NASA RUL project - manual feature generation

manual_feature_generation.py

def avg_diff(series):
  return np.mean(np.diff(series))

all_rollings_grouped = all_rollings_df_X.drop(columns=['time']).groupby('instance_id').agg(['mean', avg_diff, 'std', 'max', 'min'])

test_df_grouped = test_df.sort_values(['unit_number', 'time']).groupby('unit_number').\
                          apply(lambda group_df: group_df[[x for x in test_df.columns if 'sensor_' in x]].\
                                iloc[-WINDOW_SIZE:]).reset_index()
test_df_aggregated = test_df_grouped.drop(columns=['level_1']).groupby('unit_number').agg(['mean', avg_diff, 'std', 'max', 'min'])

X_features_manual_train = all_rollings_grouped.values
X_features_manual_test = test_df_aggregated.values
xgbr_features_manual = XGBRegressor()
xgbr_features_manual.fit(X_features_manual_train, y_train_rolling)

print_train_test_results(X_features_manual_train, X_features_manual_test,
                         y_train_rolling, y_test, xgbr_features_manual)