charDistClassifier.py 文件源码

def predict_training(self, folds=5):
        """Do cross-validation and return probabilities for each data-point.

        Args:
            folds (int): Number of folds used for prediction on training data.
        """
        partial_clf = linear_model.LogisticRegression(class_weight='balanced')
        prediction = np.zeros((len(self.features), self.num_classes))
        skf = StratifiedKFold(n_splits=folds)
        for train_index, test_index in skf.split(self.features, self.labels):
            # prepare the training and test data
            training_features = self.features[train_index]
            test_features = self.features[test_index]
            training_labels = self.labels[train_index]
            # fitting the model and predicting
            partial_clf.fit(training_features, training_labels)
            curr_pred = partial_clf.predict_proba(test_features)
            prediction[test_index] = \
                self.predict_proba_ordered(curr_pred, partial_clf.classes_)
        return prediction