ELF>@, @8@ ''[ u ''$$PtdEEEttQtdRtd''GNU 1*.J]Z^^ a MA@04"@AVD( 6!Q@!PQ "T@ ((#Da@ @0D 1"lP Xk/}+*P{`ns`cD\~\ ?{KF'3}0SS( }dFܽڃ1<\=tk s(y= aqғmRg# t#CESND`GCYdh.G/6 $a 讋Rm(MFZH)0w}vؔqX|i9jQfc; e䞓e$#AtmdA 9pPe75/ q3`%gl HkΑ3"9{Oj~3^ULJݼWaڟXI~.i8 | ^x  z{  W P  c 7Pj  / 7 [  =  t.=  F2"W Er 9 k  6  L a 9  S' p L   z 3 " #Z  #(  i4 8  c >(  R"X ZY n @ X (5 .  C ZD Pou f 0(  P  `%J ІV  /   `(, S]  @'   6  0  I= Ж   B  @ &   Y G P  Г9# K_ ' 0): ^[ pNm >"  @Wx y p  0}    W  pq & p>  t  : Юs `/ ? 0 p  )* /! 9 )t  NR  P9 9  | 0? ` # 0`s  2    , `  Q  j     G H /  p  мW Ш&V 9  p? 0S   k g " __gmon_start___init_fini_ITM_deregisterTMCloneTable_ITM_registerTMCloneTable__cxa_finalize_Py_NoneStructPyBaseObject_TypePyThreadState_Get_Py_CheckRecursionLimitPyObject_Call_Py_CheckRecursiveCallPyErr_OccurredPyExc_SystemErrorPyErr_SetStringPyObject_GetAttr_PyType_LookupPyExc_AttributeErrorPyErr_SetObjectrandom_intervalmemcpy_PyThreadState_UncheckedGetPyFrame_NewPyEval_EvalFrameEx_Py_DeallocPyExc_DeprecationWarningPyErr_WarnFormatPyExc_TypeErrorPyErr_FormatPyExc_OverflowErrorPyLong_AsLongPyLong_TypePyObject_GC_UnTrackPyObject_CallFinalizerFromDeallocPyErr_NormalizeExceptionPyException_SetTracebackPyObject_GetAttrStringPyExc_ValueErrorPyOS_snprintfPyErr_WarnExPyModule_GetDictPyDict_NewPyImport_ImportModuleLevelObjectPyList_NewPyDict_GetItemStringPyModule_GetNamePyExc_ImportErrorPyCapsule_IsValidPyCapsule_GetNamePyCapsule_GetPointerPyDict_SetItemStringPyErr_ExceptionMatchesPyErr_ClearPyInterpreterState_GetIDPyModule_NewObject_Py_TrueStruct_Py_FalseStructPyFloat_TypePyObject_RichComparePyUnicode_TypememcmpPyObject_IsTrue_PyUnicode_ReadyPyDict_GetItemWithErrorPyExc_KeyErrorPyTuple_PackPyList_TypePyTuple_TypePyLong_FromSsize_tPyObject_GetItemPyDict_NextPyUnicode_ComparePyTuple_NewPySlice_NewPyEval_EvalCodeExPyExc_NameErrorPyExc_StopIterationPyErr_GivenExceptionMatchesPyFunction_TypePyCFunction_TypePyTraceBack_Here_PyObject_GetDictPtrPyObject_NotPyObject_SetAttrPyUnicode_FromStringPyCode_NewPyUnicode_FromFormatPyMem_Realloc_PyDict_GetItem_KnownHashPyMem_Malloclegacy_waldPyDict_Sizerandom_rayleighlegacy_lognormalrandom_logisticrandom_gumbelrandom_laplacelegacy_powerlegacy_weibulllegacy_paretorandom_vonmiseslegacy_standard_tlegacy_standard_cauchylegacy_noncentral_chisquarelegacy_chisquarelegacy_noncentral_flegacy_flegacy_gammalegacy_standard_gammalegacy_normallegacy_gausslegacy_standard_exponentiallegacy_exponentiallegacy_betaPyDict_SetItemrandom_standard_uniform_fillPyDict_TypePyNumber_AddPyNumber_InPlaceAddPyNumber_IndexPyLong_AsSsize_tPyExc_IndexErrorPyMethod_TypePyLong_FromLonglegacy_random_logserieslegacy_random_geometriclegacy_random_zipflegacy_random_poissonlegacy_negative_binomialPyObject_SetItemPyFloat_FromDoublePyExc_RuntimeErrorPy_GetVersionPyFrame_TypePyBytes_FromStringAndSizePyUnicode_FromStringAndSizePyImport_AddModulePyObject_SetAttrStringPyUnicode_InternFromStringPyUnicode_DecodePyObject_HashPyLong_FromString__pyx_module_is_main_numpy__random__mtrandPyImport_GetModuleDict_Py_EllipsisObjectPyType_ReadyPyCapsule_NewPyImport_ImportModulePyCapsule_TypePyExc_ExceptionPyType_ModifiedPyCFunction_NewEx_PyDict_NewPresizedPyDict_CopyPyObject_IsInstancePyEval_SaveThreadrandom_positive_intPyEval_RestoreThreadrandom_uniformPyFloat_AsDoublePyBool_TypePyUnicode_FormatPyNumber_RemainderPyObject_SizePySequence_ListPyNumber_MultiplyPyList_AsTuplePyList_AppendPyObject_GetIterPySequence_Tuplerandom_triangularlegacy_random_binomiallegacy_random_multinomialPySequence_Containslegacy_random_hypergeometricPyNumber_LongPyNumber_InPlaceTrueDividePyNumber_SubtractPyInit_mtrandPyModuleDef_Initlogsqrtpowexp__isnanrandom_binomial_inversionrandom_binomial_btpefloorrandom_loggamrandom_standard_uniform_frandom_standard_uniformrandom_standard_uniform_fill_frandom_standard_exponentialrandom_standard_exponential_fillrandom_standard_exponential_fexpflogfrandom_standard_exponential_fill_frandom_standard_exponential_inv_fillrandom_standard_exponential_inv_fill_frandom_standard_normalrandom_standard_normal_fillrandom_standard_normal_frandom_standard_normal_fill_frandom_standard_gammarandom_standard_gamma_fpowfsqrtfrandom_positive_int64random_positive_int32random_uintrandom_normalrandom_exponentialrandom_gammarandom_gamma_frandom_betarandom_chisquarerandom_frandom_standard_cauchyrandom_paretorandom_weibullrandom_powerrandom_lognormalrandom_standard_trandom_negative_binomialrandom_noncentral_chisquarerandom_noncentral_frandom_waldacosfmodrandom_geometric_searchrandom_geometric_inversionceilrandom_bounded_uint64random_buffered_bounded_uint32random_buffered_bounded_uint16random_buffered_bounded_uint8random_buffered_bounded_boolrandom_bounded_uint64_fillrandom_bounded_uint32_fillrandom_bounded_uint16_fillrandom_bounded_uint8_fillmemsetrandom_bounded_bool_filllibm.so.6libpthread.so.0libc.so.6_edata__bss_start_endGLIBC_2.2.5] ui wui '`' '')))8))))))H)ȗ))З)))))))))) ))()@)0))8)8)`)H)h))p)`)x)))))@)))))Ș)@)И)))))))))) ))())@))H))P))`)p)h))p)))p)))))))))))))))))))))))@)P)H))P))`)H)h)))H))))H)))))Ț))К)))))))))))))) ))())0))@))H))`))h))p)))P))p))@)))))ț))Л)))))))))x))) )H)())@))H))`))h))p)H)x))))))))Ȝ))М))؜) ))))))X))) ))())@))`))h))x)) )p))؝)h))P)`)) ()X)0)`P)P)X)hx)H)))@))Ȟ)8)О) )0)))() )@@) )H)@h))p)@))))))))))))0))8)X))`)@))))))@Р))ؠ)@))) ))()H))P)`p))x))))))ȡ))))@)))8))@)`))h)@)x)) )p))آ)h)))`))()X)0)P)P)X)x)H)))@))ȣ)8)У))0)))() ) @) )H)h))p))))@)))))))))0))8)X))`)`)))@)))@Х))إ))))` ))() H))P)@p))x) )))P))Ȧ))))A)))8))@)`))h))x))~)p))0ا)h)))`)) ()X)0)3P)P)X)1x)H))?)@))?Ȩ)8)Ш)`)0))~)() ) @) )H)h))p)@~))))))))))))0))8)X))`)X))))))Ъ))ت)))) ))()PH))P)p))x)@)))))ȫ)=)))=)))8))@)`))h))x)))p))`oج)h)))`))()X)0)P)P)X)x)H))l)@))`ȭ)8)Э)8)0))8)() )0@) )H) h))p) )))))))))c))) 0))8) X))`)W))))))Я))د)))) ))()H))P)pp))x))))))Ȱ))))))).8))@).`))h))x)))p))ر)h)))`))()X)0)P)P)X)x)H)) )@))Ȳ)8)в))0)))() )@) )H)h))p)))))))))))))0))8);X))`);)))I)))д))ش)())) ))()H))P)p))x)=)))))ȵ)))))))@68))@)`))h))x)))p)) ض)h)) )`))()X)0)P)P)X)@#x)H))p)@))ȷ)8)з)@)0))@)() )@) )H)+h))p)))))))))))))0))8)X))`)))))))xй))ع))))h ))()XH))P)p))x))))H))Ⱥ)|)))|)))8))@)`))h)9)x)))p))ػ)h)))`))()X)0)P)P)X)x)H))`)@))ȼ)8)м))0))0)() )@) )H)h))p)))))))))))))80))8)8X))`))))P)))Pо))ؾ) )))@ ))()@H))P)@p))x))))))ȿ)))))))v8))@)v`))h))x)))p))q)h)))`))()X)0)P)P)X)(x)H))()@)))8)))0)) )() )@) )H)h))p))))7)))7)))h)))]0))8)]X))`)X)))@)))@))) ))) ))()vH))P)vp))x))))S)))S))))))8))@)@`))h))x)))p)))h)))`))()X)0)P)P)X)%x)H)))@)))8))p)0))@)() )@) )H)h))p))))()))5)))5)))0))8)X))`))))`)))))))))  ))()H))P)p))x))))`)))))))))j8))@)j`))h)w)x))`)p)))h)))`))N()X)0)dP)P)X)dx)H)))@))^)8))I)0))I)() )@) )H)h))p)))))))@l)))X)))X0))8)`X))`))))))))))))) a ))()`H))P)`p))x))))`)))D)))D)))R8))@)L`))h))x)))p)) W)h)))`))()X)0)P)P)X)x)H)))@))F)8))F)0))?)() )@) )H)h))p)@)))@)))))):))):0))8)TX))`)0)))0)))`T))):))): ))()H))P)p))x)@)))5)))4)))4)))08))@)+`))h)&)x)))p)))h)))`)) ()X)0)`P)P)X)`x)H)) )@)) )8)) )0)) )() )@) )H)h))p)@)))p)))p)))F))).0))8).X))`))))@F))))))))) ))()H))P)p))x)!))))))))))))@8))@)``))h)`)x))6)p))!)h)))`))()X)0)P)P)X)(x)H)))@)))8))@))0))x)() )q@) )H)h))p))))`)))))))))0))8) X))`) )))))))))))) ))() H))P) p))x)")))))))))@h)))))))?)0)X)))))"))))()`8)))@)$)) )()@)!H)`)3h)`x))) )P))),)@C)`)))p))))))))@){) )()p8)@s)@)H)X)@o)`)8h)x)i))I)5)^))6))\)))@)O))A)`)B))))>) )()8)5)@)H)X)`*)`)h)x)")))~))))0{))))w) ())`t) ())pp)( )v()m8)(@)kH)0jX)(`)[h)gx)()P)e)()G)a)()@)^) ()8)[)`()2)Y){( )*()pU8)m(@)#H)QX)Z(`)h)0Nx)N())J)=())G)3())`D)'()o)`)`()))( )()8) (@)H)X)`'`)h)x)')))`'))) ')))@')Q)t)'))P))' )e()08)@'@)<H)XX)'`)Dh)]x)').)p)')))'''''' ' '' ' ('0'8'@'H'P'X'%`'+h',p'-x'.'''''''J'L'MȎ'NЎ'R؎''W''`'''g'i' '('0'k8'l@'mH'P'oX'p`'qh'p'rx''x''{''''}''ȏ'Џ'؏'''''' '('0'8'@'H'P'X' `'h'p'x''''''''''Ȑ'А'ؐ'''''''' ' '('!0'8'"@'#H'P'$X'`'&h''p'x'(')'*'''/'0'1'2'3ȑ'4Б'5ؑ''6''7'8'9':';'< '=('>0'?8'@@'AH'BP'CX'D`'Eh'Fp'Gx'H'I'K'O'P'Q'S'T''UȒ'VВ'ؒ'X'Y'Z'[''\']'^'_ '('a0'b8'c@'dH'P'X'e`'fh'p'hx'''j'n'''''s'tȓ'uГ'vؓ'w''y'z'|'~''' '('0'8'@'H'P'X'`'h'p'x''''''''''Ȕ'Д'ؔ'HhH5"&%$&@%"&h%&h%&h% &h%&h%&h%&h%&hp%&h`%&h P%&h @%&h 0%&h %&h %&h%&h%&h%&h%&h%&h%&h%z&h%r&h%j&hp%b&h`%Z&hP%R&h@%J&h0%B&h %:&h%2&h%*&h%"&h %&h!%&h"% &h#%&h$%&h%%&h&%&h'p%&h(`%&h)P%&h*@%&h+0%&h, %&h-%&h.%&h/%&h0%&h1%&h2%&h3%&h4%z&h5%r&h6%j&h7p%b&h8`%Z&h9P%R&h:@%J&h;0%B&h< %:&h=%2&h>%*&h?%"&h@%&hA%&hB% &hC%&hD%&hE%&hF%&hGp%&hH`%&hIP%&hJ@%&hK0%&hL %&hM%&hN%&hO%&hP%&hQ%&hR%&hS%&hT%z&hU%r&hV%j&hWp%b&hX`%Z&hYP%R&hZ@%J&h[0%B&h\ %:&h]%2&h^%*&h_%"&h`%&ha%&hb% &hc%&hd%&he%&hf%&hgp%&hh`%&hiP%&hj@%&hk0%&hl %&hm%&hn%&ho%&hp%&hq%&hr%&hs%&ht%z&hu%r&hv%j&hwp%b&hx`%Z&hyP%R&hz@%J&h{0%B&h| %:&h}%2&h~%*&h%"&h%&h%&h% &h%&h%&h%&h%&hp%&h`%&hP%&h@%&h0%&h %&h%&h%&h%&h%&h%&h%&h%&h%z&h%r&h%j&hp%b&h`AVEAUIHATIUHSH}HHH@u H&HLH5H816mLK M9s#H|&MHLH5H81 AAuKM9vFIPLIAQHKML1i1L1=ZYyH uHZ1HH[]A\A]A^AWIAVIAUIH58ATIUSAPHLHHHHu(LLH5 HH&H81H-)HH&1HHHH-)HHc;)H5:)1H-)HxH-)H5.)1H_-)HNH58)1H4-)H+H5\8)1xH -)HH5I8)1UH,)HH5.8)12H,)HH51)1H,)HH57)1H],)H|H51)1H2,)HYH50)1H,)H6H50)1H+)HH59)1`H+)HH5A9)1=H+)HH5V9)1H[+)HH5:)1H0+)HH5P7)1H+)HdH52)1H*)HAH51)1H*)HH5w2)1kH*)HH50)1HHY*)HH5i1)1%H.*)HH5v4)1H*)HH5+1)1H))HoHHHH*)HQH54)1H))H.H7)H53)1tH]))HH53)1QH2))HH5 *)Hڿ1+H))HH5+)1H()HH54)1H()HuHn&H5))1H|()HKH6)H5*)1HJ()H!H5))1nH()HH5G.)1KH')HH5.)1(HH`0)H53)1HH7)L ~7)VA111AQh 5+)5.)RRPRRHPHRH/)H543)1H/H 7)L 7)QA111AQh5+)5y.)RRPRRRHPHH&)H gNH6)HYQH=)HL$~D$HD$D$)&)xZH=~6)11H-)HHt;H5+)HHHxHHu+H%!HHuHAI[A#H5k4)H=<6)H=)xxH-)H=Y)H4)HHBLApHHk)H5%)mHCH uHH=)KHHKA HHB*H5(HCH uH8H=(HHKA HH(H5(H4CH uHH=(HHUKA`HH}(H5p(H4)HBAH HHR(H5?(OHBA0HH1(H5(%H64)HBAXHH (H5'H3)HRBAHH'H5'H(BAHH'H5'HAAHH'H5_'oHp3)HAAHHm'H5.'>HAAHHA'H5'HyAAHH''H5&HOAAHH 'H5&H2)HAAHH&H5&H@AHH&H5U&eH@AHH&H5+&;H@AHHy&H5&Hv@H uH+H=V&HHHA`HH8%H5)&H'@A@HH!&H5%H?HH5I')HH?1HIHu )HuH%&H5H8nHMuH`M?AHH%H5m%Hk?H uH H=%HHGH %Hz0)HH5~%C?H \%HM0)HH5R%?H U%H 0)HH5M%\>H uHH=MPHHGH UH.0)HH5 %>H 0H0)HH5$>H H/)HH5$>H H/)HH5$b>H Hz/)HH5$}=>H HM/)HH5$X>H wH /)HH5w$3=H RH.)HH5^$=H -H.)HH5E$=H uHH=~#HHEH ;H\.)HH5$_=H fH/.)HH5#z:=H #H.)HH5$U=H tH-)HH5#0<H H-)HH5# <H H{-)HH5#<H HN-)HH5#<H H!-)HH5}#\<H cH,)HH5i#w7<H uHH=$)11hOHH+@H5#)H=-)HV5H uHaH=)11!OHH?H5n)H=w-)HQ5H uHpHH?H))HHH))HCHH=()1NHH 5H uHH5))HC^HHs;H5))H=,)Hq4H uH|HMuHnH=")11.NHH$?H5")H=,)H;HMuH&|HH>H*)HHH*)HEHH=#)MHH:HMuHH5[*)HK]HH4H5H*)H=+)Hy4HMuHH uHvHD$HD$ HD$(HD$0HD$8HD$@ HL$(HT$ HHt$ICH= HHH5 HjHMHuHHuH&H5 H8FH&H9Ct,H]&H5^H8H H 1HH H*)uHrH*)HuH&H5S H8P= H*)t& H5H̷&H81z HU*)w'H5H&H81>YAŅuHp&H59H812tHQ&H5JH81H|$HH,&I\$XH(H9HujR_HEHLu1I9~H;\HE1M9~JtH9HC@HFHsd@t[HXHtHJ1H9~H5)H="&)1s@HHt-HRH u,H߽R"RR RI$HL$(HT$ Ht$MH|$0Ht HuH|$8Ht HuH|$@HJ5HA575H &)HHk9H%)H5Y)HH:.H uHEH=^%)Hڴ&H=K%)HH)`HH9H5)H=B&)H.H uHH&)H )H9Hu)H)Ht HH).H=*)VHH=)H)H5)HH8H5[!)H?HH.H uHZH53!)H=%)H$;4HMuH.Hg%)H )H9Hu)H)Ht HH-).H=s)VHH=b)H)H5)HH7H5 )H>HH3HMuHH5k )H=$)HlE-H uHwH$)H 9)H9Hu)H$)Ht HH).H=)_UHH=)H)H5) HHL7H5)H%>HH,H uHH5)H=$)H2HMuHH#)H r)H9Hu)H])Ht HH-N).H=)THH=)H-)H5.)iHH6H5)Hn=HHt2HMuH4H5)H=f#)H+H uH HB#)H )H9Hu)H)Ht HH).H=N)SHH==)Hf)H5g)HH6H5)H<HH+H uH~H5)H=")HH1HMuHRH")H )H9Hu)H)Ht HH-).H=):SHH=)H)H5)HHZ5H5)H<HH(1HMuHH5o)H=!)H*H uHH!)H )H9Hu)H)Ht HH).H=)RHH=)H)H5)DHH4H5)HI;HH9*H uHH5Y)H=B!)HW0HMuHH!)H V)H9Hu)HA)Ht HH-2).H=))QHH=)H)H5)HH4H5)H:HH/HMuHXH5)H= )H"j)H uH-Hf )H )H9Hu)Hz)Ht HHk).H=r)QHH=a)HJ)H5K)HHh3H5)H9HH(H uHH5)H=)Hl /HMuHvH)H )H9Hu)H)Ht HH-).H=)^PHH=)H)H5)HH2H5)H$9HH.HMuHH5)H=)H!(H uHH)H )H9Hu)H )Ht HH ).H=)OHH=)H )H5 )hHH2H5E)Hm8HH'H uH4H5)H=f)H-HMuHHA)H : )H9Hu)H% )Ht HH- ).H=M)NHH=<)H )H5 )HHv1H5N)H7HHD-HMuH|H5%)H=)HF&H uHQH)H s )H9Hu)H^ )Ht HHO ).H=)9NHH=)H. )H5/ )HH0H5o)H6HH^&H uHH5G)H=)Hs,HMuHH)H )H9Hu)H )Ht HH- ).H=)MHH=)Hg )H5h )CHH*0H5)HH6HH+HMuHH5)H=@)H%H uHH)H )H9Hu)H )Ht HH ).H=()LHH=)H )H5 )HH/H5)H5HH%H uHXH5)H=)H"'+HMuH,He)H  )H9Hu)H )Ht HH- ).H=q)LHH=`)H )H5 )HH.H5)H4HH*HMuHH5)H=)HjF$H uHuH)H W )H9Hu)HB )Ht HH3 ).H=)]KHH=)H )H5 )HH8.H5#)H#4HH#H uHH5)H=)H)HMuHH)H )H9Hu)H{)Ht HH-l).H=)JHH=)HK)H5L)gHH-H5)Hl3HH`)HMuH2H5)H=d)H"H uHH@)H )H9Hu)H)Ht HH).H=L)IHH=;)H)H5)HH,H5)H2HH"H uH|H5)H=)HF(HMuHPH)H )H9Hu)H)Ht HH-).H= )8IHH= )H)H5)HHF,H5)H1HH(HMuHH5)H=)H!H uHH)H ;)H9Hu)H&)Ht HH).H= )HHH= )H)H5)BHH+H5)HG1HH:!H uHH5 )H=@)HC'HMuHH)H t)H9Hu)H_)Ht HH-P).H=' )GHH= )H/)H50)HH*H5H )H0HH&HMuHVH5 )H=)H k H uH+Hd)H )H9Hu)H)Ht HH).H=p )GHH=_ )Hh)H5i)HHT*H5y )H/HHH uHH5Q )H=)Hj%HMuHtH)H )H9Hu)H)Ht HH-).H= )\FHH= )H)H5)HH)H5J )H"/HH|%HMuHH5! )H=)H"H uHH)H )H9Hu)H )Ht HH).H= )EHH= )H)H5)fHH)H5{ )Hk.HHH uH2H5S )H=d)H$HMuHH?)H X)H9Hu)HC)Ht HH-4).H=K )DHH=: )H)H5)HHb(H5 )H-HH0$HMuHzH5{ )H=)HDH uHOH)H )H9Hu)H|)Ht HHm).H=)7DHH=)HL)H5M)HH'H5)H,HH_H uHH5)H=)H_#HMuHH)H )H9Hu)H)Ht HH-).H=)CHH=)H)H5)AHH'H5)HF,HH"HMuH H5)H=>)HH uHH)H )H9Hu)H(Ht HH(.H=&)BHH=)H(H5(HHp&H5)H+HHH uHVH5)H=)H "HMuH*Hc)H <(H9Hu)H'(Ht HH-(.H=o)BHH=^)H(H5(HH%H5)H*HH!HMuHH5)H=)HhGH uHsH)H u(H9Hu)H`(Ht HHQ(.H=)[AHH=)H0(H51(HH$%H5A)H!*HHH uHH5)H=)H HMuH輿H)H (H9Hu)H(Ht HH-(.H=)@HH=)Hi(H5j(eHH~$H5z)Hj)HHL HMuH0H5Q)H=b)HH uHH>)H (H9Hu)H(Ht HH(.H=J)?HH=9)H(H5(HH#H5)H(HHH uHzH5)H=)HD{HMuHNH)H (H9Hu)H (Ht HH-(.H=)6?HH=)H(H5(HH2#H5)H'HHHMuH½H5)H= )HH uH藽H )H Y(H9Hu)HD(Ht HH5(.H=)>HH=)H(H5(@HH"H5})HE'HH;H uH H5U)H=> )H/HMuHH )H (H9Hu)H}(Ht HH-n(.H=%)=HH=)HM(H5N(HH!H5)H&HHHMuHTH5)H= )HlH uH)Hb )H (H9Hu)H(Ht HH(.H=n)=HH=])H(H5(HH@!H5(H%HHH uH螻H5(H= )HhHMuHrH )H (H9Hu)H(Ht HH-(.H=)Z<HH=)H(H5(HH H5(H %HHhHMuHH5(H= )H#H uH軺H )H =(H9Hu)H((Ht HH(.H=);HH=(H(H5(dHHH5(Hi$HHH uH0H5(H=b )HHMuHH= )H v(H9Hu)Ha(Ht HH-R(.H=I(:HH=8(H1(H52(HHNH5*(H#HHHMuHxH5(H= )HBH uHMH )H (H9Hu)H(Ht HH(.H=(5:HH=(Hj(H5k(HHH5[(H"HH`H uH¸H53(H=)H茾EHMuH薸H)H (H9Hu)H(Ht HH-(.H=(~9HH=(H(H5(?HHH5(HD"HHHMuH H5c(H=<)HԽH uH߷H)H !(H9Hu)H (Ht HH(.H=$(8HH=(H(H5(HH\H5M(H!HHH uHTH5%(H=)HHMuH(Ha)H Z(H9Hu)HE(Ht HH-6(.H=m(8HH=\(H(H5(HHH5V(H HHuHMuH蜶H5-(H=)HfHH uHqH)H (H9Hu)H~(Ht HHo(.H=(Y7HH=(HN(H5O(HHH5w(H HHH uHH5O(H=)H谻HMuH躵H)H (H9Hu)H(Ht HH-(.H=(6HH=(H(H5(cHHjH5(HhHH#HMuH.H5(H=`)HH uHH<)H (H9Hu)H(Ht HH(.H=H(5HH=7(H(H5(HHH5(HHHH uHxH5(H=)HBOHMuHLH)H >(H9Hu)H)(Ht HH-(.H=(45HH=(H(H5(HHH5(HHHHMuHH5(H=)H芹H uH蕳H(1H=(萲HHH5(H=)H>{H uHIH(1H=)(DHHH5(H=Z)H@H uH3SHHOH(HHCH(HH(HHCH(HPHO(HHCHA(HPH(HHCH(HPH(HHCH(HP H (HHCH(HP(H(HHCH(HP0Hj(HHCH\(HP8H!(HHCH(HP@H(HHCH(HPHH(HHCH(HPPHv(HHCHh(HPXH5(HHCH'(HP`HL(HHCH>(HPhH(HHCH(HPpH(HH(HCHPxHa(HHCHS(HH(HHCH(HH(HHCH{(HH%(HHCH(HH(HHCH(HH(HHCH(HHY(HHCHK(HH(HHCH(HH(HHCH(HHU(HHCHG(HH(HHCH(HH(HHCH(HHa(HHCHS(HH-(HHCH(HH(HHCH(HH(HH(HCHH(HHCH(HH](HHCHO(HH!(HHCH(HH(HHCH(HHi(HHCH[(H H5(HHCH'(H(H(HHCH(H0H(HHCHw(H8HQ(HHCHC(H@H(HHCH(HHH(HHCH(HPH(HHCH(HXH(HHCH(H`H(HHCH(HhHq(HHCHc(HpH=(HH3(HCHxH(H= (HHCH(HH(HHCH(HH(HH(HCH5(HHN H uHY,_HHH|(H5(H } H(H5(Hj H(H5Q(HѲW H(H5(H賲D H(H5U(H蕲1 H>(H5(Hw H(H5(HY H(H5(H;H(H5(HHn(H5(HH((H5(HHZ(H53(HñH|(H5(H襱H6(H5(H臱H(H5(HisH(H5(HK`H(H5%(H-MH(H5(H:H(H5(H'H(H5[(HӰH4(H5(H走H&(H5(H藰H(H5a(HyH(H5(H[H<(H5 (H=H(H5W(HH(H5I(HHJ(H5(H|H(H5(HůiH(H5G(H觯SH(H5(H良=Hb(H5(Hk'H<(H5(HMH~(H57(H/H8(H5(HH (H5#(HH(H5%(HծH^(H5(H跮H(H5(H虮H(H5(H{wH (H5u(H]aH(H5(H?KHP(H5(H!5HJ(H5(HH5 (H=M(H H HxA[[AAg[AE1Av[AIA{[AE1A[AIA[AA[AvA[AeE1A[AQA[A@E1A[A,A\AE1A\AA$\AE1A0\AAB\AE1AN\AA`\AE1Al\AA~\AE1A\AsA\AbE1A\ANA\A=E1A\A)A\AE1A\AA\AE1A]AA]AE1A ]AA2]AE1A>]AAP]AE1A\]ApAn]A_E1Az]AKA]A:E1A]A&A]AE1A]AA]AE1A]AA]AE1A]AA^AE1A^AA"^AE1A.^AmA@^A\E1AL^AHA^^A7E1Aj^A#A|^AE1A^AA^AA^A A^AAW_AAa_Ab_Ac_Ad_Ae_Af_xAg_mAh_bAi_WAj_LAk_AAl_6Am_+An_ Ao_Ap_ Aq_Ar_As_At_Au_Av_Aw_Ax_Ay_Az_A{_A|_A}_~A~_vA_nA_fA_^A_VA_NA_FA_>A_6A_.A_&A_A_A_A_A_H uHMILǡH =HAJ[A襡H ,HAK[A胡韱H HAL[Aa}A[AhH [H=a.UAy[A2A[A!A[AA[AA[AA[AA\AA\AA!\AA3\AA?\AAQ\AwA]\AfAo\AUA{\ADA\A3A\A"A\AA\AA\AA\AA\AA\AA]AA]AA#]AA/]AxAA]AgAM]AVA_]AEAk]A4A}]A#A]AA]AA]AA]AA]AA]AA]AA]AA^AA^A|A^AnA1^A`A=^ARAO^ADA[^A6Am^A(Ay^AA^A A^AIAZAA[AA[A׭A[AƭA*[A鵭A,[A餭A.[A铭A;[A邭AY[AqAe[A`Aq[AOA[A>A[A-A[AA[A A[AA[AA[AجA\AǬA\A鶬A\A饬A.\A锬A=\A郬AL\ArA[\AaAj\APAy\A?A\A.A\AA\A A\AA\AA\A٫A\AȫA\A鷫A]A馫A]A镫A]A鄫A-]AsA<]AbAK]AQAZ]A@Ai]A/Ax]AA]A A]AA]AA]AڪA]AɪA]A鸪A]A駪A]A閪A]A酪A^AtA^AcA,^ARA;^AAAJ^A0AY^AAh^AAw^AA^AA^A۩A^A ʩA^A鹩A^A騩A__革AJ[A錩AK[A{AL[AjA2[AYH[]A\A]A^H=(HH)w&HtHDH=)(H"(H9tH>v&Ht H=(H5(H)HHH?HHtHw&HtfD=(u/UH=w&Ht H=s&ݟh(]{f.Hyv&GPHGXHDHu310Ht!H(HPH4v&HHPHHHyv&1H5(8ATIUHSHHHt HՅu!H1Ht[LH]A\[]A\Ðf.HGHHGHGE1LH@ uLGuLA1LAHL bu&HLM9tMu HxHuLHxH:H@HHHtHHHtHHHtHÐAVAUATUSHGLM|HIHL-t&p NH A;MhLHHAH̙H QP AEH=~9|HtTH[]A\A]A^ @9}葙@$[]A\A]A^[H=,t1@裙HHuH,s&H5ݶH8HGHHtfD飜ATIUSHHHoH&Ht9HPHHtHHHH[]A\fDHH[]A\HAt&LHD$H:qHD$f.AWAVLvAUATUSHM~uLHG LD$MHH$IHLfH<$LDHL$HLIL<LɗHHL軗HHL譗L)IuHr&HH[]A\A]A^A_f.AVIAUATIUHSHHC1LLHI`HtwIHa(H~%1I fDHHHHHH9u1L}AE I,$tAm H[]A\A]A^LHD$HD$1SHGHL@t+Hq&HݴLH81 H؅u [Haq&HHH5TH81H+t 1[Hh1@SHHGHGHHHHcH1H[WGHH HcʉH9tHq&H5H8@GH[WGHH HHcʉH9uH[GH[DKHcH9aHuHrCH@`HtgHHt[HHtQHp&H9Cu+@HH+H߉D$ D$ HH5(HHu苕HwHo&H5$H8̒\SHGHuoHWH{HtHCH/t@HHtHǃH/tHCH[H@f[fKfHtGuKt[ÐAUfIATIUHSHH(HGXHT$Ht$HD$HG`GXHD$HGhHGhH|$HD$H{XHt$Ht H|$\HD$HtHHD$HtHHD$Ht HHD$HT$IUI$HD$HEHH8HhHHT$HXHPHT$HPHtH/t=HtHmtAHtH+tH(1[]A\A]fHfDfH؏fDH|$IEI$HEHtH/t8H|$HtH/tHH|$HtH/t(H([]A\A]kf[fKfUSHHGXHo`H$H_hHt$~D$HOh$GXHtH(tHHtHmt,HtH+tH[]f.HH[]ҎfHȎfDH踎fDUHSHHl&HHH]HHHt H/tCHHHHHHtH/tH1[]KH1[]f;fAVAUAATIUSHtuH=^(H讔IHHHLEHHLmIH+t[L]A\A]A^H踍[L]A\A]A^@1HHthH=(-IHtE蠒HHt8LEHHLHmIuHRH+tfDHmuH1E1[]LA\A]A^fH9t[HXHt/HJH~H;rt@1 @H9tt1HH9u1DHH9tHu1H;5fk&ff.H9t7HGH;Hk&u>HGHuHtHj&H@HuuH}j&HH;i&t͌DfH*f.Gzt@UHSHHt:HHH}H/tH]H1[]@H]H1[]fDH!j&Df.ATUSHH9Hj&H9GHH9F ~ HSH9VHCHNH9@H@t H{ DF D8@ H{HA lHN0HHA@HEȃ`gDA9uEHH1u)1 L%h&L9ut1H[]A\L9uuH߉HHH;h&H;hh&uL9u4H+uH߉D$7D$뙐1H[]A\H耎fDHK0HH@HHDHt$VHt$N7HHt$+Ht$-@HvHD@Dff.UHSH"HHtHHH[]@HuHEHuH/g&H8?ǿ1衐HHtHHg&H8HmuHfDUSHHHoH$H_Ht$~D$HO$HtH(tJHtHmt.HtH+t H[]@HH[]zf.HhfDHXfDUSHHHGH;g&tjH;e&t1HhhHHEHt{Hy HH[]fHt HyHGtH;CsEHDHH[]DHt HyHGtH9CvHSHHH[]fHHHt`HH襈HmuHHD$qHD$f.HUHFHt$Ht$HxHHE)fD1HEe&Ht$H8踈Ht$tHt$HEHt$AWIAVIAUATUHSHHHHD$(LD$Ll$0HD$HD$8HD$(HD$0HD$8HD$@HT$Ht$LL賋HHt$(H{H8HH9uf.H;2HHHuHFLIHFH9GII$Ht-H8H9uLHL$0H)I I<$KHt$(fDH9u&fDHFH9GHH9HEH8H9uHT$HH52HSc&H81HH[]A\A]A^A_DHT$0H)IxDHt$(%ˈHtxnHt$(oHH9VHHT$H5]HFHb&HT$H5H81!HH[]A\A]A^A_HHHt$(DHHH@u{t|@tsAT1USH蝇IHtM1HHxI,$Ht^Ht1HM@t\HHAHmu[H]A\ D[]A\Ha&H5bH8fL؃fDHa&HH5H81AVAUATUHSH HH_pHHCHHtH1H H[]A\A]A^f.EL-a&E1HH2Hza&L貉IMtI.uLMtCLHSImIt\H L[]A\A]A^@H`&HWH5H814H E1[L]A\A]A^ÐEu[H`&Hr@L蠂fD1DL$HT$Ht$Ht$HT$HIIDL$fH踄IHt8H`&LH辈IMtI.t8I,$ LM;I.1LL@f.AWAVIAUATIUSHHLLoHo p VP H_&;AGu A$CHK0HS(1HtHEHHE1ELQLLR1PUjvH0H蚄x WP H:_&=!