UgKdZddlZddlmZddlmZddlZddlm Z ddl m Z ddl m Z d d lmZmZd Zd Zeeed ZdZdZdZdZddZddZddZdZdS)zAUtilities to handle multiclass/multioutput target in classifiers.N)Sequence)chain)issparse) get_namespace)VisibleDeprecationWarning)_assert_all_finite check_arrayct|\}}t|ds|r(|||St |S)N __array__)rhasattr unique_valuesasarraysetyxpis_array_api_compliants W/var/www/surfInsights/venv3-11/lib/python3.11/site-packages/sklearn/utils/multiclass.py_unique_multiclassrsX!.q!1!1Bq+"8 1 ...1vv ct|\}}|t|dgdjdS)Nrcsrcsccoo) input_name accept_sparser )raranger shape)rr_s r_unique_indicatorr#sK !  EB 99A#5J5J5JKKKQRST  r)binary multiclassmultilabel-indicatorcnt|\}}|stdtd|D}|ddhkrdh}t|dkrtd|z|}|dkr9ttd|Ddkrtd t |d std t|z|r6|fd |D}| |Sttj fd |D}ttd|Ddkrtd| t|S)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.c34K|]}t|VdSN)type_of_target).0xs r z unique_labels..Ns*11>!$$111111rr$r%r z'Mix type of y not allowed, got types %sr&c3RK|]"}t|gdjdV#dS)r)rr N)r r!)r+rs rr-z unique_labels..[sOQR A-B-B-BCCCI!LrzCMulti-label binary indicator input with different numbers of labelsNzUnknown label type: %sc&g|] }|Sr0r+r_unique_labelss r z!unique_labels..ls#===Q~~a00===rc3BK|]}d|DVdS)c3K|]}|VdSr)r0)r+is rr-z*unique_labels...os"(F(Fq(F(F(F(F(F(FrNr0r1s rr-z unique_labels..os<'S'S1(F(FNN14E4E(F(F(F'S'S'S'S'S'Src3@K|]}t|tVdSr)) isinstancestr)r+labels rr-z unique_labels..qs,==%z%%%======rz,Mix of label input types (string and number))r ValueErrorrlenpop_FN_UNIQUE_LABELSgetreprconcatrr from_iterablersorted)ysrrys_types label_type unique_ys ys_labelsr2s @r unique_labelsrI)s@"/!3B 9788811b11111HHl+++ > 8}}qBXMNNNJ ,,,  VX       Q   '**:t<1DHH<===+II===="===>>  ***E''S'S'S'SPR'S'S'SSSTTI 3==9=== = =>>BBGHHH ::fY'' ( ((rc  t|\}}||jdoWt|||||j|j|kS)N real floating)risdtypedtypeboolallastypeint64rs r_is_integral_floatrRwsr!.q!1!1B ::ag / / D ryy"))Arx0017;;q@AA55rct|\}}t|dst|ts|rt dddddd}t j5t jdt t|fddi|}nU#ttf$rA}t| d rt|fdti|}Yd}~nd}~wwxYwdddn #1swxYwYt|d r|jd kr|jd d ksdSt!|r|jd vr|}||j}t+|jdkp6|jd ks|jd ko d|vo|jjdvpt3|S||}|jddko)||jdpt3|S)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_featureserrorrMNComplex data not supportedr!rr )doklilbiu)rNzsigned integerzunsigned integer)rrr8rdictwarningscatch_warnings simplefilterrr r;r9 startswithobjectndimr!rformattocsrrdatar<sizerMkindrRrL)rrrcheck_y_kwargselabelss r is_multilabelro~s8"/q!1!1Bq+C*Q"9"9C=SC" !     $ & & C C  !'+D E E E C@@@@@-z: C C Cq66$$%ABB BBB>BB  C C C C C C C C C C C C C C C C Aw  AFaKKAGAJNNu{{ 8~ % % A!!!