Hyperparameter tuning

from sklearn.model_selection import GridSearchCV

def evaluate_model(model, X_train, y_train, X_test, y_test, hyperparameters=None):
    if hyperparameters is not None:
        # Perform hyperparameter tuning using GridSearchCV
        grid_search = GridSearchCV(model, hyperparameters, scoring='accuracy', cv=5)
        grid_search.fit(X_train, y_train)
        best_model = grid_search.best_estimator_
    else:
        best_model = model

    # Train the best model on the entire training set
    best_model.fit(X_train, y_train)

    # Evaluate the model on the test set
    accuracy = best_model.score(X_test, y_test)

    return accuracy, best_model

# Example usage
from sklearn.ensemble import RandomForestClassifier
from sklearn.svm import SVC
from sklearn.datasets import load_iris
from sklearn.model_selection import train_test_split

# Load dataset
iris = load_iris()
X_train, X_test, y_train, y_test = train_test_split(iris.data, iris.target, test_size=0.2, random_state=42)

# Define models
rf_model = RandomForestClassifier(random_state=42)
svc_model = SVC(random_state=42)

# Define hyperparameters for tuning (customize based on your needs)
rf_hyperparameters = {'n_estimators': [50, 100, 200], 'max_depth': [None, 10, 20]}
svc_hyperparameters = {'C': [0.1, 1, 10], 'kernel': ['linear', 'rbf']}

# Evaluate Random Forest with hyperparameter tuning
rf_accuracy, best_rf_model = evaluate_model(rf_model, X_train, y_train, X_test, y_test, hyperparameters=rf_hyperparameters)

# Evaluate SVC with hyperparameter tuning
svc_accuracy, best_svc_model = evaluate_model(svc_model, X_train, y_train, X_test, y_test, hyperparameters=svc_hyperparameters)

print(f"Random Forest Accuracy: {rf_accuracy}")
print(f"Tuned Random Forest Model: {best_rf_model}")

print(f"SVC Accuracy: {svc_accuracy}")
print(f"Tuned SVC Model: {best_svc_model}")