@9|HH[]A\A]A^A_D29}T@$fDH=D1Ht+HEHMu IcWH9t7HK0HS(BIcWL9uLLLLH?LHLH)LVMH9~1DH9|HI9uE1fJTHBt>@t5H9tbHXHt4LIM~H;QtG1H;Tt;HI9uIM9u1@HDHH9tHuH;P^&uθHHH?H9t}HXHtOHJH~H;rtb1 @H;ttSHH9uH]&HNH5HWH81蘅1+@HDHH9tHuH;5]&uH@H1\&H5H81fDUHSHHH=(HGHHtHHt#HH[]f{HfDH]&HH5eH81ՄUHSHHGHHtHHtHH[]HfDH ]&H8tH\&HH5 H81bUSHHHGHt)HkHUHH HcHHHDH+t HH[]H}HH[]fDkHcfDkCHH fkkCHH HfDHHH@`HtOHHtCHHt9H@H;[&HH5HHu3H3DcHuHZ&H5H8}H@f.USHHHGHt)HkHUHH (HcHHHDH+t HH[]H|HH[]fDkHcfDkCHH fkkCHH HfDHxHH@`HtOHHtCHHt9H@H;.Z&HH5HHu3H3D~HuHY&H5H88|H@f.AUATIUHSHF~HHEHHhID$HH'~L-X&p VP A;U1HLH}H QP AEH=~$9|*HH+t)HH[]A\A] @9}}@$HPzHH[]A\A]fH1[H]A\A]1HLSHfDH=}G@1rf}HHuHW&H5ŚH8zAHGtkHGHHHwUH5HcHDGHËGWHH fG@GWHH H }SHH@`HtvHHtjHHt`HW&H9CuHHH+t*H[HH5 HHuH@HHD$xHD$_|HuH{V&H5H8yfAUATUSHHuy\wHhXHHu1H[]A\A]HiW&H0H9fLk`LchHChCXHmt~MtImtJMtI,$uLx@H/t:HU&HH5H81W~oDLwfDHt$wHt$HwuHEtl@tcHFHtc@tZHXHt_HJH~)H;r1H;tHH9uHxtHHHH9Hu1H;5U&뿐AUATUSHuHhXHu1H[]A\A]HHU&H0H9u`fLk`LchHChCXHmt7MtImtMtI,$uLwvDLhvfDHXvHEtg@t^HFHt^@tUHXHtZHJH~$H;rP1 fH;t?HH9u HvtHQHHH9Hu1H;5>T&fAVAUATUSHGHH;S& H;T&HOQE1 Lat{xH-?S&p VP ;UL1AHmxx WP EH=~9|%HrH[]A\A]A^fD @9})x@$Lo|LL-(MwH-R&p VP ;U1LHAHwp VVDLwLgLo wH-PR&p VP ;UAFu6A~$Cu/MIIEIcVIH9WHK0HS(HK0HS(1MtIEIHE1E1LQL1R1PAUjwH0H wp VP E=Z@9v@$fD#wHHt01z@H=9tv/1[D2H|P&H5-H85t6H=4v1DLH1[]A\A]A^+yH=uY1AVL11L2HLLLH@AWAAVAUIATIUSH8RqIEE1H5r(H)D Z(DʃHcH9\m1 }4H9}$)ωHcH|>9~ى9|19A9HHH9XL(IEH(1LLpHHt;hlHsImuLqH+Ht"H8[]A\A]A^A_fImuLH8[]A\A]A^A_cqH=(HH@XfHD$IF`AFXHD$IFhIFhHD$vHH[H8Hi(H9GHP(Ht3HN&H9tH;8O&t;Hst/E1*sHN&H5ڻ(E1H=(3t~D$I~XHD$IV`D$I^hAFXIFhHt H/OHt H*XHt H+YEDfDLuIHELuIMoH((HE11L (111AQUAWATPPPPPipHPII$HI$HI/MH(H5(x}HcH9\~h1@}yAL$9~e)AAAAAIcHT9~DDDHCL1H=M]mIDPE1f.9AD9~sMcIIA9XT;5ھ(tcfHcуHoL A9|AXM(5(IEDI,$LDA95{(D~@HIcHoH~Mcċ5L(HM(ID=>(IA9ZrfHT$nHT$@HnHmLm(Lm~1fDH=(H5Ҹ(HGHH8HHHHL$ oHL$ HHHHgK&H9K&sDH5a(HV qHH~(HRH{(fDVtH&H@H(H5(XL(IEDMcIN HHHJ&HHHT$(HD$ lHD$ HT$(I8M(H/slHJ&HpJ&9sHAWfAVAUATIUHSH8L5qJ&H^)D$Lt$ H:H HHV(ID$ ML$HHHuHAH=I&HHAVj5{(5(j5(Pj5((HPHH+HHD$kHD$H8[]A\A]A^A_I\$HHH HMHSHL@HI&H5^L H81qXw3ZH c H=sf1H8[]A\A]A^A_DLIHS~qHtHQHF(HD$ ID$ LHD$ID$HD$,iIHtlHHt8MLL$HD$HT$ oHHhIH5%(LIHV%nHD$HH5(LHVnHD$HIM~H5֭(LHVmHt~HD$ ISH+t2M H 3HD$H=HD$fDHHD$iHD$@HFHHD$gI@HT$HLLH5S(Ye3HHF&H [H5FjL AHOH81^oY^[3fAVAUATUHSH L (L%G&H^LL$Ld$HDH2HHHHԪIH H۪HIHH=F&I?SIH5H8L ݫA1nX2ZH  H=ǎ1H []A\A]A^LHHHu H(H=E&AHH (ATjQPjQHPj5:((H;HWHPHHHuHHD$gHD$H []A\A]A^fHV LNfLIHHtmHHeIHLL$HT$H H g3HD$H=eHD$oFH)D$veH~HT$HLL&H5XQ({2gHFHHD$/eIMSH5l(LHVpjHtHD$IFHHD$cfHD$2fH5(LHV-jHtHD$If.AVAUATIUSH0H(H ۧ(H-&I?SIH5?H8L A1bgX1ZH @ H=؇CH01[]A\A]A^@HIH{HtHMHF(HD$ HF LHD$HFHD$ _IHHM~.H57(LHV;dH#HD$ IMLL$HL$HT$ H($DHH^IM~H5X(LHVcHtHD$IM~H52(LHVcHWHD$IDHtKB H ۡ1HD$H=nHD$H&^f.HHD$C_HD$@HFHHD$]IIHT$HLLwH5VI(1Df.AVAUATIUSH0H(H (H-<&H^HD$~D$HL$Hl$ D$)D$HpHV~$HHHV(HN LNfIHHHIt$ I$H=!=&AHUj5֪(Pj5}(QHj5q(K(H;HWHPHHHtH0[]A\A]A^fHHD$]HD$H0[]A\A]A^ÐHLHHIH ҟHHIHHN;&I?SIH5H8L A1cX61ZH w H=hH01[]A\A]A^@HIH{HtHMHF(HD$ HF LHD$HFHD$j[IHHM~.H5(LHV`H#HD$ IMLL$HL$HT$ HZ($DHHZIM~H5(LHV4`HtHD$IM~H5(LHV`HWHD$IDHtK H ;_1HD$H=9HD$H&^f.HHD$[HD$@HFHHD$ZIIHT$HLLH5E(q"1Df.AVAUATIUSH0H (H (H-\9&H^HD$~D$HL$Hl$ D$)D$HpHV~$HHHV(HN LNfIHHHIt$ I$H=7&AHUj56(Pj5ݞ(QHj5Ѣ((H;HWHPHHHtH0[]A\A]A^fHHD$3ZHD$H0[]A\A]A^ÐHLHHEIH 2HoHIHH7&I?SIH5H8L NA1"`X0ZH  H=H01[]A\A]A^@HIH{HtHMHF(HD$ HF LHD$HFHD$WIHHM~.H5(LHV\H#HD$ IMLL$HL$HT$ H($DHHOWIM~H5(LHV\HtHD$IM~H5(LHVn\HWHD$IDHtKr H 0HD$H=HD$H&^f.HHD$XHD$@HFHHD$wVIIHT$HLLGH5A(0Df.AWAVAUATIUHSH(L55&H^HD$Lt$HJH0HHV ML$HHHuHH(H=5&AHH ϣ(AVjQPjQHPj5(D(H;HWHPHH=HHHD$VHD$H([]A\A]A^A_I\$fDHHH ݘHOHL ĘLOL@HHD4&SHH5|H81\X 0ZH  H=}1H([]A\A]A^A_LIHHHHHTH5(LIHVIYHD$H MLL$HT$kHt3 H 50HD$H=|HD$=HHD$kUHD$@oFH)D$SH~HT$HLLH5 ?(;\/fHFHHD$SI'H5ɘ(LHVXHtHD$IG|f.AWAVAUATIUHSH(L52&H^HD$Lt$HJH0HHV ML$HHHuHH7(H=2&AHH (AVjQPjQHPj5(d(H;HWHPHH=HHHD$SHD$H([]A\A]A^A_I\$fDHH H HOH:L LOL@HHd1&SHH5yH81YX/ZH G H={1H([]A\A]A^A_LIHHHHHQH5(LIHVIVHD$H MLL$HT$kHt3 H /HD$H=Fz HD$=HHD$RHD$@oFH)D$PH~HT$HLLߔH5 <([\x/fHFHHD$PI'H5(LHVUHtHD$IG|f.AWAVAUATIUHSH(L50&H^HD$Lt$HJH0HHV ML$HHHuHHW(H=.&AHH (AVjQPjQHPj5ڝ((H;HWHPHH=HHHD$QHD$H([]A\A]A^A_I\$fDHH-H HOHZL LOL@HH.&SHDH5vH81WX/ZH H=Ix1H([]A\A]A^A_LIHHHHHNH5ɜ(LIHVITHD$H MLL$HT$kHt3B H +-/HD$H=w)HD$=HHD$OHD$@oFH)D$NH~HT$HLLH5 9({\.fHFHHD$MI'H5 (LHV SHtHD$IG|f.AWfAVAUATIUHSH8L5!-&H^)D$Lt$ H:H HHV(ID$ ML$HHHu AH=,&HHAVj5+(5U(j5U(Pj5((HPHH+HHD$:NHD$H8[]A\A]A^A_I\$HHTH DHMHSHL@H+&H5tL `H815TX.ZH H=u1H8[]A\A]A^A_DLIHS~qHtHQHF(HD$ ID$ LHD$ID$HD$KIHtlHHt8MLL$HD$HT$ oHHKIH5(LIHVPHD$HH5(LHVPHD$HIM~H5(LHVPHt~HD$ ISH+t2H .HD$H=EtHD$fDHHD$;LHD$@HFHHD$JI@HT$HLLH55( n.HH)&H H5qjL FAHOH81RY^d.fAWAVAUATIUHSH(L5)&H^HD$Lt$HJH0HHV ML$HHHuHH(H=(*&AHH ϗ(AVjQPjQHPj5(D(H;HWHPHH=HHHD$JHD$H([]A\A]A^A_I\$fDHHH ݌HOHL ČLOL@HHD(&SHH5pH81PX-ZH #H=ar1H([]A\A]A^A_LIHHHHHHH5є(LIHVIMHD$H MLL$HT$kHt3H .HD$H=qHD$=HHD$kIHD$@oFH)D$GH~HT$HLL׋H52(;\-fHFHHD$GI'H5Ɍ(LHVLHtHD$IG|f.AVAUATUHSH L%&&H^Ld$H HHHHH HIHHH?L ܋HLIL@HH &&SHH5^nH81NXm-ZH jH=Zpm1H []A\A]A^fDHVHHHuHE1L (H=L&&HHy(HATjPAQjPAQjP(HPHthH+uHHD$GHD$H []A\A]A^LIHHHFHHD$EHXHT$NfH+t2 H z-HD$H=eoxHD$fDHHD$FHD$HT$HLLH5+0(y_-HHEIH`H5(LHVJHtHD$IF5fDAWfAVAUATIUHSH8L5$&H^)D$Lt$ H:H HHV(ID$ ML$HHHuHAH=4%&HHAVj5(5Շ(j5݌(Pj5((HPHH+HHD$EHD$H8[]A\A]A^A_I\$HHԇH ćHMHSH3L@H5#&H5kL H81KX,ZH H=m1H8[]A\A]A^A_DLIHS~qHtHQHF(HD$ ID$ LHD$ID$HD$\CIHtlHHt8MLL$HD$HT$ oHHCIH5U(LIHVUHHD$HH5H(LHV4HHD$HIM~H5(LHV HHt~HD$ ISH+t2H :-HD$H=Ul8HD$fDHHD$CHD$@HFHHD$/BI@HT$HLL@H5,(艼,HH$!&H H5vijL ƆAHH81IY^,fAWAVAUATIUHSH(L5E!&H^HD$Lt$HJH0HHV ML$HHHuHH(H=0 &AHH O(AVjQPjQHPj5b(đ(H;HWHPHH=HHHD$WBHD$H([]A\A]A^A_I\$fDHHmH ]HOHL DLOL@HH&SHH5hH81CHXc,ZH !8H=yj$1H([]A\A]A^A_LIHHHHH@H5Q(LIHVINEHD$H MLL$HT$kHt3~H k,HD$H=iiHD$=HHD$@HD$@oFH)D$^?H~HT$HLL}H5)(軹\S,fHFHHD$?I'H5I(LHVMDHtHD$IG|f.AWfAVAUATIUSHH8L5a&Hn)D$HD$ Lt$(HqHWHHV0HK(HC LKHI$It$HAH=&HAVj5(QHj5m(Pj5T(֎(HPHH+HHD$r?HD$H8[]A\A]A^A_fDL=IH5(LIHV&CHD$HHk@HHTH DHMHUHȁL@H&H5eL `H815EX+ZH H=g1H8[]A\A]A^A_DLHfIH|HcHHF0HD$(HC(HD$ HC LHD$HCHD$1B_+AXf.AWfAVAUATIUHSH8L5q&H^)D$Lt$ H:H HHV(ID$ ML$HHHuHAH=$&HHAVj5{(5}(j5(Pj5l((HPHH+HHD$;HD$H8[]A\A]A^A_I\$HH}H }HMHSH#~L@H&H5^aL ~H81AXE+ZH c}H=df1H8[]A\A]A^A_DLIHS~qHtHQHF(HD$ ID$ LHD$ID$HD$,9IHtlHHt8MLL$HD$HT$ oHH8IH5(LIHV%>HD$HH5(LHV>HD$HIM~H5}(LHV=Ht~HD$ ISH+t2H |n+HD$H=bHD$fDHHD$9HD$@HFHHD$7I@HT$HLL0|H5!(Y3+HH&H [{H5F_jL |AH{H81^?Y^)+fAWAVAUATIUHSH8Hz(L5&HD$H^HD$Lt$ HVHDH*HHHzH zHOH{L zLOLDHH&SH1{H5l^H81>X*ZH xz3H=Xa{1H8[]A\A]A^A_f.LML$HHHuHAH=t&HHAVj5{(5y(j5|(Pj5{((HPHaH+uHHD$7HD$H8[]A\A]A^A_f.HV(ID$ efLIHsHtHHF(HD$ ID$ LHD$ID$HD$5IHHM~.H5z(LHV:HHD$ IMLL$HD$HT$ fHH/5IH5z(LIHVu:HD$HM~H5z(LHVO:HbHD$IOH+tJH zx*HD$H=U_xHD$fDH0^f.HHD$5HD$@HFHHD$W4IHHT$HLLxH56(豮*\I\$DAWAVAUATIUHSH(L5&H^HD$Lt$HJH0HHV ML$HHHuHHv(H=X&AHH (AVjQPjQHPj5y($(H;HWHPHH=HHHD$4HD$H([]A\A]A^A_I\$fDHHvH vHOHwL vLOL@HH$&SH1wH5uZH81:X%*ZH vH=]1H([]A\A]A^A_LIHHHHHh2H5w(LIHVI7HD$H MLL$HT$kHt3-H uN*HD$H=\HD$=HHD$K3HD$@oFH)D$1H~HT$HLLuH5(\*fHFHHD$o1I'H5v(LHV6HtHD$IG|f.AVAUATIUSH0Hjt(H [t(H-&H^HD$~D$HL$Hl$ D$)D$HpHV~$HHHV(HN LNfIHHHI$It$HAHH=~(UjWPj5Bv(QHjWH=d&(HPHH+tH0[]A\A]A^fDHHD$1HD$H0[]A\A]A^fHLHHsIH sHJtHIHH&I?SIH5_WH8L tA17X)ZH `sxH=ZcH01[]A\A]A^@HIH{HtHMHF(HD$ HF LHD$HFHD$*/IHHM~.H5Wt(LHV[4H#HD$ IMLL$HL$HT$ Hr($DHH.IM~H5xx(LHV3HtHD$IM~H5Rt(LHV3HWHD$IDH+tJH q)HD$H=-YHD$fDH&^f.HHD$c/HD$@HFHHD$-IIHT$HLL"rH5v(1)Df.AUATUHSH(L , &H^LL$HHHHHpH pHIHHpH?L rHLIL@HHO &SHkqH5TH814X )ZH p7H= X读1H([]A\A]fHVHHHuHE1H= &HHAQjAQAQjAQAQjAQD}(HPHt{H+uHHD$-HD$H([]A\A]LIHHHFHHD$1,L &HHT$KH+t2rH o5)HD$H=W踺HD$fDHHD$;-HD$@H+L a &HI~H5p(LHV0L ? &HtHD$IERHT$HLLoH5(ޥxHT$L &}(HDf.AUATUHSH(L &H^LL$HHHHHnH nHIHH}nH?L oHLIL@HH &SHoH5@RH81n2XZH Ln!H=UO1H([]A\A]fHVHHHuHE1H= &HHAQjAQAQjAQAQjAQz(HPHt{H+uHHD$+HD$H([]A\A]LIHHHFHHD$)L z &HHT$KH+t2EH ZmHD$H=TXHD$fDHHD$*HD$@HX)L  &HI~H5n(LHV.L &HtHD$IERHT$HLLvmH5(~xHT$L &}HDf.AVAUATUHSH L l(L%c&H^LL$Ld$HDH2HHHH$lIH lHlHIHH&I?SIH5OH8L -mA10X%ZH kH=S1H []A\A]A^LHHHuHH7k(H=&AHH u(ATjQPjQHPj5m(dx(H;HWHPHHHuHHD$(HD$H []A\A]A^fHV LNfLIHHtmHH4'IHLL$HT$HH jNHD$H=zR赵HD$oFH)D$&H~HT$HLL$kH5H(#{gHFHHD$&IMSH5k(LHV+HtHD$IFHHD$'HD$2fH5l(LHV}+HtHD$If.AWfAVAUATIUHSH8L5&H^)D$Lt$ H:H HHV(ID$ ML$HHHuHAH=&HHAVj5s(5h(j5r(Pj5ds(v(HPHH+HHD$&HD$H8[]A\A]A^A_I\$HHhH hHMHSHyiL@H%&H5~LL iH81,XZH hH={P膳1H8[]A\A]A^A_DLIHS~qHtHQHF(HD$ ID$ LHD$ID$HD$L$IHtlHHt8MLL$HD$HT$ oHH#IH5q(LIHVE)HD$HH50q(LHV$)HD$HIM~H5h(LHV(Ht~HD$ ISH+t2H *gHD$H=O(HD$fDHHD$$HD$@HFHHD$#I@HT$HLLgH5~ (yHH&H {fH5fJjL gAH9gH81~*Y^fAVAUATIUHSHH7&H^HT$M5HHLfHEH5h(HHHXHH:(HHIH5jg(LH_)gHCL5s(LMd&L-P&H QP A;UuHLHAIy&H QP AEH=9MMH+3HmH"HL[]A\A]A^HHeH dHIHHdH?L 'fHLIL@HHX&SHeH5HH81(XZH dH=LE1赯HL[]A\A]A^DIj @9m%@$@A4H+uH!Hmt}D溱E1H /dH=TL7HL[]A\A]A^H!HHHFLHD$ H\Ld$DHp!vA0hD3(HH+A2CH0!6HT$HLL/dH5(yHLH'IHfDA5DH=A#wfK$HuH%H5AH8!fDLIHH5Md(LHVQ$H-HD$IEf.AVAUATUHSH L-j%H^Ll$HHHHH:bH *bHIHHbH?L \cHLIL@HH%SHbH5EH81 &XZH auH=2J1H []A\A]A^fDHVHHu MH=O%HHn(HtmH+uHHD$:HD$H []A\A]A^LIHHHFHHD$HXHT$nfH+t2H aHD$H=]IHD$#fDHHD$HD$HT$HLLaH5k(膗yHIH`H5%b(LHV)"HtHD$IF5fDAVAUATUSHHGH5g(HHIHHK#HHH%H5Tf(H#\HEL5m(LM! L%%H QP A;$rHLHAI H QP A$H={9MRHmH+}HHHb(HHHa(HEHH=c(躎HHEHHHEHCH-a(HHHH3IMI<$H+H-9h(H %LHI9E%$HH!HIHHXqHH]Ld$~D$Lt$I$D$@IELh(ImI,$tzHH[]A\A]A^@ @9=DHAAHEDDIH ]H=_FImtvMtI,$uLjHH[]A\A]A^f.kHHH }]H=E{ImLMu fDHmttH ']1H=E(HH[]A\A]A^HvHH+a@@$/f.HhfDAHmH+DH \1H=D舧HH[]A\A]A^LLAAfDHEHLH+>H1f HfDH4HLHIH$fDADE11AH=H [DDH=C脦HIH=9zf.HuH%H59H8kH%H8YH+t1AALAA7@SIH+H ZH=C补!@HHEHH%H8'fH EZH=BCImLI.H ZH=vB@Ha%HH5YH81LAA1HH HHB%H8RH+H f.AVH5`(AUATUSHGHH}HHgHHnH%H5H_(HHCL5f(LMUL-%H QP A;UfHLHAIH QP AEH=~+9|gMNH+t@Hmt![L]A\A]A^D @9}4@H[L]A\A]A^@HHmu+@$DAH+uHHmt-DE1H WH=@[L]A\A]A^HfDAKH{H+AuHLf.HLHbIHfDAKDH=5f.HuH%H55H8@f.AUATUHSHHGH5_(HHHHHJHCH5[(HHH\IHHHMTH3H}H5p_(HGHH\HH^HEH5c[(HHHHHEHHbHEHH=~`(H.HHH_HHH5K`(HHHEHCHHEHLHHHHHI,$HEIHPHUHEHt3HL[]A\A]DH >HHHL[]A\A]fH1HNHHHAHH TDH==MQI$LE1H5fLhHX+HH TE1H=U=耟HL[]A\A]fIHH fDHHD$[ HD$wH c HHOH@`HHHHHHH%H9EHEtHEHPHwiH QHcHH'HmHHD$HD$EHՋEUHH HËE뾋EUHH H HhH%H5IH88 MH%H5uIH8 HGtkHGHHHwUH5>PHcHDGHËGWHH fG@GWHH H[ USHH@`H"HHHHH@H;%fDHCHHHH5OHcHHH5@L2sHHHfH+trH[]CHCCSHH fCSHH HHH5KrHHtBH@>fDHHD${HD$wH( c HHOH@`HHHHHHH%H9EHEtHEHPHwiH `NHcHHׇHmHHD$HD$EHՋEUHH HËE뾋EUHH H>  HhH/%H5FH8XMH%H5FH8=AWAVAUATUHSHH(HHCHH)HUH5nH(HHHH IM HHH5H(HH )ID$L5T(LML=y%H QP A;HLLAIH QP AH=9MI,$HmNH+VH(L[]A\A]A^A_fDHIMH"%I9D$Mt$MIl$IHEI,$0Lt$HEH;%H;%HUB~LbE1 uLmL=S%H QP A;yLLAIH QP A=29MuI.rHEH LLUIHEHMHEHHH+HD @9aLf@$AfLhHIH9HD$Lt$Ll$HD$1LLLPHD$H@uH%H#EH5&E1H81DA&DH DE1H=i-Ht$HII.L@A4'I,$t+HEHHEHuHT$ IT$ sL8HEHf@D[@$fIA0'A 'II,$LA2'DLHmIDHLLIH>fDA5'DH=!Tf.HuHW%H5!H8fDA'PHt$HvhI;fDH= s@I.tfDA&DH=$f.HuH'%H5H8fDA&PHt$HFbI;fDH=as@I.t(H50<(HGHHHHH=@(Ll$HGH;D$#H;%HWBHZE1 uLL5%p VP A;bLLIp VP A={29~MGHEH;%L}MLuIIHmLLLI/HImHsI.HL>HuI,$H+H([]A\A]A^A_ÐLl$H;D$`H;%HUBHZE1 L5i%x WP A;LLHp VP AH=9HImILH@9-@$t@Lc9LeO29@$L} @9M@$?@LXjHH!HHD$3HD$H([]A\A]A^A_LHD$ HD$7L;@$fLsIMmI$A@HI$u LHtHmt,DH 0H={H(1[]A\A]A^A_HhfDA-+HTI$A>HI$xfDHLH-*>(MDL5%H QP A;1HHAIx WbDHt$kILHurII/I$LAOHI$I,$7ARH+H=H= 4SH>H3%H5 H8#LHqHDLJE1 uLGHt$?LAIfLcHkL{ L5x%p VP A;FAD$u A|$$CHK0HS(1MtIGIHLE1E1QH1R1PAWj:H0I^H QP A=2H94@$Ht$HiI,fDSHH+uHA;LJ1 uH}Ht$AIDH=! \fHt$HNiH fDH= $@I/HQLDfDHuH%H5 H8fDLB1 uH}Ht$WAHqDH=Q @1MfHHuH%H55 H8=@1DH= $A;H1HH!IH= &Mt>IGIcT$IH9HK0HS(nH%H5 H8AT$uLH11TIZ1ɺLAI1ɺAI1ɺAHLHLTI LARf.AUIHATIUHSHHWH=9(HH9(H@IEI$HtHHH[]A\A]DCHuH=8(HHGHHt'HHuH%HH5O*H818HAWAVAUATUHSH(L%x%H^Ld$HnHHugH^L9H53(HFHCHHHsHH(VHHHHH)H )HIHH)H?L +HLIL@HH8%SH*H5 H81X ZH )H=tH([]A\A]A^A_fHY7(H #(H9HxH#(HHL-#(MDH-%I9ELM8qHI$HHI$HGHHHH}H/?H]HCHH52(HH IM?H5)Lp(H5{)LIHAoEHE AoMM0IE HE@HE HEHHEHwH(HCH5:.(HHHoIMQHH/LH+I,$\LOfLeHhLXKfDHt5(H !(H9HH!(HHL5!(M_HH%I9FLMSoIMI,$IEH5A-(LHHIMH%I9FM~MMfII$I.HLL I/HHI,$<H+"IELfD H [&H=^qH+E1HMFHfDIHHHFHHD$!H9H\$ofHLMHf.;IHT$HLLr&H5'E\y H5$(H=*2(1;LHHHg^Hm H '%H=d*pHHH DL;He fD @ ;IH%H5H8:, H u$H=xoHLHxIHPH5%&(LHVHmHD$IF!fL8 aH=)0(HJ(H5K(vIfDCfDH=/(lbIW@MuM`MeII$Im LL@I.H>L1fDI$HH (# H=[ &nfDfDLS7 aH=)/(H:(H5;(vIffDM~MmMfII$I.OLLiI/ILL$?H=.(,aI@I,$ H 5"E H=h 3mfDHT$ t$t$T$ L뺸R fDkII,$` LcH !ډH= lMImL+fDE1 L LE nH !` H=Q ltAVAUIATUSH H.(H (H9HH(H1HHv(HHCH5j'(HHHIHHHMH6ID$H;j%H;m%Ll$2H;+%MIT$B5HZ1 "L5˻%H QP A;iLHHH QP A=@9HSLHEHH3HEHzH;%H;Y%H;w%HŅOH+IELIEHHHH5o%HcHf.Il$fD291@$#AEAUHH HHu#HHHIH,H L[]A\A]A^@H+&H3IEHH5!((LHHHHHH_(H5X'(H0HCL-](LML5%H QP A;HLHAIH QP AH= @9MvH+HmH9@A@ AqHtaDDH ^E1H=chH L[]A\A]A^HHyAR AqH+uH@ LL}_HDH=)!(H(H5(vHHf.A> Aq0H= (\[H@ IMt$MIl$IHEI,$1LLHI.HfLYHt$LWH;fDHWA H+mHAtHmXHoKf.@$fH=TLAqAO HuHO%H5H8fDAEAUHH |@AEoAEH=LHLHIHHfDA DHt$LAHfDL 3HCA AtAh AsA AtCH=UO{H:H%H5H8H@`H%HHLHHH@L%%L9fDHEHHHH5HcHEHHmHHD$HD$EUHH H̋EHmNjEUHH HmdH1UDHH5BHHH@4HT]A] Ar_HH1%H5H8ZH@`HHHHHHL9`HCt"HCHPHH HcHHWH+HHD$HD$CH֋CSHH HċC뿋CSHH H5HAHH^HmHhHpHuH %H5H86AO AqAtAVAUIATIUHSH H4%H^HD$HT$MHHHHH HOH'L LOL@HHQ%SHH5H81X?ZH H=>a1H []A\A]A^fHV I|$HHHu E1H(AHH (jQPjQHPj5J(WH=ұ%$#(HHPHHHHt@HHtCHmiHHD$HD$H []A\A]A^fHfDiH &@HD$H=K`HD$HHHnLH5|(LIHVIHD$HMH|$HT$HHt'H $d@H="`1lHfDoFL)D$&H~HT$HLLH5X'Kq?HFLHD$IDH5(LHVHtHD$IFI\$KAVAUIATIUHSH H4%H^HD$HT$MHHHHH HOH'L LOL@HHQ%SHH5H81X<ZH RH=n^1H []A\A]A^fHV I|$HHHu E1H(AHH (jQPjQHPj5J(WH=%$ (HHPHHHHt@HHtCHmiHHD$HD$H []A\A]A^fHfDH <HD$H={]HD$HHHnLH5|(LIHVIHD$HMH|$HT$HHt'H $<H="]1lHfDoFL)D$&H~HT$HLLH5'Hq<HFLHD$IDH5(LHVHtHD$IFI\$KAVAUIATIUHSH H4%H^HD$HT$MHHHHH HOH'L LOL@HHQ%SHH5H81X0<ZH  H=[1H []A\A]A^fHV I|$HHHu E1H(AHH (jQPjQHPj5(WH=2%$(HHPHHHHt@HHtCHmiHHD$HD$H []A\A]A^fHfDPH g<HD$H=ZHD$HHHnLH5(LIHVIHD$HMH|$HT$HHt'H $KY<H="Z1lHfDoFL)D$&H~HT$HLLH5'Eq <HFLHD$IDH5(LHVHtHD$IFI\$KAUATIUHSH(H (H2%H^HD$HT$MHHHHH IH HHIHH\%I?SIH5H8L A1X;ZH  H=X1H([]A\A]@HHdHeLIHHD$HT$fDHHHu E1H (AHH=~(jWQjWH=%QHj 5t(P(HHHPHHHt9HHtLHm*HHD$lHD$H([]A\A]@HPfDHV HFC H x ;HD$H=vWHD$HHt'H D  ;H=WBW1HfDoFL)D$FHHT$HLL H5'B;DHFLHD$IMSH54 (LHV8HtHD$IEH5(LHV HtHD$If.AVfAUIATIUHSH0H %H^)D$HT$ MyHHtyHH H HMHSH L@HN%H5L H81X;ZH U H=U1H0[]A\A]A^HV(IL$ ID$HHHuHE1AH=%Hj5(5 (j5I(QHj5E(P(HHHPHHHt:HHt=HmeHHD$HD$H0[]A\A]A^HfD H ?;HD$H=THD$HF~tHtH{HF(HD$ ID$ LHD$ID$HD$IHtoHHt;MHD$HL$HT$ f.HLOIH5(LIHVHD$H%H5 (LHVtHD$HIM{H5B (LHVFHtjHD$ ILHHt'H | 1;H=zS1HfDHFLHD$IPHT$HLL3 H5'>:PHHt%H H5jL  AHH81Y^: I\$AWAVAUATIUSH8H%H^HD$(HfHMHHnHEI|$H5V(HGHHHHH5(Hn%HH9C\;IML-I(M9H%I9FI9EA~ A}  IVI;UI.]L=f%H;-%L9u H;-{%%Hc(H 'H9H H'H HL5o'M IFH5#(LHH IIHPM IHOIEH5$(LMT Ht$Ht$H QP Hu%;1LAIH QP HM%p=9%MImI.IHmLIc|$PIH_H5 (HH-IbHI5AD$X)IHH5 (HHI( HI3H;-Ԡ%H;-%H;-%H* H5 (HĠ%HH9CG 8IM& H5O(H%HH9C[ 8IM* H5 (Hl%LI9Go Z8IM. I/4H5(H6%HH9CY $8IMX H5i(H %LI9D$[ 7IMW I,$H5 (Hҟ%HH9Cx 7IMK H5 (H%HH9Cu 7HHH HT$)HT$HT Lt$~D$HLl$HP8D$L|$@~D$Ld$D$@(H HHQHH@HmHu}HHH HIHHH?L HLIL@HH%SHH5IH81wX ZH UH=1VMH8H[]A\A]A^A_@HL= %M9uUM9uHLLIH(H;%L;-%oM9fLImA_IHPED$AE1E1D$ IHE1LHT$MHT$t I,$!Mt ImMt I/"Ht H*3T$t$H H=LHH1HPHH蛾fD4@9MmDIFI}H9AHAt HEN EE DD@@8A #I~0MVHA@IDA MM0IuHA@IEDAADDE9kHE1HiIAHISE8DHN HLXLHL8L(HL [@$fLI.L޼fHHtHJHFHHD$(9HjHl$(wfDL舼HHHBHfD3H H= IHDH6CIR ?@ImDL@LPXID$AE1E1D$ HPfDH=yHt$课Ht$%fMD$!1E1D$aE1dLعHuH%H50H88HT$(HHLH5'(4pfDLHT$HT$fLHT$ӺHT$fLHT$賺HT$fH蘺%#LxHPD$E1E1D$%HظIHH5(HHVHHD$(IFifH=9'Hz'H5{'IfD!T{f&cL踹cIE1D$VD$!VH=':Iu@HPD$E1E1D$&f1LfIHD'IuHI~H(IDDIE1D$D$(HPo軹IID$M1D$(E1HIHY={ILH[IIE1D$D$(HP,II1D$D$(HuDDID$D$)HPظIID$D$)H#诸HID$D$(HIE1D$AD$ HP1DIf.AVAUATIUSHHHH=N(I$H'H9G0H'HHH-'HTHEH5'HHHFIHEHHEM HIEHHʹL5s%H QP A;HLLH螹H QP AH=~89|dHImt4I,$t%LH5APH81lHLL"HHfDImA PNLdzAfH=ĶKf.;HuHǐ%H5xH8耴fDHpHLu4Hp(H AVAUATIUSHHHH=^(I$H'H9G0H'HHH-'HTHEH5'HHHFIHEHHEM HIEHHڵL5%H QP A;HLLH讵H QP AH=~89|dHImt4I,$t;H$IHl$HD$1LHHhtLȡTI諡\fDHIL+IDLpH|$0H/\HHLL='IVLHH$蟥HH H@H$HH{HLHHrLL5I'IWLHH$FH} HHH$LM5LHAHD$8HHHHD$@H; }%HPHT$@HH@HHH|$8HD$8H/Ht$@H|$8HZH|$@HD$0HtH/YHD$0HD$@HH|$8H/HD$8H|$0H/HD$0蕞IH fHL0M9t MDHPHuLHLPMtIMtIMtIH} LT$LL$L$HL$LL$HIHD$0LT$TIL4$HD$0~$H8L`L $HhLP$Ht H/hMt I,$8Ht Hm8H5'1HH+I:M I.L藞f苞fDIH,HHFHHD$HHLl$HWfD1LLcI.Iuf.LMbE1yA?LH3@$f.A|E11H|$0Ht H/H|$8Ht H/H|$@Ht H/Mt I.MtI/tJH DE1H=|*HAHHHH.H+!fDLfD ZfD^fDbfDL؜^@$fH踜H\$0fD補fD蓜fD胜fDß@$zf.H9{%LE15AH8`{H='H'H5'H~fDE1E1A|:f.Hz%LE17H8I. AE1fD賛fDHLLʡHHfDA|E11E1HT$HHLLH5'b  L IH='DH@H|$01E1A|HD]DˡI|EfDE1E1A|f.1E1A|E11۽A|H='H'H5'fIfDLHLPHИIHH5 'LHVHHD$HIFf.۠IK1۽A|fDH=q'I@LAE1诙f.Ht$ LIfDHHHD$8fH|$8#'KsfD;KfDLR1 uIHt$ AISDH=H $H $@I.yAE1E1KHuHu%H5H8萙fD胘L$LL$LT$PHL$@HT$81L$Ht$0LT$LL$话L$LL$HLT$1HHLT$LL$LD$H$H+H $HLD$LL$LT$H)HH;t%H;s%"L9HLT$LL$LD$H$H$LD$LL$LT$H*yaILLLE11AyM hHAyE1E11ME11۽Ay8Ld$0QMt I,$HD$0H|$8Ht H/HD$8H|$@Ht H/ILLLHD$@ H*yHLT$LL$L$TLT$LL$L$LT$LL$L$.LT$LL$L$nLT$LL$L$9HLT$LL$HT$L$LT$LL$HT$L$HLT$ LL$HL$L$HD$谓LT$ LL$HT$HL$L$Hl$8H\$@LT$LL$L$ƖHHLHǽ L$LL$HD$0HD$8LT$HD$@LT$LL$L$LT$LL$L$K1ɺHt$ AIALLT$LL$L$ՒLT$LL$L$LT$LL$L$诒LT$LL$L$EE15AXUE1E1VAyE17|fAWAVAUATUSHXL-'L% 'Hmp%H^H|$Ll$~D$Ld$HD$@D$)D$0HL H ~0HHHF(HD$Lf LnfHD$HbH' H(hE111AHLHH H8H' H(hE111AHLHH H8E;CNHW'H 'H9H H'HnHL='M IGH5'LHHIIHM IHIAH;m%"E1E1AH;n%7 H;o%LL$蘓LL$HIMtLpIHEKlHK\IALML\$ LL$TLL$L\$ H L%m%QA;$P  1LL\$ LLL$AILL$L\$ H QP A$=q@93 MI+ I)H'IEL0IH= H8H'H 'H9Hs H'H HL5'Mw IFH5\'LHH IM I.QH'H 'H9HHr'H1HL^'M I@H5'LLD$HHLD$IMI(Hk%I9F$LLqMHHI(Hqk%I9GHLHL$7HL$MIH)bIHMIHn L;'l%L;k%u L;k%qDI( EJHL$HIAH=!k%LHq IH'L5k%jP59'jPATjPHT$X'IHPHI/ H+%LHmMt I,$MImLH،eL f.`D$4Lf.DV\D$H'H r'D$ H9HHS'H HL=?'M> IGH5k'LHH HIHH IH_D$ HT$(oHT$(HIf H7i%H9B=HLHT$(HT$(III.hM I/UL;%i%L;%i%u L;%i%DI,$EhHD$D$LIL\$(踍L\$(HID$ L\$藍L\$HIHt$HLMH'5:i%AH H=h%jP5'jPATjPHT$XL\$`'HPL\$HIIzHII/I,$E1E1WHxE;CNHD$fDHHIH rHHIHHg%I?SIH5?H8L A1bX$ZH @H=@1AHXH[]A\A]A^A_IA@=QLt$~D$Ht0HHl$LH\$@D$LL$)D$0LL$HI{D$%fDMPIME1E1D$^E1H2LHE1HLH@HD$fDLLL$ÈLL$fHHHtH=HF(HD$@HF HHD$8HFHD$0IHHM~.H5''HHV+H! HD$@IM HD$@Ll$0Ld$8HD$UHHIM~H5'HHVċHtHD$0IM~H5J'HHV螋HWHD$8IDL與 Hx(D$NE1E11D$$E1E1E1MtI/tdMtI.tqMtI(t>T$t$H kH=psHH+1fLfDLLD$ӆLD$@LLD$軆LD$xE1E1E1E1D$OD$$=L耆LLL$kLL$L\$ LL$衉L\$ LL$@$fDLt$~D$Ht0HHl$LH\$@D$LL$)D$0$LL$HI MjI.`LLL$ӅLL$IfL踅VLHT$(装HT$(fHLD$ L\$~LD$ L\$}LHL$[HL$)LHLLD$裉LD$AvMD$cE1D$%LhAŅqI$ME1E1D$#%E1E1D$UHfDIHu1E1LLD$訄MLD$KIHIHE10 HE1E1E1E1D$RD$$D$ χD$ HE1E1E1E1D$SD$$H=LL$L\$ IME1E1D$%E1HD$^fH=I'H'H5'薚I7fDLLD$E1xLD$fDLLD$[LD${LHH='H 'H5 '&I3fDE1E1E1D$^D$}%f.L@L؂bHf蛉ID$^D$%ME1E1E1E1@H=!'I@MqMMaII$I)ID$MA1ҿA@L E1E1D$bD$%DLE1E1DL؁:Lȁ H=Y'Hz'H5{'覘IfDE1D$cD$%.D$%H= 'ID@D$cD$%IG1LLL\$ LL$ILL$L\$ HIyIE1ME1D$%HD$^IMD$%E1D$cHfDH=I'HZ'H5['薗IfDL\$LL$LL$L\$HIcH]%H5EL\$LL$H8CL\$LL$E1D$%IMD$^HWE1E1E1D$UD$ %fHFHHD$0o~I諆LD$INfDID$%MMD$cE1HIE1H@H='I@H='|I@+HD$UD$%MNMMFIII.1LLLLL$ LD$qLL$ LD$HI)LLD$ HL$~LD$ HL$zDIMD$%E1D$cHfDE1E1ID$UD$%f.E1D$%D$cMwMM_III/jHLLHL$ L\$pI.L\$IHL$ LLD$(L\$ HL$}LD$(L\$ HL$E1E1D$UD$ %SDLjMLzIEIH*LLLpImILX}H5'H=2'1kIHHI/D$dE1E1D$ &fH5'H='1IHHGI/kE1E1E1E1D$VD$3%Z@D$eD$'&AIE1E1E1D$P%HD$YL`|IE1E1D$Z%D$ZHvLHE1E1ID$d%D$XyHT$0HHLH5c'x$D$%tLLD$ LL${LL$LD$ LL\$ HL${HL$L\$ uH{ LE1E1w{D$dD$ &LZ{AE1E1D$dD$&E1E1E1D$VD$/%E1E1E1MD$^@f.AWAVAUIATUSHHHY%L5a'H|$LfHD$ H\$(H\$0Lt$8H I ~+ItILv0IE(H$Im fH$HIMmIEHEH9H=!'Lt$ HGH;X%# H;DY% HWB LbE1 ;}H QP HW%;LLAI}H QP HW%=E@9BMID$H5'LHH IMaL;W%L;`W%I9LLT$}LT$AI*DHI'HREjH9U'gH@'HHL,'MkIBH5'LLT$HHpLT$IIHMnIHH5'1LHI/H(ID$H5`'LHHHHHpU%H9BHJHLZHIH* HLHL$L\$HL$L\$IH)oIHPM_IH3 I,$ H'MHPH9ۯ'HƯ'HeHL'MIBH5'LLT$HHLT$IIHMIHLLwIIMYHIL;=U%L;T%u I9DI*EH'H 'H9HHͮ'H,HL'MICH5'LL\$HH%L\$IIHPMIH7LLvHIHHIH; TT%H; T%u H9" DH)E H'H 'H9HfHԭ'HxHL'MH5ؾ'LLT$LT$HIIPHIBLLuIIMHIL;S%L;-S%:I91LLT$lyLT$AI*EHD$HE1HLLLH IARHT$LT$1'IXZLT$MIH1ɻ*ADLw29w@$I*D"L*tDIEH+9L%ҵ'I$Im LMHD$HE1LHLLH IARHT$LT$H'_AXLT$HII HIL H9$ILI,$I/tfDImvHm~HHH[]A\A]A^A_LLT$wLT$ALIA1E1H~LLMrDHrLr9HrWLHD$rHD$3IeA1E1HIHu,E1LHL$L$]rL$HL$Mt I+HtHHHH}DH mH=pI,$5MI/LqImLqHmHquH@pIH5'HIHVuHD$ HDMe@MHH HOHL LOLD@HH O%ATHӷH5[H81wXZH gH=1hcH ;H=hCI,$sE1LpH$HHpvMHPE1AIHR1LH $qpH $#LXp;xL IMH yW1H=uLLT$pLT$ fLo&IVHHJcHHF0HD$8IE(HD$0IE HHD$(IEHD$ $nIIC~`IaIu*M~.H5'HHVMsH HD$8IM HD$0Ll$ Hl$(Lt$8H$MunHHT${HT$II4Ht$  IuIiIH5MM%L8oHH H;L%H; L%H; $HH $rH $ H) H5L%LnHHH;L%H;9L% H9 HH $yrH $jH) AH"'H 'H9HH'HHH n'HcH5'HH $H $HHH)[H5y'HH$H$HIH*CL޺LL$mL$HHxI+IH; vK%H; $K% H9 HH $dqH $IH)I.4HH'H5l'H9pHS'H: HH ?'HHAH5'HH $HHH $HHHH HHHI%H9B HLH$WvH$IIIHPMIHIBH5'LL$HH+ L$HIHH# IHH5ۻ'HϺH $"lH $HIH5 HHL;I%L;I%I9LL$oL$ I*IHvH%I9F( LLAuMHIHPHl IHI,$tH=mSnHvHG%H5H8k[LjLpjHL\$HL$VjHL$L\$TL8jHD$HE1HLLLH IASHT$L\$'Y^L\$HII HIILi<HHL$#nHL$AAH)uHiH ϫDH=DCpH+HFHHD$ gIMH5IJ'HHVmHtHD$(IMH5'HHVlHHD$0IrlLJE1 uLGHt$ 6 LAIdUH='H'H5'fIfDHL\$KhL\$zoLT$IfD1ɻAfDH='$I@LgLHL$gHL$HgHH$gH$dI.L$g$H='Hҟ'H5ӟ'n~IfDq[LL$DgL$:nLT$IfD1ɻsAfDH=1'I @LH $fH $!DIMAE1~HP HL$fL$H ըH=fDL`f"AHy'H5R'H9p H9'H) HL%'MH55'LL\$L\$HII HILL?fHIH HI>H; C%H; C%$H9HHL$iHL$AH H)%EYHD$HE1HLLLH IASHT$L\$'AZA[L\$HIIHPAU_f.Hω$d$kDH=a'H'H5'{I%fDH1ɻAf.mH='tI@A kL\$IfDLdLd MHE1AefDAH=Y'HZ'H5['zHfDLLT$cLT$S[jH $H H='|H@AL8cQAHJHLZHIH*HLLHL$L$UHL$L$IH)HL\$L$bL$L\$iL$HAHT$ LHLH5I'+ADHPIAIA1HHω$b$&IM_AHH.'H 'H9HHޙ'HHLʙ'MH5Z'LLT$LT$HII^HILLaIIMHI(L;?