0Ph:V jddlZddlZddlZddlmZddlmZmZddlZ ddl m Z ddl m Z mZddlmZmZddlmZdd lmZmZmZmZmZmZmZd Zd Zd Zd Zd!dZ dddZ!ddddZ"dZ#dZ$dZ%edgeej&ddddgdggdddddddddZ'dddd Z(dS)"N)UserList)compressislice)issparse)_is_numpy_namespace get_namespace)Intervalvalidate_params)_approximate_mode)_is_arraylike_not_scalar _is_pandas_df_is_polars_df_or_series_use_interchange_protocol check_arraycheck_consistent_lengthcheck_random_statec,t|\}}|r||||St|r|dkrtj|}t |t rt|}|dkr ||dfn |dd|fS)zAIndex an array or scipy.sparse consistently across NumPy version.axisboolr.N)r takernpasarray isinstancetuplelist)arraykey key_dtyperxp is_array_apis W/var/www/html/test/jupyter/venv/lib/python3.11/site-packages/sklearn/utils/_indexing.py_array_indexingr$s$U++B .wwucw---9..joo#u3ii"aii5c??U111c6]:c(t|rtj|}|dkr@t|ts+tj|s|||S|dkr|jn|j}|r |dd|fn||S)z%Index a pandas dataframe or a series.intrN) r rrrsliceisscalarrilocloc)Xrr rindexers r#_pandas_indexingr.'s$$jooE:c5#9#9R[=M=Mvvcv%%%&..!&&AE"&8wqqq#vGCL8r%ctj|st|tr|S|dkrt t |Sfd|DS)zIndex a Python list.rc g|] }| Sr1).0idxr,s r# z"_list_indexing..?s " " "sAcF " " "r%)rr)rr(rr)r,rr s` r#_list_indexingr56sl {3:c511v FHQ$$%%% " " " "c " " ""r%c t|tjr|}n8tj|s$t|t st |}|dkr |dd|fS|dkr||S||}tj|rRt|j dkr:tj d}| | dS|S)z,Indexing X with polars interchange protocol.rNrpolarsr)rrndarraytolistr)r(rfilterlenshapesysmodulesSeriesrow)r,rr r X_indexedpls r#_polars_indexingrDBs#rz""jjllk#*S%"8"83ii qyyCyFxx}}#I {3+CLLA--[ "yyq))*** r%Tcd}tdtdtdtjdi}ddddddd}|dSt |t |r3 |t|S#t$rt|wxYwt |trh|std|j |jdSt|j }t|j}||||krt|||S|St |t t t"frUt%|}d|D}|sdSt'|d krt||St+|d rt-|\} } | rXt/| sI| |jdrdS| |jd rdSt| ||jjS#t$rt|wxYwt|) asDetermine the data type of key. Parameters ---------- key : scalar, slice or array-like The key from which we want to infer the data type. accept_slice : bool, default=True Whether or not to raise an error if the key is a slice. Returns ------- dtype : {'int', 'str', 'bool', None} Returns the data type of key. z~No valid specification of the columns. Only a scalar, list or slice of all integers or all strings, or boolean mask is allowedr'strr)iubOUSNzBOnly array-like or scalar are supported. A Python slice was given.c,h|]}t|Sr1)_determine_key_type)r2elts r# z&_determine_key_type..s!CCC',,CCCr%rdtypeintegral)r'rFrrbool_rrkeystypeKeyError ValueErrorr( TypeErrorstartstoprNrrsetr<pophasattrr risdtyperQkind) r accept_sliceerr_msg dtype_to_strarray_dtype_to_strkey_start_type key_stop_type unique_keykey_typer!r"s r#rNrN_s"  UD&"(FKL        {t#u\..001122& &S * * & & &W%% % &#u T  9 !14,SY77+CH55  %-*C.. )))  %! !#eX.//XX CC CCC 4 x==A  W%% %||~~sG*(--L  * 3B 7 7 *zz#)V,, *vCIz22 *u ))) *)#).99 * * * ))) * W  s#A88BHH2rcB||S|dvr"td|t|}|dkr|dkrtd|dkr$t|trtd|dkrjt |d rZt |jd krBtd t|t |j|dkr3|dkr-t|st|std t |d rt||||St|rt||||St |d rt||||St|||S)aXReturn rows, items or columns of X using indices. .. warning:: This utility is documented, but **private**. This means that backward compatibility might be broken without any deprecation cycle. Parameters ---------- X : array-like, sparse-matrix, list, pandas.DataFrame, pandas.Series Data from which to