house_prices.py 文件源码

def outlier_prediction(x_train, y_train):
        # Use built-in isolation forest or use predicted vs. actual
        # Compute squared residuals of every point
        # Make a threshold criteria for inclusion

        # The prediction returns 1 if sample point is inlier. If outlier prediction returns -1
        rng = np.random.RandomState(42)
        clf_all_features = IsolationForest(max_samples=100, random_state=rng)
        clf_all_features.fit(x_train)

        # Predict if a particular sample is an outlier using all features for higher dimensional data set.
        y_pred_train = clf_all_features.predict(x_train)

        # Exclude suggested outlier samples for improvement of prediction power/score
        outlier_map_out_train = np.array(map(lambda x: x == 1, y_pred_train))
        x_train_modified = x_train[outlier_map_out_train, ]
        y_train_modified = y_train[outlier_map_out_train, ]

        return x_train_modified, y_train_modified