line_425 __pyx_k_RandomState_multivariate_normal __pyx_k_RandomState_negative_binomial_li __pyx_k_RandomState_noncentral_chisquare __pyx_k_RandomState_noncentral_f_line_18 __pyx_k_RandomState_normal_line_1453 __pyx_k_RandomState_pareto_line_2353 __pyx_k_RandomState_permutation_line_466 __pyx_k_RandomState_poisson_line_3592 __pyx_k_RandomState_power_line_2560 __pyx_k_RandomState_rand_line_1176 __pyx_k_RandomState_randint_line_678 __pyx_k_RandomState_randn_line_1220 __pyx_k_RandomState_random_integers_line __pyx_k_RandomState_random_sample_line_3 __pyx_k_RandomState_rayleigh_line_3089 __pyx_k_RandomState_seed_line_228 __pyx_k_RandomState_shuffle_line_4542 __pyx_k_RandomState_standard_cauchy_line __pyx_k_RandomState_standard_exponential __pyx_k_RandomState_standard_gamma_line __pyx_k_RandomState_standard_normal_line __pyx_k_RandomState_standard_t_line_2149 __pyx_k_RandomState_tomaxint_line_620 __pyx_k_RandomState_triangular_line_3243 __pyx_k_RandomState_uniform_line_1049 __pyx_k_RandomState_vonmises_line_2264 __pyx_k_RandomState_wald_line_3166 __pyx_k_RandomState_weibull_line_2456 __pyx_k_RandomState_zipf_line_3675 __pyx_k_Range_exceeds_valid_bounds __pyx_k_RuntimeWarning __pyx_k_Sequence __pyx_k_Shuffling_a_one_dimensional_arra __pyx_k_T __pyx_k_This_function_is_deprecated_Plea __pyx_k_This_function_is_deprecated_Plea_2 __pyx_k_TypeError __pyx_k_Unsupported_dtype_r_for_randint __pyx_k_UserWarning __pyx_k_ValueError __pyx_k__16 __pyx_k__4 __pyx_k__5 __pyx_k__53 __pyx_k__6 __pyx_k__62 __pyx_k_a __pyx_k_a_and_p_must_have_same_size __pyx_k_a_cannot_be_empty_unless_no_sam __pyx_k_a_must_be_1_dimensional __pyx_k_a_must_be_1_dimensional_or_an_in __pyx_k_a_must_be_greater_than_0_unless __pyx_k_add __pyx_k_all __pyx_k_all_2 __pyx_k_allclose __pyx_k_alpha __pyx_k_alpha_0 __pyx_k_any __pyx_k_arange __pyx_k_args __pyx_k_array __pyx_k_array_is_read_only __pyx_k_asarray __pyx_k_astype __pyx_k_at_0x_X __pyx_k_atol __pyx_k_b __pyx_k_beta __pyx_k_bg_type __pyx_k_binomial __pyx_k_binomial_n_p_size_None_Draw_sam __pyx_k_bit_generator __pyx_k_bit_generator_2 __pyx_k_bitgen __pyx_k_bool __pyx_k_bytes __pyx_k_bytes_length_Return_random_byte __pyx_k_can_only_re_seed_a_MT19937_BitGe __pyx_k_capsule __pyx_k_casting __pyx_k_check_valid __pyx_k_check_valid_must_equal_warn_rais __pyx_k_chisquare __pyx_k_chisquare_df_size_None_Draw_sam __pyx_k_choice __pyx_k_choice_a_size_None_replace_True __pyx_k_class __pyx_k_class_getitem __pyx_k_cline_in_traceback __pyx_k_collections_abc __pyx_k_copy __pyx_k_count_nonzero __pyx_k_cov __pyx_k_cov_must_be_2_dimensional_and_sq __pyx_k_covariance_is_not_symmetric_posi __pyx_k_cumsum __pyx_k_df __pyx_k_dfden __pyx_k_dfnum __pyx_k_dirichlet __pyx_k_dirichlet_alpha_size_None_Draw __pyx_k_disable __pyx_k_dot __pyx_k_double __pyx_k_dtype __pyx_k_empty __pyx_k_empty_like __pyx_k_enable __pyx_k_enter __pyx_k_eps __pyx_k_equal __pyx_k_exit __pyx_k_exponential __pyx_k_exponential_scale_1_0_size_None __pyx_k_f __pyx_k_f_dfnum_dfden_size_None_Draw_sa __pyx_k_finfo __pyx_k_flags __pyx_k_float64 __pyx_k_format __pyx_k_gamma __pyx_k_gamma_shape_scale_1_0_size_None __pyx_k_gauss __pyx_k_gc __pyx_k_geometric __pyx_k_geometric_p_size_None_Draw_samp __pyx_k_get __pyx_k_get_bit_generator __pyx_k_get_state __pyx_k_get_state_and_legacy_can_only_be __pyx_k_greater __pyx_k_gumbel __pyx_k_gumbel_loc_0_0_scale_1_0_size_N __pyx_k_has_gauss __pyx_k_high __pyx_k_hypergeometric __pyx_k_hypergeometric_ngood_nbad_nsamp __pyx_k_id __pyx_k_ignore __pyx_k_import __pyx_k_index __pyx_k_initializing __pyx_k_int16 __pyx_k_int32 __pyx_k_int64 __pyx_k_int8 __pyx_k_intp __pyx_k_isenabled __pyx_k_isfinite __pyx_k_isnan __pyx_k_isnative __pyx_k_isscalar __pyx_k_issubdtype __pyx_k_item __pyx_k_itemsize __pyx_k_kappa __pyx_k_key __pyx_k_kwargs __pyx_k_l __pyx_k_lam __pyx_k_laplace __pyx_k_laplace_loc_0_0_scale_1_0_size __pyx_k_left __pyx_k_left_mode __pyx_k_left_right __pyx_k_legacy __pyx_k_legacy_can_only_be_True_when_the __pyx_k_legacy_seeding __pyx_k_length __pyx_k_less __pyx_k_less_equal __pyx_k_loc __pyx_k_lock __pyx_k_logical_or __pyx_k_logistic __pyx_k_logistic_loc_0_0_scale_1_0_size __pyx_k_lognormal __pyx_k_lognormal_mean_0_0_sigma_1_0_si __pyx_k_logseries __pyx_k_logseries_p_size_None_Draw_samp __pyx_k_low __pyx_k_main __pyx_k_may_share_memory __pyx_k_mean __pyx_k_mean_and_cov_must_have_same_leng __pyx_k_mean_must_be_1_dimensional __pyx_k_mode __pyx_k_mode_right __pyx_k_mt19937 __pyx_k_mu __pyx_k_multinomial __pyx_k_multinomial_n_pvals_size_None_D __pyx_k_multivariate_normal __pyx_k_multivariate_normal_mean_cov_si __pyx_k_n __pyx_k_name __pyx_k_nbad __pyx_k_ndim __pyx_k_negative_binomial __pyx_k_negative_binomial_n_p_size_None __pyx_k_newbyteorder __pyx_k_ngood __pyx_k_ngood_nbad_nsample __pyx_k_nonc __pyx_k_noncentral_chisquare __pyx_k_noncentral_chisquare_df_nonc_si __pyx_k_noncentral_f __pyx_k_noncentral_f_dfnum_dfden_nonc_s __pyx_k_normal __pyx_k_normal_loc_0_0_scale_1_0_size_N __pyx_k_np __pyx_k_nsample __pyx_k_numpy __pyx_k_numpy_core_multiarray_failed_to __pyx_k_numpy_core_umath_failed_to_impor __pyx_k_numpy_linalg __pyx_k_numpy_random_mtrand __pyx_k_numpy_random_mtrand_pyx __pyx_k_object __pyx_k_object_which_is_not_a_subclass __pyx_k_operator __pyx_k_p __pyx_k_p_must_be_1_dimensional __pyx_k_pareto __pyx_k_pareto_a_size_None_Draw_samples __pyx_k_permutation __pyx_k_permutation_x_Randomly_permute __pyx_k_pickle __pyx_k_poisson __pyx_k_poisson_lam_1_0_size_None_Draw __pyx_k_poisson_lam_max __pyx_k_pos __pyx_k_power __pyx_k_power_a_size_None_Draws_samples __pyx_k_probabilities_are_not_non_negati __pyx_k_probabilities_contain_NaN __pyx_k_probabilities_do_not_sum_to_1 __pyx_k_prod __pyx_k_pvals __pyx_k_pvals_must_be_a_1_d_sequence __pyx_k_pyx_vtable __pyx_k_raise __pyx_k_rand __pyx_k_rand_2 __pyx_k_rand_d0_d1_dn_Random_values_in __pyx_k_randint __pyx_k_randint_low_high_None_size_None __pyx_k_randn __pyx_k_randn_d0_d1_dn_Return_a_sample __pyx_k_random __pyx_k_random_integers __pyx_k_random_integers_low_high_None_s __pyx_k_random_sample __pyx_k_random_sample_size_None_Return __pyx_k_randomstate_ctor __pyx_k_ranf __pyx_k_range __pyx_k_ravel __pyx_k_rayleigh __pyx_k_rayleigh_scale_1_0_size_None_Dr __pyx_k_reduce __pyx_k_reduce_2 __pyx_k_replace __pyx_k_reshape __pyx_k_return_index __pyx_k_reversed __pyx_k_right __pyx_k_rtol __pyx_k_sample __pyx_k_scale __pyx_k_searchsorted __pyx_k_seed __pyx_k_seed_seed_None_Reseed_a_legacy __pyx_k_set_bit_generator __pyx_k_set_state __pyx_k_set_state_can_only_be_used_with __pyx_k_shape __pyx_k_shuffle __pyx_k_shuffle_x_Modify_a_sequence_in __pyx_k_side __pyx_k_sigma __pyx_k_singleton __pyx_k_size __pyx_k_sort __pyx_k_spec __pyx_k_sqrt __pyx_k_stacklevel __pyx_k_standard_cauchy __pyx_k_standard_cauchy_size_None_Draw __pyx_k_standard_exponential __pyx_k_standard_exponential_size_None __pyx_k_standard_gamma __pyx_k_standard_gamma_shape_size_None __pyx_k_standard_normal __pyx_k_standard_normal_size_None_Draw __pyx_k_standard_t __pyx_k_standard_t_df_size_None_Draw_sa __pyx_k_state __pyx_k_state_dictionary_is_not_valid __pyx_k_state_must_be_a_dict_or_a_tuple __pyx_k_str __pyx_k_strides __pyx_k_subtract __pyx_k_sum __pyx_k_sum_pvals_1_1_0 __pyx_k_sum_pvals_1_astype_np_float64_1 __pyx_k_svd __pyx_k_take __pyx_k_test __pyx_k_tobytes __pyx_k_tol __pyx_k_tomaxint_size_None_Return_a_sam __pyx_k_triangular __pyx_k_triangular_left_mode_right_size __pyx_k_type __pyx_k_u4 __pyx_k_uint16 __pyx_k_uint32 __pyx_k_uint64 __pyx_k_uint8 __pyx_k_uniform __pyx_k_uniform_low_0_0_high_1_0_size_N __pyx_k_unique __pyx_k_unsafe __pyx_k_vonmises __pyx_k_vonmises_mu_kappa_size_None_Dra __pyx_k_wald __pyx_k_wald_mean_scale_size_None_Draw __pyx_k_warn __pyx_k_warnings __pyx_k_weibull __pyx_k_weibull_a_size_None_Draw_sample __pyx_k_writeable __pyx_k_x __pyx_k_x_must_be_an_integer_or_at_least __pyx_k_you_are_shuffling_a __pyx_k_zeros __pyx_k_zipf __pyx_k_zipf_a_size_None_Draw_samples_f __Pyx_GetVtable.isra.0 __Pyx__ExceptionReset.isra.0 __Pyx__ExceptionSave.isra.0 __Pyx_PyInt_BoolEqObjC.constprop.0 __Pyx_PyErr_GivenExceptionMatchesTuple __Pyx_TypeTest __Pyx_PyErr_GivenExceptionMatches.part.0 __Pyx_ImportFrom __Pyx_PyInt_As_long __Pyx_PyObject_FastCall_fallback.constprop.0 __Pyx_PyObject_FastCallDict.constprop.0 __Pyx_PyObject_CallMethod0 __Pyx_GetKwValue_FASTCALL __Pyx_PyInt_As_int64_t.part.0 __Pyx_IterFinish __Pyx_AddTraceback __pyx_dict_version.2 __pyx_dict_cached_value.1 __pyx_code_cache __pyx_pw_5numpy_6random_6mtrand_11RandomState_21random __pyx_pw_5numpy_6random_6mtrand_11RandomState_7__getstate__ __pyx_pw_5numpy_6random_6mtrand_11RandomState_5__str__ __Pyx_PyInt_As_int64_t __pyx_f_5numpy_6random_6mtrand_11RandomState__initialize_bit_generator __pyx_builtin_ValueError __Pyx_PyObject_GetItem __pyx_pw_5numpy_6random_6mtrand_11RandomState_11__reduce__ __pyx_pw_5numpy_6random_6mtrand_11RandomState_59noncentral_chisquare __pyx_f_5numpy_6random_7_common_cont __pyx_pw_5numpy_6random_6mtrand_11RandomState_53f __pyx_pw_5numpy_6random_6mtrand_11RandomState_83wald __pyx_pw_5numpy_6random_6mtrand_11RandomState_39rand __pyx_pw_5numpy_6random_6mtrand_11RandomState_41randn __pyx_pf_5numpy_6random_6mtrand_11RandomState_2__repr__ __pyx_builtin_id __pyx_specialmethod___pyx_pw_5numpy_6random_6mtrand_11RandomState_3__repr__ __pyx_pw_5numpy_6random_6mtrand_11RandomState_67pareto __pyx_pw_5numpy_6random_6mtrand_11RandomState_69weibull __pyx_pw_5numpy_6random_6mtrand_11RandomState_57chisquare __pyx_pw_5numpy_6random_6mtrand_11RandomState_49standard_gamma __pyx_pw_5numpy_6random_6mtrand_11RandomState_63standard_t __pyx_pw_5numpy_6random_6mtrand_11RandomState_71power __Pyx_PyObject_GetAttrStrNoError __Pyx_ImportDottedModule.constprop.0 __pyx_pw_5numpy_6random_6mtrand_11RandomState_47normal __pyx_pw_5numpy_6random_6mtrand_11RandomState_77logistic __pyx_pw_5numpy_6random_6mtrand_11RandomState_79lognormal __pyx_pw_5numpy_6random_6mtrand_11RandomState_73laplace __pyx_pw_5numpy_6random_6mtrand_11RandomState_75gumbel __pyx_pw_5numpy_6random_6mtrand_11RandomState_51gamma __Pyx_GetBuiltinName __Pyx__GetModuleGlobalName __pyx_pw_5numpy_6random_6mtrand_11RandomState_1__init__ __pyx_dict_version.182 __pyx_dict_cached_value.181 __pyx_dict_version.180 __pyx_dict_cached_value.179 __pyx_f_5numpy_6random_6mtrand_int64_to_long __pyx_dict_version.120 __pyx_dict_cached_value.119 __pyx_pw_5numpy_6random_6mtrand_11RandomState_99logseries __pyx_f_5numpy_6random_7_common_disc __pyx_pw_5numpy_6random_6mtrand_11RandomState_95geometric __pyx_pw_5numpy_6random_6mtrand_11RandomState_93zipf __pyx_pw_5numpy_6random_6mtrand_11RandomState_89negative_binomial __pyx_pw_5numpy_6random_6mtrand_11RandomState_85triangular PyArray_API __pyx_dict_version.100 __pyx_dict_cached_value.99 __pyx_dict_version.98 __pyx_dict_cached_value.97 __pyx_dict_version.96 __pyx_dict_cached_value.95 __pyx_dict_version.94 __pyx_dict_cached_value.93 __pyx_dict_version.92 __pyx_dict_cached_value.91 __pyx_dict_version.90 __pyx_dict_cached_value.89 __pyx_f_5numpy_6random_7_common_cont_broadcast_3 __pyx_pw_5numpy_6random_6mtrand_11RandomState_37uniform __pyx_dict_version.82 __pyx_dict_cached_value.81 __pyx_dict_version.80 __pyx_dict_cached_value.79 __pyx_dict_version.78 __pyx_dict_cached_value.77 __pyx_dict_version.84 __pyx_dict_cached_value.83 __pyx_builtin_OverflowError __pyx_pw_5numpy_6random_6mtrand_11RandomState_31randint __pyx_dict_version.34 __pyx_dict_cached_value.33 __pyx_dict_version.32 __pyx_dict_cached_value.31 __pyx_dict_version.30 __pyx_dict_cached_value.29 __pyx_dict_version.28 __pyx_dict_cached_value.27 __pyx_f_5numpy_6random_17_bounded_integers__rand_int16 __pyx_f_5numpy_6random_17_bounded_integers__rand_int32 __pyx_dict_version.14 __pyx_dict_cached_value.13 __pyx_f_5numpy_6random_17_bounded_integers__rand_int64 __pyx_dict_version.26 __pyx_dict_cached_value.25 __pyx_f_5numpy_6random_17_bounded_integers__rand_int8 __pyx_dict_version.24 __pyx_dict_cached_value.23 __pyx_f_5numpy_6random_17_bounded_integers__rand_uint64 __pyx_dict_version.22 __pyx_dict_cached_value.21 __pyx_f_5numpy_6random_17_bounded_integers__rand_uint32 __pyx_dict_version.20 __pyx_dict_cached_value.19 __pyx_f_5numpy_6random_17_bounded_integers__rand_uint16 __pyx_dict_version.18 __pyx_dict_cached_value.17 __pyx_f_5numpy_6random_17_bounded_integers__rand_uint8 __pyx_dict_version.16 __pyx_dict_cached_value.15 __pyx_f_5numpy_6random_17_bounded_integers__rand_bool __pyx_builtin_TypeError __pyx_pymod_exec_mtrand __pyx_builtin_RuntimeWarning __pyx_builtin_DeprecationWarning __pyx_builtin_UserWarning __pyx_builtin_IndexError __pyx_builtin_ImportError __pyx_vtable_5numpy_6random_6mtrand_RandomState __pyx_type_5numpy_6random_6mtrand_RandomState __pyx_vp_5numpy_6random_7_common_POISSON_LAM_MAX __pyx_vp_5numpy_6random_7_common_LEGACY_POISSON_LAM_MAX __pyx_vp_5numpy_6random_7_common_MAXSIZE __pyx_f_5numpy_6random_7_common_check_constraint __pyx_f_5numpy_6random_7_common_check_array_constraint __pyx_f_5numpy_6random_7_common_kahan_sum __pyx_f_5numpy_6random_7_common_double_fill __pyx_f_5numpy_6random_7_common_validate_output_shape __pyx_f_5numpy_6random_7_common_discrete_broadcast_iii __pyx_dict_version.294 __pyx_dict_cached_value.293 __pyx_dict_version.292 __pyx_dict_cached_value.291 __pyx_dict_version.290 __pyx_dict_cached_value.289 __pyx_dict_version.288 __pyx_dict_cached_value.287 __pyx_dict_version.286 __pyx_dict_cached_value.285 __pyx_dict_version.284 __pyx_dict_cached_value.283 __pyx_dict_version.282 __pyx_dict_cached_value.281 __pyx_dict_version.280 __pyx_dict_cached_value.279 __pyx_dict_version.278 __pyx_dict_cached_value.277 __pyx_dict_version.276 __pyx_dict_cached_value.275 __pyx_dict_version.274 __pyx_dict_cached_value.273 __pyx_dict_version.272 __pyx_dict_cached_value.271 __pyx_dict_version.270 __pyx_dict_cached_value.269 __pyx_dict_version.268 __pyx_dict_cached_value.267 __pyx_dict_version.266 __pyx_dict_cached_value.265 __pyx_dict_version.264 __pyx_dict_cached_value.263 __pyx_dict_version.262 __pyx_dict_cached_value.261 __pyx_dict_version.260 __pyx_dict_cached_value.259 __pyx_dict_version.258 __pyx_dict_cached_value.257 __pyx_dict_version.256 __pyx_dict_cached_value.255 __pyx_dict_version.254 __pyx_dict_cached_value.253 __pyx_dict_version.252 __pyx_dict_cached_value.251 __pyx_dict_version.250 __pyx_dict_cached_value.249 __pyx_dict_version.248 __pyx_dict_cached_value.247 __pyx_dict_version.246 __pyx_dict_cached_value.245 __pyx_dict_version.244 __pyx_dict_cached_value.243 __pyx_dict_version.242 __pyx_dict_cached_value.241 __pyx_dict_version.240 __pyx_dict_cached_value.239 __pyx_dict_version.238 __pyx_dict_cached_value.237 __pyx_dict_version.236 __pyx_dict_cached_value.235 __pyx_dict_version.234 __pyx_dict_cached_value.233 __pyx_dict_version.232 __pyx_dict_cached_value.231 __pyx_dict_version.230 __pyx_dict_cached_value.229 __pyx_dict_version.228 __pyx_dict_cached_value.227 __pyx_dict_version.226 __pyx_dict_cached_value.225 __pyx_dict_version.224 __pyx_dict_cached_value.223 __pyx_dict_version.222 __pyx_dict_cached_value.221 __pyx_dict_version.220 __pyx_dict_cached_value.219 __pyx_dict_version.218 __pyx_dict_cached_value.217 __pyx_dict_version.216 __pyx_dict_cached_value.215 __pyx_dict_version.214 __pyx_dict_cached_value.213 __pyx_dict_version.212 __pyx_dict_cached_value.211 __pyx_dict_version.210 __pyx_dict_cached_value.209 __pyx_dict_version.208 __pyx_dict_cached_value.207 __pyx_dict_version.206 __pyx_dict_cached_value.205 __pyx_dict_version.204 __pyx_dict_cached_value.203 __pyx_dict_version.202 __pyx_dict_cached_value.201 __pyx_mdef_5numpy_6random_6mtrand_1seed __pyx_mdef_5numpy_6random_6mtrand_3get_bit_generator __pyx_mdef_5numpy_6random_6mtrand_5set_bit_generator __pyx_mdef_5numpy_6random_6mtrand_7sample __pyx_mdef_5numpy_6random_6mtrand_9ranf __pyx_pw_5numpy_6random_6mtrand_9ranf __pyx_dict_version.200 __pyx_dict_cached_value.199 __pyx_pw_5numpy_6random_6mtrand_7sample __pyx_dict_version.198 __pyx_dict_cached_value.197 __pyx_pw_5numpy_6random_6mtrand_3get_bit_generator __pyx_dict_version.194 __pyx_dict_cached_value.193 __pyx_pw_5numpy_6random_6mtrand_5set_bit_generator __pyx_dict_version.196 __pyx_dict_cached_value.195 __pyx_pw_5numpy_6random_6mtrand_11RandomState_81rayleigh __pyx_pw_5numpy_6random_6mtrand_11RandomState_25exponential __pyx_pw_5numpy_6random_6mtrand_11RandomState_17set_state __pyx_pw_5numpy_6random_6mtrand_11RandomState_107shuffle __pyx_dict_version.166 __pyx_dict_cached_value.165 __pyx_dict_version.164 __pyx_dict_cached_value.163 __pyx_dict_version.162 __pyx_dict_cached_value.161 __pyx_dict_version.160 __pyx_dict_cached_value.159 __pyx_dict_version.158 __pyx_dict_cached_value.157 __pyx_dict_version.156 __pyx_dict_cached_value.155 __pyx_dict_version.154 __pyx_dict_cached_value.153 __pyx_pw_5numpy_6random_6mtrand_11RandomState_15get_state __pyx_dict_version.8 __pyx_dict_cached_value.7 __pyx_dict_version.6 __pyx_dict_cached_value.5 __pyx_pw_5numpy_6random_6mtrand_11RandomState_13seed __pyx_dict_version.4 __pyx_dict_cached_value.3 __pyx_pw_5numpy_6random_6mtrand_1seed __pyx_dict_version.192 __pyx_dict_cached_value.191 __pyx_dict_version.190 __pyx_dict_cached_value.189 __pyx_dict_version.188 __pyx_dict_cached_value.187 __pyx_dict_version.186 __pyx_dict_cached_value.185 __pyx_dict_version.184 __pyx_dict_cached_value.183 __pyx_pw_5numpy_6random_6mtrand_11RandomState_91poisson __pyx_pw_5numpy_6random_6mtrand_11RandomState_55noncentral_f __pyx_pw_5numpy_6random_6mtrand_11RandomState_33bytes __pyx_dict_version.36 __pyx_dict_cached_value.35 __pyx_pw_5numpy_6random_6mtrand_11RandomState_97hypergeometric __pyx_dict_version.118 __pyx_dict_cached_value.117 __pyx_dict_version.116 __pyx_dict_cached_value.115 __pyx_dict_version.114 __pyx_dict_cached_value.113 __pyx_dict_version.112 __pyx_dict_cached_value.111 __pyx_dict_version.110 __pyx_dict_cached_value.109 __pyx_dict_version.108 __pyx_dict_cached_value.107 __pyx_pw_5numpy_6random_6mtrand_11RandomState_19random_sample __pyx_pw_5numpy_6random_6mtrand_11RandomState_105dirichlet __pyx_dict_version.152 __pyx_dict_cached_value.151 __pyx_dict_version.150 __pyx_dict_cached_value.149 __pyx_dict_version.148 __pyx_dict_cached_value.147 __pyx_dict_version.146 __pyx_dict_cached_value.145 __pyx_dict_version.144 __pyx_dict_cached_value.143 __pyx_pw_5numpy_6random_6mtrand_11RandomState_27standard_exponential __pyx_pw_5numpy_6random_6mtrand_11RandomState_45standard_normal __pyx_pw_5numpy_6random_6mtrand_11RandomState_61standard_cauchy __pyx_pw_5numpy_6random_6mtrand_11RandomState_29tomaxint __pyx_dict_version.12 __pyx_dict_cached_value.11 __pyx_dict_version.10 __pyx_dict_cached_value.9 __pyx_pw_5numpy_6random_6mtrand_11RandomState_43random_integers __pyx_dict_version.86 __pyx_dict_cached_value.85 __pyx_dict_version.88 __pyx_dict_cached_value.87 __pyx_pw_5numpy_6random_6mtrand_11RandomState_9__setstate__ __pyx_pw_5numpy_6random_6mtrand_11RandomState_103multinomial __pyx_dict_version.140 __pyx_dict_cached_value.139 __pyx_dict_version.138 __pyx_dict_cached_value.137 __pyx_dict_version.142 __pyx_dict_cached_value.141 __pyx_pw_5numpy_6random_6mtrand_11RandomState_23beta __pyx_pw_5numpy_6random_6mtrand_11RandomState_65vonmises __pyx_pw_5numpy_6random_6mtrand_11RandomState_87binomial __pyx_dict_version.106 __pyx_dict_cached_value.105 __pyx_dict_version.102 __pyx_dict_cached_value.101 __pyx_dict_version.104 __pyx_dict_cached_value.103 __pyx_pw_5numpy_6random_6mtrand_11RandomState_101multivariate_normal __pyx_dict_version.136 __pyx_dict_cached_value.135 __pyx_dict_version.134 __pyx_dict_cached_value.133 __pyx_dict_version.132 __pyx_dict_cached_value.131 __pyx_dict_version.124 __pyx_dict_cached_value.123 __pyx_dict_version.122 __pyx_dict_cached_value.121 __pyx_dict_version.130 __pyx_dict_cached_value.129 __pyx_dict_version.128 __pyx_dict_cached_value.127 __pyx_dict_version.126 __pyx_dict_cached_value.125 __pyx_pw_5numpy_6random_6mtrand_11RandomState_109permutation __pyx_dict_version.178 __pyx_dict_cached_value.177 __pyx_dict_version.176 __pyx_dict_cached_value.175 __pyx_dict_version.174 __pyx_dict_cached_value.173 __pyx_dict_version.172 __pyx_dict_cached_value.171 __pyx_dict_version.170 __pyx_dict_cached_value.169 __pyx_dict_version.168 __pyx_dict_cached_value.167 __pyx_pw_5numpy_6random_6mtrand_11RandomState_35choice __pyx_dict_version.76 __pyx_dict_cached_value.75 __pyx_dict_version.74 __pyx_dict_cached_value.73 __pyx_dict_version.72 __pyx_dict_cached_value.71 __pyx_dict_version.68 __pyx_dict_cached_value.67 __pyx_dict_version.66 __pyx_dict_cached_value.65 __pyx_dict_version.64 __pyx_dict_cached_value.63 __pyx_dict_version.62 __pyx_dict_cached_value.61 __pyx_dict_version.60 __pyx_dict_cached_value.59 __pyx_dict_version.58 __pyx_dict_cached_value.57 __pyx_dict_version.52 __pyx_dict_cached_value.51 __pyx_dict_version.50 __pyx_dict_cached_value.49 __pyx_dict_version.48 __pyx_dict_cached_value.47 __pyx_dict_version.38 __pyx_dict_cached_value.37 __pyx_dict_version.70 __pyx_dict_cached_value.69 __pyx_dict_version.46 __pyx_dict_cached_value.45 __pyx_dict_version.44 __pyx_dict_cached_value.43 __pyx_dict_version.42 __pyx_dict_cached_value.41 __pyx_dict_version.40 __pyx_dict_cached_value.39 __pyx_dict_version.56 __pyx_dict_cached_value.55 __pyx_dict_version.54 __pyx_dict_cached_value.53 __pyx_moduledef __pyx_methods __pyx_moduledef_slots __pyx_methods_5numpy_6random_6mtrand_RandomState __pyx_getsets_5numpy_6random_6mtrand_RandomState __pyx_doc_5numpy_6random_6mtrand_11RandomState_12seed __pyx_doc_5numpy_6random_6mtrand_11RandomState_14get_state __pyx_doc_5numpy_6random_6mtrand_11RandomState_16set_state __pyx_doc_5numpy_6random_6mtrand_11RandomState_18random_sample __pyx_doc_5numpy_6random_6mtrand_11RandomState_20random __pyx_doc_5numpy_6random_6mtrand_11RandomState_22beta __pyx_doc_5numpy_6random_6mtrand_11RandomState_24exponential __pyx_doc_5numpy_6random_6mtrand_11RandomState_26standard_exponential __pyx_doc_5numpy_6random_6mtrand_11RandomState_28tomaxint __pyx_doc_5numpy_6random_6mtrand_11RandomState_30randint __pyx_doc_5numpy_6random_6mtrand_11RandomState_32bytes __pyx_doc_5numpy_6random_6mtrand_11RandomState_34choice __pyx_doc_5numpy_6random_6mtrand_11RandomState_36uniform __pyx_doc_5numpy_6random_6mtrand_11RandomState_38rand __pyx_doc_5numpy_6random_6mtrand_11RandomState_40randn __pyx_doc_5numpy_6random_6mtrand_11RandomState_42random_integers __pyx_doc_5numpy_6random_6mtrand_11RandomState_44standard_normal __pyx_doc_5numpy_6random_6mtrand_11RandomState_46normal __pyx_doc_5numpy_6random_6mtrand_11RandomState_48standard_gamma __pyx_doc_5numpy_6random_6mtrand_11RandomState_50gamma __pyx_doc_5numpy_6random_6mtrand_11RandomState_52f __pyx_doc_5numpy_6random_6mtrand_11RandomState_54noncentral_f __pyx_doc_5numpy_6random_6mtrand_11RandomState_56chisquare __pyx_doc_5numpy_6random_6mtrand_11RandomState_58noncentral_chisquare __pyx_doc_5numpy_6random_6mtrand_11RandomState_60standard_cauchy __pyx_doc_5numpy_6random_6mtrand_11RandomState_62standard_t __pyx_doc_5numpy_6random_6mtrand_11RandomState_64vonmises __pyx_doc_5numpy_6random_6mtrand_11RandomState_66pareto __pyx_doc_5numpy_6random_6mtrand_11RandomState_68weibull __pyx_doc_5numpy_6random_6mtrand_11RandomState_70power __pyx_doc_5numpy_6random_6mtrand_11RandomState_72laplace __pyx_doc_5numpy_6random_6mtrand_11RandomState_74gumbel __pyx_doc_5numpy_6random_6mtrand_11RandomState_76logistic __pyx_doc_5numpy_6random_6mtrand_11RandomState_78lognormal __pyx_doc_5numpy_6random_6mtrand_11RandomState_80rayleigh __pyx_doc_5numpy_6random_6mtrand_11RandomState_82wald __pyx_doc_5numpy_6random_6mtrand_11RandomState_84triangular __pyx_doc_5numpy_6random_6mtrand_11RandomState_86binomial __pyx_doc_5numpy_6random_6mtrand_11RandomState_88negative_binomial __pyx_doc_5numpy_6random_6mtrand_11RandomState_90poisson __pyx_doc_5numpy_6random_6mtrand_11RandomState_92zipf __pyx_doc_5numpy_6random_6mtrand_11RandomState_94geometric __pyx_doc_5numpy_6random_6mtrand_11RandomState_96hypergeometric __pyx_doc_5numpy_6random_6mtrand_11RandomState_98logseries __pyx_doc_5numpy_6random_6mtrand_11RandomState_100multivariate_normal __pyx_doc_5numpy_6random_6mtrand_11RandomState_102multinomial __pyx_doc_5numpy_6random_6mtrand_11RandomState_104dirichlet __pyx_doc_5numpy_6random_6mtrand_11RandomState_106shuffle __pyx_doc_5numpy_6random_6mtrand_11RandomState_108permutation __pyx_doc_5numpy_6random_6mtrand_8ranf __pyx_doc_5numpy_6random_6mtrand_6sample __pyx_doc_5numpy_6random_6mtrand_4set_bit_generator __pyx_doc_5numpy_6random_6mtrand_2get_bit_generator __pyx_doc_5numpy_6random_6mtrand_seed deregister_tm_clones __do_global_dtors_aux completed.0 __do_global_dtors_aux_fini_array_entry frame_dummy __frame_dummy_init_array_entry random_loggam.part.0 fe_double we_double ke_double fe_float we_float ke_float wi_double ki_double fi_double random_standard_gamma.part.0 wi_float ki_float fi_float legacy_gauss.part.0 legacy_standard_gamma.part.0 __FRAME_END__ random_laplace random_buffered_bounded_bool legacy_random_zipf random_geometric_inversion legacy_f random_weibull random_f legacy_pareto random_negative_binomial random_standard_cauchy __pyx_module_is_main_numpy__random__mtrand legacy_chisquare random_standard_exponential_fill_f legacy_gauss random_standard_gamma random_binomial_btpe random_logseries legacy_normal random_rayleigh random_standard_exponential random_uniform legacy_random_binomial random_bounded_uint64_fill legacy_random_multinomial random_bounded_uint16_fill legacy_standard_exponential random_logistic legacy_negative_binomial random_standard_uniform_fill_f random_bounded_uint64 random_positive_int random_standard_gamma_f random_triangular random_buffered_bounded_uint32 legacy_rayleigh random_power random_bounded_uint8_fill random_noncentral_f random_standard_exponential_inv_fill_f legacy_wald random_buffered_bounded_uint8 random_beta random_exponential __dso_handle random_gamma legacy_random_poisson random_standard_uniform_f random_loggam random_gamma_f legacy_weibull random_standard_exponential_f random_pareto random_positive_int64 legacy_standard_gamma random_geometric_search random_standard_t random_vonmises random_bounded_uint32_fill random_standard_normal_f random_positive_int32 random_standard_uniform legacy_power random_normal legacy_exponential random_chisquare legacy_standard_cauchy legacy_gamma random_standard_exponential_fill random_interval random_wald random_noncentral_chisquare _DYNAMIC random_standard_normal legacy_beta legacy_noncentral_f random_standard_exponential_inv_fill random_lognormal random_buffered_bounded_uint16 