active_learning.py 文件源码

def __query_by_committee(self, clf, X_unlabeled):
        num_classes = len(clf[0].classes_)
        C = len(clf)
        preds = []

        if self.strategy == 'vote_entropy':
            for model in clf:
                y_out = map(int, model.predict(X_unlabeled))
                preds.append(np.eye(num_classes)[y_out])

            votes = np.apply_along_axis(np.sum, 0, np.stack(preds)) / C
            return np.apply_along_axis(entropy, 1, votes)

        elif self.strategy == 'average_kl_divergence':
            for model in clf:
                preds.append(model.predict_proba(X_unlabeled))

            consensus = np.mean(np.stack(preds), axis=0)
            divergence = []
            for y_out in preds:
                divergence.append(entropy(consensus.T, y_out.T))

            return np.apply_along_axis(np.mean, 0, np.stack(divergence))