random_forest.py 文件源码

def predict(self, X):
        y_preds = np.empty((X.shape[0], len(self.trees)))
        # Let each tree make a prediction on the data
        for i, tree in enumerate(self.trees):
            # Indices of the features that the tree has trained on
            idx = tree.feature_indices
            # Make a prediction based on those features
            prediction = tree.predict(X[:, idx])
            y_preds[:, i] = prediction

        y_pred = []
        # For each sample
        for sample_predictions in y_preds:
            # Select the most common class prediction
            y_pred.append(np.bincount(sample_predictions.astype('int')).argmax())
        return y_pred