sample rows, items or columns. `list` are only supported when `axis=0`. indices : bool, int, str, slice, array-like - If `axis=0`, boolean and integer array-like, integer slice, and scalar integer are supported. - If `axis=1`: - to select a single column, `indices` can be of `int` type for all `X` types and `str` only for dataframe. The selected subset will be 1D, unless `X` is a sparse matrix in which case it will be 2D. - to select multiples columns, `indices` can be one of the following: `list`, `array`, `slice`. The type used in these containers can be one of the following: `int`, 'bool' and `str`. However, `str` is only supported when `X` is a dataframe. The selected subset will be 2D. axis : int, default=0 The axis along which `X` will be subsampled. `axis=0` will select rows while `axis=1` will select columns. Returns ------- subset Subset of X on axis 0 or 1. Notes ----- CSR, CSC, and LIL sparse matrices are supported. COO sparse matrices are not supported. Examples -------- >>> import numpy as np >>> from sklearn.utils import _safe_indexing >>> data = np.array([[1, 2], [3, 4], [5, 6]]) >>> _safe_indexing(data, 0, axis=0) # select the first row array([1, 2]) >>> _safe_indexing(data, 0, axis=1) # select the first column array([1, 3, 5]) N)rrzR'axis' should be either 0 (to index rows) or 1 (to index column). Got {} instead.rrFz.String indexing is not supported with 'axis=0'rz!axis=1 is not supported for listsr=r7z'X' should be a 2D NumPy array, 2D sparse matrix or dataframe when indexing the columns (i.e. 'axis=1'). Got {} instead with {} dimension(s).FSpecifying the columns using strings is only supported for dataframes.r*r)rWformatrNrrr]r<r=rUrrr.rrDr$r5)r,indicesr indices_dtypes r#_safe_indexingrmsf 6 ((.t    (00M qyy]e++IJJJ qyyZ4((y<=== qyyWQ((yS\\Q->-> 3396$q''3qw<<3P3P     U " "q!! #%>q%A%A # T   q& 9 7MEEEE  # #97MEEEE G  9q'=tDDDDa-888r%) row_indexercolumn_indexerc0|tdddn|}|tdddn|}t|drTtj5tjdt ||j||f<ddddS#1swxYwYdS||||f<dS)anSafe assignment to a numpy array, sparse matrix, or pandas dataframe. Parameters ---------- X : {ndarray, sparse-matrix, dataframe} Array to be modified. It is expected to be 2-dimensional. values : ndarray The values to be assigned to `X`. row_indexer : array-like, dtype={int, bool}, default=None A 1-dimensional array to select the rows of interest. If `None`, all rows are selected. column_indexer : array-like, dtype={int, bool}, default=None A 1-dimensional array to select the columns of interest. If `None`, all columns are selected. Nr*ignore)r(r]warningscatch_warnings simplefilter FutureWarningr*)r,valuesrnros r# _safe_assignrws&.9-@%dD)))kK#1#9dD$~q& 0  $ & & 9 9  !