{KgKdZddlZddlmZddlmZddlZddlm Z ddl m Z ddl m Z d d lmZmZd Zd Zeeed ZdZdZdZdZddZddZddZdZy)zAUtilities to handle multiclass/multioutput target in classifiers.N)Sequence)chain)issparse) get_namespace)VisibleDeprecationWarning)_assert_all_finite check_arrayct|\}}t|ds|r |j|j|St |S)N __array__)rhasattr unique_valuesasarraysetyxpis_array_api_compliants \/home/alanp/www/video.onchill/myenv/lib/python3.12/site-packages/sklearn/utils/multiclass.py_unique_multiclassrsA!.q!1Bq+"8 1 ..1v cvt|\}}|jt|dgdjdS)Nrcsrcsccoo) input_name accept_sparser )raranger shape)rr_s r_unique_indicatorr#s: ! EB 99A#5JKQQRST r)binary multiclassmultilabel-indicatorct|\}}|s tdtd|D}|ddhk(rdh}t|dkDrtd|z|j }|dk(r)ttd|DdkDr td t j |d std t|z|r6|j|Dcgc] }| c}}|j|Sttjfd |D}ttd |DdkDr td|jt|Scc}w)aExtract an ordered array of unique labels. We don't allow: - mix of multilabel and multiclass (single label) targets - mix of label indicator matrix and anything else, because there are no explicit labels) - mix of label indicator matrices of different sizes - mix of string and integer labels At the moment, we also don't allow "multiclass-multioutput" input type. Parameters ---------- *ys : array-likes Label values. Returns ------- out : ndarray of shape (n_unique_labels,) An ordered array of unique labels. Examples -------- >>> from sklearn.utils.multiclass import unique_labels >>> unique_labels([3, 5, 5, 5, 7, 7]) array([3, 5, 7]) >>> unique_labels([1, 2, 3, 4], [2, 2, 3, 4]) array([1, 2, 3, 4]) >>> unique_labels([1, 2, 10], [5, 11]) array([ 1, 2, 5, 10, 11]) zNo argument has been passed.c32K|]}t|ywN)type_of_target).0xs r z unique_labels..Ns1b>!$bsr$r%r z'Mix type of y not allowed, got types %sr&c3TK|] }t|gdjd"yw)r)rr N)r r!)r+rs rr-z unique_labels..[s)VXQR A-BCII!LVXs&(zCMulti-label binary indicator input with different numbers of labelsNzUnknown label type: %sc3<K|]}d|Dyw)c3 K|]}|ywr))r+is rr-z*unique_labels...os(F4Eq4Es Nr1)r+r_unique_labelss rr-z unique_labels..os'SPR1(FN14E(FPRsc3<K|]}t|tywr)) isinstancestr)r+labels rr-z unique_labels..qs=9%z%%9sz,Mix of label input types (string and number))r ValueErrorrlenpop_FN_UNIQUE_LABELSgetreprconcatrr from_iterablersorted) ysrrys_types label_typer unique_ys ys_labelsr3s @r unique_labelsrF)sr@"/!3B 7881b11HHl++ > 8}qBXMNNJ ,,  VX    Q  '**:t  **E'''SPR'SSTI 3=9= =>BGHH ::fY' ((>sE!c t|\}}|j|jdxrQt|j |j |j ||j |j|k(S)N real floating)risdtypedtypeboolallastypeint64rs r_is_integral_floatrOwsd!.q!1B ::agg / D ryy"))Arxx0177;q@A5rct|\}}t|dst|ts|rWt dddddd}t j 5t jdt t|fddi|}dddt|d r!|jd k(r|jd d kDsyt!|r|j"d vr|j%}|j'|j(}t+|j(dk(xsM|j,d k(xs|j,d k(xrd|vxr%|j.j0dvxs t3|S|j'|}|jddkxr)|j5|j.dxs t3|S#ttf$r8}t|jd rt|fdti|}Yd}~qd}~wwxYw#1swY{xYw)a~Check if ``y`` is in a multilabel format. Parameters ---------- y : ndarray of shape (n_samples,) Target values. Returns ------- out : bool Return ``True``, if ``y`` is in a multilabel format, else ```False``. Examples -------- >>> import numpy as np >>> from sklearn.utils.multiclass import is_multilabel >>> is_multilabel([0, 1, 0, 1]) False >>> is_multilabel([[1], [0, 2], []]) False >>> is_multilabel(np.array([[1, 0], [0, 0]])) True >>> is_multilabel(np.array([[1], [0], [0]])) False >>> is_multilabel(np.array([[1, 0, 0]])) True r TFrrallow_ndforce_all_finite ensure_2densure_min_samplesensure_min_featureserrorrJNComplex data not supportedr!rr )doklilbiu)rKzsigned integerzunsigned integer)rrr5rdictwarningscatch_warnings simplefilterrr r8r6 startswithobjectndimr!rformattocsrrdatar9sizerJkindrOrI)rrrcheck_y_kwargselabelss r is_multilabelrl~s8"/q!1Bq+*Q"9=S" !   $ $ &  ! !'+D E C@@@' Aw AFFaKAGGAJN{ 88~ % A!!!&&) K1  F q HV[[A%5$HAKF&D*B  C ' &s0G5.F++G2:-G-'G5-G22G55G?cDt|d}|dvrtd|dy)aAEnsure that target y is of a non-regression type. Only the following target types (as defined in type_of_target) are allowed: 'binary', 'multiclass', 'multiclass-multioutput', 'multilabel-indicator', 'multilabel-sequences' Parameters ---------- y : array-like Target values. rr)r$r%zmulticlass-multioutputr&zmultilabel-sequenceszUnknown label type: zy. Maybe you are trying to fit a classifier, which expects discrete classes on a regression target with continuous values.N)r*r8)ry_types rcheck_classification_targetsrpsBA# .F "6(+8 8  rcpt|\}}t|txst|xs t |dxrt|t  xs|}|st d|z|jjdv}|r t dt|rytdddddd }tj5tjd tt|s t|fd d i|}d d d  t|r |dgd d fn|d}t|t$rtj&dt(t |ds+t|trt|t s t d|j,dvryt/|j0s|j,dk(ryyt|s1|j2t"k(rt|j4dt sy|j,dk(r|j0ddkDrd} nd} |j7|j2drSt|r |j8n|} |j;| |j=| t>k7rtA| |d| zStr |j8}|jC|j0ddkDs|j,dk(rtE|dkDrd| zSy#tt f$r8}t |j!d rt|fd t"i|}Yd }~'d }~wwxYw#1swY1xYw#t*$rYwxYw)a Determine the type of data indicated by the target. Note that this type is the most specific type that can be inferred. For example: * ``binary`` is more specific but compatible with ``multiclass``. * ``multiclass`` of integers is more specific but compatible with ``continuous``. * ``multilabel-indicator`` is more specific but compatible with ``multiclass-multioutput``. Parameters ---------- y : {array-like, sparse matrix} Target values. If a sparse matrix, `y` is expected to be a CSR/CSC matrix. input_name : str, default="" The data name used to construct the error message. .. versionadded:: 1.1.0 Returns ------- target_type : str One of: * 'continuous': `y` is an array-like of floats that are not all integers, and is 1d or a column vector. * 'continuous-multioutput': `y` is a 2d array of floats that are not all integers, and both dimensions are of size > 1. * 'binary': `y` contains <= 2 discrete values and is 1d or a column vector. * 'multiclass': `y` contains more than two discrete values, is not a sequence of sequences, and is 1d or a column vector. * 'multiclass-multioutput': `y` is a 2d array that contains more than two discrete values, is not a sequence of sequences, and both dimensions are of size > 1. * 'multilabel-indicator': `y` is a label indicator matrix, an array of two dimensions with at least two columns, and at most 2 unique values. * 'unknown': `y` is array-like but none of the above, such as a 3d array, sequence of sequences, or an array of non-sequence objects. Examples -------- >>> from sklearn.utils.multiclass import type_of_target >>> import numpy as np >>> type_of_target([0.1, 0.6]) 'continuous' >>> type_of_target([1, -1, -1, 1]) 'binary' >>> type_of_target(['a', 'b', 'a']) 'binary' >>> type_of_target([1.0, 2.0]) 'binary' >>> type_of_target([1, 0, 2]) 'multiclass' >>> type_of_target([1.0, 0.0, 3.0]) 'multiclass' >>> type_of_target(['a', 'b', 'c']) 