%L;W?%uI9lLLT$eLT$AUI*EHD$HE1HLLLH IARHT$LT$'AXAYLT$HIIH1ɻA$DII˻`HIH A1!kHPAH='Hg'H5h'3wIH=Ħ'?IH1ɻAL_%INHM^HII.hHLLHL$L$jRHL$L$HH)HL$_L$AMHPE1ALHL$X_HL$IA1E1HH*_HH$_H$HH$_L$HL\$H $^H $L\$LH$^H $DHω$^$IMgAHII˻hHH'H5o'H9pWHV'H3HLB'MH5'LL\$ML\$HIIHI%LֺLLT$w^LT$HHIGHI1H; '<%H; ;%H9 HHL$bHL$AH)EHD$E1HLLLH IQASHT$L\$ '^_L\$HIITHPAfAH='H'H5'sIH='IHPAC HHm H+ IMHPIDHH9YHuH;*% BAƉD$THKhLKMLL\$KL\$fLKHKH=9'H:'H5;'bIfA.E:4@H)%AHH>LLMbUHf.LKLKLJLJLJ^LJH9)' H'H4 HL-'Mm IEH5'LHHJ HIEHHA IEHnIGH5c'LHH@ IM 111LIIEMp HIE6L\$'ML\$HHD$ LXNIHH'H 'H9H H'H HL'M H5'LL\$菳L\$HH I+H5Փ'HL"O( HmHt$LHOIH H+HL$HHD$HHI.H5'H<$HH L9`lHhH_LpHEIH(LHL=;HmI M= I.I,$LLF7HH! I/IL(H%HHH='H'H5'^IfDE1A*Nf.H DH=g}Mt I/t'E1M.Im#LG1LI{GfE1AMIF@=L\$~D$HLL|$HD$L\$Ht Hl$0D$)D$ 貯L\$HI? M*I+ LFLFLFULL\$FL\$NM A11ېIHIHMw IE1HIHHtH+t{HzHmoH4$4F4$\Ll$1E1۾OAIEH$HIEHt?MftL߉4$E4$`DH߉4$E4$rDLL\$4$EL\$4$fDL4$E4$/DH=!'I@1A,NME1I1+LHMAE1M11E1H='4Ip@KHNLsMkL[IIH+LHLL\$r7I.L\$IALL\$DL\$*f11E1A;NfE1AMI11HfLkMLsIEIH+\HLL6ImILDoAHNJIAMJIH11E1JNADE1A NDIALNH2H5'H=2'1{IHH觾ImE1A[NIfIIAmN LLLMHmf.LBH;! %5L&CHIEHHMAoNPMLhBHXBLHIuLIDL0BL\$~D$HLL|$HD$L\$Ht Hl$0D$)D$ NL\$HI0@HAHL\$AL\$fHADHA*HxADHhAL[AqHNAZHAA3L4A"L'AAOBH='Hl}'H5m}'WIXH='Hj}'H5k}'WIA}NL@H@L@6L@LAE1y@[NH='IH='oIMANGIGH1E1E1۾OA1OAFIH?;M^MI^IHI.HCIAD$JH1E1OAsHs?IEN11AE1E1HDILAM߾OHILAMNHLl$&OAE1IEH$HLl$1!OAIEH$HH=d'H{'H5{'UIMANH=/'調ILl$#OAIEH$HYANHM1E1fDH=ل'Hz'H5z'&UIAN>Ll$1E1۾(OAIEH$HLHMﾼNAkH=g'IwA7OMANALkMHkIEHEH+LLH0ImIdLN=WAWNiAEOAROILL\$IA=HCD$L\$H111HLL$(CLL$(HHHm LϺHLL$(.LL$(HHI)'H+-H;- %H;-< % H;-Z % H|2D$XHmEL$XIWHBpHH@HH5$o'LHHH3IHHmH5q'H|$裗HH111HHHH+IU IEHHH9<H93HEIUH,HIEHmH5p'H|$ "HHD$ HFH: %H9F HnH LNHEIHHD$(HHMLLHLL$ NHmLL$ HrH5I)H5q'H艖IHH+H5lp'H|$LL$ ]LL$ HH111HΣLL$ HIH+IAH;H % IYH<IiHHEI)HE1ҿAH; %)H; %L\$ t$(.L\$ HHHۋt$(tHXHm'IcHHL$ HHHTHc1HL\qHL$ HHD$(H)HmH5w'H|$(IHmH5{'H^f'H9XHEf'HoHH 1f'HH5Iu'HLL$8HL$0ǔHL$0LL$8HHD$ H)H%I9AIiHIYHEHI)HT$ HHHmIWHt$ HHD$0HHMH+iH\$HHD$ HH\HD$H/%HH9X4LHH3IHHI)PHEH;%HUHHEHD$ HE HD$0HE(HD$8HD$ HHD$0HHD$8HHmbH5r'H|$@dAHYy'HBd'H9X( H)d'HHH-d'HH5us'HIHOHmBHx'Hc'H9X Hc'H"HH c'H H5Kl'HLL$@HL$艒HL$LL$@HI H)+H%I9C!Ht$0LLL$@L\$Q2L\$LL$@HLH"H+H5gh'HLL$LL$HHJ!HmHt$8HLL$(LL$HHb"H+aIA1۾H;%!H;%)H;%%H|$PLL$t$@*LL$HH"Hۋt$@tHXH\$(HcD$X1LHL$@HH\HcHHlLL$7LL$HL$@HH$H)[I)Ht$(HHD$HHHt$H%HD$H<$H+LV%IH/%H|$H5j'LLT$(HGHH$LT$(I*gHD$Lt$(HH1$IHLLd$E11E1HD$(E1A6AHD$8HD$0HD$ HD$D$@DLt$E11E1E11E1A@HD$(HD$8HD$0HD$ HD$D$@]K,I8H)%HH5NgH81+HFLHD$p#IH5%p'LHV )HD$xHHIM2H$Lt$pLd$xL$HD$@H$HD$HH5h'LHV(HtH$IM~H5p'LHV(HtH$IMxH5[g'LHVW(HtH$IMKHT$pHLLjH5D'?%@Ld$E11E1E1E1HD$(AAHD$8HD$0HD$ HD$D$@Ld$E11E1HD$(AAHD$8HD$0HD$ HD$D$@DD$Xl@Lt$E11E1HD$(E1E1AAHD$8HD$0HD$ HD$D$@DI]HMMHIImLLHLL$H+LL$HD$HLL$"LL$fDE11E1E1HD$(E1A AHD$8HD$0HD$ HD$D$@f.H=h'H]'H5]'69IfDH=h''}I"HD$(E11E1HD$(ACHD$D$@ HD$(E1E1HD$(AsCD$@ HD$KLL\$`HL$DHEIL\$`HL$NHD$(E1HD$(APCD$@ HD$AHL\$ LL$L\$ LL$HHD$(E1Lt$(1E1E1ACD$@HD$H=='H6'H56'{IH5;'H=}J'1dHHHvH+t~HD$(E1Lt$(1ACD$@E1HD$jHD$(E1Lt$(1ACD$@E1HD$@HD$(E1Lt$(1ACD$@ E1HD$HuHD$(E1Lt$(1E1ACD$@HD$Df.AWAVAUATIUSHH$H^H|$HDŽ$H$H H HS Hn I\$HD$xHHDŽ$HDŽ$9H$H H4J' L(hE1ɹAHHAIHD$xHH$HH|$xH/ HI'L$HD$xHDŽ$H _5'H9HHF5'H%HH25'H\$xHTHCH5QE'HHHIL$H|$xMH/ H"I'H 4'HD$xH9HxH4'HHL%4'M|ID$H5A'LHHIMI,$ IEH;$A1E1H;$ H;b$ L$cL$HHMtL`H9'LcIIN|HJDIELM!H QP H$;y1HLAIH QP H$= @9 MLd$xH+ Im H$H$H9G_Ht$xeH$H|$xH/V H$HD$xHH$H/J H$H;=;$HDŽ$AH;=$DP H;=$C H$D$:H/ HDŽ$L$IGH;-$HD$( -HD$ H HL(Mt L;-v$HPHuLpH@HD$M~MtIHD$HtHH3F'H 1'H9HH1'H*HH=1'H$H HGH5?'HHHD$xH$HH/H|$xH$HDŽ$H9G7HH$H$HtH/H$HDŽ$H|$xHH/H<$'HHD$xH$HD$xH@  HH$H~$HDŽ$HDŽ$D$xHD$x@Mt Im Mt I. HT$HtHHD$ HH` HD'H5 0'H9phH/'HHL%/'Ld$xMID$H55'LHHHIL$H|$xMUH/ HC'H u/'HD$xH9HHS/'HHL%?/'Ld$xMID$H5='LHHIH|$xMH/H$HD$xHAH;b$LH;e$oH;($ LT$(LT$HIHD$xHtID$HD$xHcD$H1LI\MTH$[IH$H)I,$+ H$H/QL$HDŽ$IL$HDŽ$IEAuI} HD$@HuB'H5p<'HD$0HD$Ht$HHUHHT$qIHH@HT$HHLHIHHD$H5<'HHt$LELLD$HHPLD$HHLHHH$HHPH;$@ HhH3 H@HEHH$H$H/ H$H,H$Hm1 H$HH$H/F H$HDŽ$H/8 HDŽ$GH|$0HD$H8H $HD$(Ld$`1Ld$@Lt$XHLl$@HD$HHL|$hHH\$PHHD$ HHHD$8fDHHD$M4L|$(fMHHHD$fAH|$II $ $AEXL9|$u^:^f(H,1fDfAfYAHH9D$ uHD$8H9tHIYHH9l$07H\$PLt$XLd$`Ll$@L|$hH|$H4H50'1LcXI,$HHHmILI/RImMkfLWI\$fDHH 1H 0HOH:2L 0LOL@HHd$SHI5H5H81XGZH 0H=$E1{HĸL[]A\A]A^A_@HIE@=Ld$~D$HHL|$H/'LH$D$)$VHHD$xHH$E1L$GD$f2%LpH@HD$IExf{fDAĉD$[mfDLHHH H1 HHHH5Q9'HIHVIH$H M H$H$fDLSfDfDH@$f.$RGH|$x11E1E1E1E1D$E1fHt H/H$Ht H/H$Ht H/Mt I,$Ht HmMtI*txT$4$H .H=!yMt I/E1Mt ImHtH+t!MI. LfHXfDLH{LT$6H$LT$ @LT$LT$@LT$LT$@LLT$LT$fHLT$LT$f1LIfDH<$/IH$Hq HH$H H$HDŽ$HDŽ$HC@Ld$~D$HHL|$H+'LH$D$)$hHHD$xH MtI,$iL\H|$xHHt H/ H$HD$xHt H/u~H$HDŽ$Ht H/uZH + HDŽ$H=qvH|$ H$HT$xH$W Hv$H9EQHEH<$IHh HD$0LT$0HI~ LPHHHHw HmL I,$1 H$Ht H/ H|$xHDŽ$Ht H/ H$HD$xHt H/ HD$ HL$LLHDŽ$H2_D$\GE11E1D$H$1E1E1@H$E11E1$kGD$H=I.'H#'H5#'HTfD1{fDkfDLX.LHH= DsIH$L1HD$xE1$GD$@fDHLdLEHHIH0 $]HE11D$HD$ HL$LLLT$E11E1Hz]H|$xLT$E11E1E11$mGD$H=,'4gH@I+fDHA@=HD$xHHHL$LT$H$H$>NH|$xLT$HIH$ Ht H/HD$xI*LVH=+'H*!'H5+!'6IfDH|$xE11E11E1$pGD$fHhoH$ efDH=q+'eI@I3H|$xE11E11$rGD$]DLT$~LT$7@kbfDMeMDI]I$HImHCIA1ҿDfD1E11E1$GD$f.H_HHGHHH$H$H/HT$xH$HHH$H+YH~Lfk6fD$GH|$xD$E11E1E11E1LH|$xE1E1E1$GD$I$FfDofH)$sHH$HHLz)H5.&[ G+HFHH$I@H5"'H=1'1KIH$HH]H$H/)H|$x$GHDŽ$D$1HL3IHD$xHfILH$1$GD$@HH$jKHHD$xHD$xHHHL$LT$H$H${_H|$xLT$HIH$1E1E1$HD$H5$'HHVH*H$IFH$E11$HD$H=a''H'H5'IfD{IH=)''aIg@E11E1E1$HD$)fH=&'H'H5'6HgfDH H=&'H'H5'IofDH$E11$HD$fDfDH=&'`H@HfDH=&'`I@CI1E1E1E1$HD$ f$HxfDHGH$HHWHHH|$xHT$xH/H$H|$xH~H}yHqHt$xHHAHHH$H$H/H$1ҿD$HAWLXHHL8H|$x)HvH$Ht$H80H|$xE11$HD$;H|$x1E1E1$HD$H$Ht$H8$HHDŽ$I,$H|$xE11E1D$Kvl b#H|$xE11E1$HD$ $QHE11E1D$$ ItH|$xE11E1E11$GD$ H$E1L$GD$LT$LT$=H|$xE11E1E1E1$GD$ WLE1$_HD$H|$xE1E1$ID$$aHD$E1$fHD$$A1LT$H$1ҿD$LT$HAH|$xE11E1E11$GD$nHϸ$H5H81E1E1$HD$7Hh$HAWfAVAUATUSHHXHt$HnH|$)D$0HD$@HD$HHG HH[HF0HD$L{(Lc H[H/+' H(hE111AHHHH4 H8H*' L(hE111AHLAIH_ H8}H*' L(hE111AHLAIHb H80 AE;E;HD*'Hm'H9PHT'H[HL%@'MID$H5%'LHHIMI,$H)'H'H9P/H'HHH 'H3HAH5#'HHL$HHHL$HHHHHHHCH;W$a E1E1ۿH;E$ H;$ L\$t$ L\$HHMۋt$ tLXIHEHc1JlHHIELlHL$AHL$HIhH) H+ H$I9GLLhMHI,$7 HFI(l H;e$AH;$DH;/$HQD$ H+S t$oH''H5'H9pH'H/HL='MIGH5#'LHH-IMI/M H''H'H9P]Hf'HHL=R'M!IGH5 'LHHmHIHHyIHb HAH;$A1H;$H;˵$HL$ HL$ HIHtHXHcD$IEIc1HL\$ MlIMtLHL$o?L\$ HL$HIIHI9 H)O HX$I9D$LL"MHI/ HJI(w H; $AH;ͳ$D H;$H D$H+. L$RH%'H'H9PH'HHL%o'MID$H5b!'LHHIMI,$H?%'H5'H9p3H'HZHH 'H1H5#'HHL$ >HL$ HIQH)ID$H;߱$G1H;Ѳ$H;$.HL$(t$ Hct$ HL$(HHHtHHHcD$HE1LHlILtH<=IHH+I,$H4$I9G?LLLL$LL$MHI)hHI(H;$H;$^ H;$Q HAąmH+EHD$HIH=0$HHp HL 'HjAQAVjAQAUjHT$P>"'HH@HH+HHD$HL$DL`IH5f'LIHVHD$0HtHk@HHH HMHUH7L@H5$H5L H81X4ZH R H=1_HXH[]A\A]A^A_fHD$$fDLlHHAHvA;FHf.VD$ Lf.:D$  Lf.f( d$f/T f/L$ p f.d$  HD$D$L$(HHHHD$ L$(f(vL\$HIE D$ L\$UL\$HI Ht$HMHHn'5$AH H=$jPATjPAWjPHT$`L\$X'HPL\$HH H+I+I/gI,$<Hmt'ImHt>I.L&1HHL$HL$HMtImuLMuHAljD$HIHHcHHF0HD$HHC(HD$@HC LHD$8HCHD$0 IH;~7HTHu0MDHD$HH\$0Ld$8L|$@HD$PH`M~HT$0HLLH5߹&Hy3@HC@=L\$~D$Ht0HHl$HL\$ Ll$@D$)D$0O7L\$ HIjM7I+-L fDD$H4E1E11ɺ HtH)t5t$H H=[H,Hm 1HωT$T$fDE11ɺ D$W4@LLD$LD$fHo1ɺ D$f4L@LHA@=H\$~D$Ht0HLl$HLt$@D$HL$)D$05HL$HIHH+HHL$HL$@H5'LHVHHD$HIfDLLD$LD$fHAljD$L[MLcII$H+ ID$L1ҿAqDLP|HFLHD$0IH5'LHVHD$8H IH5'LHVHD$@H IDLHL$HL$fD$5 1HHH+>H߉T$HL$T$HL$HpH`L\$~D$Ht0HHl$HL\$ Ll$@D$)D$0DIL\$ HIuD$b5M;I1E1亱 HIHHHHtFMt I/M^I,$SLT$HL$HL$T$4@H߉T$HL$T$HL$@D$P5IE11ɺ IHy1L߉T$HL$I\$HHI,$aHCIܾ1ҿD$HH$L kH5 jAH HH81#AY3AZg1E1MǺ D$]6MgMMGI$II/LLLLL$ LD$I,$LD$HLL$ LLL$ LD$5LL$ LD$gI$M㺵 E1D$@6HH D$`614I$M㺵 E1D$K6H,H5n&H= '1&IHH 9I/? D$o61E1{LHL$ LD$ULD$HL$ D$6D$j5L D$611ɺ D$41ɺ D$51ɺ D$4o1ɺ D$4[LHL$ I諼HC1ҿD$HL$ ALLL$ LD$bLD$LL$ LK D$o61D$51ɺ D$6I$M㺵 E1D$:6Hj1ɺ D$k6n H1E1亱 H@f.AWfIAVAUATUHSHH$Lf)D$`HD$pHGIuILn(IG MgH$H ' HD$0HD$8HD$@L(HD$HHD$PHD$XhE111AHH<$AIH9H8 H 'E~H(hE111AHLHHH8W EuCD$H5'L 'MH5'H '7L;-h$H[ 'H &H9HH&HHL=&MnIGH5['LHHILd$0MI/HL$0H5$HAHt$H9E1E1H;ї$H;$Vt$D$葼IHD$8HXMD$t$tLxIcIELc1HLMlH$HKDH|$0,"IHHH|$8H/HD$8H|$0H/!L|$0I?HD$0E1H'AwI HLLL'H$1AIHH;$HD$8Mt ImID$H5]&LHD$8HHHD$8HiHLM'H|$8HD$0HH/HD$8H|$0H/HL-'HD$0HQLHL$ HHT$ HD$HH@HT$HL$ HHdHH|$HD$Hq LL-'IPLLD$ HHT$赻H,HpHT$LD$ HHLHHD$8HG HpHD$@H;t$HPHT$@HH@HHH|$8HD$8H/Ht$@H|$8H`H|$@HD$0HtH/HD$0HD$@HH|$8H/OHD$8H|$0H/'HD$0HD$HE`HHE 1H<$L|$ L,$Lt$MIHH$HfDI0HHL0I@H0I8H0H6t1IANIF %pH(H0H0H@(A;~}MHcI H0H@H0Pt8H(HR8HcR H0A;~|IM93MH$Lt$L|$ H|$Hl$H5D&1H"HD$XHEH$HHEH|$XHH/ HD$XI?LKI,$WI.d@H+H~zMgIHH HMHATHL@H$H5]L H81脺X6ZH b H=E1bAHĈL[]A\A]A^A_DIH<$7f.w$<ID$ID$HPHD$HH HcHf.AD$HHD$H|$uH"HD$H=&$'@fH=x&H*D${'L;-C$H6'H o&H9HUHV&HHL=B&L|$8MTIGH51&LHHvIL|$0H|$8MnH/ HL$0H5$HD$8AHAHt$H9RH;$H;a$s fIHHD$8Ht IGHD$8HcD$IEIcLMlH$HIDH|$01IHD$@HH I/ H|$0H/ HD$@HD$0HH|$@H/ L|$0H'HD$@HD$0AwI HMoH5&HD$IHHH5&dHD$@HHL$H9H HPH H@HHH|$@HD$@H/2 H|$@HHT$HT$HD$0H*HD$0HH|$@H/ HD$@H|$0H/ HD$0!H|$HD$~cHt$HE`HM Ld$Ld$H\$ HIlLt$(MID$HLLIٰIFL9uLd$H\$ Lt$(H|$H58&1LHD$XI,$FLd$XMI,$HD$XI? L袯DusHP0H;0HHP0H0H0H01LISMtI,$uL?Mt I.H fHcL MA(M9(iIA(H0H(H)0+IA(H0H(H)00H0HcL MA(M;(}ILD(H0H(H0H@0H0H@(H0H(H+0H0H0dH HH5b&EIH*HH5[&&HD$8H3HD$@H $H9HHPHT$@HH@HHH|$8HD$8H/)Ht$@HD$8HH衷H|$@HD$0HtH/ HD$0HD$@HH|$8H/WHD$8H|$0H/5HD$0ܫHL$HHT$PHHt$XHD$Ht$$HU`H} 虭HqIHD$0H\HD$HL$HHD$0HT$PHt$XH#1LLd$HH5&HD$PI/&L|$PMI/hHD$PL|$HHD$HI.fL(II~qItIHF(HD$pIG LHD$hIGHD$`nIItnIMt:MD HD$hLd$`Ll$pH$bDM'HIH5&LIHVeHD$`HH5&LHVDHD$hH IM|H5&LHVH HD$pIIHA@=L<$~$Ht`HL,$H$HHD$p$)D$`aIHMt I/ MfD$L71E1E1" @H|$0HtH/t`H|$8HtH/t`H|$@HtH/t84$H H=7MI/E1D ffL8E1E1$ $m7IfL踩L|$0fD裩fDH &HL1IHH;$HD$0 H&H &HD$0H9H- H&HT HL=&M H5&L,HD$8H7 I/DH5 &LIHy HL$8H5$HAHt$H9| E1E1H;$ H;‡$ t$D$迫HD$@H MD$t$tLxIcLcHHLlH$HJTH|$81bIHD$0Hf H|$@H/ HD$@H|$8H/fHD$0HD$8HH|$0H/?L|$8MHD$0HD$8fDHA@=xHD$8Ht`HHLl$hHD$`H*$HD$pIHD$@HH|$8Ht H/HD$8DAD$HHAD$H HHD$AD$HD$fAD$HHAD$H HT$fH=y&'I@æfDL谦HT$螦HT$H=WH E1P- 3H|$8HD$0$7DKvfD;NfDL(5fDHD$HfE1E1( $7ifL<$~$Ht`HL,$Hl$HHD$p$)D$`#IH$7+ fDMI/t!E1$:J I/uLE1UHHD$8NfH|$8/H/HD$0ofDfDfDE1E1) $7aۤZfDˤfDLxHD$ HfD諎H*H3h$H5H8Ht$HfHfDH=輍a@ImTL荊GHuHg$H5XH8`fDH@`H^HHNHIH=H@H;h$f?MeIT$HH AHcHEeAMcImLÉfDEeAEII I@EeImOEeAEII ImLE1ULH5oaIH|HT$HL$eHHL$|HL$VH|WHHL`HL$ -fDL{uHD$fIH#~aHtHHF(HD$`HE LHD$XHEHD$PzIHt^Ht}Ht.M H|$PH3HyIH5&LIHVHD$PH H5&LHV~HD$XH IM~H5ƾ&LHV~H HD$`IYzfDz}fD@DzfDH|$@$D11D$tE1E111If$EE1D$u111E1/+z=fD$EH|$@D$11E11fDyqfDyIfDy!fD}@$f.HyH5&H=&1IHD$HH HH|$HH/HD$HE1$/ED$zH|$@111E1H&?@L yHyLyI(H=&Hr&H5s&ΏHfD$ED$n@H|$HIfDHHD$HfLxxkxfDH=&tH`@11E1$ED$DH]xfDH|$PAxEHt H/HD$PH|$@Ht H/HD$@H|$HHt H/H DHD$HH=HL$@HT$PHHt$HYHT$I9GIH<$yHHHD$(xzHT$(HHHPHLHD$(svHL$(HII/0H)H|$HHt H/HD$HH|$PHt H/HD$PH|$@Ht H/HLl$(HD$@~D$(H8LxD$ HhL`Ht H/OMt I/PH(HmH4vH=&H±&H5ñ&HfD$ED$@ufDufDu fDH=&H3@AzEDk|@fD{ufD$ED$@AEPDHGHD$HH,HWHHH|$PHT$PH/-Ht$HH|$PHLgfDLH$tH$HtLtHL$(fDAEDH|$PAEHFHHD$PsI`HLLzHHH|$@11$ED$)f+tifDtvfD tfDLss fDH=vH|$@$EH|$@$5F11D$E1+wIHwH|$@11E1$ED$O$E11E1D$HLl$~D$H8LpD$ HhL`Ht H/Mt I.HtHmH|$@E11@H|$@E1HQ$LH8rH|$@11$HFD$fr#fDHYQ$LH8r$JFHD$HI/*H|$@11E1D$+$LED$}@HT$HL$rHT$HL$fLHT$HL$qHT$HL$HHT$E11HL$qH|$@HL$HT$D$XF>@$NED$}F@LhwIH11$ED$1$ED$$ED$L"q1$ED$H|$@1E1$FD$pHT$PHLLϷH5]&XDDDH@`HHHHHH@L-O$L9HCHPHD$HH ɹHcHD{AIcHD$H+H pD{CII IL|$ыCHD$H+D{CII L|$H+HoHD$DHH5HHcH@H4sHD$M$+ED$zHHM$H zH5ejL AH)H81}uY^DOH]H9L$H5H8orHHL$H5!H8oH@`HHHHHHL9hHEt'HEHD$HHH HcHHHD$Hm#H8nD}AIcHD$D}EII IL|$뿋EHD$D}EII L|$H5 HHHDH+HmHqqHD$\BqHuH^K$H5߮H8n$JFfAWIAVAUATUHSHHFH =u YL5rL$L9YH;J$H@hHH@H1HHHL-p&I9gHK$H9CI9E { A}  HSI;UH+uHlH5&H=&1HH HH+huH߉T$ 4$9l4$T$ H wH=D1}HH[]A\A]A^A_H5&Him ;H5\&H=&1HHdH2H+bZueDL%I$L9uM9uLHkIHH;I$L;-jI$M9LoImAE7AAgE11H+1E1HH $jMH $vI,$kLH $jH $VfDHEHHH5&Hl HEE1HEH5X&HHH} HHW HCH5&LM H4$mL54H$H4$H QA;P  1HAI^mx WP AH= @9:M H+H8G$I9D$5Lnf.] I,$AGXHEH5k&HHHp IMr ID$H5&HHf H4$lL5FG$H4$H QA;P  1LHqlx WP AH= @9H I,$yHC` HCHH6H{HcHfDHCIMH9@H@t H{ Au 8@  @HK0LCHIDH@  IM0IH@IDHȃ6  DA9HE1HjAH+Et{[@H5A&H=Ҷ&1HHHH+fiNfDAD$@H]HH+"lHHHEL9HH;D$H@hHNH@HA1HIMfH5&LHlTI,$lIHHHEL9+H;4D$H@hHH@HHHHH5g&HLH $XlH $H)HEL9H;C$@H@hHH@HHHHH5&HLH $kH $H)H5%&LHkI,$HiHHHE1H+ E11Aj1AI,$HtH)t]H DD1H=wHtHmt&M ImL*eDHefDHefDHEL I$LdHdL$d$ g@$fHEHHHLeI$lf.Lhdzg@$UfHHdHEHHH1fIHuQfH Ug1H=Q@HM HMHcHHdI,$HLcfE1DH+>IEgPHH5Ħ&HGHHpЅHA$HfDDcAܐAufAHtA@ArfCSHH HHcAH9tHA$H5߄H8cDDcfCSHH HcAH9tfImDLbd@L`TH hH=$H@hHlH@H_HIMH50&LH}_kImtHIHq+fgH{19cIHt,HHaImIL`E11AAj|fHHdHcAH99Hz dHl"@1H~fIHaA-Aq{$c$HcI,$uL`H Hq01H= DaBfAAkHE11HHf.E11AAkdf.H=9H4$pbH4$6 bA-AqHH_<$H5H8`eIr;1LeHHf.I,$ArA=1faIHHH_ImHLH$u^H $@AAkH=H4$PaH4$_aHJHK;$H5~H8_/afDAAk#H8\AAj1D_IHHH^ImHPLH$e]H $;@IuHH{HAAksHE1laIfD@HELhIE fDL\2HELh IEgL\Lm0IEDgLm8IE2^IHkHHp]I,$IL:\~HALAmE11AAkTHݺmL^IHAHH\I,$IL[rHA LAnE11AAkHݺn EH@`HHHHIHH@L%9$L9fDIFHHHڤHcHEfAf.I.LZAFAVHH HHcAH9tH8$H5|H8[I.bLZUEfAFAVHH HcAH9{I.ALQZ@LH5gYIHH@L]HcAH9HG]H9JE1Hݺm1AAgc]HH{7$H5H8ZeE1Hݺn TH@`HteHHtYLHHtLL9`u*HH$H$AH*UH=YHH5ZHIHHuv\HhH6$H5PH8YMHXH +fH=)H r=1H=ʏSH jH=aAAj11E1_H bVH=n'HIEH 3$HT$0H9H@hHH@(HHL$HLHL$H|$0H/IEHT$8HD$0H9H@hH"H@(HLLЅH|$8H/HD$8HH|$HHt H/"HD$HH|$PHt H/"HD$PH|$XHt H/"H5&1LHD$X[HD$XI/O"L|$XM"I/b"@H91$HHH5&LHIMH5&L9t\ID$H;X1$I|$uA|$t:f.H-0$L50$HEH-fA.D$zuDL50$H-b0$ILHD$0I,$[ H|$0L9H9RH;=[0$EVH|$0ADžH/& HD$0IMH¡&EH9HH5&LH'HD$8HH5g&H9tHPH;70$Hx L5/$H-/$ILHT$0H(HD$8H|$0L9H9H;=q/$UH|$0ADžH/HD$0EH3&H &H9HgH&H1HH=&H|$8H/H5*&ͺIHD$@HH|$8H/=H5ސ&LHD$8e?HD$8HH|$@H -$H9OCHyZHD$0H|$8H/=HD$8Ld$0MH|$@H/HD$H5[&HD$@Ld$0HD$0H IHAHD$H58&HHD$@H/HD$8H ,$H9HHPHT$8HzH@HHH|$@HD$@H/ Ht$8HD$@HGHwYH|$8HD$0HtH/HD$0HD$8HH|$@H/HD$@H|$0H/HD$0HMHL$HHT$PHt$XHHD$蒷H>HD$H HD$H|$HSHD$H9 11HL1HD$0HOH5,$HLLH|$0H/11HLHD$0HHD$0HIEH ^-$H9%H@hHH@(HHL$ Ht$LHL$ JH|$0H/HD$0IEH9H@hHH@(HLHLЅ1HH|$XHt H/ HD$XH|$PHt H/HD$PH|$HHt H/H5n&1LHD$HCHD$HI/L|$HMI/HD$HH-+$gDH|$0E1SE1JHt H/H|$8Ht H/MtI/trH|$@HtH/trH H=1MtI,$tHh[]A\A]A^A_fDLHD$#LHD$Hh[]A\A]A^A_LLfDK뇐KMfDLE1E1KAfDHH5&LHHD$0HeL9H9u H;)$H( HD$0TH-)$I9IUIEH5\&LHD$HHDILt$0MIFH;N*$H;i($H@hHH@H1LIH|$0MA H/qHD$0L?IHI/WIEH5 &LHHIMID$H5O&LHHT IL|$0M) I,$H|$0,?IH H|$0H/H9&H B&HD$0H9H H &H HH= &H|$0H HGH5+&HH IH|$0M H/HD$0L LIHD$0H LIHD$8Hq HD$0HD$0IGJNIHD$0H HR&H K&H9H H2&HA HL=&M} IGH5 &LHH HD$@H I/HT$@H5!&H|$0oNoH|$@H/`HT$0Ht$8LHD$@荱IHD$@HI,$H|$8H/HD$8H|$0H/HD$0Ld$@HD$@I9ID$H5F&HD$HD$HIHHD$H50&HHD$0H#HD$8H $$H9HTHPHT$8HBH@HHH|$0HD$0H/Ht$8HD$0HHoQH|$8HD$@HtH/NHD$@HD$8H/H|$0H/HD$0H|$@H/HD$@EHL$XHT$PHt$HH蓯LSIMHD$H\$H HD$(LIHH|$(LLT$ KHL$H|$LIHHHL$EIHL$HLH2IHt$HLL)ILT$ IuH}Hl$@tHD$@H|$HHt H/uEHD$HH|$PHt H/uEHD$PH|$XHt H/uEH5&1LHD$XЮHD$XI/YL|$XM>I/ HD$XHEHIFL8IH|$0H/AE@L0EL EEfDM~IH|$05fDDhfDLDDfDLDL%&MIUI9LHXHNHqH~&L;a)1@L;dHH9uH"$IL$E1H5jHRE1[1JH81JH|$0qfLd$8\;JM~I,$ E1kDJIH|$0E1佂E1zLff.@z 'DH-!$L5!$HEHDHGHD$0H|$0E1WE1$JCCfDL0CHDHH9@HuH;!$)fE1WJE13BfDBpfDH xH$H5oE1[1JH8CH|$0fDsBUfDDI1DIH HLZCI,$I]L$BPnJbE1I,$tH|$0E1L@LE1AH|$03sEH1M@J\E1H|$0E1]KJfkHIE1\=JfDIEHfD>fD>LfDbJbH>GH>IH>gJby{>jfDk>fDiJbIH=&Hzz&H5{z&6UIHfD#>*fDH;y$L~>IHD$0H JWfDkJbfDfDH=I&ľI@HHL$HT$?HT$HL$HkHLHL$HD$;LD$HL$I(9LljD$>=HL$D$H=&H5By&H3y&THfD|]LH|$0E1E1HGkDLH|$@Ht H/HD$@H|$0Ht H/HD$0H|$8Ht H/H ~HD$8H=sHL$@HT$0HHt$83HL$@HT$01Ht$8CIH 1HLGI/HzI,$bHY H;G$H;$ H;$H5@H+AEySLfDHL$XHT$PE1E1HHt$H袲H|$0LfH\$8EkHt H+( HD$8H|$0Ht H/u HD$0H|$@Ht H/b HHL$XHD$@HT$PHt$HH$HDH+DbH:DLHT$=HT$HIHL8I.LD$q:D$H=I&tH@H|$0E1|E1_LfD#:fDL3fDL#fDL9rLfD9fD9fD9!fD9TfDpJbf{9fDk9afD[99fDK9fDH5&I|$菹-H|$0cJE1hH|$0dJT@8fDIEHt$Ho8IEHI H=y&ƸHmCKj>H|$0E1佅LxLaLI/H|$0E1佅E1E1mHKE1~H|$0E1\=JgLHp66Ll$@Ld$0(:H޻MLLH肧HD$8HD$0HD$@H;$H7HD$0H[Ld$8mEKeL^6T6J6H|$0dKL)6KAwH|$@Ht H/]HD$@H|$0Ht H/JHD$0H|$8Ht H/7H xDHD$8H=l H|$HL$8HT$@Ht$0qHL$8HT$@1Ht$0HHVd&HHCH5r&HHH IHHMHHfH$I9FI^H{INHHI.rLHHLT$(HL$ H+HL$ ILT$(I*M,H)&L;%$7I/H<$H5t&HGHHnIM;Hx&H54c&H9pHc&HHHc&HRH5q&HgIHH+Hz$I9FInHINHEHI.HLHHL$ HmHL$ HlIm5HH)cH;$H$HHD$ HHJHD$HH=Z$LHp ILL qn&j5m&Sj5n&ATjLD$XHT$Plv&IH@HbI.ZLMoHH$Hl$IHE11D$D$?Lx%IH5m&LIHV*HD$0HH]@HHhH hHMHSHmL@HM$H5LL iH81,Xj=ZH hH=]1謳HXH[]A\A]A^A_f.HD$fDH&H&FH%H%H$;B)!LIH& LIHA HHH\ K.H9 HD$LLI$(IH LHD$'LT$HI H'LT$HHSHt$HE1LjAH=$5k&H Pj52l&AVj5k&ARHT$`LT$Xt&HPLT$HIQI,$6I*I.H+LEIHHmtPI/Lt]@H$HHD$HHtkMImL?$f.E1HL"$MtI/uL$H<$ufDH#<H#fDHIHmHcHHF0HD$HHE(HD$@HE LHD$8HEHD$0$"IHc~7H|Hu0MHD$HLl$0Ld$8H\$@HD$H`M~HT$0HLLH5yc&LHV}#HDHD$HI1fDH= f&H:Z&H5;Z&V6IfDH@HFLHD$0IH5ef&LHV#HD$8HD IH5e&LHV"HD$@H I`DLHL$HL$WfL+LHL$HL$fLLT$sLT$fHXHLD$CLD$fLLU(LHD$H=d&HX&H5X&4HwfDE1E1E1D$D$q>f.LwH LLLLT$sLT$fLT$~D$Ht0HHl$LLT$ L|$@D$LD$)D$0GLD$LT$ HII$D$1D$>H1I$HtE1E1f.LLT$(E1E1LD$ HL$HL$LD$ LT$(E1E1D$D$s>DH=c&茝H@;#IHHD$CLT$vfH=b&H W&H5 W&3H fDE1E1D$D$v> DLD$H$Ht0H~D$Ll$LLD$ HD$@D$)D$0ЙLD$ HI~IED$>HIE1D$HtEI$1E1HuID$6>E11D$HIHuMfLLD$#MLD$uE11E14@H=a&H@!I H IE11D$x>D$LLLT$ $LLT$ IDI$1E1D$D${>HfDLHL$ cHL$ )fH=`&dI@I$1D$D$}>H)f LT$IfDHHMPM" IXIHI( HCI1һA|+HE1D$E11D$=E1fHE1D$E11D$=E1RfHE1D$E11D$=E1"fH5Y&H= h&1IHMHGI.UE1D$E11D$>E1DHHL$ HL$ VMD$M I\$IHI,$HCI1һDI$1E1E1D$HD$,>3LLH"LH7DLHL$ HL$ HLT$ LT$ fI$D$D$>HHLE11ID$D$>I^HINHHI.(LHHLT$ HL$ H+HL$ILT$ HLT$ HL$ LT$ HL$qDI$E1D$D$>HIE1D$@>D$HmLLT$(HL$ HL$ LT$(mIED$>HIE1D$J>D$H H5V&H=[e&1lIHH蘑I.E1D$E11D$>E1I$E1D$D$>HHLT$(HL$ LT$(HL$ E11D$D$[>HeLHL$ HL$ ZIaE1E11D$ D$ ?uHMH@H=[&HO&H5O&!,HDE1E1D$ D$?LLT$LT$LHL$ HL$ LH=\[&וHE1D$ D$?rIE1E11ID$ D$!?HHL$ ]HL$ }H5,d&Hx裔3Ld$E11E1D$ D$$?9E1Hl$E11D$ D$/?IE1Hl$E1D$ D$1?H=cZ&HtN&H5uN&*H LLT$AHCI1һLT$]LpH=Z&H2IHl$1E1ID$ D$3?8HH#H LUH579jL VAHZH81OY^L=}LLD$IHC1һLD$bE1Hl$1ID$ D$C?H5kb&I|$Hl$E11E1D$ D$F?wME1Hl$E11D$ D$Q?R ILLT$ HL$HL$LT$ ME1Hl$E1D$ D$S?H=zX&H{L&H5|L&(H`HH|#AH57jL UH SH8HX1_F=AXMHl$E1D$ D$U?yH=W&mHL=ME1Hl$E1ID$ D$e?2H5`&H{bOMHl$IE1D$ 1E1D$h?H$M1MHl$E1D$ D$}?E1wE1E11D$D$ >1 I$1D$D$>HPIE1MD$>D$HE1E11D$D$>!E1E111E1D$x>D$ Df.AWAVAUATIUSHXL-#H^H|$HD$0Ll$8Ll$@HHHHHHQH QHOHRL QLOLDHH#SHMVH5Q5H81X'ZH ]QH=FE1]HXL[]A\A]A^A_Ll$LMd$I$H_&HEL9IH H&H9Hp HH&H HHH&H< HCH5P&HHH IHHMq HHH=[&H5WX&HGHH HHu 8IH H5U&LHH5{W&HL HCH5]&LM] Ht$L#Ht$H QA;P eLT$ LHAHD$LT$ LL$H QP A=29MH+^I.4IGH;y#3E1E1H;g# H;*#dLL$ t$&Hct$LL$ HHMtLpH[&INLHHDIGLML#H QP A;LT$1HLAILT$H QP A=29 MH+ I/(Im H|$H5qQ&HGHH IM H#H9]&H IH H@H5wM&H9^ IGHPH H[AWHzHuH)HH I/IH Ld$~D$H\$I$D$@IHH HT$H5N&HQ HS&H5{U&Hk HLLtIHIm6 I/ H+ f.I,$HmH DH D&H9H7 HhD&HWHL=TD&M IGH5xL&LHH HIHHP IHH=V&H5T&HGHH IM IH[ H5Q&LHHD$LL$IGH5Y&LM LL$ Ht$ Ht$LL$ H La#QA;P  LLT$ LLL$AI LT$ LL$H QP A=29;M I/I)HCH;3# A1E1H;!# H;#DL$ t$ Hct$LcL$ HI MtLxHrW&H1HMtLHKDLT$qLT$HII HIH+KI)1I$ImHI&HI,$LIHF(HD$Il$ DLl$L.HfHEH5dI&I@HHHtHHF(HD$@ID$ HHD$8ID$HD$0IHHM~.H5 K&HHV H( HD$@IM HD$@Ld$0Hl$8HD$DHjHgIH5N&HIHV HD$0H M~H53P&HHV HZHD$8IG@DIA1W(E1HIHtPHtHHHHt\MtI)tqMtI.t~H kHDH==E1mhLt$LL$t$LL$@H߉t$LL$t$LL$@Lωt$t$zLt$t$mIG@=Lt$~D$Ht0HLL$HTT&LLL$ HD$@D$)D$0mLL$ HIn Mt I. I)LfLLL$LL$fHLL$LL$fIA1X(E1HNfDLL$LL$@$7LxoLh@DA/F(H=iF&H*>&H5+>&&HfD@DLLHC@=%L|$~D$Ht0HLt$HR&HHD$@D$)D$0=lIH Mt I/W I.CLLL$kLL$,LH IHfIA1Y(HfLLL$LL$fH=)E&I@E1A/H(MfH=D&H'@ IBIE1E1A1S(H3c HUH`f.IE1A1U(HfDH8 {@$fLLL$LL$fIA)'E1HfDLLL$LL$@$(ImIA4E1E1H0Lt$~D$Ht0HLL$HYP&LLL$ HD$@D$)D$0eLL$ HII1A/t(HLLI DLLHLL$LL$fLt$t$ HLL(fDCIkA4("A(' H=YB&H*:&H5+:&IfDIm1۾(Lt$A4Hۋt$E1E1A4{fDE1E1A('Rf.{HsHFHHD$0IImuLa(H;#PLHH=LT$ /Ht$LT$ xIA1Y(E1HMwM I_IHI/rHCI߾1ҿALL$>LL$HPH#H5rLL$A1H8oIY(LL$Hf+IfHE1A)'HLfDL|$~D$Ht0HLt$HL&HHD$@D$)D$0 |IHMHA('HIm(E1E1A4(Of.HHHC`LHIE1A)'HfD(fDfDIA/(H1HL3IHIE1E1A/(H{LLLL$LL$HIIA)'H@H=YLT$LT$IA/E1E1ɾ(HDHRHD$Hn#E1H5A/H8I(LL$HL{MKHSIHH+HBHA1ҿH=LT$(Ht$LL$ LT$(>IA)'E1HfDLL$LL$HH#H5:LL$A)H87I'LL$HA4(LLL$LL$(EHT$0HHLAH5%s'HA((HHE1MA((7AAGHH HAGAWHH H)LLL$IAEHC1ҿLL$LLL$LL$HHT$HT$ I\$~DAXGPHcE1I1A/}(HPA1HA((Hf.AWAVAUATUHSHH#H^H|$H$H#HDŽ$H$Hb#H$H*Hw~%H{H Lf0Lu(HE H L5'#IHmH$HDŽ$HDŽ$HDŽ$HDŽ$HDŽ$HDŽ$HDŽ$HEH$HHH&I$H1&H9XV+H1&H,HL=1&L$M*IGH5D&LHH4+HH$H.