Ugx ddlZddlZddlZddlmZddlmZddlZddl m Z ddl m Z mZmZddlmZddlmZmZddlmZmZdd lmZmZdd lmZdd lmZmZm Z gd Z!Gd dee dZ"Gddee dZ#eddgdgeedddgeedddgdgdddddddZ$dZ%dZ&Gd d!ee dZ'dS)"N) defaultdict)Integral) BaseEstimatorTransformerMixin _fit_context) column_or_1d)_encode_unique)Intervalvalidate_params)type_of_target unique_labels) min_max_axis) _num_samples check_arraycheck_is_fitted)label_binarizeLabelBinarizer LabelEncoderMultiLabelBinarizerc0eZdZdZdZdZdZdZdZdS)raEncode target labels with value between 0 and n_classes-1. This transformer should be used to encode target values, *i.e.* `y`, and not the input `X`. Read more in the :ref:`User Guide `. .. versionadded:: 0.12 Attributes ---------- classes_ : ndarray of shape (n_classes,) Holds the label for each class. See Also -------- OrdinalEncoder : Encode categorical features using an ordinal encoding scheme. OneHotEncoder : Encode categorical features as a one-hot numeric array. Examples -------- `LabelEncoder` can be used to normalize labels. >>> from sklearn.preprocessing import LabelEncoder >>> le = LabelEncoder() >>> le.fit([1, 2, 2, 6]) LabelEncoder() >>> le.classes_ array([1, 2, 6]) >>> le.transform([1, 1, 2, 6]) array([0, 0, 1, 2]...) >>> le.inverse_transform([0, 0, 1, 2]) array([1, 1, 2, 6]) It can also be used to transform non-numerical labels (as long as they are hashable and comparable) to numerical labels. >>> le = LabelEncoder() >>> le.fit(["paris", "paris", "tokyo", "amsterdam"]) LabelEncoder() >>> list(le.classes_) [np.str_('amsterdam'), np.str_('paris'), np.str_('tokyo')] >>> le.transform(["tokyo", "tokyo", "paris"]) array([2, 2, 1]...) >>> list(le.inverse_transform([2, 2, 1])) [np.str_('tokyo'), np.str_('tokyo'), np.str_('paris')] cPt|d}t||_|S)zFit label encoder. Parameters ---------- y : array-like of shape (n_samples,) Target values. Returns ------- self : returns an instance of self. Fitted label encoder. Twarnr r classes_selfys [/var/www/surfInsights/venv3-11/lib/python3.11/site-packages/sklearn/preprocessing/_label.pyfitzLabelEncoder.fitTs(  & & &   cZt|d}t|d\|_}|S)aFit label encoder and return encoded labels. Parameters ---------- y : array-like of shape (n_samples,) Target values. Returns ------- y : array-like of shape (n_samples,) Encoded labels. Trreturn_inverserrs r! fit_transformzLabelEncoder.fit_transformes4  & & &"1T::: qr#ct|t||jjd}t |dkrt jgSt||jS)aTransform labels to normalized encoding. Parameters ---------- y : array-like of shape (n_samples,) Target values. Returns ------- y : array-like of shape (n_samples,) Labels as normalized encodings. T)dtyperr)uniques)rr rr)rnparrayr rs r! transformzLabelEncoder.transformvs_  $-"5D A A A ??a  8B<< q$-0000r#ct|t|d}t|dkrtjgStj|tjt|j}t|rtdt|ztj |}|j|S)a Transform labels back to original encoding. Parameters ---------- y : ndarray of shape (n_samples,) Target values. Returns ------- y : ndarray of shape (n_samples,) Original encoding. Trrz'y contains previously unseen labels: %s) rr rr+r, setdiff1darangelenr ValueErrorstrasarray)rr diffs r!inverse_transformzLabelEncoder.inverse_transforms   & & & ??a  8B<< |AryT]););<<== t99 TFTRSS S JqMM}Qr#c ddgiSNX_types1dlabelsrs r! _more_tagszLabelEncoder._more_tagsJ<((r#N) __name__ __module__ __qualname____doc__r"r'r-r6r=r;r#r!rr"sj//b""111*   