-i.SSKJr SSKJr SSKJr SSKrSSKJ r J r J r J r J r SSKJr SSS .S jrSS jr"S S \5rSr"SS\5rSrSrSS.SjrSSjr"SS\5rSrg))Counter)suppress) NamedTupleN)_isin _searchsorteddevice get_namespacexpx) 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)valuesrrs H/var/www/html/venv/lib/python3.13/site-packages/sklearn/utils/_encode.py_uniquers6>||v    ] c<[U5up4SupVU(aU(aURU5uptpVOGU(aURU5upuO,U(aURU5upvOUR U5nUR (a`[ US5(aM[XsRUS9nUSUS-nU(aXXX:'U(aURXhS5Xh'USUS-nU4n U(aX4- n U(aX4- n [U 5S:XaU S$U $)zHelper function to find unique values for numpy arrays that correctly accounts for nans. See `_unique` documentation for details.)NNxpNrr) r unique_allunique_inverse unique_counts unique_valuessizer rnansumlen) rrrr_inversecountsuniquesnan_idxrets rrr=s & !EB OG-&(mmF&;#GV ,,V4 **62""6*|| gbk22B7-GaK( )0G% &  ffVH%56FOMgk*F *C z yX]3q6++rc4\rSrSr%Sr\\S'\\S'SrSrg) MissingValuesdz'Data class for missing data informationr"nonec/nUR(aURS5 UR(aUR[R5 U$)z3Convert tuple to a list where None is always first.N)r.appendr"np)selfoutputs rto_listMissingValues.to_listjs6 99 MM$  88 MM"&& ! rN) __name__ __module__ __qualname____firstlineno____doc__bool__annotations__r4__static_attributes__r6rrr,r,ds1 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)r"r.rT)r r,r$)rvaluemissing_values_setoutput_missing_valuesr3s r_extract_missingrCts""!%]mE6J6 }U;;; !! ! "a '$1e$$G !%2d$F ! -$U C (F  (('s A6A6c2^\rSrSrSrU4SjrSrSrU=r$)_nandictz!Dictionary with support for nans.c>[TU]U5 UR5Hup#[U5(dMX0l g gN)super__init__itemsr nan_value)r2mappingkeyr@ __class__s rrJ_nandict.__init__s5 !!--/JCS!!!&*rcr[US5(a[U5(a UR$[U5e)NrL)hasattrr rLKeyErrorr2rNs r __missing___nandict.__missing__- 4 % %-*<*<>> !smr)rL) r7r8r9r:r;rJrUr> __classcell__rOs@rrErEs+rrEc[X5up#[[U5VVs0sHupEXT_M snn5nURUVs/sHovUPM sn[ U5S9$s snnfs snf)z,Map values based on its position in uniques.)r )r rE enumerateasarrayr )rr(rr%ivaltablevs r_map_to_integerrasb & *EB 9W+=>+=cf+=> ?E ::0AQx0: HH?0s A# A)c[U5n[U5up4[U5nURUR 55 [ R "XPRS9nU4nU(aU[X54- nU(aU[X54- n[U5S:XaUS$U$![a1 [S[SU5555n[SU35ef=f)Nrc38# UHoRv M g7frH)r9).0ts r !_unique_python..sL/K!~~/Kc38# UHn[U5v M g7frH)type)rer`s rrgrhs2KFq477FrizPEncoders require their input argument must be uniformly strings or numbers. Got rr) setrCsortedextendr4r1arrayr TypeErrorra _get_countsr$)rrr uniques_setmissing_valuesr(typesr*s rrrs  &k &6{&C# %~--/0((7,,7 *C 022 F,..X]3q6++  Ls2KF2K/KLL '',g /   s A B'';C"T) check_unknownc[X5up4URURS5(d [X5$U(a [ X5nU(a[ SU35e[XUS9$![an[ SU35eSnAff=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 numericz%y contains previously unseen labels: Nr)r isdtyperrarS ValueError_check_unknownr)rr(rurr%ediffs r_encoder}s: & *EB ::fllI . . J"63 3 !&2D #H!OPPW44 JDQCHI I Js A,, B 6BB c^^[X5up4SnURURS5(Gd6[U5n[ U5upg[U5m[ T5ummUT- nUR =(a TR (+n UR =(a TR (+n UU4Sjn U(a`U(dU (dU (a(URUV s/sH o"U 5PM sn 5nO#UR[U5URS9n[U5nU (aURS5 U (aUR[R 5 OURU5n [R "XSUS9nU(aAUR"(a [%XU5nO#UR[U5URS9nUR'UR)U55(aYUR)U5nUR'U5(a2UR"(aU(aUR)U5nSX_'X)n[U5nU(aX4$U$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``. Nrwc>UT;=(d< TR=(a USL=(d TR=(a [U5$rH)r.r"r )r@missing_in_uniquesrrs ris_valid _check_unknown..is_validsA$E&++= E&**C}U/C rrcT) assume_uniquerr)r rxrrlrCr"r.roonesr$r<listr0r1r r setdiff1dr!ranyisnan)r known_values return_maskrr% valid_mask values_setmissing_in_valuesr| nan_in_diff none_in_diffrr@r diff_is_nanis_nanrrrs @@rrzrzs2 & /EBJ ::fllI . .[ (8(D% ,' *:;*G' 'K''++J4F4J4J0J (--M6H6M6M2M   {lXXF&KF5xF&KL WWS[W@ Dz  KK   KK ((0 }}]QST yy"6< WWS[W@  66"((<( ) )((4.Kvvk""99XXf-F)*J&L)Dz KC'Ls$I.c8^\rSrSrSrU4SjrSrSrSrU=r $) _NaNCounteriJz$Counter with support for nan values.cB>[TU]URU55 grH)rIrJ_generate_items)r2rKrOs rrJ_NaNCounter.__init__Ms --e45rc## UHFn[U5(dUv M[US5(dSUlU=RS- slMH g7f)z>Generate items without nans. Stores the nan counts separately. nan_countrrN)r rRr)r2rKitems rr_NaNCounter._generate_itemsPsDD && 4--!" NNa N sAAcr[US5(a[U5(a UR$[U5e)Nr)rRr rrSrTs rrU_NaNCounter.__missing__ZrWr)r) r7r8r9r:r;rJrrUr>rXrYs@rrrJs.6 rrc|URRS;ak[U5n[R"[ U5[R S9n[U5H#upE[[5 X%X4'SSS5 M% U$[USS9upg[R"XSS9n[R"US5(a#[R"US5(aSUS'[R"XaU5n [R"U[R S9nXyX8'U$!,(df  M=f)zGet the count of each of the `uniques` in `values`. The counts will use the order passed in by `uniques`. For non-object dtypes, `uniques` is assumed to be sorted and `np.nan` is at the end. OUrcNT)r)rr)rkindrr1zerosr$int64r[rrSrisinr searchsorted zeros_like) rr(counterr3r]rr r'uniques_in_valuesunique_valid_indicess rrqrq`s ||D f%#g,bhh7 )GA(##M $#* &vTBMdK xx b!""rxx '<'< $"??=BS:TU ]]7"(( 3F & rs $',5&R$,N J  #)L t  I,4/3(5VQh',r