+H/DHDŽ$IH$H+HEHhIH$H,H#H5B&HR*H$H$H`IH$H0H+(H$H/(H$HDŽ$H/d(H$HDŽ$HmHD$p0(H|$pH5 >&HDŽ$HGHHl1IL$M0H5_8&L9tIGH;/#12IH#HH$I/(H$H;=#HDŽ$H;=D# H;=b# H$Å0H/{(HDŽ$g H$H$HH$H^HE&H5Q/&H9p4H8/&HG8HH=$/&H$H4H5>&_H$H&8H$H/$0H5E>&H|$pHDŽ$O_HH38Hl#HD$ H9E*LmM*L}IEIHmX1LL H$Imj-H$H9I/O0H$HD$ H9G9H$H$H$H/0H$H$HDŽ$9H/0H$L$HDŽ$HDŽ$Ht H/]-H$HDŽ$Ht H/*-H$HDŽ$Ht H/,H55&LHDŽ$'HH$HKH;#H;#+H;#+HH$Ņ LH+N2HDŽ$ HkC&H,&H9XiPH,&HqRHL-,&L$MOH58&L\H$IH$HQH/5H$H$HDŽ$HD$ H9GSHIH$L$HtH/IL$HDŽ$MASH$H/]5H53&1H$HDŽ$ceIH$HTH$H/7H$H;=6#HDŽ$H;=#0H;=#0H$ÅWH/HHDŽ$XH52&H=@&1ZIH$HzHlH$H/`H$E111Hl$pE1E1HDŽ$D$`2D$hHD$@HD$8HD$ HD$(HD$HHD$PHD$HD$0HD$HD$XHD$f.fDIffA.Gz fDHa#HD$`aE11E1D$hE1E1H$HD$@HD$8HD$ HD$(HD$HHD$PHD$HD$0HD$HD$XHD$Ht H/Ht H+H$Ht H/H$Ht H/Ht H)Mt I(T$ht$`H 11H='|Mt I/Mt ImHT$HtHHD$`HH{HL$XHtHHD$HHlHt$HtHHD$HH]HT$0HtHHD$HHNHL$HtHHD$HH?H$Ht H/8Ht$PHtHHD$HH)HT$HHtHHD$HHHL$(HtHHD$HH Ht$ HtHHD$HHHT$8HtHHD$HHHL$@HtHHD$HHMt I.HmH$Ht H/Mt I,$HH[]A\A]A^A_LIH59&LIHVH$H%H]fHH5/H %/HOHb0L /LOLD@HH#SH3H5H81 XZH .&H=h$1y'@sHhxHXHHH8H(fDHHHHHHLHmH fDLxLhILXIHLD$pCLD$pfL(HL$xLD$pHL$xLD$pafHHL$xLD$pHL$xLD$pMHL$xLD$pHL$xLD$p?f.HL$xLD$pHL$xLD$p.fIL5#H51&H|$pTIH$HS,H5,&H9#H@H;#l-IuA#Hq#HH$I/$H$H;=L#HDŽ$H;=#u H;=# H/$HDŽ$-H5-&H|$pSIH$H@/111H&aIH$H@H$H/!L$L;= +&HDŽ$HDŽ$L;%\#FLNHH~DH:9&Hc"&H9XEHJ"&HFHL-6"&L$MDH5,&LRIH$H FH$H/`+H8&H!&HDŽ$H9XHH!&HaJHH!&HGH5a2&HQRHHIH+3-HT8&H]!&H9XnKHD!&H'NHH0!&HvKH51&HHL$QHL$HI NH+?H#HD$ H9AOHLHL$HL$H$HIm>L$MOH+@H51&H$`QIHQH$H/@H$HD$ HDŽ$H9G3SL'H$H$Ht H/BHDŽ$ImD@L$MESH$H/L@I|$H5r6&HDŽ$L$HDŽ$MYuH6&H&H9Xu^H~&H`HHj&HD$H$H_H5/&H-PHH`H$H/%PH5p0&LHL$HDŽ$OHL$HHD$H$fHDŽ$HAH;D$ ~g1H;#YH;#bNt$HL$HL$t$HIoH$HtI@HDŽ$H$HcHLD$(HHL$ITH4&HcLHID1HDŽ$NHL$LD$(HHD$H$nrI(TH)lRH$H;=#H;=#EH;=#EH$Å(pH/RHDŽ$ZH4&Hl&H9X}HS&H}HH ?&H˄H5'&HHL$NHL$HIH)hH4&H&H9X̃H&HHH&HD$H$HH5-&HLD$MLD$HHD$H$J|H$H/kH5-&LLD$HDŽ$UMLD$HHH$H$HD$ H9GMHLD$(LD$HH$H/ kHDŽ$HH$H/rH5-&HLD$HL$HDŽ$LHL$LD$HHH$4H).rHD$ I9@H$LLD$vLD$H$H$H/2rH$HDŽ$HD$HI(vIEH$LaHHqH;&#H;Կ# fH; #eHHL$HL$ǏH)^vwqH$HH$H$ImwH$H/wH$H$HH$H/wHDŽ$H$ImwHDŽ$IݐH91& H(hE111AHLHD$H$HQH$HH$H/ AH$HDŽ$I,$HD$`@HD$`H;#HDŽ$RH|$`H5x'&LgWJHH$HSH5!&H_SHD$H$HVH$H/JEH$H;=0#HDŽ$H;=ҽ#o9H;=#b9H$Å/WH/|GHDŽ$[H5N#&H|$`IHD$H$Ht_HǺLH$HD$H$HRbH/@KH$H;=_#HDŽ$H;=#a>H;=#T>DH$ÅcH/LHDŽ$piHL-&H.&H&D$H9XfH{&HkHHg&HD$H$HPeH5b'&HZHH$IHamH/IPD$LD$(HDŽ$pLD$(HHD$H$jHD$ I9@0pHt$LLD$LD$H$LH$H/OH$HDŽ$HD$HSpH+SH$H;=#H;=m#HH;=#HÅpH$H/THDŽ$rHI-&H&H9XytH&HUtHL&MR{H5%&LLD$(FLD$(HHD$H$zI(^H$H5D!&FH$IHyH/2bH5*&H|$`1LD$(HDŽ$LD$(HHD$H$$tHD$ I9@VIhHVIXHEHI(iH$HHH$Hm"hH$H/hH$HDŽ$HD$HwH+FgH$H;=ܹ#H;=#PH;=#PÅZH$H/8hHDŽ$ZD$\%fT%HH$HsLHnIHƆH$H/AqL;!#HDŽ$L;ø#\L;#\LLD$LD$҅I(pLd$`ӌH$H;#H#HHD$HW*&HHD$XH&HH$H$H/z3L;5R#L;5#L;5#L@> L;%#3H5$&LCHH$HJKHٶ#HD$ H9C:3LsM-3HCIHH$H$H/>H$LgH$I."AH$H$HqMH/#;L$1ɺHHDŽ$LLL$HDŽ$wPLL$HHH$NLHLL$LL$HH$OH$H/`?H$HDŽ$I)HD$0?H5\&H|$HDŽ$VBHH$H1RHD$ H9C7LsM7HCIHH$H$H/DHT$XH$L{H$I.aFH$HOXH$H/CH$H5&HDŽ$H|$HDŽ$HD$0AH$H#\HH$HsYH\$0HH$HX7IH_H&H5&HHD$LD$KH$H$LLD$ ?H$LD$ HHD$H$cH/KH$HDŽ$H/`KHDŽ$I(=KH$H&&HDŽ$HD$H~&&H9XhH&HljHH&H$HiH5"&H@IHIjH$H/OLD$ HDŽ$LD$ HHH$ZlH\$LD$ HH$HXLD$ HHH$lHx#H5q &HLD$ 4LD$ ]H$H$LLD$ Z>LD$ HH$0tI(\H$H/\H$HDŽ$H/ZH$H5 &HDŽ$>H$HH$H݇H/bHDŽ$HH$HH #HHCvHH$H'wH&H5&H vH$H$H$7=HH}H$H/bvH$HDŽ$H/pH$HDŽ$H/jpHt$HDŽ$HHD$ HHrH\$HD$@HD$8HD$ HD$(HD$HHD$PH\$H5#&H{FH5 &H8=IH$HnHM#I9FHNI^H;NIFHHH$H$H/`H&H$HYH$H+`L$MnH$H/6]Ht$H$HDŽ$HHD$`HHYHDŽ$H\$H5f&H|$pD~HL5&L$M}H5&L2:IH$H}H$H/[rHDŽ$IH$HkyH5H&H|$p9IH%yH5+&H$HHD$`nLD$`xI(,H$H58&H$8IHNH$H/H$HDŽ$H/Ht$H|$pHDŽ$IHH5&HLHD$`1LD$`?I((ILHl$pfHfDdfDHx?HfIHTHcHHF0H$HE(H$HE LH$HEH$IH~kHHu-M~1H5E&LHVH$H$IM$H$H$L$L$Hu_@L*{{fDE11E1E1HD$@HD$8HD$ HD$(HD$HHD$PHD$HD$0HD$HD$XHD$D$`UD$h[DH=&H&H5&IfDHE11E1E1HD$@E1HD$8HD$ HD$(HD$HHD$PHD$HD$0HD$HD$XHD$D$`WD$hzf.H=&4MI@E11E1E1HD$@HD$8HD$ HD$(HD$HHD$PHD$HD$0HD$HD$XHD$D$`ZD$hDH$E11E1HD$@E1HD$8HD$ HD$(HD$HHD$PHD$HD$0HD$HD$XHD$D$`_D$hEDHIUUH$E1h+H$ÅH$E111Hl$pE1E1E1D$`SD$hHD$@HD$8HD$ HD$(HD$HHD$PHD$HD$0HD$HD$XHD$d@HI&H&H9X,Hi&H.HL-U&L$M+H5u&L3IH$H-H$H/H$H$HDŽ$HĦ#H9Gm0HIH$L$HtH/"L$HDŽ$H$M0H/!H5 &1H$HDŽ$?H@D$`#fDUfDD$`D$hH$D$`SӼH;/#L4IH$HvH$E111E1E1HD$@Hl$pHD$8HD$ HD$(HD$HHD$PHD$HD$0HD$HD$XHD$D$`PD$h^H5'%H= &1)%IH$Hb1HM7H$H/ H$E111Hl$pE1E1E1HDŽ$D$`bD$hHD$@HD$8HD$ HD$(HD$HHD$PHD$HD$0HD$HD$XHD$zH$HtH/=HDŽ$I/D$`L|HHD$ۺHL$̺D$`H3\HoH HGHEHH$H$H/u!H$H$HH$HmHIH$E111E1E1HD$@Hl$pHD$8HD$ HD$(HD$HHD$PHD$HD$0HD$HD$XHD$D$`uD$h譹H$LHH$H 5H;З#H;~#H;#H辽H$Aƅ7H+{#HDŽ$EU8H5%H$1膹HH$HK=H;C#H;#vH;#iH1H$AƅY;H+5'HDŽ$ElAL;%Ȗ#y5H&H4%H9X5EH%H/NHH%H$HGH5?&HO"H$HH$HHH/.H5%LHDŽ$iHH$HIH#H$HD$ H9G4IHH$H$H/1H$HDŽ$HH$H/&2H$1H$HDŽ$ŷHH$HTH$H/08H$H;=h#HDŽ$H;= #%H;=(#%MÅ|PH$H/<HDŽ$NQHn%LHH5&H$ HH$HPHDŽ$HD$ H9CV=HCH$HA=HSHHH$H$H/CH$H$H=3H$H$Ht H/CH$HDŽ$6QH$H/<H$HDŽ$I,$HD$`v<H&H5%HDŽ$H9XiH%HfHH%H$HPfH5<%HTHH$HeH$H/BHDŽ$8HH$HdH\$XHH$HXH$HcHZ#H53%H胺VH$H$H$HD$PH4cH$H/LH$HDŽ$H/KH$HDŽ$H/KH5%H|$PHDŽ$%HH$HWHDŽ$HD$ H9CKHCH$HKHSHHH$H$H/fKH$H$HZK譽HD$HH$Ht H/!XH|$HH$HDŽ$ZH/2SL$1l$01HD$@E1HHDŽ$HD$8L|$Ll$hLt$xH$H$1]IHZH;"#L;=А#GL;=#wGLAŅqI/MdEXrH5%H|$H$HqH$H$˹IH$HhH$HD$ HDŽ$H9G?fHGH$H*fHWHHH$H$H/(gH$L$H$HeL`IH$Ht H/OeH$HDŽ$H/fHDŽ$H$MzhH/fHDŽ$Mt I,$fH5%H$蜱IHsH;a#AH;#DHL;=+#HLMAąjI/dEdH&H5Q%H9pfH8%H2kHL5$%L$MjH5\%LIH$H"xH$H/bL$HD$ HDŽ$I9FGxHt$`LFIH$Ht H/beHDŽ$M_wH$H/aHDŽ$Ht HmBx1ɺHLV'IHxHL߱H$HzI/zH$I.zH5%HHDŽ$gHH$H?ziIHyIELh/H$H\yH%H5%HȴxH$H$LIH$H\xH$H/}HDŽ$I/|H$H/|HDŽ$L$Ht H+wH%H%HDŽ$H9Xb|H%H>|HH %H$H{H5%HH$HZ{H$H/>{HDŽ$IH$HzI$H$L`赲IHIhE11E1Hl$pHD$@HD$8HD$ HD$(HD$HHD$PHD$HD$0HD$HD$XHD$D$` D$hH=J%H+%H5,%藹I鐯H$E111E1Hl$pHD$@HD$8HD$ HD$(HD$HHD$PHD$HD$0HD$HD$XHD$D$`D$hPH=%#ILuMcHuI921fDL;lHI9uE1IEeA@eHFHe@eIXHeHJ1H9tHH9IM9JtI9rE111E1HD$@Hl$pHD$8HD$ HD$(HD$HHD$PHD$HD$0HD$HD$XHD$D$` D$hH=2%!I醭Ht$XH蠪HH$DH$E11E1HD$@E1Hl$pHD$8HD$ HD$(HD$HHD$PHD$HD$0HD$HD$XHD$D$`D$hH=`%H%H5%譶H\L蝟.HLD$苟LD$||HGH$H̬HWHHH$H$H/CH$H$H$H辑I郬E11E1Hl$pHD$@HD$8HD$ HD$(HD$HHD$PHD$HD$0HD$HD$XHD$D$`D$hE1E1E1Hl$pH$HD$@HD$8HD$ HD$(HD$HHD$PHD$HD$0HD$HD$XHD$D$`D$hCH=%H閵ڝH$E111E1Hl$pHD$@HD$8HD$ HD$(HD$HHD$PHD$HD$0HD$HD$XHD$D$`D$h閭H=%H%H5%,IGH$E111E1Hl$pHD$@HD$8HD$ HD$(HD$HHD$PHD$HD$0HD$HD$XHD$D$`D$hH=.%H%HL$H5%vHL$H遴E1E1E1Hl$pH$HD$@HD$8HD$ HD$(HD$HHD$PHD$HD$0HD$HD$XHD$D$`D$h+LD$ћLD$E11E1Hl$pHD$@HD$8HD$ HD$(HD$HHD$PHD$HD$0HD$HD$XHD$D$`D$h鰫=H=%LIGOH$E111Hl$pD$`2 E1D$hHD$@HD$8HD$ HD$(HD$HHD$PHD$HD$0HD$蘚鬺H$E111Hl$pD$`!E1E1D$hHD$@HD$8HD$ HD$(HD$HHD$PHD$HD$0HD$HD$XHD$QLLD$֙LD$[H=e%HL$HL$HƱH$E1E1HD$@HD$8Hl$pHD$ HD$(HD$HHD$PHD$HD$0HD$HD$XHD$D$`D$hsLLL$HGH$H~HWHHH$H$H/3H$H$H$H7LI5E111E1HD$@Hl$pHD$8HD$ HD$(HD$HHD$PHD$HD$0HD$HD$XHD$D$`D$h]zLѾLAMOHYIHH)LLHLD$pLD$H$I(/L街"HH$E11E1Hl$pHD$@HD$8HD$ HD$(HD$HHD$PHD$HD$0HD$HD$XHD$D$`D$h\HA@=H$HHHHL$H$H$H$H%H$PHL$HHD$H$EZH$Ht H/9+H$HDŽ$H/HDŽ$镱E11E1Hl$pHD$@HD$8HD$ HD$(HD$HHD$PHD$HD$0HD$HD$XHD$D$`D$h8HD$HL$ǯH讕xH$E111E1Hl$pHD$@HD$8HD$ HD$(HD$HHD$PHD$HD$0HD$HD$XHD$D$`D$hjHl$pE111D$`E1E1D$hHD$@HD$8HD$ HD$(HD$HHD$PHD$HD$0HD$HD$XHD$苔PHr#11E1H$Hl$pHD$@HD$8HD$ HD$(HD$HHD$PHD$HD$0HD$D$`D$hHD$HH=%H%H5%ުIѓ鶴HGH$HHWHHH$H$H/H$H$HyL tE11E1Hl$pHD$@HD$8HD$ HD$(HD$HHD$PHD$HD$0HD$HD$XHD$D$` D$hTHp#H$1E1HD$@Hl$pHD$8HD$ HD$(HD$HHD$PHD$HD$0HD$D$`D$hHD$騢H=%lI=H<釭2u ffA.F'!HVp#HHo#11E1H$Hl$pHD$@HD$8HD$ HD$(HD$HHD$PHD$HD$0HD$D$`D$hHD$鿡Hg]LP钹xHLo#1E1HD$@HD$8Hl$pHD$ HD$(HD$HHD$PHD$HD$0HD$D$`D$hHD$5D$`D$h>譐pHn#Hl$p11H$D$` E1D$hHD$@HD$8HD$ HD$(HD$HHD$PHD$HD$0HD$HD$rLHL$HL$QHn#H$1E1HD$@Hl$pHD$8HD$ HD$(HD$HHD$PHD$HD$0HD$D$`D$hHD$ןH= %HQ%LD$H5M%hLD$H Hdm#H$1E1HD$@Hl$pHD$8HD$ HD$(HD$HHD$PHD$HD$0D$`D$hHD$0H=y%LD$LD$HqE11E1Hl$pHD$@HD$8HD$ HD$(HD$HHD$PHD$HD$0HD$HD$XD$`D$h鴞E11E1Hl$pHD$@HD$8HD$ HD$(HD$HHD$PHD$HD$0HD$D$`G D$hAHD$ɍLD$飯躍H5%HxQLd$`Hl$pE11H$D$`1E1D$hHD$@HD$8HD$ HD$(HD$HHD$PHD$HD$0HD$HD$XHD$YLd$`E11E1H$Hl$pHD$@HD$8HD$ HD$(HD$HHD$PHD$HD$0HD$HD$XHD$D$`D$hǜH$HHHHL$H$H$H$H %H$P HL$HHD$H$E1E1HD$@Hl$pHD$8HD$ HD$(HD$HHD$PHD$HD$0HD$HD$XD$`9D$h E11E1Hl$pHD$@HD$8HD$ HD$(HD$HHD$PHD$HD$0HD$D$`U D$hxL 鶴LD$LD$錴LD$LD$ZH$11E1Hl$pD$` D$hHD$@HD$8HD$ HD$(HD$HHD$PHD$ۚ8H$E111E1E1HD$@Hl$pHD$8HD$ HD$(HD$HHD$PHD$HD$0HD$HD$XHD$D$`^D$hAH߉dH$E11E1HD$@Hl$pHD$8HD$ HD$(HD$HHD$PHD$HD$0D$`b D$h鸙cULd$`E11E1HD$@Hl$pHD$8HD$ HD$(HD$HHD$PHD$HD$0HD$HD$XD$`D$hKE11E1LL$HD$@Hl$pHD$8HD$ HD$(HD$HHD$PHD$HD$0D$`d D$hܘi@Ld$`Hl$pE11D$`1E1D$hHD$@HD$8HD$ HD$(HD$HHD$PHD$HD$0HD$HD$XHD$(H=q%H%H5%辞HD$釡诇襇L蘇eH$11E1Hl$pD$` D$hHD$@HD$8HD$ HD$(HD$HHD$PHD$HD$0HD$iH$E111E1Hl$pHD$@HD$8HD$ HD$(HD$HHD$PHD$HD$0HD$HD$XD$`#D$hHd#H$1E1HD$@Hl$pHD$8HD$ HD$(HD$HHD$PHD$HD$0HD$D$` D$hHD$_ pHD$ LD$ H$E11E1HD$@Hl$pHD$8HD$ HD$(HD$HHD$PHD$HD$0D$`q D$hϕHt$LLD$蝏LD$H$L釩H=%lHD$=H$E11E1HD$@Hl$pHD$8HD$ HD$(HD$HHD$PHD$HD$0HD$HD$XHD$D$`%D$hH5l%L̎H$芄L}鱲HD$Hl$pE1HH6H$E11E1HD$@Hl$pHD$8HD$ HD$(HD$HHD$PHD$HD$0HD$D$`!D$h4H5%H=%1HD$H$H'H!H$H/Ld$`Hl$pE11HDŽ$E1D$`D$hHD$@HD$8HD$ HD$(HD$HHD$PHD$HD$0HD$HD$XHD$wH5*%H|$HH$H)7H-`#H9CLsMvHCIHH$H$H/H$LL=uH$I.H$H|*H$H/H$E1E11H$1HDŽ$}HH$H6H$H/jH$H5%HDŽ$HDŽ$HT$XHGH|$HHO*ЅH$E111Hl$pD$`N#E1D$hHD$@HD$8HD$ HD$(HD$HHD$PHD$0HD$锑H$E111Hl$pD$`!E1D$hHD$@HD$8HD$ HD$(HD$HHD$PHD$HD$0HD$H5%H=%1HH$H2HH$H/H$E111Hl$pD$`!E1HDŽ$D$hHD$@HD$8HD$ HD$(HD$HHD$PHD$HD$0HD$K鈮HLD$LD$Ld$`E11E1HD$@Hl$pHD$8HD$ HD$(HD$HHD$PHD$HD$0HD$HD$XD$`D$hǏE11E1Hl$pHD$@HD$8HD$ HD$(HD$HHD$PHD$HD$0D$` D$h]~H$E11E1HD$@Hl$pHD$8HD$ HD$(HD$HHD$PHD$HD$0HD$HD$XD$`(D$h鱎Hl$pHt$E1HHH$H-HbH$H/+H$E111Hl$pD$`7!E1HDŽ$D$hHD$@HD$8HD$ HD$(HD$HHD$PHD$HD$0HD$駆H$E111E1Hl$pHD$@HD$8HD$ HD$(HD$HHD$PHD$HD$0HD$HD$XHD$D$`.D$hH$1E1HD$@HD$8Hl$pHD$ HD$(HD$HHD$PHD$HD$0HD$HD$XHD$D$`ID$h鎅9uH55%H=>%1OHD$H$HNH|$oH$H/ Ld$`Hl$pE11H$1E1HDŽ$D$`D$hHD$@HD$8HD$ HD$(HD$HHD$PHD$HD$0HD$HD$XHD$靄HEt魘Hl$pE111D$`YE1D$hHD$@HD$8HD$ HD$(HD$HHD$PHD$HD$0HD$HD$XHD$ sHsї11E1Hl$pHD$@HD$8HD$ HD$(HD$HHD$PD$` D$h雃H=%_HD$۔H=ι%H߫%H5%Hĺss龗Ld$`1E1Hl$pHD$@HD$8HD$ HD$(HD$HHD$PHD$HD$0HD$HD$XD$`2D$h|rrr_Leri[rrE1Hl$pHD$@HD$8HD$ HD$(HD$HHD$PHD$HD$0HD$HD$XD$`TD$hMHq;q=1E1HD$@Hl$pHD$8HD$ HD$(HD$HHD$PHD$HD$0HD$D$` D$h龁LHu{H$E11E1Hl$pHD$@HD$8HD$ HD$(HD$HHD$PHD$HD$0HD$D$`T!D$h3Ld$`11E1HD$@Hl$pHD$8HD$ HD$(HD$HHD$PHD$HD$0HD$HD$XHD$D$`/D$h錀HLD$/pLD$黍HL$LD$pHL$LD$PIEL$铎LD$oLD$麍H$1E1HD$@HD$8Hl$pHD$ HD$(HD$HHD$PHD$HD$0HD$D$` D$hE11E1Hl$pHD$@HD$8HD$ HD$(HD$HHD$PHD$HD$0HD$D$`V!D$hFE11E1Hl$pHD$@HD$8HD$ HD$(HD$HHD$PHD$HD$0HD$D$`g!D$h~LwMHGIHH$H$H/H$H$L`H$I.LnrE11E1Hl$pHD$@HD$8HD$ HD$(HD$HHD$PHD$HD$0HD$D$`Y!D$h~IhHÏIXHEHI(H$HH`H$HmHTm雏H=%H %H5 %5HLd$`I1E1HD$@Hl$pHD$8HD$ HD$(HD$HHD$PHD$HD$0HD$HD$XD$`AD$h}Ld$`Hl$pE11H$D$`D1E1D$hHD$@HD$8HD$ HD$(HD$HHD$PHD$HD$0HD$HD$XHD$h|H$E11E1HD$@Hl$pHD$8HD$ HD$(HD$HHD$PD$` D$h|H=Q%H鋕H$11E1HD$@Hl$pHD$8HD$ HD$(HD$HHD$PD$` D$h{HL$;kHL$D铸H k镉LkH5%H=%1)HH$H3HMH$H/pLd$`Hl$pE11H$1E1HDŽ$D$`SD$hHD$@HD$8HD$ HD$(HD$HHD$PHD$HD$0HD$HD$XHD${zH=İ%?HȱffA.F HRH#HH$E111Hl$pD$`#D$hzH$E111Hl$pD$`#E1D$hyLiHD$iLD$髎LsiniiE_iLRiH$1E1HD$@HD$8Hl$pHD$ HD$(HD$HHD$PD$` D$h@yH$1E1HD$@HD$8Hl$pHD$ HD$(HD$HHD$PD$` D$hxH=,%I颋H=%Hi%H5j%eI逋XhfNh'Dh:h׳0h鐴HHD$H顴E> hgLd$`1E1Hl$pHD$@HD$8HD$ HD$(HD$HHD$PHD$HD$0HD$HD$XD$`mD$hwg駖ygH;D#LLgIH$Hu0H$E111Hl$pD$`#D$hmwH$11E1HD$@Hl$pHD$8HD$ HD$(HD$HHD$PHD$HD$0HD$HD$XD$`kD$hvHfH=&%HbH=%H%H5%_}H@H$E111Hl$pD$`l!E1D$hHD$@HD$8HD$ HD$(HD$HHD$PHD$HD$0HD$*vH$E11E1HD$@Hl$pHD$8HD$ HD$(HD$HHD$PHD$HD$0HD$D$`!D$huH50%H=i%1zHH$H 'HH$H/9H$E111Hl$pD$`{!E1HDŽ$D$hHD$@HD$8HD$ HD$(HD$HHD$PHD$HD$0HD$tE11E1Hl$pHD$@HD$8HD$ HD$(HD$HHD$PHD$HD$0HD$D$`!D$htH$E111Hl$pD$`n#D$hGtH$E111Hl$pD$`|#D$htc@Ld$`I1E1HD$@Hl$pHD$8HD$ HD$(HD$HHD$PHD$HD$0HD$HD$XD$`{D$hs>c錏4cdH$E11E1HD$@Hl$pHD$8HD$ HD$(HD$HHD$PHD$HD$0HD$D$`j!D$hsLb,bbb1Ld$`11E1HD$@Hl$pHD$8HD$ HD$(HD$HHD$PHD$HD$0HD$HD$XHD$D$`jD$hPrLd$`1E1Hl$pHD$@HD$8HD$ HD$(HD$HHD$PHD$HD$0HD$HD$XD$`gD$hqLd$`11E1H$Hl$pHD$@HD$8HD$ HD$(HD$HHD$PHD$HD$0HD$HD$XHD$D$`eD$hAqH`]1E1HD$@Hl$pHD$8HD$ HD$(HD$HHD$PD$` D$hpH$1E1HD$@HD$8Hl$pHD$ HD$(HD$HHD$PHD$HD$0HD$HD$XHD$D$`nD$hUp`ĬH=%H%LD$H5%vLD$HD$&|H$1E1HD$@HD$8Hl$pHD$ HD$(HD$HHD$PHD$HD$0HD$HD$XHD$D$`fD$hoH$E11E1HD$@Hl$pHD$8HD$ HD$(HD$HHD$PHD$HD$0HD$HD$XHD$D$`dD$hoH$11E1HD$@Hl$pHD$8HD$ HD$(HD$HHD$PHD$HD$0HD$HD$XD$`iD$hnH=̤%LD$BLD$HD$lzLd$`Hl$pE11H$D$`!1E1D$hHD$@HD$8HD$ HD$(HD$HHD$PHD$HD$0HD$m]雍]锉H$E111Hl$pD$` E1D$hHD$@HD$8HD$ HD$(HD$HHD$PkmH$E11E1HD$@Hl$pHD$8HD$ HD$(HD$HHD$PD$` D$h mLd$`E111H$E1HD$@HD$8Hl$pHD$ HD$(HD$HHD$PHD$HD$0HD$HD$XD$`D$hlLd$`E11E1HD$@Hl$pHD$8HD$ HD$(HD$HHD$HD$0HD$D$`!D$h/lLd$`E11E1HD$@Hl$pHD$8HD$ HD$(HD$HHD$PHD$HD$0HD$HD$XD$`D$hk;[էH$1E1HD$@HD$8Hl$pHD$ HD$(HD$HHD$PHD$HD$0HD$HD$XHD$D$`}D$hjIXHDxIHHHI(H$HHHL$!MHL$H$H+IxHLD$JZLD$xH$E1HD$@HD$8Hl$pHD$ HD$(HD$HHD$PHD$HD$0HD$HD$XHD$D$`D$hjLOMvHGIHH$H$H/<H$H$LLD$LL$LLL$LD$HI)\vLHL$LD$:YHL$LD$;vLd$`E111E1Hl$pHD$@HD$8HD$ HD$(HD$HD$0HD$D$`!D$hiL|$Ll$hI1Hl$E1H$H\$ Hl$p1Ld$(Ld$`HD$HD$0D$`!D$hh1E1HD$@Hl$pHD$8HD$ HD$(HD$HHD$PHD$HD$0HD$HD$XD$`D$h\hH$E11E1HD$@Hl$pHD$8HD$ HD$(HD$HHD$PHD$HD$0HD$D$`>#D$hgH|$ZH$M1E1HD$@Hl$pHD$8HD$ HD$(HD$HHD$PHD$HD$0HD$HD$XHD$D$`D$h'gH$E111Hl$pD$`#D$hfH$11E1Hl$pD$`#D$hfH$11E1Hl$pD$`#D$hfH$E111Hl$pD$`#D$hfH$E11E1HD$@Hl$pHD$8HD$ HD$(HD$HHD$PD$` D$h#fH5Ė%H=ݤ%1HH$HHH$H/Ld$`Hl$pE11H$1E1HDŽ$D$`D$hHD$@HD$8HD$ HD$(HD$HHD$PHD$HD$0HD$HD$XHD$@eLTaTH$E111Hl$pD$`#E1D$hdLd$`Hl$p11H$D$`E1D$hHD$@HD$8HD$ HD$(HD$HHD$PHD$HD$0HD$HD$XHD$ldLd$`11E1H$Hl$pHD$@HD$8HD$ HD$(HD$HHD$PHD$HD$0HD$HD$XHD$D$`D$hcLd$`E11E1H$Hl$pHD$@HD$8HD$ HD$(HD$HHD$PHD$HD$0HD$HD$XHD$D$`D$hIcLd$`Hl$pE11H$D$`~1E1D$hHD$@HD$8HD$ HD$(HD$HHD$PHD$HD$0HD$HD$XHD$b`R VRH$E111Hl$pD$`#D$hxbH$E111Hl$pD$`#D$hObH=%I鹁H=%HU%H5V%hI闁H$M1E1Hl$pD$`D$hHD$@HD$8HD$ HD$(HD$HHD$PHD$HD$0HD$HD$XHD$aLd$`E111H$E1HD$@HD$8Hl$pHD$ HD$(HD$HHD$HD$0HD$D$`!D$haLd$`E11E1HD$@Hl$pHD$8HD$ HD$(HD$HHD$PHD$HD$0HD$D$`!D$h`Ld$`E11E1H$Hl$pHD$@HD$8HD$ HD$(HD$HHD$PHD$HD$0HD$D$`!D$h`E11E1Hl$pHD$@HD$8HD$ HD$(HD$HHD$PD$` D$h_Ld$`E11E1H$Hl$pHD$@HD$8HD$ HD$(HD$HHD$PHD$HD$0HD$D$`!D$hC_Ld$`E11E1H$Hl$pHD$@HD$8HD$ HD$(HD$HHD$PHD$HD$0HD$D$`!D$h^H= %H ZN6PNLCN~L6N馛,NR"NםH$E11E1HD$@Hl$pHD$8HD$ HD$(HD$HHD$PHD$HD$0HD$D$`!D$h]LM~H5~%H=%1谶HD$H3H\$HHHD$HHx H$E111Hl$pD$`E1D$hHD$@HD$8HD$ HD$(HD$HHD$PHD$HD$0HD$HD$XHD$]E11E1Hl$pHD$@HD$8HD$ HD$(HD$HHD$PD$` D$h\H=%H%H5%OcHBL駚L5LhHT$xH|$HE11A1dIHHɍ%H|$`HDJ\I/#LKLUIKH$E11E1HD$@Hl$pHD$8HD$ HD$(HD$HHD$PHD$HD$0HD$D$`0#D$h[H$E11E1HD$@Hl$pHD$8HD$ HD$(HD$HHD$PHD$HD$0HD$D$`A#D$h[JCJ`JΘLJeJ锚MLl$(L|$1Hl$Ll$hE1Ld$`Hl$pH\$ 1H$D$`""D$hHD$HD$0ZL|$Ll$(I1Hl$Ll$hE1Ld$`H\$ 1H$Hl$pHD$HD$0D$` "D$h(ZH=q%Hb%H5c%`I*L|$Ll$hE11Hl$H$H\$ Hl$pHLd$(Ld$`HD$HD$0D$`!D$hYH$E11E1HD$@Hl$pHD$8HD$ HD$(HD$HHD$PHD$HD$0HD$D$`3!D$h1YL|$Ll$hE11Hl$E1Hl$pH\$ 1Ld$(Ld$`HD$HD$0D$`"D$hXHD$0HD$8ME1L|$Ld$`Hl$Ll$(H$Ll$hHl$pH\$ 1LD$8E1HD$@HD$D$` #D$huXHD$0HD$8ME1L|$Ld$`Hl$Ll$(H$Ll$hHl$pH\$ 1LD$8E1HD$@HD$D$` #D$h XGHD$8MLl$(1L|$Ll$hHl$E1H\$ Ld$`1LD$8H$E1HD$@Hl$pD$`#D$hHD$HD$0WH=G遝HD$0HD$8ME1L|$Ld$`Hl$Ll$(H$Ll$hHl$pH\$ 1LD$8E1HD$@HD$D$`#D$h WHHH L|$HDHPL|$E1Hk$#H5~Hl$Ll$(Ll$hH81H\$ 1LLD$1HD$8Ld$`H$D$`#LD$8Hl$pE1HD$@D$hHD$HD$0zV%FL$\MLl$(L|$1Hl$Ll$hE1Ld$`Hl$pH\$ 1H$D$`"D$hHD$HD$0VL|$Ll$(E11Hl$Ll$hE1Ld$`H\$ HD$Hl$pHD$0D$`5"D$hUH=%yIŔL|$Ll$(Hl$Ll$hHH5HHH MHEH"#1E1H5zH81WKLd$ E11Ld$`H$D$`"Hl$pD$hHD$HD$0UH;##BJH$HH$H/hH$HDŽ$HGHIHH$H$HlH$ӾHH$H/HDŽ$aLd$ Hl$pE11Ld$`H$1E1D$`"D$hHD$HD$0SCHCMHG!#H5{i1E1H81ILd$ E11Ld$`H$D$`"Hl$pD$hHD$HD$0S,C!MLl$(L|$1Hl$Ll$h1E1Ld$ H$Ld$`Hl$pD$`"D$hHD$HD$0SML|$Hl$Ll$(Ll$hH$H/LD$HDŽ$LD$Ld$ Hl$p11Ld$`H$E1D$`"D$hHD$HD$0RL|$Ll$(I1Hl$Ll$hhBL|$Ll$(E11Hl$Ll$hE1Ld$ Hl$pLd$`D$hHD$HD$0D$`")RHWH\HGL8H@H$ӔHH HLD$xH H5LwHEH!#1E1H81GLd$ 1Ld$`H$Hl$pD$`"D$hLD$xHD$HD$0eQLD$ ALD$dH$E111Hl$pD$`#D$h(QMLl$hL|$1Hl$E1H$H\$ Hl$p1Ld$(Ld$`D$hD$`!HD$HD$0PL|$Ll$hE11Hl$E1Hl$pLd$(Ld$`H\$ HD$HD$0D$`!D$hPHD$PL|$Ld$(Ll$hLd$`Hl$H\$ l$0HHD$HD$0l?ٖ?顖H|$1E1?Hl$pE11H$D$`D$hHD$@HD$8HD$ HD$(HD$HHD$PHD$HD$0HD$HD$XHD$OH$E111E1Hl$pHD$@HD$8HD$ HD$(HD$HHD$PHD$HD$0HD$HD$XD$`D$h OL$IHLHL$>HL$ H$Hl$p11D$`#D$hNH$11Hl$pD$`#D$hNLD$LL$:>LL$LD$H$E11E1HD$@Hl$pHD$8HD$ HD$(HD$HHD$PHD$HD$0HD$D$`w!D$hN=Ld$`E11E1H$Hl$pHD$@HD$8HD$ HD$(HD$HHD$PHD$HD$0HD$HD$XHD$D$`D$hdML|$Ll$(I1Hl$Ll$hE1Ld$`H\$ 1H$Hl$pHD$HD$0D$`"D$hMH;#L=IH$HkH$E111Hl$pD$`#D$hLHj#HD$bE1E1HD$@Hl$pHD$8HD$ HD$(HD$HHD$PHD$HD$0HD$HD$XD$`BD$hDL;鹀L<y}LHH9}Hu1H;56#ͩtLHD$0HD$8ME1L|$Ld$`Hl$Ll$(H$Ll$hHl$pH\$ 1LD$8E1HD$@HD$D$`"D$hhKHD$0HD$8ME1L|$Ld$`Hl$Ll$(H$Ll$hHl$pH\$ 1LD$8E1HD$@HD$D$`"D$hKL: :HD$8MLl$(1L|$Ll$hHl$E1LD$8Hl$pE1Ld$ H$Ld$`HL$0HD$@HD$D$`"D$hJH):I:Ht$8H=DH$%HD$0HD$8M1L|$Ll$(E1Hl$Ll$hLD$8H$E1Ld$ Hl$pLd$`HD$@HD$D$`"D$hI99HD$8MLl$(1L|$Ll$hHl$E1LD$8Hl$pE1Ld$ H$Ld$`HL$0HD$@HD$D$`"D$hlIH9[ 9/HmH$AVfɉ *@AY H9DI>IF@A\L$HcAD\$ \D$L$(W-q ( f\$ L$*YYT$X/KH([]A\A]A^fv *Y c\! ZH[]\A\A]A^(@f.H~3ATL$UHSHDHH !CI9u[]A\DH~KATL$UHSHDH}HU g\f(8fWgCI9u[]A\ÐDf.H~kATL$UHSHDH}HUf f *YRZ\f(ZWְCI9u[]A\Df.AWAVIAUL-ATL%UHSHH(I>IFL$Hc\$\$L$%ԮD$Yf(Y}$YT$\$L$Xf/wAI>AVfII HLH!H*AYLtfW fI94CH(f([]A\A]A^A_I>IF57e\f(b I>Y $AV= e\f(5 $fWef(XYf/vX ƭAffW ieY@H~3ATL$UHSHDHHlCI9u[]A\DAVIAUL-"ATL%UH-SHI>IFTHcDT$ \D$%fZL$Y f(YfT$ *Y YL$XZf/wCI>AVf H*AYDD$t WD$A98D$H[]A\A]A^DI>IFf5 *Y\(I>YT$AVfϫ *Y \ST$(W C(YX/oXT$@WT$.fDH~3ATL$UHSHDHHCI9u[]A\Df.`bRff.4SHH0=XYH,HaT$ff.EфEH0[fDf/Ӹr@f.Hl>HH?D$\$PL$$f/vf(fYHXf/wHfHHH?$P=\f()=\$D$f( L$^f(JHH,f/=rf.SHH \=f(D$vD$H;SH;$S%O=\$$D$ L=^L$f(E M===f(f(fTf.v7H,f%<fUH*f(f(fT\f(fVf/^=<f/Lf(L$$^XL$$f(\<l$Y^Yf(\c<^f/H H,[ff(f(H8H\\H?T$L$D$(f(\$^l$ 4$P4$\$L$T$f/r3l$ fd$(YYf.QwHXH8f(@f(\ ;\fYYf.Qw*\H8f(d$$d$$f(T$ $T$ $1HATIIUHI SHLHI LHL IIL III LH I ĸH9wfDH;SD!H9r[]A\DH;SL!H9sH;SL!H9rf.Df.AWAVAUATIUSHHttIIHHH?H9wqIFAEJL$ Dl$ AME9v$1AAA9sI>AVAME9wI IHL[]A\A]A^A_@IFHEuTLbIHHI9v+H1HIIH9sfDI>AVIHI9wHL$DI>IFL!H9rL$pfDI>IFD!D9wL$PfDЉI>@I0fDAWAVAUATUSHteIẢAH?IFEucJL$ Dd$ IA9v%1AA9sI>AVIA9wH DH[]A\A]A^A_fDI>IFD!9rA\ff.AWAVAUATUSHH\$PfLAIE f AAEDrE T$ H?AUT$ E3EAfA9vY™AAf9r$FD3Ex}3AfA9v$uI}AUE3AfA9wA H[]A\A]A^A_Ð+EDHDMD!fA9s"EuI}AUED!fA9rHD[]A\A]A^A_fEuCH?AUEH[]DA\A]A^A_fD+Ex}+mDf.AWAVAUATUSHH\$PLAIE AAEDzE"T$ H?AUT$ E DA8vVE™AA@8r? ExD} A8v#uI}AUDE A8wfA4H[]A\A]A^A_f.+EDHDMD!A8s!EuI}AUED!A8rHD[]A\A]A^A_@EuCH?AUEH[]DA\A]A^A_fD+Ex}+mDf.USHHl$ tAtmA)EH[]@HLH?PEfAWAVAUATUSHHu]H~DHHLH4$$HHLDHH9uHHH9tI4H[]A\A]A^A_DLIHIH9EH~IDbH$MЉD$ I?AWID9s(D$ 1AA9sfDI?AWIA9wH HHHKH9$uP@HEH0ILbIH$DI?AWIIIL9s%L1III9sI?AWIII9wLHHHCH;$uDHM$I?HAWHHCL9uf.HM$I?HAWHHCL9u`@III LHI LHI LHI LHI LH I HM4I?AWL!I9rHHHCL9u@III LHI LHI LHI LHI HM4f.I?AWD!D9wHHHCI9ux1mDAWAVAUATUSHH~uHAHHʉ4$fn $LHHfpLfHH9uHHH9t(HxHA4H9~HAtH9~AtH[]A\A]A^A_ÐLAՉIEH~IADbH$MDl$ I?AWIA9v(D$ 1AA9sfDI?AWIA9wH HKH;$uH[]A\A]A^A_@HGM$I?HAWCL9uH[]A\A]A^A_@III LHI LHI LHI LHA HM4I?AWD!A9rHCL9uH[]A\A]A^A_1uf.AWAVAUATUSHfHHAHf4$HLHHfn$LfafpHH9uHHH9tcHxHfA4AH9}QHxfAtH9~BHxfAtH9~3HxfAtH9~$HxfAtH9~HfAt H9}fAt H[]A\A]A^A_fDALIfE H~DrIIE1H$A1D$ EI?AWAfA9vAD$ Af9s2EtE1fA9vI?AWȉfA9wAHDfKH;$'EE1fHI,IHDfCH9I?AWATfHSH9u@AHHH HHH HHH HH HM$I11t@1!fA9sI?AW!fA9rDHfSL9uH[]A\A]A^A_1DuH@HL@AWIAVAAUATUSLHE7HI, DjE1ɉD$ 1f.EI?AWAD@A8vk+D$ EݙAA8r3QI?AWD@A8vDA@A8v EtDA@A8wfHDKH9YH[]A\A]A^A_fH~I, 11HA KH9tuI?HAWASH9uAHHH HHH HH HlM, 11$I?AW!A8sH!A8st!A8r@DHSI9uH[]A\A]A^A_fDHSI9uf.AL@ADH~StWAT1I1UI, SL˅uI<$AT$#HH9t#HH9u[]A\D@HLqAWIAVAUATM`UHSH(H|$LD$M~lIM1 Q*L$A\LHI9tBADH|$LLL$^II)HDMH([]A\A]A^A_H~HD$L|H([]A\A]A^A_HH while calling a Python objectNULL 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.%.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 does not export expected C variable %.200sC variable %.200s.%.200s has wrong signature (expected %.500s, got %.500s)%.200s does not export expected C function %.200sC function %.200s.%.200s has wrong signature (expected %.500s, got %.500s)Interpreter change detected - this module can only be loaded into one interpreter per process.