U mdG@sdZddlmZddlmZddlZddlmZddlmZddlm Z ddl Z dd l m Z mZd d lmZd d ZddZeeedZddZddZddZddZd"ddZd#ddZd$ddZd d!ZdS)%zX Multi-class / multi-label utility function ========================================== )Sequence)chainN)issparse) dok_matrix) lil_matrix) check_array_assert_all_finite) get_namespacecCs6t|\}}t|ds|r*|||St|SdS)N __array__)r hasattr unique_valuesasarrayset)yxp is_array_apirQ/home/sam/Atlas/atlas_env/lib/python3.8/site-packages/sklearn/utils/multiclass.py_unique_multiclasss rcCs tt|ddddgdjdS)Nrcsrcsccoo) input_name accept_sparser)npZarangershaperrrr_unique_indicatorsr)binary multiclassmultilabel-indicatorcst|\}}|stdtdd|D}|ddhkr>> from sklearn.utils.multiclass import unique_labels >>> unique_labels([3, 5, 5, 5, 7, 7]) array([3, 5, 7]) >>> unique_labels([1, 2, 3, 4], [2, 2, 3, 4]) array([1, 2, 3, 4]) >>> unique_labels([1, 2, 10], [5, 11]) array([ 1, 2, 5, 10, 11]) zNo argument has been passed.css|]}t|VqdSN)type_of_target).0xrrr Qsz unique_labels..r r!rz'Mix type of y not allowed, got types %sr"css&|]}t|dddgdjdVqdS)rrr)rrN)rrr%rrrrr'^szCMulti-label binary indicator input with different numbers of labelsNzUnknown label type: %scsg|] }|qSrrr(Z_unique_labelsrr osz!unique_labels..c3s |]}dd|DVqdS)css|] }|VqdSr#r)r%irrrr'rsz*unique_labels...Nrr(r)rrr'rscss|]}t|tVqdSr#) isinstancestr)r%labelrrrr'tsz,Mix of label input types (string and number))r ValueErrorrlenpop_FN_UNIQUE_LABELSgetreprconcatrr from_iterablersorted)ZysrrZys_typesZ label_typeZ unique_ysZ ys_labelsrr)r unique_labels,s@       r8cCs |jjdkot|t|kS)Nf)dtypekindrallastypeintrrrr_is_integral_floatzsr?c Cst|\}}t|ds$t|ts$|rtddddddd}tztdtj zt |fddi|}WnLtj t fk r}z(t | d rt |fdti|}W5d}~XYnXW5QRXt|d r|jd kr|jd d ksdSt|r\t|ttfr|}||j}t|jdkpZ|jd ksF|jd koZd|koZ|jjd kpZt|S||}t|dko|jjd kpt|SdS)a~Check if ``y`` is in a multilabel format. Parameters ---------- y : ndarray of shape (n_samples,) Target values. Returns ------- out : bool Return ``True``, if ``y`` is in a multilabel format, else ```False``. Examples -------- >>> import numpy as np >>> from sklearn.utils.multiclass import is_multilabel >>> is_multilabel([0, 1, 0, 1]) False >>> is_multilabel([[1], [0, 2], []]) False >>> is_multilabel(np.array([[1, 0], [0, 0]])) True >>> is_multilabel(np.array([[1], [0], [0]])) False >>> is_multilabel(np.array([[1, 0, 0]])) True r TFrrZallow_ndZforce_all_finiteZ ensure_2dZensure_min_samplesZensure_min_featureserrorr:NComplex data not supportedrr rZbiu)r r r,rdictwarningscatch_warnings simplefilterrVisibleDeprecationWarningrr/r- startswithobjectndimrrrrZtocsrrdatar0sizer:r;r?)rrrcheck_y_kwargselabelsrrr is_multilabel~s@  0"  " rQcCs$t|dd}|dkr td|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)r r!zmulticlass-multioutputr"zmultilabel-sequenceszUnknown label type: %rN)r$r/)rZy_typerrrcheck_classification_targetss rSc Cst|\}}t|ts(t|s(t|dr4t|t p6|}|sHtd||jjdk}|r`tdt |rldSt ddddddd }t t d tjt|s zt|fd d i|}WnNtjtfk r}z(t|d rt|fd ti|}W5d }~XYnXW5QRXz 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'r"TFrr@rAr:NrBzYou 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.)rr unknownrr r z -multioutputrTr9rRZ continuousr!)"r r,rrr r-r/ __class____name__rQrDrErFrGrrHrrIrJ IndexErrorrKminrr:Zflatr;rLanyr=r>r Zgetrowrr0) rrrrZvalidZ sparse_pandasrNrOsuffixrL first_rowrrrr$sH     0      ( 0r$cCsrt|dddkr"|dkr"tdnL|dk rnt|dddk r`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/rZ array_equalr]r8)Zclfclassesrrr_check_partial_fit_first_calls  r`cCsg}g}g}|j\}}|dk r(t|}t|rp|}t|j}t|D]}|j|j||j|d} |dk r|| } t |t | } nd} |jd||} tj |j |j||j|ddd\} } tj | | d}d| kr|| dk| 7<d| kr@|||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)rrrrZtocscdiffZindptrrangeindicessumuniquerLZbincountinsertappend)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_distributionsH         rlc 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``. rrNrC)rrZzerosrcabs) Z predictionsZ confidencesrirjZvotesZsum_of_confidencesrkr+jZtransformed_confidencesrrr_ovr_decision_functions  $$$$ ro)rT)N)N)__doc__collections.abcr itertoolsrrEZ scipy.sparserrrnumpyrZ validationrr Zutils._array_apir rrr2r8r?rQrSr$r`rlrorrrrs0      NH - # J