legacy_random_hypergeometric random_uint random_gumbel random_standard_uniform_fill legacy_standard_t random_standard_normal_fill_f legacy_logseries legacy_random_geometric random_bounded_bool_fill __GNU_EH_FRAME_HDR __TMC_END__ _GLOBAL_OFFSET_TABLE_ legacy_vonmises random_binomial_inversion legacy_noncentral_chisquare random_standard_normal_fill legacy_lognormal PyUnicode_FromFormat log1pf@@GLIBC_2.2.5 PyObject_SetItem PyList_New _PyUnicode_Ready PyExc_SystemError PyDict_SetItemString free@@GLIBC_2.2.5 PyDict_Size PyException_SetTraceback PyMethod_Type _ITM_deregisterTMCloneTable PyFloat_Type PyTuple_Type PyObject_Format PyErr_Restore PyList_AsTuple _PyThreadState_UncheckedGet PyModuleDef_Init PyEval_RestoreThread Py_EnterRecursiveCall PyFrame_New __isnan@@GLIBC_2.2.5 PyCapsule_GetName PyNumber_InPlaceAdd exp@@GLIBC_2.2.5 PyNumber_Add PyObject_GetAttrString PyImport_AddModule PyBytes_FromStringAndSize _PyObject_GenericGetAttrWithDict PyObject_SetAttrString PyErr_WarnEx _Py_Dealloc PyModule_NewObject PyErr_SetObject PyErr_NormalizeException PyNumber_Multiply PyObject_RichCompare _fini PyImport_GetModuleDict PyExc_RuntimeError PyCMethod_New PyNumber_Long PyErr_GivenExceptionMatches PyErr_SetString PyObject_IsInstance PyExc_Exception PyExc_ValueError PyExc_DeprecationWarning PyExc_TypeError PyInterpreterState_GetID PySequence_Contains memset@@GLIBC_2.2.5 PyMem_Realloc PyErr_ExceptionMatches pow@@GLIBC_2.2.5 log@@GLIBC_2.2.5 PyOS_snprintf PyTraceBack_Here log1p@@GLIBC_2.2.5 fmod@@GLIBC_2.2.5 PyObject_CallFinalizerFromDealloc PyObject_Not PyNumber_InPlaceTrueDivide PyLong_FromSsize_t PyFloat_FromDouble PyType_Ready acos@@GLIBC_2.2.5 PyLong_FromLong memcmp@@GLIBC_2.2.5 PyLong_AsSsize_t PyModule_GetName PyErr_Clear PyList_Append PyCapsule_IsValid PyExc_KeyError PyImport_GetModule _PyUnicode_FastCopyCharacters _Py_FalseStruct __gmon_start__ expf@@GLIBC_2.2.5 PyTuple_New PyObject_GenericGetAttr PyThreadState_Get PyExc_OverflowError memcpy@@GLIBC_2.14 expm1@@GLIBC_2.2.5 PyNumber_Remainder PyType_Modified PyObject_SetAttr PyErr_Occurred _Py_EllipsisObject PyLong_AsLong PyImport_ImportModule sqrtf@@GLIBC_2.2.5 _PyDict_GetItem_KnownHash Py_LeaveRecursiveCall PyDict_GetItemString powf@@GLIBC_2.2.5 PyObject_Size malloc@@GLIBC_2.2.5 _Py_NoneStruct PyFloat_AsDouble PyObject_IsTrue _PyType_Lookup PyImport_ImportModuleLevelObject PyObject_Hash PyUnicode_Compare PyInit_mtrand _Py_TrueStruct logf@@GLIBC_2.2.5 PyDict_New PyExc_IndexError PyObject_GC_IsFinalized PyBool_Type PyDict_Type PyDict_Next PyBaseObject_Type memmove@@GLIBC_2.2.5 PyUnicode_AsUTF8 PyLong_Type PyCapsule_Type _PyObject_GetDictPtr PyErr_Fetch PyUnicode_FromString PyObject_GetIter PyEval_SaveThread PyUnicode_InternFromString PyExc_ImportError PyDict_SetItem PySequence_Tuple PyExc_AttributeError PyDict_Copy PyExc_StopIteration PySequence_List floor@@GLIBC_2.2.5 PyUnicode_Type PyCapsule_New PyType_IsSubtype PyUnicode_Decode PyErr_Format PyCapsule_GetPointer PySlice_New PyExc_NameError PyUnicode_FromStringAndSize PyModule_GetDict _ITM_registerTMCloneTable PyUnicode_Concat PyNumber_Index PyObject_GetAttr sqrt@@GLIBC_2.2.5 PyCFunction_Type _PyDict_NewPresized ceil@@GLIBC_2.2.5 PyUnicode_Format PyLong_FromString PyMem_Malloc PyErr_WarnFormat __cxa_finalize@@GLIBC_2.2.5 _init PyNumber_Subtract PyUnicode_New PyTuple_Pack PyCode_NewWithPosOnlyArgs Py_GetVersion PyCode_NewEmpty PyObject_GC_UnTrack PyDict_GetItemWithError PyList_Type PyImport_Import .symtab .strtab .shstrtab .note.gnu.build-id .gnu.hash .dynsym .dynstr .gnu.version .gnu.version_r .rela.dyn .rela.plt .init .text .fini .rodata .eh_frame_hdr .eh_frame .init_array .fini_array .data.rel.ro .dynamic .got .got.plt .data .bss .comment 8 8 $ . o ` ` 4 8 h @ + H o , , ^ U o P d H n B (5 (5
x P P s P P ~ X X ċ
?
(
(
x @
0 / p !}