%s() got multiple values for keyword argument '%U'%.200s() keywords must be strings%s() got an unexpected keyword argument '%U'calling %R should have returned an instance of BaseException, not %Rraise: exception class must be a subclass of BaseException'%.200s' object is unsliceableCannot convert %.200s to %.200stoo many values to unpack (expected %zd)%.200s() takes %.8s %zd positional argument%.1s (%zd given)numpy.random.mtrand.RandomState.waldnumpy.random.mtrand.RandomState.rayleighnumpy.random.mtrand.RandomState.lognormalnumpy.random.mtrand.RandomState.logisticnumpy.random.mtrand.RandomState.gumbelnumpy.random.mtrand.RandomState.laplacenumpy.random.mtrand.RandomState.powernumpy.random.mtrand.RandomState.weibullnumpy.random.mtrand.RandomState.paretonumpy.random.mtrand.RandomState.vonmisesnumpy.random.mtrand.RandomState.standard_tnumpy.random.mtrand.RandomState.standard_cauchynumpy.random.mtrand.RandomState.noncentral_chisquarenumpy.random.mtrand.RandomState.chisquarenumpy.random.mtrand.RandomState.noncentral_fnumpy.random.mtrand.RandomState.fnumpy.random.mtrand.RandomState.gammanumpy.random.mtrand.RandomState.standard_gammanumpy.random.mtrand.RandomState.normalnumpy.random.mtrand.RandomState.standard_normalnumpy.random.mtrand.RandomState.standard_exponentialnumpy.random.mtrand.RandomState.exponentialnumpy.random.mtrand.RandomState.betanumpy.random.mtrand.RandomState.randomnumpy.random.mtrand.RandomState.random_samplenumpy.random.mtrand.RandomState.__reduce__numpy.random.mtrand.RandomState.__getstate__numpy.random.mtrand.RandomState.__str__'%.200s' object is not subscriptablecannot fit '%.200s' into an index-sized integernumpy.random.mtrand.RandomState.randnnumpy.random.mtrand.RandomState.randnumpy.random.mtrand.RandomState.__setstate__numpy.random.mtrand.RandomState.__repr__hasattr(): attribute name must be stringnumpy.random.mtrand.RandomState.__init__numpy.random.mtrand.int64_to_longnumpy.random.mtrand.RandomState.logseriesnumpy.random.mtrand.RandomState.geometricnumpy.random.mtrand.RandomState.zipfnumpy.random.mtrand.RandomState.poissonnumpy.random.mtrand.RandomState.negative_binomialnumpy.random.mtrand.RandomState.get_stateModule 'mtrand' has already been imported. Re-initialisation is not supported.compiletime version %s of module '%.100s' does not match runtime version %sinvalid vtable found for imported typenumpy.random._bounded_integersPyObject *(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 objectmodule compiled against ABI version 0x%x but this version of numpy is 0x%xmodule compiled against API version 0x%x but this version of numpy is 0x%xFATAL: module compiled as unknown endianFATAL: module compiled as little endian, but detected different endianness at runtimenumpy.random.mtrand.RandomState.seednumpy.random.mtrand.RandomState.tomaxintnumpy.random.mtrand.RandomState.uniformnumpy.random.mtrand.RandomState.randintnumpy.random.mtrand.RandomState.permutationneed more than %zd value%.1s to unpacknumpy.random.mtrand.RandomState.multivariate_normalnumpy.random.mtrand.RandomState.dirichletnumpy.random.mtrand.RandomState.triangularnumpy.random.mtrand.RandomState.binomialnumpy.random.mtrand.RandomState.bytesnumpy.random.mtrand.RandomState.multinomialnumpy.random.mtrand.RandomState.set_statenumpy.random.mtrand.RandomState.shufflenumpy.random.mtrand.RandomState.hypergeometricnumpy.random.mtrand.RandomState.random_integersnumpy.random.mtrand.RandomState.choice'%.200s' object does not support slice %.10snumpy.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 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_locationsMissing type objectname '%U' is not definedcannot import name %Snumpy/random/mtrand.c%s (%s:%d)at leastat mostwaldmtrand.pyxrayleighlognormallogisticgumbellaplacepowerweibullparetovonmisesstandard_tstandard_cauchynoncentral_chisquarenoncentral_fstandard_gammastandard_normalstandard_exponentialbetarandomrandom_samplerandn__init__BitGeneratorlogserieszipfpoissonnegative_binomialget_state%d.%d%sbuiltinscython_runtime__builtins__4294967296complexnumpydtypeflatiterbroadcastndarraygenericnumberunsignedintegerinexactcomplexfloatingflexiblecharacterufuncnumpy.random.bit_generatorSeedSequenceSeedlessSequencenumpy.random._commondoubleLEGACY_POISSON_LAM_MAXuint64_tMAXSIZE_rand_uint64_rand_uint32_rand_uint16_rand_uint8_rand_bool_rand_int64_rand_int32_rand_int16_rand_int8check_constraintcheck_array_constraintdouble (double *, npy_intp)kahan_sumdouble_fillvalidate_output_shapecontdisccont_broadcast_3discrete_broadcast_iiinumpy.core._multiarray_umath_ARRAY_API_ARRAY_API not found_ARRAY_API is NULL pointer__init__.pxdnumpy.import_arrayinit numpy.random.mtrandnumpy.random.mtrand.samplenumpy.random.mtrand.ranfseedtomaxintuniformrandintmultivariate_normaldirichlettriangularnumpy.PyArray_MultiIterNew2numpy.PyArray_MultiIterNew3multinomialhypergeometricrandom_integersassignmentdeletionchoice_bit_generator__getstate____setstate____reduce__set_statebytesshufflepermutation%%0%x%@%:::::P< <;H<0<>>>>>xzyyyT4,L<8 8/ JOدЯܰİܱӱtP'brfEMGGxGl؁́_` bYPd2G$%d $l$,,8-- -n.b.J...@008x0 88fF@FF~FF6H%H HNHXH4SRRlStSW[/[[[[,ne\This function is deprecated. Please call randint({low}, {high} + 1) insteadx must be an integer or at least 1-dimensionalprobabilities are not non-negativenumpy.core.umath failed to importmean and cov must have same lengthget_state and legacy can only be used with the MT19937 BitGenerator. To silence this warning, set `legacy` to False.covariance is not positive-semidefinite.cov must be 2 dimensional and squarecheck_valid must equal 'warn', 'raise', or 'ignore'can only re-seed a MT19937 BitGeneratora must be 1-dimensional or an integerThis function is deprecated. Please call randint(1, {low} + 1) insteadRandomState.triangular (line 3154)RandomState.standard_t (line 2083)RandomState.standard_normal (line 1335)RandomState.standard_exponential (line 545)RandomState.standard_cauchy (line 2010)RandomState.random_sample (line 373)RandomState.random_integers (line 1239)RandomState.permutation (line 4499)RandomState.noncentral_f (line 1763)RandomState.noncentral_chisquare (line 1923)RandomState.negative_binomial (line 3413)RandomState.multinomial (line 4122)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 ValueErrorNegative dimensions are not allowedInvalid bit generator. The bit generator must be instantized.Fewer non-zero entries in p than sizeCannot 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 continuous 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 ``zipf`` method of a ``default_rng()`` 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. Generator.zipf: which should be used for new code. Notes ----- The probability density for the Zipf distribution is .. math:: p(x) = \frac{x^{-a}}{\zeta(a)}, 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 = 2. # parameter >>> s = np.random.zipf(a, 1000) Display the histogram of the samples, along with the probability density function: >>> import matplotlib.pyplot as plt >>> from scipy import special # doctest: +SKIP Truncate s values at 50 so plot is interesting: >>> count, bins, ignored = plt.hist(s[s<50], 50, density=True) >>> x = np.arange(1., 50.) >>> y = x**(-a) / special.zetac(a) # doctest: +SKIP >>> plt.plot(x, y/max(y), linewidth=2, color='r') # doctest: +SKIP >>> plt.show() `x` isn't a recognized object; `shuffle` is not guaranteed to behave correctly. E.g., non-numpy array/tensor objects with view semantics may contain duplicates after shuffling. 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 ``weibull`` method of a ``default_rng()`` 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 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 ``vonmises`` method of a ``default_rng()`` 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. 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 ``uniform`` method of a ``default_rng()`` 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 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)``. 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 ``triangular`` method of a ``default_rng()`` 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 -------- 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]]]) 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 ``standard_t`` method of a ``default_rng()`` 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 -------- 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? We have 10 degrees of freedom, so is the sample mean within 95% of the recommended value? >>> s = np.random.standard_t(10, size=100000) >>> np.mean(intake) 6753.636363636364 >>> intake.std(ddof=1) 1142.1232221373727 Calculate the t statistic, setting the ddof parameter to the unbiased value so the divisor in the standard deviation will be degrees of freedom, N-1. >>> t = (np.mean(intake)-7725)/(intake.std(ddof=1)/np.sqrt(len(intake))) >>> import matplotlib.pyplot as plt >>> h = plt.hist(s, bins=100, density=True) For a one-sided t-test, how far out in the distribution does the t statistic appear? >>> np.sum(s>> 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))) 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 ``rayleigh`` method of a ``default_rng()`` 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 -------- 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 ``integers`` method of a ``default_rng()`` 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. 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 ``power`` method of a ``default_rng()`` 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 < 1. See Also -------- 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 ``pareto`` method of a ``default_rng()`` 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. 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 ``normal`` method of a ``default_rng()`` 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. 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 N(3, 6.25): >>> 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 ``noncentral_f`` method of a ``default_rng()`` 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 -------- 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 ``noncentral_chisquare`` method of a ``default_rng()`` 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 -------- 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 ``negative_binomial`` method of a ``default_rng()`` 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 -------- 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 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) The following is probably true, given that 0.6 is roughly twice the standard deviation: >>> list((x[0,0,:] - mean) < 0.6) [True, True] # random 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 ``multinomial`` method of a ``default_rng()`` 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 -------- 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 ``logseries`` method of a ``default_rng()`` 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. 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 ``lognormal`` method of a ``default_rng()`` 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. 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.product(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 ``logistic`` method of a ``default_rng()`` 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. 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 ``hypergeometric`` method of a ``default_rng()`` 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. 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 ``gumbel`` method of a ``default_rng()`` 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 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 ``geometric`` method of a ``default_rng()`` 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 -------- 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 ``gamma`` method of a ``default_rng()`` 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. 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 ``f`` method of a ``default_rng()`` 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. 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. 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 ``choice`` method of a ``default_rng()`` 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 a 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 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 Generator.choice: which should be used in new code Notes ----- 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 -------- 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 ``bytes`` method of a ``default_rng()`` instance instead; please see the :ref:`random-quick-start`. Parameters ---------- length : int Number of random bytes. Returns ------- out : str String of length `length`. See Also -------- Generator.bytes: which should be used for new code. Examples -------- >>> np.random.bytes(10) ' 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 ``binomial`` method of a ``default_rng()`` 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. 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 takenUnsupported dtype %r for randintRandomState.standard_gamma (line 1507)RandomState.multivariate_normal (line 3948)RandomState.logseries (line 3860)RandomState.lognormal (line 2887)RandomState.hypergeometric (line 3727)RandomState.geometric (line 3666)RandomState.dirichlet (line 4242)RandomState.chisquare (line 1848) 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 ``wald`` method of a ``default_rng()`` 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 -------- 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 ``standard_normal`` method of a ``default_rng()`` 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. Generator.standard_normal: which should be used for new code. Notes ----- For random samples from :math:`N(\mu, \sigma^2)`, 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 :math:`N(3, 6.25)`: >>> 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 ``standard_gamma`` method of a ``default_rng()`` 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. 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 ``standard_exponential`` method of a ``default_rng()`` 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 -------- 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 ``standard_cauchy`` method of a ``default_rng()`` 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 -------- 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 ``shuffle`` method of a ``default_rng()`` 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 -------- 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]]) 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 ``random`` method of a ``default_rng()`` 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 -------- 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 ``standard_normal`` method of a ``default_rng()`` 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. Generator.standard_normal: which should be used for new code. Notes ----- For random samples from :math:`N(\mu, \sigma^2)`, use: ``sigma * np.random.randn(...) + mu`` Examples -------- >>> np.random.randn() 2.1923875335537315 # random Two-by-four array of samples from N(3, 6.25): >>> 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 ``poisson`` method of a ``default_rng()`` instance instead; please see the :ref:`random-quick-start`. Parameters ---------- lam : float or array_like of floats Expectation of interval, must be >= 0. A sequence of expectation intervals 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 -------- 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 ``permutation`` method of a ``default_rng()`` 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 -------- 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]]) 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 ``laplace`` method of a ``default_rng()`` 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 -------- 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 ``dirichlet`` method of a ``default_rng()`` 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 -------- 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 2185)RandomState.rayleigh (line 3002)RandomState.logistic (line 2802)RandomState.binomial (line 3262)state dictionary is not valid.probabilities do not sum to 1RandomState.weibull (line 2375)RandomState.uniform (line 1008)RandomState.tomaxint (line 587)RandomState.shuffle (line 4390)RandomState.poisson (line 3499)RandomState.laplace (line 2586)RandomState.randint (line 645)RandomState.pareto (line 2273)RandomState.normal (line 1400)RandomState.gumbel (line 2679)'a' and 'p' must have same sizeRandomState.randn (line 1175)RandomState.power (line 2478)RandomState.gamma (line 1587)RandomState.choice (line 806)mean must be 1 dimensionalRange exceeds valid boundsRandomState.zipf (line 3580)RandomState.wald (line 3078)RandomState.rand (line 1131)RandomState.bytes (line 770)probabilities contain NaNRandomState.seed (line 223)'p' must be 1-dimensionala must be 1-dimensionalRandomState.f (line 1670)standard_exponentialnoncentral_chisquarenumpy.random.mtrandmultivariate_normalngood + nbad < nsamplecline_in_tracebackDeprecationWarningnegative_binomial__randomstate_ctormay_share_memorysum(pvals[:-1]) > 1.0standard_normalstandard_cauchyrandom_integers_poisson_lam_maxcollections.abcstandard_gamma_legacy_seedinghypergeometricRuntimeWarningrandom_samplecount_nonzerobit_generatorOverflowErrorsearchsortedreturn_indexnumpy.linalgnoncentral_fnewbyteorderpermutationmultinomialexponentialcheck_validUserWarningRandomStateImportErrortriangularstandard_tstacklevel__pyx_vtable__mtrand.pyxmode > rightlogical_orless_equalleft == rightissubdtypeempty_likeValueErrorIndexErrorset_statelogserieslognormalleft > modehas_gaussget_stategeometricdirichletchisquareTypeErrorMT19937warningsvonmisessubtractreversedrayleighoperatorlogisticitemsizeisscalarisnativeisfinitebinomialallcloseSequenceweibulluniformtobytesstridesshufflereshapereplacerandintpoissonnsample_mt19937laplacegreaterfloat64castingcapsule at 0x{:X}asarrayalpha <= 0_MT19937unsafeuniqueuint64uint32uint16samplereducerandom_rand_pickleparetonormallegacykwargs__import__ignoregumbelformatdoublecumsumcompatchoiceastypearangezerosuint8statesigmashapescalerightravelrangerandnraisepvalspowernumpyngoodkappaisnanint64int32int16indexgaussgammafinfoequal__enter__emptydtypedfnumdfden__class__bytesarrayalpha__all__zipfwarnwald__test__takesqrtsortsizesideseedrtolranfrandprodnoncndimnbad__name__modemean__main__longlocklessleftitemintpint8high__exit__copybool_betaatolargstolsvd__str__poslowloclamkeygetepsdotcovanyalladd?UUUUUU?"@m{??@>@3?r?q?0@0C@?/*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>nC>@>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®3r35333x37333p3-33731b33l44(44h4C44 4` 4M 47 44?4nB44L4 i4a4T044542`44p. 4!4"4i$4%4@'4t(4>*4+4,4j.4/4'P1424):4454&)7484c:4;4$=4+>4@4A4KC4vD4B(F4G4:I4J4rTL4M4GuO4Q4R44T4U4EiW4Y4 Z4G\4]4_4:a4b4d4Bf4\g4ji4bk4m4n4p4\r4}"t4Yu4Hw4[y4X{46.