rf_upsample_downsample_employee.py

# Build random forest classifier
methods_data = {"Original": (X_train, y_train),
                "Upsampled": (X_train_u, y_train_u),
                "Downsampled": (X_train_d, y_train_d)}
for method in methods_data.keys():
    pip_rf = make_pipeline(StandardScaler(),
                           RandomForestClassifier(n_estimators=500,
                                                  class_weight="balanced",
                                                  random_state=123))
    
    hyperparam_grid = {
        "randomforestclassifier__n_estimators": [10, 50, 100, 500],
        "randomforestclassifier__max_features": ["sqrt", "log2", 0.4, 0.5],
        "randomforestclassifier__min_samples_leaf": [1, 3, 5],
        "randomforestclassifier__criterion": ["gini", "entropy"]}
    
    gs_rf = GridSearchCV(pip_rf,
                         hyperparam_grid,
                         scoring="f1",
                         cv=10,
                         n_jobs=-1)
    
    gs_rf.fit(methods_data[method][0], methods_data[method][1])
    
    print(f"\033[1m\033[0mThe best hyperparameters for {method} data:")
    for hyperparam in gs_rf.best_params_.keys():
        print(hyperparam[hyperparam.find("__") + 2:], ": ", gs_rf.best_params_[hyperparam])
        
    print(f"\033[1m\033[94mBest 10-folds CV f1-score: {gs_rf.best_score_ * 100:.2f}%.")