aa6af82f458acf3f853e5174d34b11d319eea1c0,unbalanced_dataset/under_sampling/instance_hardness_threshold.py,InstanceHardnessThreshold,transform,#InstanceHardnessThreshold#,189

Before Change

            mask = probabilities >= self.threshold
        elif self.kind_sel == "maj":
            ratios = np.zeros(100, )
            probs = np.linspace(0., 1., 100)

            for i, p in enumerate(probs):
                ratios[i] = self.stats_c_[self.min_c_] / np.count_nonzero(np.logical_or(probabilities >= p, y == self.min_c_))
                ratios = np.abs(ratios - self.ratio)

            threshold = probs[ratios.argmin()]
            mask = np.logical_or(probabilities >= self.threshold, y == self.min_c_)

        X_resampled = X[mask]
        y_resampled = y[mask]

After Change

            mask = probabilities >= self.ratio_
        elif self.kind_sel == "maj":
            min_count = np.sum(y == self.min_c_)
            max_count = len(y) - min_count
            rem_count = max_count - (min_count / self.ratio_)

            threshold = np.percentile(probabilities[y != self.min_c_], 
                    100*(rem_count/max_count))
            mask = np.logical_or(probabilities >= threshold, y == self.min_c_)

        X_resampled = X[mask]
        y_resampled = y[mask]

Instances