}4 4q4a4]S4F4N<434,4+(4{%4$4o&4,*4'04m84 C4P4_4q474{4w4>ԕ44s4<4d444$4 (4a44lߢ4$4l44x 4_444{4 4EP4±4{:4귴4);4nķ4S444<*4տ44A4.44ע44f4RW4R4*Y4Fk44δ444444g44k4<444y44u4_45555@5ó 5 5]5^555q5v 5!5%5V*5s/5;S55:<5D5NO5^5Nv5QHqoMֻanjDotTrotou$w'xx,jyy7\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~}~~~~~pH`  i   6  H  A!B+m 5XttW3 `wK\ L   s   G {V~~~d~~x~~K~~~~~~~~~)~~~a~~~{~;~~A~~~m~~z~~~"~k~]~~~ԃ~|~s~j~Ua~W~K~?~2~$~~~ }}} }}i}A}}|Q|D|{3N{zeyww7ms?7E?P?'{{?*!?bv?mU?9U1T?/v?x]?&1$-?~ 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??@YH?/֎@?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?$ka?%> T+Y? O?K 2=?]d<A]X`<+M[Ij<[5q&<.8eG< h#ឪV <;LC%K<ꆭh NVeΙVn6nvK zicp%E tQ)2U1WQ9Lin?23F:L"3\LQ V f[_rWDdx h+*k2=Ko:qr Mu\x?A{FS~8;b=ZV`bBtu9=JE>XدGwdO 8cx AFẙi&zqVYםΡag6 X83:뇡koɣj_ۤ| Mg^ݧt|Ψ_ΓXp2X^ttH蟿W;ޭl~$\z[߁İPp:J+N!X ɦ֬ ᆴX7(. Ɉ?5}h.G{tr&oya=cA/˺DH0⤮<)9O@ᣩTrVj֋@?˷dsI^i@(0߾ta&⊂l1EA1T[n&mi#d)B}QJwt}B < EOvpc/F<Ң"Ae އ0~ Rfq(*QtH3D@M`P}hwx%ƿ8*JG+[EliPIw+ E>ҙ02yΩ4A (Nt.Ȱ--̕^&܌z#;ޖu~g6X .pmF 3n bH޵LaEZvpR(-x_b˿ӰdyQӶVg<7܆ut7$MH𯋉ld"rqտH)݄ /0 wپ}2}K D5z&R cM,}uc?Ѡp5.bJ3ʸT[vv+\[U@ضBi"7oLeiFγ>SR(D2Z> B0$y1gWr-ެ @樫(afoeW-|&aY +M?V#z?u?q?}n?k?Lh?e?Rc?`?Zw^?*+\?Y?RW?U?_S?XQ?߱O?M?3K?J?GH?F?jD?`C?(`A?j??>?x,>N>>q>>>j>>k>>Π>>F>>>'>\>#>u>J>*>_F>d>+>$>w>>>JK>y>|>iݿ>>I>;>ʾ>t>5<> ~>>>O>>>~3>T>ե>(>g~>ՠ>G/>>>F>J> >:n>bԓ>Q<>>x>~>>>^>Ј>D>l>1>>%>\D>@|>?y>Bv>Hs>Qp>#^m>mj>|g>md>a>^>$[> Y>=3V>[S>P>M>J>~H>UE>B>?>=>S:>7>"4>=22>T/>d,>m+*>m'>c$>N?">,>>m>t>F>>1*> > >Y>>ʗ>>I=_={==^==&=_=g=='0===P6=˙=\= s==d= =yo=/=6=.=fЍ=x=i'=܀=a1y=p=xIh=_==W=TO=G=>=N6=.=&===-H==<א<̀<<<.4V?4=3@4A4A4qB4C4D4udE4-CF4K"G4H4H41I4J4vK4\fL4HM4+N4aO4O4bP4ٽQ4R4ԊS4crT4ZU4CV4-W4ZX4Y4UY4Z4[4(\4_]4^4_4C`4va4alb40cc47[d4~Te4Of4Jg42Hh4Fi4Fj4Hk4Kl4MPm4Vn4^o48hp4sq4r4s4 t4u4v4Cw4x4 z42{40S|4u}4~44v4@ 4L4>4ق4v444lV44R4F44p4 I44"4_44Ќ4l4L4`4ԏ4坐4y4ݖ4%44r&4k44(4444.4Q4N4t44\۶4H94̻4p44~X4w4p_4~444wE`mru\zw8xky5zz/ {ԃ{{7|3}|&|H|}C}g}ۇ}}a}g}]}~~4%~5~C~Q~g^~ij~u~>~2~~r~դ~Ƭ~N~u~C~~~~k~~~~~~t~~~6 < :#%](*.-z/13579;=?EABD:FGNIJ8LMNLPQR T=UdVWXYZ[\]^~__`;abbcod.eefLggh~~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;?$"?zaWF}?Gz‘B?Oq1? OU?ߺH?7a?nV,? K?Xhw?հ<?Vp\?m?)?zP?ZcX?*;Q^?#*'g? U7?e&$ ?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$?œ߉?52?Ҙl'?DɤT?<(i?qE8 ? Uī?OQM?o^?Sq͒?Gط5?zx?1zd}?:R!?Wg?~& ~k?=~-2?ZҿҶ?'|j_]?it?[?8R?uqb?#h?z|J?G~`?\!>?GF?vJ?l󈬚?5hȩmE?㭍?-l ?uG?1i%?調?M?e*|?zè?^V?4<%F?B}u?c-@c?n? R=?Kr?*}T#?,"k>?R) ?K{o?vaӽ?命8? t;I_? h?3xk?3Ӻ?b3?vZ9S?LJisk?M$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<~;[xo6xu{fUY>9>{ppCBwS(:5^dܓAN}8) YfHqն&|s f2,2Ztզޗ .n ZR'ӯB)[l@u Pҍ'TȈt(5wI'L/$;nXMØT`OArW,+jtȳRfARnqӊ<KZW$eKs) 4<=>)G'QA@Y.(5bX jz>lq{2Xx{~JH҄Cc`Qz%~ )Q\HsrUb'Bkq-hnק Ψ;3Kd)P^٨Tv$Hx"$ 5..&$ŗ: Aޓ=?~)@ lѿ3 ; @@@5gG8?SˆB?AAz?<ٰj_?$+K?88C?J?llf?UUUUUU?dg?$@= ףp=@n?[ m?h|?5?333333 @r?$~?B>٬ @r鷯?Q?Q?9v?(\@ffffff@.@4@x&??UUUUUU?a@X@`@|@@MA-DT! @h㈵>-DT!@C;t0ir s t u 2vT wt(1@ 4H0\ @pL @ d P ( P 0 4 `  pD P \`p pT@`pP`H$ l`@ @`@"$'T*.2P5`8<(`>@(CF`JLD S @V0!Y!]!`,"bX"e"l"0r#0ux#v#d$$P$T%%l&&|'(г)l))T** l+l,/,p,--``.`.8///;\00[01q192:(2:@2p=|2=2=2>2@>2`>2?(3?H3@l3 A3@A3B30B3`B3D04`DP4Dh4E4`J4pJ4J4J5J$5J85JP5Jd50K5K5L6L@6 N6`N6N6@O(7Pt7 Q7R70S8UT8X8X8X8X8X8Z 9Z89[P90[h9P[9p[9`\9\9\9]:@]4:]L:]d:P^:^:_:0_:_;P`(; cp;Pc;m;0p<p<<r|<pr<`s<v< w=w4=wL=x`=Py=`z={=p|(>0}t>~>pl???|@P@\AAzRx $b FJ w?;*3$"DX XD{ A 4tPEBDD d GBI AABh d(_LBBB A(A0p (A BBBA Y (A BBBH 8l@LxvBDA G0e  JABH H  AABD DBBF B(A0A8DP8A0A(B BBB@BEB D(D0G@p 0A(A BBBH |A~ A g I <@AD A AI  AH ^ AI G AH DAT K ~LBID D(GP (C ABBJ | (F ABBI 4TAAD0M AAK D DAG 4(wADD K CAH I CAC P`hBEH D(D0GxHfAZ0D(A BBB\BBE D(A0O (D BBBI I (D BBBE {(A EBBD+iBEE L(D0A8B@8C0A(B BBBD\iBEE L(D0A8B@8C0A(B BBB8jyBEE G(A0[(C BBB8j]BBD A(A0I(D ABBHf0|4DQADD ^ CAE M CAG @|8TBAC D02  AABH d  AABH (TADD U DAE 4AAD0K AAE D DAO @$YAAG0~ DAD h AAF k AAC dh,[BEE B(A0D8H] 8A0A(B BBBF  8F0A(B BBBA D$gCA M DBJ AABD` lBBB A(D0DPj 0D(A BBBL ` 0D(A BBBE ` 0D(D BBBB \hBBE B(D0A8G@WHJPGXC`AhBpI@o 8D0A(B BBBF ,D E (mADG e DAJ (DpADD ^ DAD 4pcAAG a DAA L DAG 4LcAAG a DAA L DAG \XBBI D(D0 (D ABBD d (D ABBC D (C DBBA @ yD E AA 8d BBA A(D@\ (A ABBD 8 WBBA A(D0T (A ABBD d BBB A(A0 (A BBBG 8J@FHCPBXB`I0 (A BBBH D OBEB E(D0C8Dp 8A0A(B BBBJ N 8A0A(B BBBH dxTABBAAAAAIp `^BFB B(D0D8DpKxZBFFBFABFJpi 8A0A(B BBBA cxDkxFp^ 8A0A(B BBBF xW_xAp BBB A(D0DPeXL``XFP^ 0A(A BBBD NXe`BhApAxBADBFQPg 0A(A BBBJ XBBB D(A0D`h_pBxFABFAEFQ`U 0A(A BBBC V 0A(A BBBB shLp`hF`\ 0C(A BBBE TBBB D(A0D`h_pBxFABFAEFQ`U 0A(A BBBC V 0A(A BBBB shLp`hF`\ 0C(A BBBE T PBBB D(A0D`h_pBxFABFAEFQ`U 0A(A BBBC V 0A(A BBBB shLp`hF`\ 0C(A BBBE LBBB D(A0D`h_pBxFABFAEFQ`U 0A(A BBBC V 0A(A BBBB shLp`hF`\ 0C(A BBBE HBBB B(D0D8D`JhepBxAABADBFQ`k 8A0A(B BBBA @hHpYhF`^ 8A0A(B BBBD 4BBB B(D0D8D`JhepBxAABADBFQ`k 8A0A(B BBBA @hHpYhF`^ 8A0A(B BBBD BBB B(D0D8D`JhepBxAABADBFQ`k 8A0A(B BBBA @hHpYhF`^ 8A0A(B BBBD d ^BFB B(D0D8DpKxZBFFBFABFJpi 8A0A(B BBBA cxDkxFp^ 8A0A(B BBBF xW_xApBBB B(D0D8D`JhepBxAABADBFQ`k 8A0A(B BBBA @hHpYhF`^ 8A0A(B BBBD  :BBB A(D0DPeXH`YXFP^ 0A(A BBBG OXe`BhApBxBABBAJPa 0A(A BBBD 4 ^BFB B(D0D8DpKxZBFFBFABFJpi 8A0A(B BBBA cxDkxFp^ 8A0A(B BBBF xW_xApBBB B(D0D8D`JhepBxAABADBFQ`k 8A0A(B BBBA @hHpYhF`^ 8A0A(B BBBD xBFB B(D0A8GpOx`BFAEFABFJpi 8A0A(B BBBG UxDkxFp^ 8A0A(B BBBF xW_xApNxV`xGp0^BFB B(D0D8DpKxZBFFBFABFJpi 8A0A(B BBBA cxDkxFp^ 8A0A(B BBBF xW_xApkBBB B(D0D8DpxHYxFp^ 8A0A(B BBBK SxZBFFBFABFJpe 8A0A(B BBBK xBBB B(D0D8D`JhepBxAABADBFQ`k 8A0A(B BBBA @hHpYhF`^ 8A0A(B BBBD BBB D(A0D`h_pBxAABFAEAQ`S 0A(A BBBG V 0A(A BBBJ shLp`hF`\ 0C(A BBBE |QBBA D(DPeXH`YXFP^ (A ABBC OXW`BhBpBxBBBBBJPa (A ABBI |4 QBBA D(DPeXH`YXFP^ (A ABBC OXW`BhBpBxBBBBBJPa (A ABBI "BBB A(D0DPeXL``XFP^ 0A(A BBBD NXe`BhApAxBADBFQPg 0A(A BBBJ @$^BFB B(D0D8DpKxZBFFBFABFJpi 8A0A(B BBBA cxDkxFp^ 8A0A(B BBBF xW_xApx'BBB D(D0D@" 0D(A BBBA yHHPYHF@_ 0D(A BBBF m 0D(A BBBH dh*BBB A(D0DPeXH`YXFP^ 0A(A BBBG G 0A(A BBBI ,BBB A(A0D@, 0D(A BBBE r 0D(A BBBK  0D(A BBBI  0D(A BBBI `X3BBIB A(A0 (D BBBF Y (D BBBE b (D BBBD `5BBA D(D0| (D ABBF l (D ABBC  (D ABBC D T8bAD G0  DABK `  AABA Lh;ZBED A(GP (D ABBG  (D ABBC (=yAD0 AAD (@yAD0 AAD HDC'BBB B(A0D8G` 8D0A(B BBBG H\(I'BBB B(A0D8G` 8D0A(B BBBG X OBBE A(A0DP 0A(A BBBF P 0C(A BBBF LQBBA A(D@ (D ABBF ~ (G ABBF TS BBB E(A0A8D`S 8A0A(B BBBB  8A0A(B BBBH  8C0A(B BBBA :hJpFxCBBI`8]BHD D(D0s (D ABBF T,^ BBB B(A0D8D`hHpYhF`a 8C0A(B BBBC XPg BBE A(A0DPI 0D(A BBBE I 0D(A BBBD pBBE D(D0DPkXH`YXFP^ 0A(A BBBC TXa`AhApBxADBFATPC 0A(A BBBJ lsBBE D(D0DPkXH`YXFP^ 0A(A BBBC TXa`AhApBxADBFATPC 0A(A BBBJ |uBBE D(D0DPkXH`YXFP^ 0A(A BBBC TXa`AhApBxADBFATPC 0A(A BBBJ wBBD D(DPeXL``XFP^ (A ABBE SXa`AhApBxAHEFAPP@ (A ABBE !|zBFE D(D0D`KhDpkhF`^ 0A(A BBBA YhZpFxFBFAEFAP`@ 0A(A BBBD hWp_hA`X!}#BBB B(D0A8DpxHYxFp^ 8D0A(B BBBE "OIZBBB A(A0J NEFFAAAAAN{NEFFAAAAANM0A(A BBBX"BBB D(A0G@ 0D(A BBBC L 0D(A BBBI X"LBBB D(A0G@ 0D(A BBBC L 0D(A BBBI T#BBB E(A0A8D`~ 8D0A(B BBBD yhHpYhF`\ 8C0A(B BBBH  8C0A(B BBBF \#tBBB B(A0D8DHYF_ 8D0A(B BBBD @$bBBB B(A0A8DoBAFBABBAR2SSAFBABBATL`F^ 8D0A(B BBBH $'BBB E(A0A8D_TA_QBg 8D0A(B BBBI IYF_QA_RB_RBdGQABTA}ERBKGQAL% BBB B(A0D8D~ 8D0A(B BBBD lH&LaABFB B(A0D8GuDlFa 8D0A(B BBBG 9%W_F\&LC-BBB B(D0A8G HYFb 8D0A(B BBBE 'bBFB B(A0A8GeBBBBBBRDkF^ 8D0A(B BBBC USSABBABBATQV`GW`Gl'$BIB B(A0D8G2EkFb 8D0A(B BBBF GW_Fd\(5BBB B(A0A8G`+ 8A0A(B BBBJ  8C0A(B BBBF l(`BFB B(A0D8DTDkF^ 8D0A(B BBBG >W_AH4)9BEB B(A0D8DPC 8D0A(B BBBD d)9(BBB E(A0A8D 8A0A(B BBBG V 8A0A(B BBBH )  BFB B(A0D8DRbFABFBBWDkF^ 8D0A(B BBBK HSEBFBBFBTW_A2V`GX*)VBBB B(D0A8DHYF_ 8D0A(B BBBD \+?BBB B(A0D8G 8D0A(B BBBI vHYFx+ $+x(LG0EDU0+/Dj8+]G@| AG x AG +AD[@, D U , 'D b8, >\ ]P,4 ?D nh,\ DQ0,d &OK0w EJ KALK0,` WAG AA , IO0 EA ,| (D c- DI (- AG0e EA L-8&IXh-L/AG ]A0-\AG@ AQ l AS A-SAG }A-D U-}Ai F LH.pYBBE E(D0D8DU 8D0A(B BBBD `.t..|.x.t.p%G]. ,.9GED ^ABG, /IGED qABDHP/BIH H(GP (E ABBE c(A AFB,/9GED _ABFT/2BEI H(H0D@ 0D(A BBBH r0A(A FBB,$09GED _ABF,T0QGED {ABB,0qGED UABHH0BBE I(H0K8K` 8E0A(B BBBI ,1d9GED _ABF@01tBEI H(H0D@ 0A(A BBBF ,t19GED _ABF81]G@y AB x AG (AG[@81d[G0 AD t AK ;AD[02GJ42GJL2GJd2 0x2rAD@C EAH `2!(D c2!D U2!,D g2!D U 3!D U($3!AG0J AM AP3"DQh3"SAG }A3"/AG ]A3"'D b3#>\ ]3,#?D n(3T#AG R AM XA4#gAG UA<4$NAG DA\48$DIt4@$^D B E 4$AG0e EA D4 %AHDpa DAE M DAF ! DAA 4'&IXL5' BFG E(A0D8J 8D0A(B BBBG 8h5 2:BED D(Dpk (A ABBD 54YiFPL<54/AG0 AD m AJ L AC P DE 65WAG AA (65IO0 EA 4L66AGP AG ^ AA L AC 69AG@ AG 69WD R6D:`D V6: 6:NAG0?F 7; L@ I r E 047<MGG T ABF hHh7,=ZBBB B(D0A8DP} 8D0A(B BBBE H7@>BBB B(A0A8FPm 8C0A(B BBBG x8>BDB B(A0A8DP 8A0A(B BBBB @ 8D0A(B BBBC \ 8A0A(E BBBG x|8?BDB B(A0A8DP 8A0A(B BBBK ~ 8D0A(B BBBE \ 8A0A(E BBBG (8@GACD a AAE H$9 ABBB B(A0A8DPR 8A0A(B BBBF p9CBBB B(A0A8DP 8A0A(B BBBB  8A0A(B BBBE i 8A0A(B BBBE i 8A0A(B BBBA d:,EBBB B(A0A8DP 8A0A(B BBBG  8A0A(B BBBA tp:dGKbEE B(A0A8GP8A0A(B BBBAJP 8A0A(B BBBC ,:>> 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 ``shuffle`` method of a ``default_rng()`` 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 -------- 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 ``dirichlet`` method of a ``default_rng()`` 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 -------- 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 ``multinomial`` method of a ``default_rng()`` 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 -------- 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 ``multivariate_normal`` method of a ``default_rng()`` 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 -------- 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) The following is probably true, given that 0.6 is roughly twice the standard deviation: >>> list((x[0,0,:] - mean) < 0.6) [True, True] # random 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 ``logseries`` method of a ``default_rng()`` 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. 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 ``hypergeometric`` method of a ``default_rng()`` 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. 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 ``geometric`` method of a ``default_rng()`` 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 -------- 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 continuous 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 ``zipf`` method of a ``default_rng()`` 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. Generator.zipf: which should be used for new code. Notes ----- The probability density for the Zipf distribution is .. math:: p(x) = \frac{x^{-a}}{\zeta(a)}, 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 = 2. # parameter >>> s = np.random.zipf(a, 1000) Display the histogram of the samples, along with the probability density function: >>> import matplotlib.pyplot as plt >>> from scipy import special # doctest: +SKIP Truncate s values at 50 so plot is interesting: >>> count, bins, ignored = plt.hist(s[s<50], 50, density=True) >>> x = np.arange(1., 50.) >>> y = x**(-a) / special.zetac(a) # doctest: +SKIP >>> plt.plot(x, y/max(y), linewidth=2, color='r') # doctest: +SKIP >>> 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 ``poisson`` method of a ``default_rng()`` instance instead; please see the :ref:`random-quick-start`. Parameters ---------- lam : float or array_like of floats Expectation of interval, must be >= 0. A sequence of expectation intervals 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 -------- 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 ``negative_binomial`` method of a ``default_rng()`` 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 -------- 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 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 ``triangular`` method of a ``default_rng()`` 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 -------- 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 ``wald`` method of a ``default_rng()`` 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 -------- 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 ``rayleigh`` method of a ``default_rng()`` 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 -------- 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 ``lognormal`` method of a ``default_rng()`` 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. 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.product(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 ``logistic`` method of a ``default_rng()`` 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. 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 ``gumbel`` method of a ``default_rng()`` 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 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 ``laplace`` method of a ``default_rng()`` 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 -------- 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 ``power`` method of a ``default_rng()`` 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 < 1. See Also -------- 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 ``weibull`` method of a ``default_rng()`` 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 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 ``pareto`` method of a ``default_rng()`` 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. 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 ``vonmises`` method of a ``default_rng()`` 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. 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 ``standard_t`` method of a ``default_rng()`` 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 -------- 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? We have 10 degrees of freedom, so is the sample mean within 95% of the recommended value? >>> s = np.random.standard_t(10, size=100000) >>> np.mean(intake) 6753.636363636364 >>> intake.std(ddof=1) 1142.1232221373727 Calculate the t statistic, setting the ddof parameter to the unbiased value so the divisor in the standard deviation will be degrees of freedom, N-1. >>> t = (np.mean(intake)-7725)/(intake.std(ddof=1)/np.sqrt(len(intake))) >>> import matplotlib.pyplot as plt >>> h = plt.hist(s, bins=100, density=True) For a one-sided t-test, how far out in the distribution does the t statistic appear? >>> np.sum(s>> 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 ``noncentral_chisquare`` method of a ``default_rng()`` 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 -------- 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 ``chisquare`` method of a ``default_rng()`` 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 -------- 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 ``noncentral_f`` method of a ``default_rng()`` 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 -------- 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 ``f`` method of a ``default_rng()`` 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. 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 ``gamma`` method of a ``default_rng()`` 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. 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 ``standard_gamma`` method of a ``default_rng()`` 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. 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 ``normal`` method of a ``default_rng()`` 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. 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 N(3, 6.25): >>> 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 ``standard_normal`` method of a ``default_rng()`` 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. Generator.standard_normal: which should be used for new code. Notes ----- For random samples from :math:`N(\mu, \sigma^2)`, 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 :math:`N(3, 6.25)`: >>> 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 ``standard_normal`` method of a ``default_rng()`` 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. Generator.standard_normal: which should be used for new code. Notes ----- For random samples from :math:`N(\mu, \sigma^2)`, use: ``sigma * np.random.randn(...) + mu`` Examples -------- >>> np.random.randn() 2.1923875335537315 # random Two-by-four array of samples from N(3, 6.25): >>> 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 ``uniform`` method of a ``default_rng()`` 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 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)``. 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 ``choice`` method of a ``default_rng()`` 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 a 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 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 Generator.choice: which should be used in new code Notes ----- 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) ' 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 ``integers`` method of a ``default_rng()`` 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. 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 ``standard_exponential`` method of a ``default_rng()`` 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 -------- 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 ``exponential`` method of a ``default_rng()`` 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. See Also -------- 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 ``beta`` method of a ``default_rng()`` 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 -------- 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 ``random`` method of a ``default_rng()`` 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 -------- 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() 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. Returns ------- out : {tuple(str, ndarray of 624 uints, int, int, float), dict} 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(self, 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))) )8)))H))))))))@))8)H))`)))@)))@)))))))))))p)))p))))))))))))P)))H))H))H)))))))))))))))))))P)p)@))))))))x))H))))))H))))))) )))X))))))Ax) p)&h)P `)  X)`>P)h H)@)8) $0)()@ )@ )@ )!))"))")@))@")@)') )`!)")")$)@,)*)-)@%x) p)h)$`) X)P)H)@)8)(0)%() ! )) )@(),)')()#)` )@#)@ )!)`)  )@) )P) )A)G)L) x)~!p)0 h) `) X)3P)1H)?@)?8)` 0)~0()  )&)@~5)))) ))X )))))P))@ ))=)=))) x) p)`oh)`)X)P)H)lj@)`(8)80)8()0 )  ) 4) ) )c ) ) )W3 ) )))))p))%)))).).)x)p)h)`) X) P)1 H) @)8)0)()  ) ))) ) ) ););)I ))())))= )) ) )@6J)) x) p) uh) `)X)P)@#H)p @)8)@0)@()1 )+)) )))))))x ))h )X ) ))H )|)|)))9x)p)h)`)X) P)H)` @)8)0)0() ) )))) )8 )8 )? )P )P ) )@ )@ )@ ))) ))v)v)#x)p)qh) `) X) P)(H)(@) 8) 0)  () )))7)7)h )])])X)@)@) G ) )v)v))S)S)))@ ) x) p)3 h)`)X)eP)%H)@)8)p0)@'()" ) ))( )5)5))))`) ) ) ))))` )))j)j)w x)`#p)h)`)NX)dP)dH)@)^8)I0)I() )q)))@lE )X)X)`u))))) a )`)`))`)D)D)R)L) x) p) W h)`)X)P) H) @)F8)F0)?() ))@)@) ):):)T})0 )0 )`T?):):)))@)5)4)4)0)+)&x) p)h)`)  X)`P)`H) @) 8) 0)  () ))@)p )p )F ).).))@F!))) )))!) )))@S)` )` x)6[ p)!h)`)X)P)(H)@)8)@)0 0)x()q ) ) )` ))): ) ) ) ))) ) ) /)")))@ ))?D"))`@$!3`) P),@C`)p))@{)p@s)@o)8i)I5^)6\)@O)A`B)>)5)`*)")~)0{)w (`t (pp(vm(k0j([g(Pe(Ga(@^ (8[`(2Y{(*pUm(#QZ(0NN(J=(G3(`D'(o``(( (`''`' '@'Qt'P)'e0@'<X'D]'.p''GCC: (GNU) 4.4.7 20120313 (Red Hat 4.4.7-23)GCC: (GNU) 8.3.1 20190311 (Red Hat 8.3.1-3)x/ 1`1x Ю   t E(L''''''') *3 pm X** E @ W P(r _   v p  **J |r P   p! "w ( "5*= kQ jf iy ]' #f $| $Q $T1 @'F 'd `(Y )[ , - .h! @0H 1^ 1ms*{ @2p 2c 4c 5X 6 8 9W+ ;D >OW*h*p*)))* `D^ `)/)?)O)^))))`)  G)@)( Jb)r) )  0N)))   Q< ) S  pU )  Y @) H) )  [? )V  ^ `)  a^ ) H) P) ) @) .  