'multiclass' >>> type_of_target(np.array([[1, 2], [3, 1]])) 'multiclass-multioutput' >>> type_of_target([[1, 2]]) 'multilabel-indicator' >>> type_of_target(np.array([[1.5, 2.0], [3.0, 1.6]])) 'continuous-multioutput' >>> type_of_target(np.array([[0, 1], [1, 1]])) 'multilabel-indicator' r z:Expected array-like (array or non-string sequence), got %r) SparseSeries SparseArrayz1y cannot be class 'SparseSeries' or 'SparseArray'r&TFrrQrWrJNrXzSupport for labels represented as bytes is deprecated in v1.5 and will error in v1.7. Convert the labels to a string or integer format.zYou appear to be using a legacy multi-label data representation. Sequence of sequences are no longer supported; use a binary array or sparse matrix instead - the MultiLabelBinarizer transformer can convert to this format.)r runknownr r$rz -multioutputrHrn continuousr%)#rr5rrrr6r8 __class____name__rlr]r^r_r`rr rarbbyteswarn FutureWarning IndexErrorrcminr!rJflatrIrfanyrMintr rr9) rrrrvalid sparse_pandasrirjfirst_row_or_valsuffixrfs rr*r*sP"/q!1B Ax JHQK J71k3J #1c" " " !  H1 L  KK((,KKMLMMQ%  N  "g'@A{ C@@@ # )1 1aS!V91 & . MM  (+6+X6/5;  vvV qww< 66Q; A;177f,Zq 35O vv{qwwqzA~ zz!''?+!!qvv! 66$"))D#.. / t ;&( ( !+00   #a'AFFaKC@PB  C # "N    sC7&LK5A;L(L -L LLLL%( L54L5ct|dd | td|ct|ddEtj|jt |std|d|jyt ||_yy)a"Private helper function for factorizing common classes param logic. Estimators that implement the ``partial_fit`` API need to be provided with the list of possible classes at the first call to partial_fit. Subsequent calls to partial_fit should check that ``classes`` is still consistent with a previous value of ``clf.classes_`` when provided. This function returns True if it detects that this was the first call to ``partial_fit`` on ``clf``. In that case the ``classes_`` attribute is also set on ``clf``. classes_Nz8classes must be passed on the first call to partial_fit.z `classes=z7` is not the same as on last call to partial_fit, was: TF)getattrr8np array_equalrrF)clfclassess r_check_partial_fit_first_callrssJ%-'/STT   3 D ) 5>>#,, g0FG 18#,,H  )1CL rc,g}g}g}|j\}}|tj|}t|r|j }tj |j }t|D]}|j|j ||j |dz} |1|| } tj|tj| z } nd} |jd||z } tj|j|j ||j |dzd\} } tj| | }d| vr|| dk(xx| z cc<d| vrC|||jdkr.tj| dd} tj|d| }|j| |j| jd|j||jz nt|D]}tj|dd|fd\} } |j| |j| jdtj| |}|j||jz |||fS)azCompute class priors from multioutput-multiclass target data. Parameters ---------- y : {array-like, sparse matrix} of size (n_samples, n_outputs) The labels for each example. sample_weight : array-like of shape (n_samples,), default=None Sample weights. Returns ------- classes : list of size n_outputs of ndarray of size (n_classes,) List of classes for each column. n_classes : list of int of size n_outputs Number of classes in each column. class_prior : list of size n_outputs of ndarray of size (n_classes,) Class distribution of each column. Nr rT)return_inverse)weights)r!rrrtocscdiffindptrrangeindicessumuniquerfbincountinsertappend)r sample_weightr n_classes class_prior n_samples n_outputsy_nnzk col_nonzeronz_samp_weightzeros_samp_weight_sum classes_ky_k class_prior_ks rclass_distributionrsG,GIK77Iy  =1 { GGI!y!A))AHHQK!((1q5/BK(!.{!;(*}(=~@V(V%!%() U1X(=%YYqxx{QXXa!e_5dNIsKK^DMI~i1n-1FF- !eAh&;IIiA6 " -rspG $!,37!$-K)\F R 6vr FG-T*+r