(M : : :28AF;. / 9 9 9 9 9 9 9 9 9 9 9 9 9 9 9 9 9 9*0+~ %&&&s'BB Bc ttj||}n,#t$r}t d|dz d|d|d}~wwxYwtj|S)Nzall features must be in [0, rz] or [-z, 0])rmrarange IndexErrorrW atleast_1dr:)r n_columnsr3es r##_get_column_indices_for_bool_or_intr~8sRYy11377  P9q= P P P P P    =   $ $ & &&s"% AA  Act|}t|r#t|||S|jd}t |t tfr|sgS|dvrt||S |j }n#t$rtdwxYwt |tr|g}nt |trp|j|j}}|||}|||dz}n|dz}t t#t%|||St |} g}|D]Y} || } t | t&jstd|d|| Zn"#t,$r} td| d} ~ wwxYw|S)zGet feature column indices for input data X and key. For accepted values of `key`, see the docstring of :func:`_safe_indexing`. rrr'riNzSelected columns, z, are not unique in dataframe/A given column is not a column of the dataframe)rNr_get_column_indices_interchange __dataframe__r=rrrr~columnsAttributeErrorrWrFr(rYrZget_locrrangenumbersIntegralappendrV) r,rr r| all_columnsrrYrZcolumn_indicescolcol_idxr}s r#_get_column_indicesrCs. $C((I ##R.q/@/@#yQQQ I#e}%%(c( o % %23 BBB )KK   X   c3   eGG U # # )SX4E #++E22"**40014 1}uY//==>> >3iiG WN / /%--c22!'7+;<<$SWSSS%%g....  / W W WNOOUV V Ws%B B&AF66 GGGc|}t|ttfr|sgS|dvrt ||St|t|t r|jdvrtd|j |j }}| |}| |dz}n|dz}ttt|||Stj|r|gn|} fd|DS#t $r}t!d|d}~wwxYw)zBSame as _get_column_indices but for X with __dataframe__ protocol.r)rNzkey.step must be 1 or NoneNrc:g|]}|Sr1)index)r2r column_namess r#r4z3_get_column_indices_interchange..s'HHHL&&s++HHHr%r) num_columnsrrrr~rr(stepNotImplementedErrorrYrZrrrrr)rW) X_interchangerr r|rYrZselected_columnsr}rs @r#rrys~))++I#e}%%WcW o % %23 BBBM668899 c5 ! ! ?xy(()*FGGG)SX4E $**511#))$//!3 1}uY//==>> >$&K$4$4=C55# WHHHH7GHHH H W W WNOOUV V Ws" D00 E:E  Ebooleanleft)closed random_state)z array-likez sparse matrixN)replace n_samplesrstratify)prefer_skip_nested_validationcx|}t|}t|dkrdS|d}t|dr |jdnt|}||}n||kr|st d||fzt ||R|r|d||fn`tj|| d|n+t|dd}|j dkrtj d |D}tj |d \}} |jd} tj| } tjtj| d tj| dd} t%| ||} gt'| D];}|| || ||}|<|d|D}fd|D}t|dkr|dS|S)aW Resample arrays or sparse matrices in a consistent way. The default strategy implements one step of the bootstrapping procedure. Parameters ---------- *arrays : sequence of array-like of shape (n_samples,) or (n_samples, n_outputs) Indexable data-structures can be arrays, lists, dataframes or scipy sparse matrices with consistent first dimension. replace : bool, default=True Implements resampling with replacement. If False, this will implement (sliced) random permutations. n_samples : int, default=None Number of samples to generate. If left to None this is automatically set to the first dimension of the arrays. If replace is False it should not be larger than the length of arrays. random_state : int, RandomState instance or None, default=None Determines random number generation for shuffling the data. Pass an int for reproducible results across multiple function calls. See :term:`Glossary `. stratify : {array-like, sparse matrix} of shape (n_samples,) or (n_samples, n_outputs), default=None If not None, data is split in a stratified fashion, using this as the class labels. Returns ------- resampled_arrays : sequence of array-like of shape (n_samples,) or (n_samples, n_outputs) Sequence of resampled copies of the collections. The original arrays are not impacted. See Also -------- shuffle : Shuffle arrays or sparse matrices in a consistent way. Examples -------- It is possible to mix sparse and dense arrays in the same run:: >>> import numpy as np >>> X = np.array([[1., 0.], [2., 1.], [0., 0.]]) >>> y = np.array([0, 1, 2]) >>> from scipy.sparse import coo_matrix >>> X_sparse = coo_matrix(X) >>> from