2)))))r#r)auto_wrap_output_keysceZdZUdZegegdgdZeed<dddddZe d d Z d Z d Z ddZ dZdS)ra Binarize labels in a one-vs-all fashion. Several regression and binary classification algorithms are available in scikit-learn. A simple way to extend these algorithms to the multi-class classification case is to use the so-called one-vs-all scheme. At learning time, this simply consists in learning one regressor or binary classifier per class. In doing so, one needs to convert multi-class labels to binary labels (belong or does not belong to the class). `LabelBinarizer` makes this process easy with the transform method. At prediction time, one assigns the class for which the corresponding model gave the greatest confidence. `LabelBinarizer` makes this easy with the :meth:`inverse_transform` method. Read more in the :ref:`User Guide `. Parameters ---------- neg_label : int, default=0 Value with which negative labels must be encoded. pos_label : int, default=1 Value with which positive labels must be encoded. sparse_output : bool, default=False True if the returned array from transform is desired to be in sparse CSR format. Attributes ---------- classes_ : ndarray of shape (n_classes,) Holds the label for each class. y_type_ : str Represents the type of the target data as evaluated by :func:`~sklearn.utils.multiclass.type_of_target`. Possible type are 'continuous', 'continuous-multioutput', 'binary', 'multiclass', 'multiclass-multioutput', 'multilabel-indicator', and 'unknown'. sparse_input_ : bool `True` if the input data to transform is given as a sparse matrix, `False` otherwise. See Also -------- label_binarize : Function to perform the transform operation of LabelBinarizer with fixed classes. OneHotEncoder : Encode categorical features using a one-hot aka one-of-K scheme. Examples -------- >>> from sklearn.preprocessing import LabelBinarizer >>> lb = LabelBinarizer() >>> lb.fit([1, 2, 6, 4, 2]) LabelBinarizer() >>> lb.classes_ array([1, 2, 4, 6]) >>> lb.transform([1, 6]) array([[1, 0, 0, 0], [0, 0, 0, 1]]) Binary targets transform to a column vector >>> lb = LabelBinarizer() >>> lb.fit_transform(['yes', 'no', 'no', 'yes']) array([[1], [0], [0], [1]]) Passing a 2D matrix for multilabel classification >>> import numpy as np >>> lb.fit(np.array([[0, 1, 1], [1, 0, 0]])) LabelBinarizer() >>> lb.classes_ array([0, 1, 2]) >>> lb.transform([0, 1, 2, 1]) array([[1, 0, 0], [0, 1, 0], [0, 0, 1], [0, 1, 0]]) boolean neg_label pos_label sparse_output_parameter_constraintsrFc0||_||_||_dSNrF)rrGrHrIs r!__init__zLabelBinarizer.__init__s""*r#Tprefer_skip_nested_validationc|j|jkr td|jd|jd|jr5|jdks |jdkrtd|jd|jt |d|_d |jvrtd t |dkrtd |ztj||_ t||_ |S) aaFit label binarizer. Parameters ---------- y : ndarray of shape (n_samples,) or (n_samples, n_classes) Target values. The 2-d matrix should only contain 0 and 1, represents multilabel classification. Returns ------- self : object Returns the instance itself. z neg_label=z& must be strictly less than pos_label=.rz`Sparse binarization is only supported with non zero pos_label and zero neg_label, got pos_label=z and neg_label=r ) input_name multioutput@Multioutput target data is not supported with label binarizationy has 0 samples: %r) rGrHr2rIry_type_rspissparse sparse_input_rrrs r!r"zLabelBinarizer.fit s. >T^ + +/T^//!