:i{,SSKJr SSKJr SSKJr SSKrSSKJ r SSS.S jr SS jr "S S \5r S r "SS\5rSrSrSS.SjrSSjr"SS\5rSrg))Counter)suppress) NamedTupleN) is_scalar_nanFreturn_inverse return_countscRUR[:Xa [XUS9$[XUS9$)a)Helper function to find unique values with support for python objects. Uses pure python method for object dtype, and numpy method for all other dtypes. Parameters ---------- values : ndarray Values to check for unknowns. return_inverse : bool, default=False If True, also return the indices of the unique values. return_counts : bool, default=False If True, also return the number of times each unique item appears in values. Returns ------- unique : ndarray The sorted unique values. unique_inverse : ndarray The indices to reconstruct the original array from the unique array. Only provided if `return_inverse` is True. unique_counts : ndarray The number of times each of the unique values comes up in the original array. Only provided if `return_counts` is True. r)dtypeobject_unique_python _unique_np)valuesr r s X/srv/projetos/modelo_ml_acdoc/venv/lib/python3.13/site-packages/sklearn/utils/_encode.py_uniquer s6>||v    ] c[R"XUS9nSupEU(aUGtp5U(aUGtp4U(dU(aUSnUR(av[US5(ac[R"U[R 5nUSUS-nU(aXdXF:'U(a"[R "XVS5XV'USUS-nU4nU(aXt4- nU(aXu4- n[U5S:XaUS$U$)zHelper function to find unique values for numpy arrays that correctly accounts for nans. See `_unique` documentation for details.r)NNrNr)npuniquesizer searchsortednansumlen)rr r uniquesinversecountsnan_idxrets rrr3sii]G!OG"#!*|| gbk22//'2662-GaK( )0G% &  ffVH%56FOMgk*F *C z yX]3q6++rc4\rSrSr%Sr\\S'\\S'SrSrg) MissingValues\z'Data class for missing data informationrnonec/nUR(aURS5 UR(aUR[R5 U$)z3Convert tuple to a list where None is always first.N)r%appendrr)selfoutputs rto_listMissingValues.to_listbs6 99 MM$  88 MM"&& ! rN) __name__ __module__ __qualname____firstlineno____doc__bool__annotations__r*__static_attributes__r,rrr#r#\s1 I Jrr#cUVs1sHob[U5(dMUiM nnU(d U[SSS94$SU;a%[U5S:Xa [SSS9nO[SSS9nO [SSS9nX- nXC4$s snf)aExtract missing values from `values`. Parameters ---------- values: set Set of values to extract missing from. Returns ------- output: set Set with missing values extracted. missing_values: MissingValues Object with missing value information. NF)rr%rT)rr#r)rvaluemissing_values_setoutput_missing_valuesr)s r_extract_missingr9ls""!%]mE6J6 }U;;; !! ! "a '$1e$$G !%2d$F ! -$U C (F  (('s A6A6c2^\rSrSrSrU4SjrSrSrU=r$)_nandictz!Dictionary with support for nans.c>[TU]U5 UR5Hup#[U5(dMX0l g gN)super__init__itemsr nan_value)r(mappingkeyr6 __class__s rr@_nandict.__init__s5 !!--/JCS!!!&*rcr[US5(a[U5(a UR$[U5e)NrB)hasattrrrBKeyErrorr(rDs r __missing___nandict.__missing__- 4 % %-*<*<>> !smr)rB) r-r.r/r0r1r@rKr4 __classcell__rEs@rr;r;s+rr;c[[U5VVs0sHup#X2_M snn5n[R"UVs/sHoTUPM sn5$s snnfs snf)z,Map values based on its position in uniques.)r; enumeraterarray)rrivaltablevs r_map_to_integerrWsN 9W+=>+=cf+=> ?E 88v.v!1Xv. //?.s A Ac[U5n[U5up4[U5nURUR 55 [ R "XPRS9nU4nU(aU[X54- nU(aU[X54- n[U5S:XaUS$U$![a1 [S[SU5555n[SU35ef=f)Nr c38# UHoRv M g7fr>)r/).0ts r !_unique_python..sL/K!