a lDfI@sdZddlZddlmZddlmZddlZddlm Z ddl m Z ddl m Z d d lmZmZd d Zd dZeeedZddZddZddZddZd!ddZd"ddZd#ddZdd ZdS)$zw The :mod:`sklearn.utils.multiclass` module includes utilities to handle multiclass/multioutput target in classifiers. N)Sequence)chain)issparse) get_namespace)VisibleDeprecationWarning)_assert_all_finite check_arraycCs6t|\}}t|ds|r*|||St|SdS)N __array__)rhasattr unique_valuesasarraysetyxpis_array_api_compliantre/nfs/NAS7/SABIOD/METHODE/ermites/ermites_venv/lib/python3.9/site-packages/sklearn/utils/multiclass.py_unique_multiclasss rcCs*t|\}}|t|dgddjdS)NrZcsrZcscZcoo) input_name accept_sparser)rZaranger shape)rr_rrr_unique_indicators r)binary multiclassmultilabel-indicatorcst|\}}|stdtdd|D}|ddhkr>> from sklearn.utils.multiclass import unique_labels >>> unique_labels([3, 5, 5, 5, 7, 7]) array([3, 5, 7]) >>> unique_labels([1, 2, 3, 4], [2, 2, 3, 4]) array([1, 2, 3, 4]) >>> unique_labels([1, 2, 10], [5, 11]) array([ 1, 2, 5, 10, 11]) zNo argument has been passed.css|]}t|VqdSN)type_of_target).0xrrr Pz unique_labels..rrrz'Mix type of y not allowed, got types %srcss$|]}t|gddjdVqdS)r)rrN)r rr"rrrrr$]szCMulti-label binary indicator input with different numbers of labelsNzUnknown label type: %scsg|] }|qSrrr&Z_unique_labelsrr nr%z!unique_labels..c3s |]}dd|DVqdS)css|] }|VqdSr r)r"irrrr$qr%z*unique_labels...Nrr&r'rrr$qr%css|]}t|tVqdSr ) isinstancestr)r"labelrrrr$sr%z,Mix of label input types (string and number))r ValueErrorrlenpop_FN_UNIQUE_LABELSgetreprconcatr r from_iterablersorted)ZysrrZys_typesZ label_typeZ unique_ysZ ys_labelsrr'r unique_labels+s@       r6c Cs@t|\}}||jdo>t|||||j|j|kS)N real floating)risdtypedtypeboolallastypeint64rrrr_is_integral_floatys  r>c Cst|\}}t|ds$t|ts$|rtddddddd}ttdtzt |fddi|}WnLtt fy}z0t | d rt |fdt i|}WYd}~n d}~00Wdn1s0Yt|d r|jd kr|jd d ksdSt|rj|jd vr|}||j}t|jdkph|jd ksT|jd kohd|voh|jjdvpht|S||}|jddko||jdpt|SdS)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 TFrrZallow_ndZforce_all_finiteZ ensure_2dZensure_min_samplesZensure_min_featureserrorr9NComplex data not supportedrrr)ZdokZlilZbiu)r:zsigned integerzunsigned integer)rr r*rdictwarningscatch_warnings simplefilterrr r-r+ startswithobjectndimrrformatZtocsrr datar.sizer9kindr>r8)rrrcheck_y_kwargselabelsrrr is_multilabelsB   H"   " rQcCs(t|dd}|dvr$td|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)rrzmulticlass-multioutputrzmultilabel-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-)rZy_typerrrcheck_classification_targetss  rSc Cst|\}}t|ts(t|s(t|dr4t|t p6|}|sHtd||jjdv}|r`tdt |rldSt ddddddd }t t d tt|szt|fd d i|}WnNttfy}z0t|d rނt|fd ti|}WYd }~n d }~00Wd n1s0YzTt|rF|dgd d fn|d}t|dszt|trzt|tsztdWntyYn0|jdvrdSt|js|jdkrdSdSt|s|jtkrt|jdtsdS|jdkr|jddkrd} nd} ||jdrdt|r4|jn|} || || tkrdt| |dd| St|rt|j}||jddks|jdkrt|dkrd| SdSd S)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)Z SparseSeriesZ SparseArrayz1y cannot be class 'SparseSeries' or 'SparseArray'rTFrr?r@r9NrAzYou 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.)rrunknownrrrz -multioutputrTr7rRZ continuousr) rr*rrr r+r- __class____name__rQrCrDrErFrr rGrH IndexErrorrIminrr9Zflatr8rKanyr<intr r r.) rrrrZvalidZ sparse_pandasrNrOZ first_rowsuffixrKrrrr!sH      J$   (  0r!cCsrt|dddur"|dur"tdnL|durnt|dddur`t|jt|sntd||jfnt||_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-npZ array_equalr]r6)Zclfclassesrrr_check_partial_fit_first_calls  racCsg}g}g}|j\}}|dur(t|}t|rp|}t|j}t|D]}|j|j||j|d} |dur|| } t |t | } nd} |jd||} tj |j |j||j|ddd\} } tj | | d}d| vr|| dk| 7<d| vr@|||jdkr@t | dd} t |d| }|| || jd||| qNnht|D]^}tj |dd|fdd\} } || || jdtj | |d}||| qx|||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. NrrT)Zreturn_inverse)weights)rr_rrZtocscdiffZindptrrangeindicessumuniquerKZbincountinsertappend)rZ sample_weightr` n_classesZ class_prior n_samplesZ n_outputsZy_nnzkZ col_nonzeroZnz_samp_weightZzeros_samp_weight_sumZ classes_kZy_kZ class_prior_krrrclass_distributionsF         rmc Cs|jd}t||f}t||f}d}t|D]}t|d|D]}|dd|f|dd|f8<|dd|f|dd|f7<||dd|fdk|fd7<||dd|fdk|fd7<|d7}qDq2|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``. rrNrB)rr_zerosrdabs) Z predictionsZ confidencesrjrkZvotesZsum_of_confidencesrlr)jZtransformed_confidencesrrr_ovr_decision_functions  $$$$ rq)rT)N)N)__doc__rDcollections.abcr itertoolsrnumpyr_Z scipy.sparserZutils._array_apirZ utils.fixesrZ validationr r rrr0r6r>rQrSr!rarmrqrrrrs.     NI / # J