^///    4>Q#6#6$.A:M:MM!^MM<@NMM  &aC888 DL ( (R  ??a  2Q677 7[^^%a((  r#cR|||S)aFit label binarizer/transform multi-class labels to binary labels. The output of transform is sometimes referred to as the 1-of-K coding scheme. Parameters ---------- y : {ndarray, sparse matrix} of shape (n_samples,) or (n_samples, n_classes) Target values. The 2-d matrix should only contain 0 and 1, represents multilabel classification. Sparse matrix can be CSR, CSC, COO, DOK, or LIL. Returns ------- Y : {ndarray, sparse matrix} of shape (n_samples, n_classes) Shape will be (n_samples, 1) for binary problems. Sparse matrix will be of CSR format. )r"r-rs r!r'zLabelBinarizer.fit_transform5s"(xx{{$$Q'''r#c t|t|d}|r)|jdst dt ||j|j|j|j S)aTransform multi-class labels to binary labels. The output of transform is sometimes referred to by some authors as the 1-of-K coding scheme. Parameters ---------- y : {array, sparse matrix} of shape (n_samples,) or (n_samples, n_classes) Target values. The 2-d matrix should only contain 0 and 1, represents multilabel classification. Sparse matrix can be CSR, CSC, COO, DOK, or LIL. Returns ------- Y : {ndarray, sparse matrix} of shape (n_samples, n_classes) Shape will be (n_samples, 1) for binary problems. Sparse matrix will be of CSR format. multilabelz0The object was not fitted with multilabel input.)classesrHrGrI) rr startswithrWr2rrrHrGrI)rr y_is_multilabels r!r-zLabelBinarizer.transformKs( (++66|DD  Q4<#:#:<#H#H QOPP P Mnn,     r#NcNt|||j|jzdz }|jdkrt ||j}nt ||j|j|}|jrtj |}n(tj |r| }|S)aTransform binary labels back to multi-class labels. Parameters ---------- Y : {ndarray, sparse matrix} of shape (n_samples, n_classes) Target values. All sparse matrices are converted to CSR before inverse transformation. threshold : float, default=None Threshold used in the binary and multi-label cases. Use 0 when ``Y`` contains the output of :term:`decision_function` (classifier). Use 0.5 when ``Y`` contains the output of :term:`predict_proba`. If None, the threshold is assumed to be half way between neg_label and pos_label. Returns ------- y : {ndarray, sparse matrix} of shape (n_samples,) Target values. Sparse matrix will be of CSR format. Notes ----- In the case when the binary labels are fractional (probabilistic), :meth:`inverse_transform` chooses the class with the greatest value. Typically, this allows to use the output of a linear model's :term:`decision_function` method directly as the input of :meth:`inverse_transform`. Ng@ multiclass) rrHrGrW_inverse_binarize_multiclassr_inverse_binarize_thresholdingrZrX csr_matrixrYtoarray)rY thresholdy_invs r!r6z LabelBinarizer.inverse_transformms@   $.8C?I << ' '0DMBBEE24< E   $M%((EE [   $MMOOE r#c ddgiSr8r;r<s r!r=zLabelBinarizer._more_tagsr>r#rM)r?r@rArBrrJdict__annotations__rNrr"r'r-r6r=r;r#r!rrsVVrZZ#$$D %&%+++++ \555&&65&P(((,    D1111f)))))r#r array-likez sparse matrixneither)closedrE)r r^rGrHrITrOrKFrFcxt|tst|dddd}n%t|dkrt d|z||kr#t d|||r/|dks|dkr#t d |||dk}|r| }t |}d |vrt d |d krt d tj|r |j dnt|}t|}tj |}|dkrk|dkrP|rtj |dftStjt|dft} | |z } | St|dkrd}tj|} |dkrmt#|dr |j dnt|d} |j| kr0t d|t'||dvrt)|}tj||} || } tj| | }tjdtj| f}tj|}||tj |||f||f} nh|dkrPtj |} |dkr5tj| j}|||| _nt d|z|sK| } | td} |dkr || | dk<|r