~~/Kc38# UHn[U5v M g7fr>)type)r[rVs rr]r^s2KFq477Fr_zPEncoders require their input argument must be uniformly strings or numbers. Got rr) setr9sortedextendr*rrRr TypeErrorrW _get_countsr)rr r uniques_setmissing_valuesrtypesr!s rrrs  &k &6{&C# %~--/0((7,,7 *C 022 F,..X]3q6++  Ls2KF2K/KLL '',g /   s A B'';C"T) check_unknownc,URRS;a [X5$U(a)[ X5nU(a[ S[ U535e[R"X5$![an[ S[ U535eSnAff=f)axHelper function to encode values into [0, n_uniques - 1]. Uses pure python method for object dtype, and numpy method for all other dtypes. The numpy method has the limitation that the `uniques` need to be sorted. Importantly, this is not checked but assumed to already be the case. The calling method needs to ensure this for all non-object values. Parameters ---------- values : ndarray Values to encode. uniques : ndarray The unique values in `values`. If the dtype is not object, then `uniques` needs to be sorted. check_unknown : bool, default=True If True, check for values in `values` that are not in `unique` and raise an error. This is ignored for object dtype, and treated as True in this case. This parameter is useful for _BaseEncoder._transform() to avoid calling _check_unknown() twice. Returns ------- encoded : ndarray Encoded values OUSz%y contains previously unseen labels: N) r kindrWrI ValueErrorstr_check_unknownrr)rrrjediffs r_encoderss:||E! O"63 3 !&2D #HT !TUUw// ODSVHMN N Os A-- B7BBc^^SnURRS;Ga;[U5n[U5upE[U5m[T5ummUT- nUR=(a TR(+nUR =(a TR (+nUU4Sjn U(adU(dU(dU(a-[ R"UV s/sH o"U 5PM sn 5nO"[ R"[U5[S9n[U5nU(aURS5 U(aUR[ R5 GO[ R"U5n [ R"XSS9nU(aJUR(a[ R "X5nO"[ R"[U5[S9n[ R""U5R%5(ab[ R""U5n U R%5(a7UR(a!U(a[ R""U5n SX='Xl)n[U5nU(aXc4$U$s sn f)a= Helper function to check for unknowns in values to be encoded. Uses pure python method for object dtype, and numpy method for all other dtypes. Parameters ---------- values : array Values to check for unknowns. known_values : array Known values. Must be unique. return_mask : bool, default=False If True, return a mask of the same shape as `values` indicating the valid values. Returns ------- diff : list The unique values present in `values` and not in `know_values`. valid_mask : boolean array Additionally returned if ``return_mask=True``. Nrlc>UT;=(d< TR=(a USL=(d TR=(a [U5$r>)r%rr)r6missing_in_uniquesrgs ris_valid _check_unknown..is_validsG$)%**"TM)&)))!%(  rrYT assume_uniquer)r rmrbr9rr%rrRonesrr2listr'r setdiff1drisinisnanany)r known_values return_mask valid_mask values_setmissing_in_valuesrr nan_in_diff none_in_diffrwr6 unique_values diff_is_nanis_nanrvrgs @@rrprps2J ||E![ (8(D% ,' *:;*G' 'K''++J4F4J4J0J (--M6H6M6M2M   {lXXF&KF5xF&KL WWS[= Dz  KK   KK  &) ||MtL yyWWV: WWS[=  88L ! % % ' '((4.K  99XXf-F)*J&L)Dz KC'LsI9c8^\rSrSrSrU4SjrSrSrSrU=r $) _NaNCounteriAz$Counter with support for nan values.cB>[TU]URU55 gr>)r?r@_generate_items)r(rArEs rr@_NaNCounter.__init__Ds --e45rc## UHFn[U5(dUv M[US5(dSUlU=RS- slMH g7f)z>Generate items without nans. Stores the nan counts separately. nan_countrrN)rrHr)r(rAitems rr_NaNCounter._generate_itemsGsDD && 4--!" NNa N sAAcr[US5(a[U5(a UR$[U5e)Nr)rHrrrIrJs rrK_NaNCounter.__missing__QrMr)r) r-r.r/r0r1r@rrKr4rNrOs@rrrAs.6 rrc|URRS;ak[U5n[R"[ U5[R S9n[U5H#upE[[5 X%X4'SSS5 M% U$[USS9upg[R"XSS9n[R"US5(a#[R"US5(aSUS'[R"XaU5n [R"U[R S9nXyX8'U$!,(df  M=f)zGet the count of each of the `uniques` in `values`. The counts will use the order passed in by `uniques`. For non-object dtypes, `uniques` is assumed to be sorted and `np.nan` is at the end. OUrYNT)r ryr)r rmrrzerosrint64rQrrIrr~rr zeros_like) rrcounterr)rSrrruniques_in_valuesunique_valid_indicess rrfrfWs ||D f%#g,bhh7 )GA(##M $#* &vTBMdK xx b!""rxx '<'< $"??=BS:TU ]]7"(( 3F & rsr#',5&R&,R J  #)L t  0 ,4/3'0TRj',r