WeaklySupervisedRadiusClassifier

class scikit_weak.classification.WeaklySupervisedRadiusClassifier(radius=1.0, metric='minkowski')

A class to perform classification for weakly supervised data, based on radius neighbors. The y input to the fit method should be given as an iterable of DiscreteWeakLabel

Parameters

• radius (float, default=1.0) – The size of the radius

• metric (str or callable, default 'minkowski') – The metric for neighbors queries

Variables

• y (ndarray) – A copy of the input y

• n_classes (int) – The number of unique classes in y

fit(X, y)

Fit the WeaklySupervisedRadiusClassifier model

predict(X)

Returns predictions for the given X

predict_proba(X)

Returns probability distributions for the given X