o tBh3@@sdZddlmZddlmZddlZddlmZddlmZddlm Z ddl Z dd l m Z mZd d Zd d ZeeedZddZddZddZddZd ddZd!ddZd!ddZddZdS)"zX Multi-class / multi-label utility function ========================================== )Sequence)chainN)issparse) dok_matrix) lil_matrix) check_array_assert_all_finitecCs"t|dr tt|St|S)N __array__)hasattrnpuniqueasarraysetyro/var/www/html/riverr-enterprise-integrations-main/venv/lib/python3.10/site-packages/sklearn/utils/multiclass.py_unique_multiclasss rcCstt|dgddjdS)Nrcsrcsccoo) input_name accept_sparser)r arangershaperrrr_unique_indicatorsr)binary multiclassmultilabel-indicatorcs|stdtdd|D}|ddhkrdh}t|dkr$td||}|dkr=ttd d|Ddkr=td t|d sMtd t|ttfd d|D}ttdd|Ddkrltdt t |S)awExtract 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 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.css|]}t|VqdSN)type_of_target).0xrrr Mz unique_labels..rrrz'Mix type of y not allowed, got types %sr css&|]}t|gddjdVqdS)r)rrN)rrr#rrrrr%Zs zCMulti-label binary indicator input with different numbers of labelsNzUnknown label type: %sc3s|]}|VqdSr!rr'_unique_labelsrrr%ir&css|]}t|tVqdSr!) isinstancestr)r#labelrrrr%lsz,Mix of label input types (string and number)) ValueErrorrlenpop_FN_UNIQUE_LABELSgetreprr from_iterabler arraysorted)ysys_types label_type ys_labelsrr(r unique_labels*s4    r:cCs |jjdkot|t|kS)Nf)dtypekindr allastypeintrrrr_is_integral_floatrs rAc Cs&t|ds t|tr>t(tdtjzt|}Wntjy.tj |t d}YnwWdn1s9wYt|drO|j dkrO|j ddksQdSt |r~t|ttfr`|}t|jd kp}t|jjdko}|jjd vp}tt|jSt|}t|d ko|jjd vpt|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 errorr<NrrFrbiu)r r*rwarningscatch_warnings simplefilterr VisibleDeprecationWarningrr4objectndimrrrrtocsrr.datar sizer<r=rA)rlabelsrrr is_multilabelvs0 "   rQcCs$t|dd}|dvrtd|dS)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)rrzmulticlass-multioutputr zmultilabel-sequenceszUnknown label type: %rN)r"r-)ry_typerrrcheck_classification_targetss  rTc Cst|tp t|p t|dot|t }|std||jjdv}|r(tdt|r.dSt (t dt j zt |}Wnt j yRt j|td}YnwWdn1s]wYzt|d ds|t|d tr|t|d ts|td Wn tyYnw|jd ks|jtkrt|rt|jd tsd S|jd kr|jd d krd S|jd kr|jd d krd}nd}|jjdkrt ||tkrt||dd|Stt |d ks|jd krt|d d krd|SdS)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 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 rBrCNrzYou 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.rDunknownrz -multioutputrUr;rR continuousrr)r*rrr r+r- __class____name__rQrGrHrIr rJrrK IndexErrorrLr<r.flatrr=anyr?r@r r )rrvalid sparse_pandassuffixrrrr"sbG       ,  ,r"cCsrt|dddur|durtd|dur7t|dddur0t|jt|s.td||jfdSt||_dSdS)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.zD`classes=%r` is not the same as on last call to partial_fit, was: %rTF)getattrr-r array_equalrbr:)clfclassesrrr_check_partial_fit_first_callUs rgcCsg}g}g}|j\}}|durt|}t|r|}t|j}t|D]}|j|j||j|d} |durJ|| } t |t | } n d} |jd||} tj |j |j||j|ddd\} } tj | | d}d| vr|| dk| 7<d| vr|||jdkrt | dd} t |d| }|| || jd||| q&n3t|D].}tj |dd|fdd\} } || || jdtj | |d}||| q|||fS)a{Compute 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. NrrT)return_inverse)weights)rr rrtocscdiffindptrrangeindicessumr rNbincountinsertappend)r sample_weightrf n_classes class_prior n_samples n_outputsy_nnzk col_nonzeronz_samp_weightzeros_samp_weight_sum classes_ky_k class_prior_krrrclass_distributionxsH         rc Cs|jd}t||f}t||f}d}t|D]X}t|d|D]N}|dd|f|dd|f8<|dd|f|dd|f7<||dd|fdk|fd7<||dd|fdk|fd7<|d7}q"q|dt|d} || S)ayCompute a continuous, tie-breaking OvR decision function from OvO. It is important to include a continuous value, not only votes, to make computing AUC or calibration meaningful. Parameters ---------- predictions : array-like of shape (n_samples, n_classifiers) Predicted classes for each binary classifier. confidences : array-like of shape (n_samples, n_classifiers) Decision functions or predicted probabilities for positive class for each binary classifier. n_classes : int Number of classes. n_classifiers must be ``n_classes * (n_classes - 1 ) / 2``. rrNrF)rr zerosrmabs) predictions confidencesrtrvvotessum_of_confidencesryijtransformed_confidencesrrr_ovr_decision_functions  $$$$ r)rUr!)__doc__collections.abcr itertoolsrrG scipy.sparserrrnumpyr validationrr rrr0r:rArQrTr"rgrrrrrrs0     H>  # K