Create Part 5 Model Tuning

Author: sandipanpaul21

Part 5 Model Tuning

@@ -0,0 +1,61 @@
+Inspecting the hyperparameters of a CART
+# Import DecisionTreeClassifier
+from sklearn.tree import DecisionTreeClassifier
+
+# Set seed to 1 for reproducibility
+SEED = 1
+
+# Instantiate a DecisionTreeClassifier 'dt'
+dt = DecisionTreeClassifier(random_state=SEED)
+
+# Print out 'dt's hyperparameters
+print(dt.get_params())
+
+# Import GridSearchCV
+from sklearn.model_selection import GridSearchCV
+
+# Define the grid of hyperparameters 'params_dt'
+params_dt = {
+              'max_depth': [3, 4,5, 6],
+              'min_samples_leaf': [0.04, 0.06, 0.08],
+              'max_features': [0.2, 0.4,0.6, 0.8]
+            }
+
+# Instantiate a 10-fold CV grid search object 'grid_dt'
+grid_dt = GridSearchCV(estimator=dt, param_grid=params_dt, scoring='accuracy', cv=10, n_jobs=-1)
+
+# Fit 'grid_dt' to the training data
+grid_dt.fit(X_train, y_train)
+
+# Extract best hyperparameters from 'grid_dt'
+best_hyperparams = grid_dt.best_params_
+print('Best hyerparameters:\n', best_hyperparams)
+
+# Extract best CV score from 'grid_dt'
+best_CV_score = grid_dt.best_score_
+print('Best CV accuracy'.format(best_CV_score))
+
+# Extract best model from 'grid_dt'
+best_model = grid_dt.best_estimator_
+
+# Evaluate test set accuracy
+test_acc = best_model.score(X_test,y_test)
+
+# Print test set accuracy
+print("Test set accuracy of best model: {:.3f}".format(test_acc))
+
+# Import roc_auc_score from sklearn.metrics 
+from sklearn.metrics import roc_auc_score
+
+# Extract the best estimator
+best_model = grid_dt.best_estimator_
+
+# Predict the test set probabilities of the positive class
+y_pred_proba = best_model.predict_proba(X_test)[:,1]
+
+# Compute test_roc_auc
+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))
+