Update Part 5 Model Tuning

Author: sandipanpaul21

Part 5 Model Tuning

@@ -59,3 +59,51 @@ test_roc_auc = roc_auc_score(y_test, y_pred_proba)
 # Print test_roc_auc
 print('Test set ROC AUC score: {:.3f}'.format(test_roc_auc))
 
+
+# Inspecting RF Hyperparameters in sklearn
+# Import RandomForestRegressor
+from sklearn.ensemble import RandomForestRegressor
+
+# Set seed for reproducibility
+SEED = 1
+
+# Instantiate a random forests regressor 'rf'
+rf = RandomForestRegressor(random_state= SEED)
+
+# Inspect rf' s hyperparameters
+rf.get_params()
+
+# Basic imports
+from sklearn.metrics import mean_squared_error as MSE
+from sklearn.model_selection import GridSearchCV
+
+# Define a grid of hyperparameter 'params_rf'
+params_rf = {
+                'n_estimators': [300, 400, 500],
+                'max_depth': [4, 6, 8],
+                'min_samples_leaf': [0.1, 0.2],
+                'max_features': ['log2','sqrt']
+            }
+
+# Instantiate 'grid_rf'
+grid_rf = GridSearchCV(estimator=rf,param_grid=params_rf, cv=3, scoring= 'neg_mean_squared_error',verbose=1, n_jobs=-1)
+
+# Searching for the best hyperparameters
+# Fit 'grid_rf' to the training set
+grid_rf.fit(X_train, y_train)
+
+# Extract best hyperparameters from 'grid_rf'
+best_hyperparams = grid_rf.best_params_
+print('Best hyerparameters:\n', best_hyperparams)
+
+# Extract best model from 'grid_rf'
+best_model = grid_rf.best_estimator_
+
+# Predict the test set labels
+y_pred = best_model.predict(X_test)
+
+# Evaluate the test set RMSE
+rmse_test = MSE(y_test, y_pred)**(1/2)
+
+# Print the test set RMSE
+print('Test set RMSE of rf: {:.2f}'.format(rmse_test))