sklearn.utils import resample >>> X, X_sparse, y = resample(X, X_sparse, y, random_state=0) >>> X array([[1., 0.], [2., 1.], [1., 0.]]) >>> X_sparse >>> X_sparse.toarray() array([[1., 0.], [2., 1.], [1., 0.]]) >>> y array([0, 1, 0]) >>> resample(y, n_samples=2, random_state=0) array([0, 1]) Example using stratification:: >>> y = [0, 0, 1, 1, 1, 1, 1, 1, 1] >>> resample(y, n_samples=5, replace=False, stratify=y, ... random_state=0) [1, 1, 1, 0, 1] rNr=z@Cannot sample %d out of arrays with dim %d when replace is False)sizeF) ensure_2drQr7c^g|]*}d|d+S) rF)joinastype)r2rAs r#r4zresample..s0CCC##((3::e#4#455CCCr%T)return_inverse mergesort)r_)rcXg|]'}t|r|n|(Sr1)rtocsr)r2as r#r4zresample..1s/ > > >!8A;;-aggiiiA > > >r%c0g|]}t|Sr1)rm)r2rrks r#r4zresample..2s#CCCqq'22CCCr%r)rr<r]r=rWrrandintrryshufflerndimruniquebincountsplitargsortcumsumr rchoiceextend permutation)rrrrarrays max_n_samplesfirstyclasses y_indices n_classes class_counts class_indicesn_irG indices_iresampled_arraysrks @r#resamplers|M%l33L 6{{at 1IE")%"9"9I As5zzI! ) # #g # Ni( )   V$$  ."**1i}>N*OOGGi **G   ) ) )n}n-GG E > > > 6Q;;CCCCCDDAYq>>>M!$ {9--  Jy{ 3 3 3RY|5L5LSbS5Q   m\JJy!! & &A$++M!,v > > >FCCCCFCCC !!""r%)rrct|d||dS)aShuffle arrays or sparse matrices in a consistent way. This is a convenience alias to ``resample(*arrays, replace=False)`` to do random permutations of the collections. Parameters ---------- *arrays : sequence of indexable data-structures Indexable data-structures can be arrays, lists, dataframes or scipy sparse matrices with consistent first dimension. random_state : int, RandomState instance or None, default=None Determines random number generation for shuffling the data. Pass an int for reproducible results across multiple function calls. See :term:`Glossary `. n_samples : int, default=None Number of samples to generate. If left to None this is automatically set to the first dimension of the arrays. It should not be larger than the length of arrays. Returns ------- shuffled_arrays : sequence of indexable data-structures Sequence of shuffled copies of the collections. The original arrays are not impacted. See Also -------- resample : Resample arrays or sparse matrices in a consistent way. Examples -------- It is possible to mix sparse and dense arrays in the same run:: >>> import numpy as np >>> X = np.array([[1., 0.], [2., 1.], [0., 0.]]) >>> y = np.array([0, 1, 2]) >>> from scipy.sparse import coo_matrix >>> X_sparse = coo_matrix(X) >>> from sklearn.utils import shuffle >>> X, X_sparse, y = shuffle(X, X_sparse, y, random_state=0) >>> X array([[0., 0.], [2., 1.], [1., 0.]]) >>> X_sparse >>> X_sparse.toarray() array([[0., 0.], [2., 1.], [1., 0.]]) >>> y array([2, 1, 0]) >>> shuffle(y, n_samples=2, random_state=0) array([0, 1]) F)rrr)r)rrrs r#rr:s%D  ),   r%)T))rr>rr collectionsr itertoolsrrnumpyr scipy.sparser _array_apirr _param_validationr r extmathr validationr rrrrrrr$r.r5rDrNrmrwr~rrrrrr1r%r#rs  &&&&&&&&!!!!!!::::::::88888888&&&&&& ; ; ; 9 9 9 # # #:QQQQh()]9]9]9]9]9@,0"0"0"0"0"0J'''333lWWWD;hw/DHHH$O'(999  #'#dPTS S S S S l#'$DDDDDDDr%