d| | |k<n&| jtd| _tj|| kr!tj| |}| dd|f} |dkr7|r| d} n| dddf d} | S)aBinarize labels in a one-vs-all fashion. Several regression and binary classification algorithms are available in scikit-learn. A simple way to extend these algorithms to the multi-class classification case is to use the so-called one-vs-all scheme. This function makes it possible to compute this transformation for a fixed set of class labels known ahead of time. Parameters ---------- y : array-like or sparse matrix Sequence of integer labels or multilabel data to encode. classes : array-like of shape (n_classes,) Uniquely holds the label for each class. neg_label : int, default=0 Value with which negative labels must be encoded. pos_label : int, default=1 Value with which positive labels must be encoded. sparse_output : bool, default=False, Set to true if output binary array is desired in CSR sparse format. Returns ------- Y : {ndarray, sparse matrix} of shape (n_samples, n_classes) Shape will be (n_samples, 1) for binary problems. Sparse matrix will be of CSR format. See Also -------- LabelBinarizer : Class used to wrap the functionality of label_binarize and allow for fitting to classes independently of the transform operation. Examples -------- >>> from sklearn.preprocessing import label_binarize >>> label_binarize([1, 6], classes=[1, 2, 4, 6]) array([[1, 0, 0, 0], [0, 0, 0, 1]]) The class ordering is preserved: >>> label_binarize([1, 6], classes=[1, 6, 4, 2]) array([[1, 0, 0, 0], [0, 1, 0, 0]]) Binary targets transform to a column vector >>> label_binarize(['yes', 'no', 'no', 'yes'], classes=['no', 'yes']) array([[1], [0], [0], [1]]) r csrFN)rS accept_sparse ensure_2dr)rrVz7neg_label={0} must be strictly less than pos_label={1}.zuSparse binarization is only supported with non zero pos_label and zero neg_label, got pos_label={0} and neg_label={1}rTrUunknownz$The type of target data is not knownbinaryrKr)rbmultilabel-indicatorshapez:classes {0} mismatch with the labels {1} found in the data)rurbryz7%s target data is not supported with label binarization)copy)r|rK)! isinstancelistrrr2formatrrXrYryr1r+r4reintzerossorthasattrsizerr isin searchsortedhstackcumsum empty_likefilldatarfastypeanygetcolreshape)r r^rGrHrI pos_switchy_type n_samples n_classesrg sorted_class y_n_classes y_in_classesy_seenindicesindptrrs r!rrsuL a  8  #Ue4    ??a  2Q677 7I E L L9      )q..INN vi++    aJJ A  F N   ?@@@ k!nn8 #a&&IG Ij!!G  >> }i^3????Hc!ffa[444Y \\Q  !F77##L '''$+Aw$7$7FagajjS1YY <; & &LSS]1--  ))) OOwq'** </,77Ary66788}W%% ) M4&1)Y9O P P P ) ) ) M!   >>=((D IIi AF E N     0 IIKK HHSuH % % >>!Aa1fI  " !Aa9n s// vg%&&/,88 aaajM   * AA!!!R%  ))A Hr#c0tj|}tj|r|}|j\}}tj|}t|dd}tj|j }tj ||}tj ||j k}|ddkr(tj |t|j g}tj||j dd} tj |jdg} | || } d| tj|dkd<tj||dk|dkz} | D]N} |j|j | |j | dz}|tj||d| | <O|| S||ddS)z}Inverse label binarization transformation for multiclass. Multiclass uses the maximal score instead of a threshold. rKr|rN)axisclip)mode)r+r4rXrYtocsrryr0rr5rrepeat flatnonzerorappendr1rrwhereravelr/takeargmax)r r^r n_outputsoutputsrow_maxrow_nnzy_data_repeated_maxy_i_all_argmaxindex_first_argmax y_ind_ext y_i_argmaxsamplesiinds r!rcrcYs j!!G {1~~!; GGII w 9)I&&q!$$Q''!(## i99(;qv(EFF 2;!  Y~AF }EEN _^QXcrc]KKIai!-- ~.@AB 01 28GqL))!,-)I&&!  18L'MN C CA)AHQK!