NASA RUL project - baseline performance

baseline_performance.py

test_df.drop(columns=[f'sensor_{i}' for i in [3, 4, 8, 9, 13, 19, 21, 22, 25, 26]], inplace=True, errors='ignore')
for col_name in [x for x in test_df.columns if 'sensor_' in x]:
  test_df[col_name] = MIN_MAX_SCALERS[col_name].transform(test_df[col_name].values.reshape(-1, 1)).squeeze()
X_test = test_df.groupby('unit_number').apply(lambda group_df: group_df.iloc[group_df['time'].argmax()])[[x for x in test_df.columns if 'sensor_' in x]].values
y_test = pd.read_csv('/content/drive/MyDrive/Datasets/NASA_CMAPSS/RUL_FD001.txt', header=None).values.squeeze().clip(max=125)

def print_train_test_results(X_train, X_test, y_train, y_test, model):
  y_pred_train = model.predict(X_train)
  y_pred_test = model.predict(X_test)
  print(f'RMSE on train set: {mean_squared_error(y_train, y_pred_train, squared=False)}')
  print(f'RMSE on test set: {mean_squared_error(y_test, y_pred_test, squared=False)}')  
  
print_train_test_results(X_train, X_test, y_train, y_test, xgbr)