Code snippet to optimize the hyperparameters of XGBoost algorithm

hyperparameter_tuning_xgboost.py

from sklearn.model_selection import RandomizedSearchCV

xgb_clf = xgboost.XGBClassifier(random_state=SEED, n_jobs=-1)
params = {'n_estimators': [50, 100, 200, 300],
          'learning_rate': [0.01, 0.05, 0.1, 0.15],
          'min_child_weight': [1, 2, 3, 5, 10],
          'gamma': [0.1, 0.2, 0.3, 0.4, 0.5, 1],
          'subsample': [0.6, 0.7, 0.8],
          'colsample_bytree': [0.6, 0.7, 0.8],
          'max_depth': [3, 4, 5],
         }
folds = 5
param_comb = 800
random_search = RandomizedSearchCV(xgb_clf, param_distributions=params, 
                                   n_iter=param_comb, scoring='f1', 
                                   n_jobs=-1, cv=folds, verbose=3, random_state=SEED)

random_search.fit(X_train, y_train)
_ = myUtilityFunction.prediction_evaluation(random_search.best_estimator_, X_train, X_test, 
                                            y_train, y_test, 
                                            X_train.columns, "features")