bigframes.ml.metrics.recall_score#

bigframes.ml.metrics.recall_score(y_true:DataFrame|Series,y_pred:DataFrame|Series,*,average:str|None='binary')→Series[source]#

Compute the recall.

The recall is the ratiotp/(tp+fn), wheretp is the number oftrue positives andfn the number of false negatives. The recall isintuitively the ability of the classifier to find all the positive samples.

The best value is 1 and the worst value is 0.

Examples:

>>>importbigframes.pandasasbpd>>>importbigframes.ml.metrics
>>>y_true=bpd.DataFrame([0,1,2,0,1,2])>>>y_pred=bpd.DataFrame([0,2,1,0,0,1])>>>recall_score=bigframes.ml.metrics.recall_score(y_true,y_pred,average=None)>>>recall_score0    11    02    0dtype: int64
Parameters:

  • y_true (Series orDataFrame ofshape (n_samples,)) – Ground truth (correct) target values.

  • y_pred (Series orDataFrame ofshape (n_samples,)) – Estimated targets as returned by a classifier.

  • average ({'micro','macro','samples','weighted','binary'} orNone,default='binary') – This parameter is required for multiclass/multilabel targets.Possible values are ‘None’, ‘micro’, ‘macro’, ‘samples’, ‘weighted’, ‘binary’.Only average=None is supported.

Returns:

Recall

of the positive class in binary classification or weightedaverage of the recall of each class for the multiclass task.

Return type:

float (if average is not None) orSeries offloat of shape n_unique_labels,)

On this page

This Page