logreg_employee.py

# Build logistic model classifier
pip_logmod = make_pipeline(StandardScaler(),
                           LogisticRegression(class_weight="balanced"))
hyperparam_range = np.arange(0.5, 20.1, 0.5)
hyperparam_grid = {"logisticregression__penalty": ["l1", "l2"],
                   "logisticregression__C":  hyperparam_range,
                   "logisticregression__fit_intercept": [True, False]
                  }
gs_logmodel = GridSearchCV(pip_logmod,
                           hyperparam_grid,
                           scoring="accuracy",
                           cv=2,
                           n_jobs=-1)
gs_logmodel.fit(X_train, y_train)
print(f"\033[1m\033[0mThe best hyperparameters:\n{'-' * 25}")
for hyperparam in gs_logmodel.best_params_.keys():
    print(hyperparam[hyperparam.find("__") + 2:], ": ", gs_logmodel.best_params_[hyperparam])
print(f"\033[1m\033[94mBest 10-folds CV f1-score: {gs_logmodel.best_score_ * 100:.2f}%.")