U 3d #@sTdZddlmZddlZddlmZmZddlm Z dddZ dd d Z d d Z dS)z Common code for all metrics. ) combinationsN) check_arraycheck_consistent_length)type_of_targetcCsd}||krtd|t|}|dkr8td||dkrN||||dSt|||t|}t|}d}|}d} |d kr|dk rt||jd}|}|}nj|d kr|dk rtj t |t |d d d } ntj |d d } t | drd Sn|dkr|} d}d }|j dkr*| d }|j dkr@| d }|j|} t| f} t| D]@} |j| g|d } |j| g|d }|| ||d| | <q^|dk r| dk rt| } d | | d k<tj| | dS| SdS)aMAverage a binary metric for multilabel classification. Parameters ---------- y_true : array, shape = [n_samples] or [n_samples, n_classes] True binary labels in binary label indicators. y_score : array, shape = [n_samples] or [n_samples, n_classes] Target scores, can either be probability estimates of the positive class, confidence values, or binary decisions. average : {None, 'micro', 'macro', 'samples', 'weighted'}, default='macro' If ``None``, the scores for each class are returned. Otherwise, this determines the type of averaging performed on the data: ``'micro'``: Calculate metrics globally by considering each element of the label indicator matrix as a label. ``'macro'``: Calculate metrics for each label, and find their unweighted mean. This does not take label imbalance into account. ``'weighted'``: Calculate metrics for each label, and find their average, weighted by support (the number of true instances for each label). ``'samples'``: Calculate metrics for each instance, and find their average. Will be ignored when ``y_true`` is binary. sample_weight : array-like of shape (n_samples,), default=None Sample weights. binary_metric : callable, returns shape [n_classes] The binary metric function to use. Returns ------- score : float or array of shape [n_classes] If not ``None``, average the score, else return the score for each classes. )Nmicromacroweightedsampleszaverage has to be one of {0})binaryzmultilabel-indicatorz{0} format is not supportedr ) sample_weightNrr )r r)Zaxisgr weights) ValueErrorformatrrrnprepeatshapeZravelsummultiplyZreshapeisclosendimzerosrangeZtakeZasarrayaverage) binary_metricy_truey_scorerr Zaverage_optionsZy_typeZnot_average_axisZ score_weightZaverage_weight n_classesZscorecZy_true_cZ y_score_cr"9/tmp/pip-unpacked-wheel-zrfo1fqw/sklearn/metrics/_base.py_average_binary_scores`+              r$rcCst||t|}|jd}||dd}t|}|dk}|rNt|nd} tt|dD]~\} \} } || k} || k}t| |}|rt|| | <| |}||}||||| f}||||| f}||d|| <q`tj|| dS)aLAverage one-versus-one scores for multiclass classification. Uses the binary metric for one-vs-one multiclass classification, where the score is computed according to the Hand & Till (2001) algorithm. Parameters ---------- binary_metric : callable The binary metric function to use that accepts the following as input: y_true_target : array, shape = [n_samples_target] Some sub-array of y_true for a pair of classes designated positive and negative in the one-vs-one scheme. y_score_target : array, shape = [n_samples_target] Scores corresponding to the probability estimates of a sample belonging to the designated positive class label y_true : array-like of shape (n_samples,) True multiclass labels. y_score : array-like of shape (n_samples, n_classes) Target scores corresponding to probability estimates of a sample belonging to a particular class. average : {'macro', 'weighted'}, default='macro' Determines the type of averaging performed on the pairwise binary metric scores: ``'macro'``: Calculate metrics for each label, and find their unweighted mean. This does not take label imbalance into account. Classes are assumed to be uniformly distributed. ``'weighted'``: Calculate metrics for each label, taking into account the prevalence of the classes. Returns ------- score : float Average of the pairwise binary metric scores. rr rr Nr) rruniquerempty enumerater logical_orr)rrrrZ y_true_uniquer Zn_pairsZ pair_scoresZ is_weightedZ prevalenceixabZa_maskZb_maskZab_maskZa_trueZb_trueZ a_true_scoreZ b_true_scorer"r"r#_average_multiclass_ovo_scores&(     r,cCst|}|dkr|jjdksht|ddgst|ddgst|dgst|dgst|dgsddd|D}td |d n |dkrd}|S) aCheck if `pos_label` need to be specified or not. In binary classification, we fix `pos_label=1` if the labels are in the set {-1, 1} or {0, 1}. Otherwise, we raise an error asking to specify the `pos_label` parameters. Parameters ---------- pos_label : int, str or None The positive label. y_true : ndarray of shape (n_samples,) The target vector. Returns ------- pos_label : int If `pos_label` can be inferred, it will be returned. Raises ------ ValueError In the case that `y_true` does not have label in {-1, 1} or {0, 1}, it will raise a `ValueError`. NZOUSrr rz, css|]}t|VqdS)N)repr).0r!r"r"r# sz/_check_pos_label_consistency..zy_true takes value in {zr} and pos_label is not specified: either make y_true take value in {0, 1} or {-1, 1} or pass pos_label explicitly.)rr%ZdtypekindZ array_equaljoinr)Z pos_labelrclassesZ classes_reprr"r"r#_check_pos_label_consistencys*       r3)N)r) __doc__ itertoolsrZnumpyrutilsrrZutils.multiclassrr$r,r3r"r"r"r#s   m F