ei x)u ) ) )  g: )  0j^B )Q )` ) w  m )  pp x) h)% p)5 )(L )\  `t^ `)  wk ) ) @)  0{Q )h ~)  Q)  QR)i p) @^)) )  W)o) p*) B)V8)g))h) B ).)=X)KP)Y p `Z   '()  '@ |)   ))))% @ ` x0))x)8))p)h)0)2@)I@)X)q)P)  ))) )()+()=H)JP)W )))) @)6 k ) p))x) /);)G) ^ P#)@)0)())0)H)%)5)E)S)a)x) ?IZ`)@)p)h)`)X)h))) )6)J)b){))x))0))H)-p)C)]`)r)h)))X)@)8).p)Z)()) )))))&)6()b)r) ))))()),0)W)g))8))p))x)2)Bh)k){))8))p) )/ )? )e x)u H) p) h) h) @) `) )!X)!x):!P)J!)v!H)!)!@)!)!)!8)"):"0)J"()Z" )j")")")")")")")#)/#)?#0)j#)z#()#)#)#()#X)#)#),$)Z$H)o$ )$)$*$*$*%* %*<%0*m%(*% *%x*&p*>&h*v&`*&X*&P*'H*Q'@*'8*'*'*&(*P()()()())))).)8)>)H)R)`)d)*p)))P))()))))))))*)$*)7*)P*x)n*X)~*p)*h)*)*`)*X)+)+P)*+H)H+`)\+@)u+8)+)+0)+()+)+ ),)#,)3,)L,)j,),),),),),`),)-)4-8)M-)f-)-h)-)-)-)-)-).)+.)D.)b.)v.).).@).).x).()/p)1/h)O/)k/`)/X)/)/P)/H)/)0@)(08)F0h)W00)p0()0)0 )0)0)0)1)#1)51)N1)l1)|1)1)18)1)1)1) 2)$2)B2)R2)k2)2)2)2)2)2)3)"3);3)Y3)l3)3x)3p)3h)3`)3X)4)#4P)<4H)Z4p)t4@)48)4X)40)4()5@)5 )35)Q5)j5)5)5)5)5)5)6) 6H)26)K6)i6 )|6)6)6)6)6)6) 7)$7)B7)Q7)o7) 7) 7)7x)7P)7)8)8X),8)B8)N8)^8)r8x)8X)80)8`)8)8)8)88)9 )19)M9)l9x)9`)9)9)9)9)90)9)9):):)9:)Q:)`:x)s: ):):):):h):P):8) ; )%;):;)O;@)a;)t;);););););); )<)D<0)p<H)<)<)<)=)E=H)m=H)=)=)=)>8);>)d> )>P)>)>@)?)0?8)\?)?)?X)?x)@0)/@)Z@)@)@)@)@p)%A)QA)|A)A)A)A`)(B)TB)B)B)B)C)+Cp)SC)~C)C)CX)CX)#D)LDP)wD)D)D)D)E)JEp)uE()E)E)Ex)F)FFp)qF)F)F)F)G`)EG)pG)G)G)G()H)BH)mH)H)H)H0)I)EIP)oI)I)I)I)Jh)CJ)RJ zJ)J)J pJ)J)K `CK )\K)zK)K KP)KH)L0)L@)*L8)HL)XL8)hL)wL )L)L `bL)L) M) M)9Mx)WM)eMp)~Mh)M)M)M)M)M@)N) N 5'RN)eN)~N)N)N)N)N)N)O)1O)JO)hO)xOp)Oh)O)O)O`)OX)P)P)/P)MP)\P )(sP)P)PX)P)P)P`)Q)Q):Qh)KQ)dQ)QP)Q)Qx)Q`)Qx)R ] @R`)YRX)wR)RP)RH)R)R)R@)R8)S)2S0)KS()iS )S)S)S)S)S taA+T):T)HT )_T@)xT8)T0)T()TX)T )T)U@)'U)8U)QU)oUH)}U)U)U)U)U )U)U)0 V@)V)5V)SV)fV)V)V)V0)V)V)V)V 0-9W)RW)pW)~W)W)W )W)W)X)X)*Xx)HX)XXp)qXh)X)X)X )X `Y )Y):Y)SY)qYh)Y)Y)Y)Y)Y) Z)(Z)AZ)_Z)oZP)~Z)(Zp)Z@)Z $ZP)[H)$[0)=[()[[@)t[8)[) [ 5[ )[)\p)$\)6\ P)s\P)\`)\X)\P)\H)\X)]) ] @C9R])`] X9(])])])])^x)^)5^)S^()h^)z^)^)^)^)^)^  :_)S_)q_)_)_()_)_)_)_)`x)3`p)L`h)j``)`X)`)`@)`)`)``)(`)aH)a VZa)sa)a)a)a)a)"b) 9b @pb`)bX)b)bP)bH)b)b@)c8)3c`)Bc )[c)yc)c)c)c)c)c)d)d)h h i i $Hi ^i @i @ i !i i " j 1j "Yj @yj j @"j @j 'k  8k `!_k "k "k $k @,l *)l -Rl @%{l l l $l  m 8m [m m m (m %m !n ?n  en @(n ,n 'n (o #1o ` Wo @#o @ o !o `o  p @9p \p Psp  p Ap Gp Lp  p ~!q 0 0q  Cq Oq 3Zq 1eq ?oq ` q ~0q q &r @~5,r 8r Dr Rr  cr qr X r r r r r Pr r @ r r =r  s  s `oCs Ys fs ts ljs `(s 8s 0s  s 4"t  4t c \t kt W3 t  t t t t t pu u %;u )du su .~u u u  u 1 u u u u  v  v  +v 7v Ev  Rv  fv ;pv I v v (v v v = v  w  w @6JCw Ow  aw uw w w @#w p w w @x 1/x +:x Ix)Zx  ix wx x x x x x x x x h x X x  y y H -y |;y Gy Vy 9`y ly |y  y y ` y y y 0y z  z 'z 4z  Gz 8 Xz ? z P z z @ z @ z {  {  { 3{ v@{ #i{ { q{  {  {  { ({  {  | 2| Z| 7d| h q| ]~| X| @| G |  | v|  } S} 5} @ ]}  r} 3 } } e} %} } p} @'"~ "K~  `~ |~ ( ~ 5~ ~ ~ `~   ) 8 H ` o   j w  `#  : NG dU h ^v I  q ɀ @lE  X `u& 5 M a u `  `ˁ D؁ R L   W - < L \  q   F ?  @  ς :܂ T} 0  `T?> :L \ @ 5 4 0 + &Ń  ؃    `4 [ r    @؄ p  F  .! G @F!o {      !ͅ  څ   @S ` 1 6[ Y !d s   (  @)0 ׆ x q   ` . ; : b o       /  " $ @ L) Z)0p))P҈)})uC`) ~)){)C+@s)Gh@o)i)S^)E !\)jXO)3 B)0 ɋ>)q5)u6`*) w"))e) 0 ( g ( (3 ؍( ( Y( ( ֎(  (H`( {( m( Z()N(? c=(3( ؐ'(: `([ J( (G Ǒ`' ' 6`'Jq '1@' '2' p@'1 ''$'hK'hs~   )'ߔ `' ! + 5 ? H Q Z 4d <n ,x $ ( s''Eʕ)֕' p,=Odp G 0 0`Ԗ Sݖ > 0S  @'-:GVr Ш& /ԗ !2?V)  Г9 0( ))0  EQdt  ( ^ 0ٙ ,  t% 0}< pWjx P `ٚ_ '7 `/Sl pN  &ԛ I, ZBS pgx p   Ϝ 0?! K;ҝH W\w pqĝѝ $ BS_sžў ݞ  !-?Sfv   `%ӟ +E  NT p>cx 2Ƞ '֠* ; 0Q g мW @   ϡ ` Ж P  1@)L^n ?{ `(   /Ϣ # P9D T ` /|  ǣ @Wۣ Q &; Zk},  YǤ֤   g" 9? Qeu 9 @ͥۥ Po'3C_p :  &Ϧ ):LYj" Ю 9ǧէ І/usr/lib/../lib64/crti.ocall_gmon_startmtrand.c__pyx_f_5numpy_6random_6mtrand_11RandomState__reset_gauss__pyx_tp_new_5numpy_6random_6mtrand_RandomState__pyx_vtabptr_5numpy_6random_6mtrand_RandomState__pyx_empty_tuple__pyx_tp_traverse_5numpy_6random_6mtrand_RandomState__pyx_getprop_5numpy_6random_6mtrand_11RandomState__bit_generator__Pyx_PyCFunction_FastCall__Pyx__ExceptionSave__Pyx_PyObject_Call__Pyx_PyObject_GetAttrStr__Pyx_PyObject_LookupSpecial__pyx_f_5numpy_6random_6mtrand_11RandomState__shuffle_raw__Pyx_PyFunction_FastCallNoKw__pyx_pyframe_localsplus_offset__Pyx_PyNumber_IntOrLongWrongResultType__Pyx_PyInt_As_int__pyx_tp_dealloc_5numpy_6random_6mtrand_RandomState__Pyx__GetException__Pyx_ErrRestoreInState__pyx_tp_clear_5numpy_6random_6mtrand_RandomState__Pyx_ImportType__Pyx_Import__pyx_m__Pyx_ImportVoidPtr__Pyx_ImportFunction__Pyx_copy_spec_to_module__pyx_pymod_createmain_interpreter_id.19788__Pyx_IsSubtype__Pyx_PyInt_NeObjC.isra.11__pyx_setprop_5numpy_6random_6mtrand_11RandomState__bit_generator__Pyx_PyUnicode_Equals__Pyx_PyDict_GetItem__Pyx__ExceptionReset.isra.27__Pyx_GetItemInt_Fast.constprop.36__Pyx_ParseOptionalKeywords.constprop.37__Pyx_Raise.constprop.38__Pyx_PyObject_GetSlice.isra.28.constprop.40__Pyx_PyFunction_FastCallDict.constprop.42__Pyx_PyErr_GivenExceptionMatchesTuple__Pyx_TypeTest.isra.3__Pyx_GetBuiltinName__pyx_b__Pyx_ImportFrom__Pyx_PyInt_As_int64_t.part.23__Pyx_PyInt_As_Py_intptr_t.part.20__Pyx__PyObject_CallOneArg__Pyx_PyInt_As_long__Pyx_IternextUnpackEndCheck__Pyx_IterFinish__Pyx_PyObject_CallNoArg__Pyx_AddTraceback__pyx_code_cache__pyx_d__pyx_cython_runtime__pyx_dict_version.20445__pyx_dict_cached_value.20446__pyx_n_s_cline_in_traceback__pyx_empty_bytes__pyx_pw_5numpy_6random_6mtrand_11RandomState_83wald__pyx_kp_u__12__pyx_float_0_0__pyx_n_u_scale__pyx_n_u_mean__pyx_f_5numpy_6random_7_common_cont__pyx_n_s_mean__pyx_n_s_scale__pyx_n_s_size__pyx_pyargnames.18128__pyx_pw_5numpy_6random_6mtrand_11RandomState_81rayleigh__pyx_float_1_0__pyx_pyargnames.18077__pyx_pw_5numpy_6random_6mtrand_11RandomState_79lognormal__pyx_n_u_sigma__pyx_n_s_sigma__pyx_pyargnames.18022__pyx_pw_5numpy_6random_6mtrand_11RandomState_77logistic__pyx_n_u_loc__pyx_n_s_loc__pyx_pyargnames.17966__pyx_pw_5numpy_6random_6mtrand_11RandomState_75gumbel__pyx_pyargnames.17910__pyx_pw_5numpy_6random_6mtrand_11RandomState_73laplace__pyx_pyargnames.17854__pyx_pw_5numpy_6random_6mtrand_11RandomState_71power__pyx_n_u_a__pyx_n_s_a__pyx_pyargnames.17805__pyx_pw_5numpy_6random_6mtrand_11RandomState_69weibull__pyx_pyargnames.17757__pyx_pw_5numpy_6random_6mtrand_11RandomState_67pareto__pyx_pyargnames.17709__pyx_pw_5numpy_6random_6mtrand_11RandomState_65vonmises__pyx_n_u_kappa__pyx_n_u_mu__pyx_n_s_mu__pyx_n_s_kappa__pyx_pyargnames.17658__pyx_pw_5numpy_6random_6mtrand_11RandomState_63standard_t__pyx_int_0__pyx_n_u_df__pyx_n_s_df__pyx_pyargnames.17609__pyx_pw_5numpy_6random_6mtrand_11RandomState_61standard_cauchy__pyx_pyargnames.17564__pyx_pw_5numpy_6random_6mtrand_11RandomState_59noncentral_chisquare__pyx_n_u_nonc__pyx_n_s_nonc__pyx_pyargnames.17514__pyx_pw_5numpy_6random_6mtrand_11RandomState_57chisquare__pyx_pyargnames.17465__pyx_pw_5numpy_6random_6mtrand_11RandomState_55noncentral_f__pyx_n_u_dfden__pyx_n_u_dfnum__pyx_n_s_dfnum__pyx_pyargnames.17411__pyx_n_s_dfden__pyx_pw_5numpy_6random_6mtrand_11RandomState_53f__pyx_pyargnames.17358__pyx_pw_5numpy_6random_6mtrand_11RandomState_51gamma__pyx_n_u_shape__pyx_n_s_shape__pyx_pyargnames.17304__pyx_pw_5numpy_6random_6mtrand_11RandomState_49standard_gamma__pyx_pyargnames.17255__pyx_pw_5numpy_6random_6mtrand_11RandomState_47normal__pyx_pyargnames.17200__pyx_pw_5numpy_6random_6mtrand_11RandomState_45standard_normal__pyx_pyargnames.17154__pyx_pw_5numpy_6random_6mtrand_11RandomState_27standard_exponential__pyx_pyargnames.16421__pyx_pw_5numpy_6random_6mtrand_11RandomState_25exponential__pyx_pyargnames.16372__pyx_pw_5numpy_6random_6mtrand_11RandomState_23beta__pyx_n_u_b__pyx_n_s_b__pyx_pyargnames.16321__pyx_pw_5numpy_6random_6mtrand_11RandomState_21random__pyx_n_s_random_sample__pyx_pyargnames.16274__pyx_pw_5numpy_6random_6mtrand_11RandomState_19random_sample__pyx_f_5numpy_6random_7_common_double_fill__pyx_pyargnames.16230__pyx_pw_5numpy_6random_6mtrand_11RandomState_11__reduce____pyx_n_s_get_state__pyx_n_s_legacy__pyx_n_s_randomstate_ctor__pyx_n_s_pickle__pyx_n_u_bit_generator__pyx_pw_5numpy_6random_6mtrand_11RandomState_7__getstate____pyx_pw_5numpy_6random_6mtrand_11RandomState_5__str____pyx_n_s_class__pyx_n_s_name__pyx_kp_u__3__pyx_kp_u__4__Pyx_PyObject_GetItem__Pyx_PyObject_Call2Args__Pyx_PyInt_As_Py_intptr_t__Pyx_PyInt_As_int64_t__pyx_pw_5numpy_6random_6mtrand_11RandomState_41randn__pyx_n_s_standard_normal__pyx_pw_5numpy_6random_6mtrand_11RandomState_39rand__pyx_pw_5numpy_6random_6mtrand_11RandomState_9__setstate____pyx_n_s_set_state__Pyx_PyObject_CallOneArg__pyx_pw_5numpy_6random_6mtrand_11RandomState_3__repr____pyx_n_s_str__pyx_kp_u_at_0x_X__pyx_n_s_format__pyx_builtin_id__Pyx__GetModuleGlobalName__pyx_pw_5numpy_6random_6mtrand_11RandomState_1__init____pyx_n_u_capsule__pyx_dict_version.15951__pyx_dict_cached_value.15952__pyx_n_s_capsule__pyx_n_s_lock__pyx_dict_version.15957__pyx_dict_cached_value.15958__pyx_n_s_legacy_seeding__pyx_pyargnames.15917__pyx_tuple__2__pyx_builtin_ValueError__pyx_n_s_seed__pyx_n_s_MT19937__pyx_f_5numpy_6random_6mtrand_int64_to_long__pyx_dict_version.15897__pyx_dict_cached_value.15898__pyx_n_s_isscalar__pyx_n_s_astype__pyx_n_u_unsafe__pyx_n_s_casting__pyx_tuple___pyx_n_s_np__pyx_pw_5numpy_6random_6mtrand_11RandomState_99logseries__pyx_n_u_p__pyx_f_5numpy_6random_7_common_disc__pyx_n_s_p__pyx_pyargnames.18788__pyx_pw_5numpy_6random_6mtrand_11RandomState_95geometric__pyx_pyargnames.18612__pyx_pw_5numpy_6random_6mtrand_11RandomState_93zipf__pyx_pyargnames.18563__pyx_pw_5numpy_6random_6mtrand_11RandomState_91poisson__pyx_n_u_lam__pyx_pyargnames.18512__pyx_n_s_lam__pyx_pw_5numpy_6random_6mtrand_11RandomState_89negative_binomial__pyx_n_u_n__pyx_n_s_n__pyx_pyargnames.18460__pyx_pw_5numpy_6random_6mtrand_11RandomState_15get_state__pyx_n_s_state__pyx_n_u_MT19937_2__pyx_dict_version.16178__pyx_dict_cached_value.16179__pyx_n_s_warn__pyx_tuple__6__pyx_n_u_has_gauss__pyx_n_u_gauss__pyx_n_u_state__pyx_n_u_key__pyx_n_u_pos__pyx_pyargnames.16142__pyx_n_s_warnings__pyx_pymod_exec_mtrand__pyx_string_tab__pyx_float_1eneg_8__pyx_int_1__pyx_int_2__pyx_int_4294967296__pyx_int_neg_1__pyx_n_s_ValueError__pyx_n_s_main__pyx_n_s_id__pyx_n_s_TypeError__pyx_builtin_TypeError__pyx_n_s_RuntimeWarning__pyx_builtin_RuntimeWarning__pyx_n_s_range__pyx_n_s_DeprecationWarning__pyx_builtin_DeprecationWarning__pyx_n_s_OverflowError__pyx_builtin_OverflowError__pyx_n_s_reversed__pyx_n_s_UserWarning__pyx_builtin_UserWarning__pyx_n_s_IndexError__pyx_builtin_IndexError__pyx_n_s_ImportError__pyx_builtin_ImportError__pyx_n_u_l__pyx_kp_u_Invalid_bit_generator_The_bit_ge__pyx_kp_u_can_only_re_seed_a_MT19937_BitGe__pyx_tuple__5__pyx_kp_u_get_state_and_legacy_can_only_be__pyx_kp_u_state_dictionary_is_not_valid__pyx_tuple__7__pyx_kp_u_state_must_be_a_dict_or_a_tuple__pyx_tuple__8__pyx_kp_u_set_state_can_only_be_used_with__pyx_tuple__9__pyx_tuple__10__pyx_tuple__11__pyx_tuple__13__pyx_kp_u_Providing_a_dtype_with_a_non_nat__pyx_tuple__15__pyx_tuple__16__pyx_kp_u_a_must_be_1_dimensional_or_an_in__pyx_tuple__17__pyx_kp_u_a_must_be_greater_than_0_unless__pyx_tuple__18__pyx_kp_u_a_must_be_1_dimensional__pyx_tuple__19__pyx_kp_u_a_cannot_be_empty_unless_no_sam__pyx_tuple__20__pyx_kp_u_p_must_be_1_dimensional__pyx_tuple__21__pyx_kp_u_a_and_p_must_have_same_size__pyx_tuple__22__pyx_kp_u_probabilities_contain_NaN__pyx_tuple__23__pyx_kp_u_probabilities_are_not_non_negati__pyx_tuple__24__pyx_kp_u_probabilities_do_not_sum_to_1__pyx_tuple__25__pyx_kp_u_Cannot_take_a_larger_sample_than__pyx_tuple__26__pyx_kp_u_Negative_dimensions_are_not_allo__pyx_tuple__27__pyx_kp_u_Fewer_non_zero_entries_in_p_than__pyx_tuple__28__pyx_tuple__29__pyx_kp_u_Range_exceeds_valid_bounds__pyx_tuple__30__pyx_kp_u_left_mode__pyx_tuple__31__pyx_kp_u_mode_right__pyx_tuple__32__pyx_kp_u_left_right__pyx_tuple__33__pyx_kp_u_ngood_nbad_nsample__pyx_tuple__34__pyx_kp_u_mean_must_be_1_dimensional__pyx_tuple__35__pyx_kp_u_cov_must_be_2_dimensional_and_sq__pyx_tuple__36__pyx_kp_u_mean_and_cov_must_have_same_leng__pyx_tuple__37__pyx_slice__38__pyx_kp_u_check_valid_must_equal_warn_rais__pyx_tuple__39__pyx_kp_u_covariance_is_not_positive_semid__pyx_tuple__40__pyx_tuple__41__pyx_tuple__42__pyx_kp_u_sum_pvals_1_1_0__pyx_tuple__43__pyx_kp_u_alpha_0__pyx_tuple__44__pyx_tuple__45__pyx_kp_u_x_isn_t_a_recognized_object_shu__pyx_tuple__46__pyx_kp_u_x_must_be_an_integer_or_at_least__pyx_tuple__47__pyx_kp_u_numpy_core_multiarray_failed_to__pyx_tuple__48__pyx_kp_u_numpy_core_umath_failed_to_impor__pyx_n_s_kwargs__pyx_n_s_args__pyx_n_s_sample__pyx_kp_s_mtrand_pyx__pyx_n_s_ranf__pyx_vtable_5numpy_6random_6mtrand_RandomState__pyx_type_5numpy_6random_6mtrand_RandomState__pyx_n_s_pyx_vtable__pyx_n_s_RandomState__pyx_ptype_5numpy_6random_6mtrand_RandomState__pyx_ptype_5numpy_dtype__pyx_ptype_5numpy_broadcast__pyx_ptype_5numpy_ndarray__pyx_ptype_5numpy_integer__pyx_ptype_5numpy_floating__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_17_bounded_integers__rand_uint64__pyx_f_5numpy_6random_17_bounded_integers__rand_uint32__pyx_f_5numpy_6random_17_bounded_integers__rand_uint16__pyx_f_5numpy_6random_17_bounded_integers__rand_uint8__pyx_f_5numpy_6random_17_bounded_integers__rand_bool__pyx_f_5numpy_6random_17_bounded_integers__rand_int64__pyx_f_5numpy_6random_17_bounded_integers__rand_int32__pyx_f_5numpy_6random_17_bounded_integers__rand_int16__pyx_f_5numpy_6random_17_bounded_integers__rand_int8__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_validate_output_shape__pyx_f_5numpy_6random_7_common_cont_broadcast_3__pyx_f_5numpy_6random_7_common_discrete_broadcast_iii__pyx_n_s_operator__pyx_n_s_Sequence__pyx_n_s_collections_abc__pyx_n_s_numpy__pyx_n_s_MT19937_2__pyx_n_s_mt19937PyArray_API__pyx_n_s_poisson_lam_max__pyx_k__14__pyx_n_s_rand_2__pyx_dict_version.19818__pyx_dict_cached_value.19819__pyx_n_s_beta__pyx_dict_version.19820__pyx_dict_cached_value.19821__pyx_n_s_binomial__pyx_dict_version.19822__pyx_dict_cached_value.19823__pyx_n_s_bytes__pyx_dict_version.19824__pyx_dict_cached_value.19825__pyx_n_s_chisquare__pyx_dict_version.19826__pyx_dict_cached_value.19827__pyx_n_s_choice__pyx_dict_version.19828__pyx_dict_cached_value.19829__pyx_n_s_dirichlet__pyx_dict_version.19830__pyx_dict_cached_value.19831__pyx_n_s_exponential__pyx_dict_version.19832__pyx_dict_cached_value.19833__pyx_n_s_f__pyx_dict_version.19834__pyx_dict_cached_value.19835__pyx_n_s_gamma__pyx_dict_version.19836__pyx_dict_cached_value.19837__pyx_dict_version.19838__pyx_dict_cached_value.19839__pyx_n_s_geometric__pyx_dict_version.19840__pyx_dict_cached_value.19841__pyx_n_s_gumbel__pyx_dict_version.19842__pyx_dict_cached_value.19843__pyx_n_s_hypergeometric__pyx_dict_version.19844__pyx_dict_cached_value.19845__pyx_n_s_laplace__pyx_dict_version.19846__pyx_dict_cached_value.19847__pyx_n_s_logistic__pyx_dict_version.19848__pyx_dict_cached_value.19849__pyx_n_s_lognormal__pyx_dict_version.19850__pyx_dict_cached_value.19851__pyx_n_s_logseries__pyx_dict_version.19852__pyx_dict_cached_value.19853__pyx_n_s_multinomial__pyx_dict_version.19854__pyx_dict_cached_value.19855__pyx_n_s_multivariate_normal__pyx_dict_version.19856__pyx_dict_cached_value.19857__pyx_n_s_negative_binomial__pyx_dict_version.19858__pyx_dict_cached_value.19859__pyx_n_s_noncentral_chisquare__pyx_dict_version.19860__pyx_dict_cached_value.19861__pyx_n_s_noncentral_f__pyx_dict_version.19862__pyx_dict_cached_value.19863__pyx_n_s_normal__pyx_dict_version.19864__pyx_dict_cached_value.19865__pyx_n_s_pareto__pyx_dict_version.19866__pyx_dict_cached_value.19867__pyx_n_s_permutation__pyx_dict_version.19868__pyx_dict_cached_value.19869__pyx_n_s_poisson__pyx_dict_version.19870__pyx_dict_cached_value.19871__pyx_n_s_power__pyx_dict_version.19872__pyx_dict_cached_value.19873__pyx_n_s_rand__pyx_dict_version.19874__pyx_dict_cached_value.19875__pyx_n_s_randint__pyx_dict_version.19876__pyx_dict_cached_value.19877__pyx_n_s_randn__pyx_dict_version.19878__pyx_dict_cached_value.19879__pyx_n_s_random__pyx_dict_version.19880__pyx_dict_cached_value.19881__pyx_n_s_random_integers__pyx_dict_version.19882__pyx_dict_cached_value.19883__pyx_dict_version.19884__pyx_dict_cached_value.19885__pyx_n_s_rayleigh__pyx_dict_version.19886__pyx_dict_cached_value.19887__pyx_dict_version.19888__pyx_dict_cached_value.19889__pyx_dict_version.19890__pyx_dict_cached_value.19891__pyx_n_s_shuffle__pyx_dict_version.19892__pyx_dict_cached_value.19893__pyx_n_s_standard_cauchy__pyx_dict_version.19894__pyx_dict_cached_value.19895__pyx_n_s_standard_exponential__pyx_dict_version.19896__pyx_dict_cached_value.19897__pyx_n_s_standard_gamma__pyx_dict_version.19898__pyx_dict_cached_value.19899__pyx_dict_version.19900__pyx_dict_cached_value.19901__pyx_n_s_standard_t__pyx_dict_version.19902__pyx_dict_cached_value.19903__pyx_n_s_triangular__pyx_dict_version.19904__pyx_dict_cached_value.19905__pyx_n_s_uniform__pyx_dict_version.19906__pyx_dict_cached_value.19907__pyx_n_s_vonmises__pyx_dict_version.19908__pyx_dict_cached_value.19909__pyx_n_s_wald__pyx_dict_version.19910__pyx_dict_cached_value.19911__pyx_n_s_weibull__pyx_dict_version.19912__pyx_dict_cached_value.19913__pyx_n_s_zipf__pyx_n_s_numpy_random_mtrand__pyx_mdef_5numpy_6random_6mtrand_1sample__pyx_mdef_5numpy_6random_6mtrand_3ranf__pyx_n_u_beta__pyx_n_u_binomial__pyx_n_u_bytes__pyx_n_u_chisquare__pyx_n_u_choice__pyx_n_u_dirichlet__pyx_n_u_exponential__pyx_n_u_f__pyx_n_u_gamma__pyx_n_u_geometric__pyx_n_u_get_state__pyx_n_u_gumbel__pyx_n_u_hypergeometric__pyx_n_u_laplace__pyx_n_u_logistic__pyx_n_u_lognormal__pyx_n_u_logseries__pyx_n_u_multinomial__pyx_n_u_multivariate_normal__pyx_n_u_negative_binomial__pyx_n_u_noncentral_chisquare__pyx_n_u_noncentral_f__pyx_n_u_normal__pyx_n_u_pareto__pyx_n_u_permutation__pyx_n_u_poisson__pyx_n_u_power__pyx_n_u_rand__pyx_n_u_randint__pyx_n_u_randn__pyx_n_u_random__pyx_n_u_random_integers__pyx_n_u_random_sample__pyx_n_u_ranf__pyx_n_u_rayleigh__pyx_n_u_sample__pyx_n_u_seed__pyx_n_u_set_state__pyx_n_u_shuffle__pyx_n_u_standard_cauchy__pyx_n_u_standard_exponential__pyx_n_u_standard_gamma__pyx_n_u_standard_normal__pyx_n_u_standard_t__pyx_n_u_triangular__pyx_n_u_uniform__pyx_n_u_vonmises__pyx_n_u_wald__pyx_n_u_weibull__pyx_n_u_zipf__pyx_n_u_RandomState__pyx_n_s_all_2__pyx_kp_u_seed_self_seed_None_Reseed_a_le__pyx_kp_u_RandomState_seed_line_223__pyx_kp_u_random_sample_size_None_Return__pyx_kp_u_RandomState_random_sample_line_3__pyx_kp_u_standard_exponential_size_None__pyx_kp_u_RandomState_standard_exponential__pyx_kp_u_tomaxint_size_None_Return_a_sam__pyx_kp_u_RandomState_tomaxint_line_587__pyx_kp_u_randint_low_high_None_size_None__pyx_kp_u_RandomState_randint_line_645__pyx_kp_u_bytes_length_Return_random_byte__pyx_kp_u_RandomState_bytes_line_770__pyx_kp_u_choice_a_size_None_replace_True__pyx_kp_u_RandomState_choice_line_806__pyx_kp_u_uniform_low_0_0_high_1_0_size