DT.py

# hyperparameter tuning the DecisionTree model
params ={'max_depth':[1, 5, 10, 50],'min_samples_split':[5, 10, 100, 500]}
# Create a custom (MCC) metric for evaluation of the model performance while 

mcc = make_scorer(matthews_corrcoef, greater_is_better=True)

# Create an XGBoost classifier object with log-loss as the loss function to minimize
dt_clf = tree.DecisionTreeClassifier(random_state=42, class_weight='balanced')


# Perform stratified 5-fold cross validation
grid_clf = GridSearchCV(dt_clf, params, scoring=mcc, cv=5, return_train_score=True)

# Fit the model
grid_clf .fit(X_train, y_train)
print(f"Best CV score: {grid_clf.best_score_}")

ok