(1q5/9:C#BL#$>$>?BJqMMz""||AHH!H,,6|:::r#cd|dkrC|jdkr8|jddkr'td|j|dkr-|jdt |krtdt j|}tj|r|dkr[|jdvr| }t j |j |kt|_ | nQt j ||kt}nt j ||kt}|dkrtj|r|}|jdkr#|jddkr||d d dfSt |dkr(t j|dt |S||S|d kr|Std |) z=Inverse label binarization transformation using thresholding.rurrKz'output_type='binary', but y.shape = {0}zAThe number of class is not equal to the number of dimension of y.r)rqcscrvNrxz{0} format is not supported)ndimryr2rr1r+r4rXrYrr,rreliminate_zerosrfrr)r output_typer^rhs r!rdrdsh16Q;;171:>>BII!'RRSSSh171:W#=#= O   j!!G {1~~ / q==x~--GGIIXafy0<<>  A 6Q;;171:??1QQQT7# #7||q  ySVV444qwwyy)) . . .6==kJJKKKr#ceZdZUdZddgdgdZeed<ddddZed d Z ed d Z d Z dZ dZ dZdZdS)raTransform between iterable of iterables and a multilabel format. Although a list of sets or tuples is a very intuitive format for multilabel data, it is unwieldy to process. This transformer converts between this intuitive format and the supported multilabel format: a (samples x classes) binary matrix indicating the presence of a class label. Parameters ---------- classes : array-like of shape (n_classes,), default=None Indicates an ordering for the class labels. All entries should be unique (cannot contain duplicate classes). sparse_output : bool, default=False Set to True if output binary array is desired in CSR sparse format. Attributes ---------- classes_ : ndarray of shape (n_classes,) A copy of the `classes` parameter when provided. Otherwise it corresponds to the sorted set of classes found when fitting. See Also -------- OneHotEncoder : Encode categorical features using a one-hot aka one-of-K scheme. Examples -------- >>> from sklearn.preprocessing import MultiLabelBinarizer >>> mlb = MultiLabelBinarizer() >>> mlb.fit_transform([(1, 2), (3,)]) array([[1, 1, 0], [0, 0, 1]]) >>> mlb.classes_ array([1, 2, 3]) >>> mlb.fit_transform([{'sci-fi', 'thriller'}, {'comedy'}]) array([[0, 1, 1], [1, 0, 0]]) >>> list(mlb.classes_) ['comedy', 'sci-fi', 'thriller'] A common mistake is to pass in a list, which leads to the following issue: >>> mlb = MultiLabelBinarizer() >>> mlb.fit(['sci-fi', 'thriller', 'comedy']) MultiLabelBinarizer() >>> mlb.classes_ array(['-', 'c', 'd', 'e', 'f', 'h', 'i', 'l', 'm', 'o', 'r', 's', 't', 'y'], dtype=object) To correct this, the list of labels should be passed in as: >>> mlb = MultiLabelBinarizer() >>> mlb.fit([['sci-fi', 'thriller', 'comedy']]) MultiLabelBinarizer() >>> mlb.classes_ array(['comedy', 'sci-fi', 'thriller'], dtype=object) rmNrEr^rIrJFc"||_||_dSrMr)rr^rIs r!rNzMultiLabelBinarizer.__init__s *r#TrOcd|_|j:tttj|}nMtt|jt|jkrtd|j}td|Drtnt}tj t|||_||jdd<|S)aFit the label sets binarizer, storing :term:`classes_`. Parameters ---------- y : iterable of iterables A set of labels (any orderable and hashable object) for each sample. If the `classes` parameter is set, `y` will not be iterated. Returns ------- self : object Fitted estimator. NztThe classes argument contains duplicate classes. Remove these duplicates before passing them to MultiLabelBinarizer.c3@K|]}t|tVdSrMr}r.0cs r! z*MultiLabelBinarizer.fit..s,??!:a--??????r#rv) _cached_dictr^sortedset itertoolschain from_iterabler1r2allrobjectr+emptyr)rr r^r)s r!r"zMultiLabelBinarizer.fits ! < S!>!