_N__pyx_kp_u_RandomState_uniform_line_1008__pyx_kp_u_rand_d0_d1_dn_Random_values_in__pyx_kp_u_RandomState_rand_line_1131__pyx_kp_u_randn_d0_d1_dn_Return_a_sample__pyx_kp_u_RandomState_randn_line_1175__pyx_kp_u_random_integers_low_high_None_s__pyx_kp_u_RandomState_random_integers_line__pyx_kp_u_standard_normal_size_None_Draw__pyx_kp_u_RandomState_standard_normal_line__pyx_kp_u_normal_loc_0_0_scale_1_0_size_N__pyx_kp_u_RandomState_normal_line_1400__pyx_kp_u_standard_gamma_shape_size_None__pyx_kp_u_RandomState_standard_gamma_line__pyx_kp_u_gamma_shape_scale_1_0_size_None__pyx_kp_u_RandomState_gamma_line_1587__pyx_kp_u_f_dfnum_dfden_size_None_Draw_sa__pyx_kp_u_RandomState_f_line_1670__pyx_kp_u_noncentral_f_dfnum_dfden_nonc_s__pyx_kp_u_RandomState_noncentral_f_line_17__pyx_kp_u_chisquare_df_size_None_Draw_sam__pyx_kp_u_RandomState_chisquare_line_1848__pyx_kp_u_noncentral_chisquare_df_nonc_si__pyx_kp_u_RandomState_noncentral_chisquare__pyx_kp_u_standard_cauchy_size_None_Draw__pyx_kp_u_RandomState_standard_cauchy_line__pyx_kp_u_standard_t_df_size_None_Draw_sa__pyx_kp_u_RandomState_standard_t_line_2083__pyx_kp_u_vonmises_mu_kappa_size_None_Dra__pyx_kp_u_RandomState_vonmises_line_2185__pyx_kp_u_pareto_a_size_None_Draw_samples__pyx_kp_u_RandomState_pareto_line_2273__pyx_kp_u_weibull_a_size_None_Draw_sample__pyx_kp_u_RandomState_weibull_line_2375__pyx_kp_u_power_a_size_None_Draws_samples__pyx_kp_u_RandomState_power_line_2478__pyx_kp_u_laplace_loc_0_0_scale_1_0_size__pyx_kp_u_RandomState_laplace_line_2586__pyx_kp_u_gumbel_loc_0_0_scale_1_0_size_N__pyx_kp_u_RandomState_gumbel_line_2679__pyx_kp_u_logistic_loc_0_0_scale_1_0_size__pyx_kp_u_RandomState_logistic_line_2802__pyx_kp_u_lognormal_mean_0_0_sigma_1_0_si__pyx_kp_u_RandomState_lognormal_line_2887__pyx_kp_u_rayleigh_scale_1_0_size_None_Dr__pyx_kp_u_RandomState_rayleigh_line_3002__pyx_kp_u_wald_mean_scale_size_None_Draw__pyx_kp_u_RandomState_wald_line_3078__pyx_kp_u_triangular_left_mode_right_size__pyx_kp_u_RandomState_triangular_line_3154__pyx_kp_u_binomial_n_p_size_None_Draw_sam__pyx_kp_u_RandomState_binomial_line_3262__pyx_kp_u_negative_binomial_n_p_size_None__pyx_kp_u_RandomState_negative_binomial_li__pyx_kp_u_poisson_lam_1_0_size_None_Draw__pyx_kp_u_RandomState_poisson_line_3499__pyx_kp_u_zipf_a_size_None_Draw_samples_f__pyx_kp_u_RandomState_zipf_line_3580__pyx_kp_u_geometric_p_size_None_Draw_samp__pyx_kp_u_RandomState_geometric_line_3666__pyx_kp_u_hypergeometric_ngood_nbad_nsamp__pyx_kp_u_RandomState_hypergeometric_line__pyx_kp_u_logseries_p_size_None_Draw_samp__pyx_kp_u_RandomState_logseries_line_3860__pyx_kp_u_multivariate_normal_mean_cov_si__pyx_kp_u_RandomState_multivariate_normal__pyx_kp_u_multinomial_n_pvals_size_None_D__pyx_kp_u_RandomState_multinomial_line_412__pyx_kp_u_dirichlet_alpha_size_None_Draw__pyx_kp_u_RandomState_dirichlet_line_4242__pyx_kp_u_shuffle_x_Modify_a_sequence_in__pyx_kp_u_RandomState_shuffle_line_4390__pyx_kp_u_permutation_x_Randomly_permute__pyx_kp_u_RandomState_permutation_line_449__pyx_n_s_test__pyx_pw_5numpy_6random_6mtrand_1sample__pyx_dict_version.19426__pyx_dict_cached_value.19427__pyx_pw_5numpy_6random_6mtrand_3ranf__pyx_dict_version.19455__pyx_dict_cached_value.19456__pyx_pw_5numpy_6random_6mtrand_11RandomState_13seed__pyx_dict_version.16121__pyx_dict_cached_value.16122__pyx_pyargnames.16091__pyx_pw_5numpy_6random_6mtrand_11RandomState_29tomaxint__pyx_dict_version.16522__pyx_dict_cached_value.16523__pyx_n_s_empty__pyx_dict_version.16524__pyx_dict_cached_value.16525__pyx_n_s_int64__pyx_n_s_dtype__pyx_n_s_exit__pyx_n_s_enter__pyx_pyargnames.16465__pyx_pw_5numpy_6random_6mtrand_11RandomState_37uniform__pyx_dict_version.16991__pyx_dict_cached_value.16992__pyx_n_s_subtract__pyx_dict_version.16998__pyx_dict_cached_value.16999__pyx_n_s_all__pyx_dict_version.17000__pyx_dict_cached_value.17001__pyx_n_s_isfinite__pyx_dict_version.16986__pyx_dict_cached_value.16987__pyx_n_s_low__pyx_n_s_high__pyx_pyargnames.16919__pyx_pw_5numpy_6random_6mtrand_11RandomState_31randint__pyx_n_s_isnative__pyx_dict_version.16607__pyx_dict_cached_value.16608__pyx_n_s_newbyteorder__pyx_dict_version.16612__pyx_dict_cached_value.16613__pyx_n_s_int32__pyx_dict_version.16615__pyx_dict_cached_value.16616__pyx_dict_version.16617__pyx_dict_cached_value.16618__pyx_n_s_int16__pyx_dict_version.16633__pyx_dict_cached_value.16634__pyx_n_s_compat__pyx_n_s_long__pyx_dict_version.16635__pyx_dict_cached_value.16636__pyx_n_s_array__pyx_dict_version.16619__pyx_dict_cached_value.16620__pyx_n_s_int8__pyx_pyargnames.16556__pyx_dict_version.16621__pyx_dict_cached_value.16622__pyx_n_s_uint64__pyx_dict_version.16623__pyx_dict_cached_value.16624__pyx_n_s_uint32__pyx_dict_version.16625__pyx_dict_cached_value.16626__pyx_n_s_uint16__pyx_dict_version.16627__pyx_dict_cached_value.16628__pyx_n_s_uint8__pyx_dict_version.16629__pyx_dict_cached_value.16630__pyx_n_s_bool__pyx_kp_u_Unsupported_dtype_r_for_randint__pyx_pw_5numpy_6random_6mtrand_11RandomState_109permutation__pyx_dict_version.19336__pyx_dict_cached_value.19337__pyx_n_s_arange__pyx_dict_version.19344__pyx_dict_cached_value.19345__pyx_n_s_asarray__pyx_n_s_ndim__pyx_dict_version.19348__pyx_dict_cached_value.19349__pyx_n_s_may_share_memory__pyx_dict_version.19354__pyx_dict_cached_value.19355__pyx_dict_version.19361__pyx_dict_cached_value.19362__pyx_dict_version.19363__pyx_dict_cached_value.19364__pyx_n_s_intp__pyx_pw_5numpy_6random_6mtrand_11RandomState_101multivariate_normal__pyx_n_u_warn__pyx_n_s_svd__pyx_n_s_numpy_linalg__pyx_dict_version.18904__pyx_dict_cached_value.18905__pyx_dict_version.18909__pyx_dict_cached_value.18910__pyx_n_s_reshape__pyx_dict_version.18923__pyx_dict_cached_value.18924__pyx_n_s_double__pyx_n_u_ignore__pyx_dict_version.18947__pyx_dict_cached_value.18948__pyx_n_s_dot__pyx_dict_version.18949__pyx_dict_cached_value.18950__pyx_n_s_sqrt__pyx_n_s_cov__pyx_n_s_check_valid__pyx_n_s_tol__pyx_pyargnames.18840__pyx_n_u_raise__pyx_dict_version.18936__pyx_dict_cached_value.18937__pyx_n_s_allclose__pyx_dict_version.18938__pyx_dict_cached_value.18939__pyx_n_s_T__pyx_n_s_rtol__pyx_n_s_atol__pyx_dict_version.18944__pyx_dict_cached_value.18945__pyx_pw_5numpy_6random_6mtrand_11RandomState_105dirichlet__pyx_dict_version.19151__pyx_dict_cached_value.19152__pyx_n_s_any__pyx_dict_version.19153__pyx_dict_cached_value.19154__pyx_n_s_less_equal__pyx_dict_version.19163__pyx_dict_cached_value.19164__pyx_n_s_index__pyx_dict_version.19172__pyx_dict_cached_value.19173__pyx_n_s_zeros__pyx_dict_version.19174__pyx_dict_cached_value.19175__pyx_n_s_float64__pyx_n_s_alpha__pyx_pyargnames.19086__pyx_pw_5numpy_6random_6mtrand_11RandomState_85triangular__pyx_dict_version.18256__pyx_dict_cached_value.18257__pyx_dict_version.18258__pyx_dict_cached_value.18259__pyx_n_s_greater__pyx_dict_version.18266__pyx_dict_cached_value.18267__pyx_dict_version.18268__pyx_dict_cached_value.18269__pyx_dict_version.18276__pyx_dict_cached_value.18277__pyx_dict_version.18278__pyx_dict_cached_value.18279__pyx_n_s_equal__pyx_n_s_left__pyx_pyargnames.18181__pyx_n_s_mode__pyx_n_s_right__pyx_pw_5numpy_6random_6mtrand_11RandomState_87binomial__pyx_dict_version.18379__pyx_dict_cached_value.18380__pyx_dict_version.18425__pyx_dict_cached_value.18426__pyx_dict_version.18386__pyx_dict_cached_value.18387__pyx_pyargnames.18303__pyx_pw_5numpy_6random_6mtrand_11RandomState_33bytes__pyx_dict_version.16673__pyx_dict_cached_value.16674__pyx_kp_u_u4__pyx_n_s_tobytes__pyx_pw_5numpy_6random_6mtrand_11RandomState_103multinomial__pyx_n_u_pvals__pyx_dict_version.19046__pyx_dict_cached_value.19047__pyx_dict_version.19055__pyx_dict_cached_value.19056__pyx_n_s_pvals__pyx_pyargnames.18977__pyx_pw_5numpy_6random_6mtrand_11RandomState_17set_state__pyx_n_s_get__pyx_pw_5numpy_6random_6mtrand_11RandomState_107shuffle__pyx_dict_version.19275__pyx_dict_cached_value.19276__pyx_dict_version.19277__pyx_dict_cached_value.19278__pyx_n_s_stacklevel__pyx_dict_version.19257__pyx_dict_cached_value.19258__pyx_n_s_empty_like__pyx_n_s_strides__pyx_n_s_itemsize__pyx_dict_version.19240__pyx_dict_cached_value.19241__pyx_dict_version.19242__pyx_dict_cached_value.19243__pyx_pw_5numpy_6random_6mtrand_11RandomState_97hypergeometric__pyx_dict_version.18741__pyx_dict_cached_value.18742__pyx_dict_version.18743__pyx_dict_cached_value.18744__pyx_n_s_less__pyx_dict_version.18745__pyx_dict_cached_value.18746__pyx_n_s_add__pyx_dict_version.18757__pyx_dict_cached_value.18758__pyx_dict_version.18762__pyx_dict_cached_value.18763__pyx_dict_version.18767__pyx_dict_cached_value.18768__pyx_n_u_ngood__pyx_n_u_nsample__pyx_n_u_nbad__pyx_n_s_ngood__pyx_pyargnames.18663__pyx_n_s_nbad__pyx_n_s_nsample__pyx_pw_5numpy_6random_6mtrand_11RandomState_43random_integers__pyx_dict_version.17132__pyx_dict_cached_value.17133__pyx_kp_u_This_function_is_deprecated_Plea_2__pyx_dict_version.17122__pyx_dict_cached_value.17123__pyx_kp_u_This_function_is_deprecated_Plea__pyx_pyargnames.17081__pyx_pw_5numpy_6random_6mtrand_11RandomState_35choice__pyx_dict_version.16770__pyx_dict_cached_value.16771__pyx_n_s_copy__pyx_dict_version.16775__pyx_dict_cached_value.16776__pyx_n_s_item__pyx_dict_version.16785__pyx_dict_cached_value.16786__pyx_n_s_prod__pyx_dict_version.16795__pyx_dict_cached_value.16796__pyx_dict_version.16797__pyx_dict_cached_value.16798__pyx_n_s_finfo__pyx_dict_version.16799__pyx_dict_cached_value.16800__pyx_n_s_eps__pyx_dict_version.16805__pyx_dict_cached_value.16806__pyx_n_s_issubdtype__pyx_dict_version.16811__pyx_dict_cached_value.16812__pyx_dict_version.16813__pyx_dict_cached_value.16814__pyx_dict_version.16828__pyx_dict_cached_value.16829__pyx_n_s_isnan__pyx_dict_version.16832__pyx_dict_cached_value.16833__pyx_n_s_logical_or__pyx_n_s_reduce__pyx_n_s_cumsum__pyx_n_s_searchsorted__pyx_n_u_right__pyx_n_s_side__pyx_dict_version.16848__pyx_dict_cached_value.16849__pyx_dict_version.16900__pyx_dict_cached_value.16901__pyx_dict_version.16791__pyx_dict_cached_value.16792__pyx_n_s_replace__pyx_dict_version.16836__pyx_dict_cached_value.16837__pyx_dict_version.16838__pyx_dict_cached_value.16839__pyx_dict_version.16853__pyx_dict_cached_value.16854__pyx_n_s_count_nonzero__pyx_dict_version.16860__pyx_dict_cached_value.16861__pyx_n_s_ravel__pyx_dict_version.16868__pyx_dict_cached_value.16869__pyx_dict_version.16875__pyx_dict_cached_value.16876__pyx_n_s_unique__pyx_n_s_return_index__pyx_n_s_sort__pyx_n_s_take__pyx_pyargnames.16698__pyx_moduledef__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_3262__pyx_k_RandomState_bytes_line_770__pyx_k_RandomState_chisquare_line_1848__pyx_k_RandomState_choice_line_806__pyx_k_RandomState_dirichlet_line_4242__pyx_k_RandomState_f_line_1670__pyx_k_RandomState_gamma_line_1587__pyx_k_RandomState_geometric_line_3666__pyx_k_RandomState_gumbel_line_2679__pyx_k_RandomState_hypergeometric_line__pyx_k_RandomState_laplace_line_2586__pyx_k_RandomState_logistic_line_2802__pyx_k_RandomState_lognormal_line_2887__pyx_k_RandomState_logseries_line_3860__pyx_k_RandomState_multinomial_line_412__pyx_k_RandomState_multivariate_normal__pyx_k_RandomState_negative_binomial_li__pyx_k_RandomState_noncentral_chisquare__pyx_k_RandomState_noncentral_f_line_17__pyx_k_RandomState_normal_line_1400__pyx_k_RandomState_pareto_line_2273__pyx_k_RandomState_permutation_line_449__pyx_k_RandomState_poisson_line_3499__pyx_k_RandomState_power_line_2478__pyx_k_RandomState_rand_line_1131__pyx_k_RandomState_randint_line_645__pyx_k_RandomState_randn_line_1175__pyx_k_RandomState_random_integers_line__pyx_k_RandomState_random_sample_line_3__pyx_k_RandomState_rayleigh_line_3002__pyx_k_RandomState_seed_line_223__pyx_k_RandomState_shuffle_line_4390__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_2083__pyx_k_RandomState_tomaxint_line_587__pyx_k_RandomState_triangular_line_3154__pyx_k_RandomState_uniform_line_1008__pyx_k_RandomState_vonmises_line_2185__pyx_k_RandomState_wald_line_3078__pyx_k_RandomState_weibull_line_2375__pyx_k_RandomState_zipf_line_3580__pyx_k_Range_exceeds_valid_bounds__pyx_k_RuntimeWarning__pyx_k_Sequence__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__12__pyx_k__3__pyx_k__4__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_asarray__pyx_k_astype__pyx_k_at_0x_X__pyx_k_atol__pyx_k_b__pyx_k_beta__pyx_k_binomial__pyx_k_binomial_n_p_size_None_Draw_sam__pyx_k_bit_generator__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_cline_in_traceback__pyx_k_collections_abc__pyx_k_compat__pyx_k_copy__pyx_k_count_nonzero__pyx_k_cov__pyx_k_cov_must_be_2_dimensional_and_sq__pyx_k_covariance_is_not_positive_semid__pyx_k_cumsum__pyx_k_df__pyx_k_dfden__pyx_k_dfnum__pyx_k_dirichlet__pyx_k_dirichlet_alpha_size_None_Draw__pyx_k_dot__pyx_k_double__pyx_k_dtype__pyx_k_empty__pyx_k_empty_like__pyx_k_enter__pyx_k_eps__pyx_k_equal__pyx_k_exit__pyx_k_exponential__pyx_k_f__pyx_k_f_dfnum_dfden_size_None_Draw_sa__pyx_k_finfo__pyx_k_float64__pyx_k_format__pyx_k_gamma__pyx_k_gamma_shape_scale_1_0_size_None__pyx_k_gauss__pyx_k_geometric__pyx_k_geometric_p_size_None_Draw_samp__pyx_k_get__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_n_s_import__pyx_k_import__pyx_k_index__pyx_k_int16__pyx_k_int32__pyx_k_int64__pyx_k_int8__pyx_k_intp__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_seeding__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_long__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_mtrand_pyx__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_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_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_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_self_seed_None_Reseed_a_le__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_size__pyx_k_sort__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_pvals_1_1_0__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_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_x_isn_t_a_recognized_object_shu__pyx_k_x_must_be_an_integer_or_at_least__pyx_k_zeros__pyx_k_zipf__pyx_k_zipf_a_size_None_Draw_samples_f__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_2ranf__pyx_doc_5numpy_6random_6mtrand_samplecrtstuff.cderegister_tm_clones__do_global_dtors_auxcompleted.7182__do_global_dtors_aux_fini_array_entryframe_dummy__frame_dummy_init_array_entrylegacy-distributions.cfe_doublewe_doubleke_doublefe_floatwe_floatke_floatwi_doubleki_doublefi_doublewi_floatki_floatfi_float__FRAME_END____dso_handle_DYNAMIC__GNU_EH_FRAME_HDR__TMC_END___GLOBAL_OFFSET_TABLE_PyUnicode_FromFormatPyObject_SetItemPyList_Newrandom_laplace_PyUnicode_ReadyPyExc_SystemErrorPyDict_SetItemStringPyDict_Sizerandom_buffered_bounded_boollegacy_random_zipfrandom_geometric_inversionPyException_SetTracebacklegacy_frandom_weibullPyMethod_Typerandom_f_ITM_deregisterTMCloneTablelegacy_paretoPyFloat_TypePyTuple_TypePyList_AsTuple_PyThreadState_UncheckedGetPyModuleDef_InitPyEval_RestoreThreadPyFrame_Newrandom_negative_binomialrandom_standard_cauchyPyCFunction_NewEx__isnan@@GLIBC_2.2.5PyCapsule_GetNamePyNumber_InPlaceAddexp@@GLIBC_2.2.5PyNumber_AddPyObject_GetAttrString__pyx_module_is_main_numpy__random__mtrandlegacy_chisquarePyImport_AddModulePyBytes_FromStringAndSizerandom_standard_exponential_fill_fPyObject_SetAttrStringlegacy_gaussPyErr_WarnExrandom_standard_gamma_edatarandom_binomial_btpe_Py_DeallocPyModule_NewObjectPyErr_SetObjectPyErr_NormalizeExceptionlegacy_normalPyNumber_Multiplyrandom_rayleighrandom_standard_exponentialPyObject_RichComparerandom_uniformPyCode_New_finiPyImport_GetModuleDictlegacy_random_binomialrandom_bounded_uint64_fillPyExc_RuntimeErrorPyNumber_LongPyErr_GivenExceptionMatcheslegacy_random_multinomialPyErr_SetStringrandom_bounded_uint16_fillPyObject_IsInstancePyExc_ExceptionPyExc_ValueErrorPyExc_DeprecationWarningPyExc_TypeErrorlegacy_standard_exponentialPyInterpreterState_GetIDPyEval_EvalFrameExrandom_logisticPySequence_Containslegacy_random_logserieslegacy_negative_binomialmemset@@GLIBC_2.2.5PyMem_Reallocrandom_standard_uniform_fill_fPyErr_ExceptionMatchesrandom_bounded_uint64pow@@GLIBC_2.2.5random_positive_intlog@@GLIBC_2.2.5random_standard_gamma_frandom_triangularrandom_buffered_bounded_uint32PyOS_snprintfPyTraceBack_Herefmod@@GLIBC_2.2.5PyObject_CallFinalizerFromDeallocrandom_powerrandom_bounded_uint8_fillPyObject_Notrandom_noncentral_fPyNumber_InPlaceTrueDividerandom_standard_exponential_inv_fill_fPyLong_FromSsize_tPyFloat_FromDoublePyType_Readyacos@@GLIBC_2.2.5PyLong_FromLongmemcmp@@GLIBC_2.2.5PyLong_AsSsize_tlegacy_waldrandom_buffered_bounded_uint8PyModule_GetNamePyErr_Clearmemcpy@@GLIBC_2.2.5PyList_Append_Py_CheckRecursiveCall_Py_CheckRecursionLimitPyCapsule_IsValidPyExc_KeyErrorrandom_beta_Py_FalseStruct__gmon_start__random_exponentialexpf@@GLIBC_2.2.5PyTuple_NewPyThreadState_GetPyExc_OverflowErrorPyNumber_RemainderPyType_Modifiedrandom_gammalegacy_random_poissonPyObject_SetAttrPyErr_Occurredrandom_standard_uniform_f_Py_EllipsisObjectrandom_loggamPyLong_AsLongPyImport_ImportModulesqrtf@@GLIBC_2.2.5_PyDict_GetItem_KnownHashrandom_gamma_flegacy_weibullPyDict_GetItemStringPyEval_EvalCodeExpowf@@GLIBC_2.2.5PyObject_Sizerandom_standard_exponential_frandom_pareto_Py_NoneStructPyFloat_AsDouble_endPyObject_IsTrue_PyType_LookupPyImport_ImportModuleLevelObjectrandom_positive_int64legacy_standard_gammarandom_geometric_searchPyObject_Hashrandom_standard_tPyUnicode_ComparePyInit_mtrandrandom_vonmisesrandom_bounded_uint32_fillrandom_standard_normal_frandom_positive_int32random_standard_uniform_Py_TrueStruct__bss_startlogf@@GLIBC_2.2.5PyFunction_Typelegacy_powerrandom_normallegacy_exponentialrandom_chisquarePyDict_Newlegacy_standard_cauchyPyExc_IndexErrorPyBool_TypePyDict_TypePyDict_Nextlegacy_gammaPyBaseObject_Typerandom_standard_exponential_fillrandom_intervalrandom_waldrandom_noncentral_chisquarePyLong_TypePyFrame_Typerandom_standard_normallegacy_betaPyCapsule_Typelegacy_noncentral_frandom_standard_exponential_inv_fill_PyObject_GetDictPtrrandom_lognormalPyUnicode_FromStringrandom_buffered_bounded_uint16PyObject_GetIterPyEval_SaveThreadPyUnicode_InternFromStringPyExc_ImportErrorlegacy_random_hypergeometricPyDict_SetItemrandom_uintPySequence_TuplePyExc_AttributeErrorrandom_gumbelPyDict_Copyrandom_standard_uniform_filllegacy_standard_tPyExc_StopIterationPySequence_Listrandom_standard_normal_fill_ffloor@@GLIBC_2.2.5legacy_random_geometricPyUnicode_TypePyCapsule_NewPyUnicode_DecodePyErr_Formatrandom_bounded_bool_fillPyCapsule_GetPointerPySlice_NewPyExc_NameErrorPyUnicode_FromStringAndSizePyModule_GetDictrandom_binomial_inversion_ITM_registerTMCloneTablelegacy_noncentral_chisquarePyNumber_IndexPyObject_GetAttrsqrt@@GLIBC_2.2.5PyCFunction_Type_PyDict_NewPresizedceil@@GLIBC_2.2.5PyUnicode_FormatPyLong_FromStringPyMem_MallocPyErr_WarnFormat__cxa_finalize@@GLIBC_2.2.5_initPyNumber_Subtractrandom_standard_normal_fillPyTuple_PackPy_GetVersionlegacy_lognormalPyObject_GC_UnTrackPyDict_GetItemWithErrorPyList_Type.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$.o8 @xxHo//Uo 1 1@d`1`1onBxxXxЮЮs ~tt 0t EEt(L(Lx;''''' ''S ) ( 0 Y@ @z  +