Never Forget Another Line of Code

 1|  from xgboost import XGBRegressor
 2|  from sklearn.metrics import mean_squared_error, mean_absolute_error, max_error, explained_variance_score, mean_absolute_percentage_error
 3|  
 4|  # Step 1: Initialise and fit XGBoost regression model
 5|  model = XGBRegressor(objective='reg:squarederror', 
 6|                        n_estimators=1000,
 7|                        max_depth=4,
 8|                        learning_rate=0.1,
 9|                        min_child_weight=1,
10|                        colsample_bytree=0.9,
11|                        subsample=0.9,
12|                        n_jobs=-1,
13|                        random_state=101)
14|  model.fit(X_train, y_train)
15|  
16|  model.save_model('xgb_regressor.model')
17|  
18|  # Step 2: Plot feature importances
19|  features = X_train.columns
20|  importance_values = model.feature_importances_
21|  
22|  plt.barh(y=range(len(features)),
23|           width=importance_values,
24|           tick_label=features)
25|  plt.show()
26|  
27|  # Step 3: Make prediction for test data & evaluate performance
28|  y_pred = model.predict(X_test)
29|  print('RMSE:',mean_squared_error(y_test, y_pred, squared = False))
30|  print('MAE:',mean_absolute_error(y_test, y_pred))
31|  print('MAPE:',mean_absolute_percentage_error(y_test, y_pred))
32|  print('Max Error:',max_error(y_test, y_pred))
33|  print('Explained Variance Score:',explained_variance_score(y_test, y_pred))