>q!A!ABBCCGG T\"" # #c$,&7&7 7 7/  lG??w?????KVWU;;; " aaa r#c~|j(|||Sd|_t t }|j|_|||}t||j }td|Drt nt}tjt||}||dd<tj|d\|_}tj||j|jj|_|js|}|S)aMFit the label sets binarizer and transform the given label sets. Parameters ---------- y : iterable of iterables A set of labels (any orderable and hashable object) for each sample. If the `classes` parameter is set, `y` will not be iterated. Returns ------- y_indicator : {ndarray, sparse matrix} of shape (n_samples, n_classes) A matrix such that `y_indicator[i, j] = 1` iff `classes_[j]` is in `y[i]`, and 0 otherwise. Sparse matrix will be of CSR format. Nkeyc3@K|]}t|tVdSrMrrs r!rz4MultiLabelBinarizer.fit_transform..9s,;;!:a--;;;;;;r#rvTr%)r^r"r-rrr__len__default_factory _transformrgetrrr+rr1uniquerr4rr)rIrf)rr class_mappingyttmpr)inverses r!r'z!MultiLabelBinarizer.fit_transforms$ < #88A;;((++ + $C(( (5(= % __Q . .] (9:::;;s;;;;;GS777  aaa!#=!N!N!N wZ 32:;KLLL ! B r#ct||}|||}|js|}|S)aTransform the given label sets. Parameters ---------- y : iterable of iterables A set of labels (any orderable and hashable object) for each sample. If the `classes` parameter is set, `y` will not be iterated. Returns ------- y_indicator : array or CSR matrix, shape (n_samples, n_classes) A matrix such that `y_indicator[i, j] = 1` iff `classes_[j]` is in `y[i]`, and 0 otherwise. )r _build_cacherrIrf)rr class_to_indexrs r!r-zMultiLabelBinarizer.transformEsS **,, __Q / /! B r#c |jFtt|jt t |j|_|jSrM)rrkziprranger1r<s r!rz MultiLabelBinarizer._build_cache_sB   $ $Sc$->P>P8Q8Q%R%R S SD   r#ctjd}tjddg}t}|D]}t}|D]C} |||#t$r||Y@wxYw|||t ||r;tjd t|ttj t |t} tj| ||ft |dz t |fS)a/Transforms the label sets with a given mapping. Parameters ---------- y : iterable of iterables A set of labels (any orderable and hashable object) for each sample. If the `classes` parameter is set, `y` will not be iterated. class_mapping : Mapping Maps from label to column index in label indicator matrix. Returns ------- y_indicator : sparse matrix of shape (n_samples, n_classes) Label indicator matrix. Will be of CSR format. rrz%unknown class(es) {0} will be ignoredrrvrKrz)r,raddKeyErrorextendrr1warningsrrrr3r+onesrrXre) rr rrrrtlabelsindexlabelrs r!rzMultiLabelBinarizer._transformesh$+c""S1#&&%% ( (FEEE ' ''IImE23333'''KK&&&&&' NN5 ! ! ! MM#g,, ' ' ' '   M7>>vgSV?W?W?WXX   ws7||3///} 7F #CKK!OS=O=O+P    sA,,B Bctjdtjkr@t dtjjdt jrtj dkrz9MultiLabelBinarizer.inverse_transform..sPE3dm((E#I)>??@@r#Nr|z8Expected only 0s and 1s in label indicator. Also got {0}c^g|])}tj|*Sr;)rrcompress)r indicatorsrs r!rz9MultiLabelBinarizer.inverse_transform..s1SSS*E$-00<<==SSSr#)rryr1rr2rrXrYrrr+r/rr)rr unexpecteds`` r!r6z%MultiLabelBinarizer.inverse_transforms  8A;#dm,, , ,AHH &&   ;r?? TB27||q  Sbg1v)F)F%G%G!%K%K !NOOO"%binbim"D"D  b1a&11J:"" NUU" TSSSPRSSS Sr#c ddgiS)Nr92dlabelsr;r<s r!r=zMultiLabelBinarizer._more_tagsr>r#)r?r@rArBrJrkrlrNrr"r'r-rrr6r=r;r#r!rrs<<~!$'#$$D #'e+++++\55565@\555))65)V4!!! & & & P'T'T'TR)))))r#r)(r,rr collectionsrnumbersrnumpyr+ scipy.sparsesparserXbaserrrutilsr utils._encoder r utils._param_validationr r utils.multiclassrrutils.sparsefuncsrutils.validationrrr__all__rrrrcrdrr;r#r!rs ######@@@@@@@@@@ ,,,,,,,,????????<<<<<<<<,,,,,,IIIIIIIIII   C)C)C)C)C)#]$C)C)C)C)Ly)y)y)y)y)%}Dy)y)y)y)xO , >hxtIFFFGhxtIFFFG# #'   -.%h h h h   h V(;(;(;V)L)L)LXG)G)G)G)G)*MQUG)G)G)G)G)G)r#