two_sigma_financial_modelling.py 文件源码

def outlier_identification(self, model, x_train, y_train):
        # Split the training data into an extra set of test
        x_train_split, x_test_split, y_train_split, y_test_split = train_test_split(x_train, y_train)
        print('\nOutlier shapes')
        print(np.shape(x_train_split), np.shape(x_test_split), np.shape(y_train_split), np.shape(y_test_split))
        model.fit(x_train_split, y_train_split)
        y_predicted = model.predict(x_test_split)
        residuals = np.absolute(y_predicted - y_test_split)
        rmse_pred_vs_actual = self.rmse(y_predicted, y_test_split)
        outliers_mask = residuals >= rmse_pred_vs_actual
        outliers_mask = np.concatenate([np.zeros((np.shape(y_train_split)[0],), dtype=bool), outliers_mask])
        not_an_outlier = outliers_mask == 0
        # Resample the training set from split, since the set was randomly split
        x_out = np.insert(x_train_split, np.shape(x_train_split)[0], x_test_split, axis=0)
        y_out = np.insert(y_train_split, np.shape(y_train_split)[0], y_test_split, axis=0)
        return x_out[not_an_outlier, ], y_out[not_an_outlier, ]