B \v;@sdZddlmZddlmZddlmZddlmZddlm Z ddlm Z ddl Z d d l mZd d lmZd d lmZddZddZeeedZddZddZddZddZddZd#ddZd$dd Zd!d"ZdS)%zX Multi-class / multi-label utility function ========================================== )division)chain)issparse)spmatrix) dok_matrix) lil_matrixN) string_types) _Sequence) check_arraycCs&t|drtt|St|SdS)N __array__)hasattrnpuniqueasarrayset)yr7lib/python3.7/site-packages/sklearn/utils/multiclass.py_unique_multiclasss rcCstt|dddgjdS)Ncsrcsccoor )rZaranger shape)rrrr_unique_indicatorsr)binary multiclasszmultilabel-indicatorcs|s tdtdd|D}|tddgkr8tdg}t|dkrPtd||}|dkrttd d|Ddkrtd t|d std t|ttfd d|D}ttdd|Ddkrtdt t |S)ayExtract an ordered array of unique labels We don't allow: - mix of multilabel and multiclass (single label) targets - mix of label indicator matrix and anything else, because there are no explicit labels) - mix of label indicator matrices of different sizes - mix of string and integer labels At the moment, we also don't allow "multiclass-multioutput" input type. Parameters ---------- *ys : array-likes Returns ------- out : numpy array of shape [n_unique_labels] An ordered array of unique labels. Examples -------- >>> from sklearn.utils.multiclass import unique_labels >>> unique_labels([3, 5, 5, 5, 7, 7]) array([3, 5, 7]) >>> unique_labels([1, 2, 3, 4], [2, 2, 3, 4]) array([1, 2, 3, 4]) >>> unique_labels([1, 2, 10], [5, 11]) array([ 1, 2, 5, 10, 11]) zNo argument has been passed.css|]}t|VqdS)N)type_of_target).0xrrr Msz unique_labels..rrr z'Mix type of y not allowed, got types %szmultilabel-indicatorcss$|]}t|dddgjdVqdS)rrrr N)r r)rrrrrr!XszCMulti-label binary indicator input with different numbers of labelsNzUnknown label type: %sc3s|]}|VqdS)Nr)rr)_unique_labelsrrr!bscss|]}t|tVqdS)N) isinstancer )rZlabelrrrr!esz,Mix of label input types (string and number)) ValueErrorrlenpop_FN_UNIQUE_LABELSgetreprr from_iterablerZarraysorted)ZysZys_typesZ label_typeZ ys_labelsr)r"r unique_labels*s&     r,cCs |jjdkot|t|kS)Nf)dtypekindrallastypeint)rrrr_is_integral_floatksr3cCst|drt|}t|dr6|jdkr6|jddks:dSt|rt|ttfrX| }t |j dkpt |j j dko|jjdkptt |j St |}t |dko|jjdkpt|Sd S) a Check if ``y`` is in a multilabel format. Parameters ---------- y : numpy array 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 rrr FrZbiuN)rrrndimrrr#rrZtocsrr%datarsizer.r/r3)rlabelsrrr is_multilabelos  "   r9cCs t|}|dkrtd|dS)a*Ensure 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 )rrzmulticlass-multioutputzmultilabel-indicatorzmultilabel-sequenceszUnknown label type: %rN)rr$)rZy_typerrrcheck_classification_targetss r:cCst|ttfst|do"t|t }|s4td||jjdk}|rLtdt|rXdSyt |}Wntk rzdSXy6t|ddst|dtrt|dtstdWnt k rYnX|j d ks|j tkrt|rt|jdtsdS|j d kr|jd dkrdS|j d kr:|jd d kr:d }nd }|j jd krjt ||tkrjd|Stt |d ks|j d krt|dd krd|SdSdS)aDetermine 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 Returns ------- target_type : string 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 -------- >>> 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]]) 'multiclass-multioutput' >>> 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 %rZ SparseSeriesz!y cannot be class 'SparseSeries'.zmultilabel-indicatorunknownrzYou 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.rr z -multioutputr-Z continuousrrN)r#Sequencerrr r$ __class____name__r9rr IndexErrorr5r.objectr%Zflatrr/anyr1r2r)rZvalidZ sparseseriessuffixrrrrsB@   $2rcCsrt|dddkr"|dkr"tdnL|dk rnt|dddk r`t|jt|sntd||jfnt||_dSdS)a!Private helper function for factorizing common classes param logic Estimators that implement the ``partial_fit`` API need to be provided with the list of possible classes at the first call to partial_fit. Subsequent calls to partial_fit should check that ``classes`` is still consistent with a previous value of ``clf.classes_`` when provided. This function returns True if it detects that this was the first call to ``partial_fit`` on ``clf``. In that case the ``classes_`` attribute is also set on ``clf``. classes_Nz8classes must be passed on the first call to partial_fit.zD`classes=%r` is not the same as on last call to partial_fit, was: %rTF)getattrr$rZ array_equalrDr,)Zclfclassesrrr_check_partial_fit_first_call%s  rGcCsg}g}g}|j\}}t|rh|}t|j}xt|D] }|j|j||j|d} |dk rt|| } t |t | } nd} |jd||} tj |j |j||j|ddd\} } tj | | d}d| kr|| dk| 7<d| kr6|||jdkr6t | dd} t |d| }|| || jd||| q@Wnlxjt|D]^}tj |dd|fdd\} } || || jdtj | |d}||| qrW|||fS)azCompute class priors from multioutput-multiclass target data Parameters ---------- y : array like or sparse matrix of size (n_samples, n_outputs) The labels for each example. sample_weight : array-like of shape = (n_samples,), optional Sample weights. Returns ------- classes : list of size n_outputs of arrays of size (n_classes,) List of classes for each column. n_classes : list of integers of size n_outputs Number of classes in each column class_prior : list of size n_outputs of arrays of size (n_classes,) Class distribution of each column. r NrT)Zreturn_inverse)Zweights)rrZtocscrZdiffZindptrrangeindicesrsumrr6Zbincountinsertappend)rZ sample_weightrF n_classesZ class_prior n_samplesZ n_outputsZy_nnzkZ col_nonzeroZnz_samp_weightZzeros_samp_weight_sumZ classes_kZy_kZ class_prior_krrrclass_distributionHsD       rPcCsB|jd}t||f}t||f}d}xt|D]}xt|d|D]}|dd|f|dd|f8<|dd|f|dd|f7<||dd|fdk|fd7<||dd|fdk|fd7<|d7}qHWq4W|} |} | | kr |St|jj} tt | t | } d| | } ||| S)atCompute 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, shape (n_samples, n_classifiers) Predicted classes for each binary classifier. confidences : array-like, 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`` rr Ng?) rrZzerosrHmaxminZfinfor.epsabs)Z predictionsZ confidencesrMrNZvotesZsum_of_confidencesrOijZmax_confidencesZmin_confidencesrSZmax_abs_confidenceZscalerrr_ovr_decision_functions& $$$$  rW)N)N)__doc__Z __future__r itertoolsrZ scipy.sparserZscipy.sparse.baserrrZnumpyrZ externals.sixr Z utils.fixesr r=Z validationr rrr'r,r3r9r:rrGrPrWrrrrs.         A.w # J