&)) KK1  F q HV[A%5$HAKF&D*B C/C 7CC/C  C//C36C3cVt|d}|dvrtd|ddS)aAEnsure that target y is of a non-regression type. Only the following target types (as defined in type_of_target) are allowed: 'binary', 'multiclass', 'multiclass-multioutput', 'multilabel-indicator', 'multilabel-sequences' Parameters ---------- y : array-like Target values. rr)r$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*r;)ry_types rcheck_classification_targetsrss\A# . . .F  86 8 8 8   rct|\}}t|tst|st |drt|t  p|}|st d|z|jjdv}|rt dt|rdStdddddd }tj 5tj d tt|sf t|fd d i|}nU#tt f$rA}t |d rt|fd t"i|}Yd }~nd }~wwxYwd d d n #1swxYwY t|r |dgd d fn|d}t|t$rtjdt(t |ds9t|tr$t|t st dn#t*$rYnwxYw|jdvrdSt/|js|jdkrdSdSt|s2|jt"kr"t|jdt sdS|jdkr|jddkrd} nd} ||jdr`t|r|jn|} || || t>krtA| |d| zSt|r|j}|!|jddks|jdkrtE|dkrd| zSdS)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&TFrrTrZrMNr[zSupport 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 -multioutputrtrKrq continuousr%)#rr8rrrr9r; __class____name__ror`rarbrcrr rdrebyteswarn FutureWarning IndexErrorrfminr!rMflatrLrianyrPintr rr<) rrrrvalid sparse_pandasrlrmfirst_row_or_valsuffixris rr*r*scP"/q!1!1B Ax JHQKK J71k3J3J #1c"" " " !   H1 L   K(,KKMNLMMMQ&%%  N  " " C Cg'@AAA{{ C C@@@@@-z: C C Cq66$$%ABB BBB>BB  C C C C C C C C C C C C C C C C )1 =1aS!!!V991 & . .  M    (+66 +X66 /55  ;        vVy qw<< 6Q;;8y A;;17f,,Zq 35O5O,y v{{qwqzA~~ zz!'?++)!!+qvv! 66$"))D#... / / ) t ; ; ; ;&( ( !!1+0  #a''AFaKKC@P#, g0F0FGG  j18#,,H )11CL4 5rc^g}g}g}|j\}}|tj|}t|r|}tj|j}t|D]}|j|j||j|dz} |2|| } tj |tj | z } nd} |jd||z } tj |j |j||j|dzd\} } tj | | }d| vr|| dkxx| z cc<d| vrC|||jdkr,tj | dd} tj |d| }|| || jd||| z nt|D]}tj |dd|fd\} } || || jdtj | |}||| z |||fS)azCompute class priors from multioutput-multiclass target data. Parameters ---------- y : {array-like, sparse matrix} of size (n_samples, n_outputs) The labels for each example. sample_weight : array-like of shape (n_samples,), default=None Sample weights. Returns ------- classes : list of size n_outputs of ndarray of size (n_classes,) List of classes for each column. n_classes : list of int of size n_outputs Number of classes in each column. class_prior : list of size n_outputs of ndarray of size (n_classes,) Class distribution of each column. Nr rT)return_inverse)weights)r!rrrtocscdiffindptrrangeindicessumuniqueribincountinsertappend)r sample_weightr n_classes class_prior n_samples n_outputsy_nnzk col_nonzeronz_samp_weightzeros_samp_weight_sum classes_ky_k class_prior_ks rclass_distributionrs,GIK7Iy  =11 {{'D GGII!!y!! D DA)AHQK!(1q5/$ABK(!.{!;(*}(=(=~@V@V(V%%!%() U1X(=%Yqx{QXa!e_45dNIsK^DDDMI~~i1n---1FF--- !!eAh&;&;IiA66 " -rIrRrorsr*rrrr0rrrsnGG $$$$$$!!!!!!,,,,,,33333377777777!$-K)K)K)\F F F R   6vvvvr    FG-G-G-G-T*+*+*+*+*+r