import optuna

import lightgbm as lgb
import sklearn.datasets
import sklearn.metrics
from sklearn.model_selection import train_test_split


def objective(trial):
    data, target = sklearn.datasets.load_breast_cancer(return_X_y=True)
    train_x, valid_x, train_y, valid_y = train_test_split(data, target, test_size=0.25)
    dtrain = lgb.Dataset(train_x, label=train_y)
    dvalid = lgb.Dataset(valid_x, label=valid_y)

    param = {
        "objective": "binary",
        "metric": "auc",
        "verbosity": -1,
        "boosting_type": "gbdt",
        "lambda_l1": trial.suggest_float("lambda_l1", 1e-8, 10.0, log=True),
        "lambda_l2": trial.suggest_float("lambda_l2", 1e-8, 10.0, log=True),
        "num_leaves": trial.suggest_int("num_leaves", 2, 256),
        "feature_fraction": trial.suggest_float("feature_fraction", 0.4, 1.0),
        "bagging_fraction": trial.suggest_float("bagging_fraction", 0.4, 1.0),
        "bagging_freq": trial.suggest_int("bagging_freq", 1, 7),
        "min_child_samples": trial.suggest_int("min_child_samples", 5, 100),
    }

    # Add a callback for pruning.
    pruning_callback = optuna.integration.LightGBMPruningCallback(trial, "auc")
    evals_result = {}
    evals_result_callback = lgb.record_evaluation(evals_result)
    gbm = lgb.train(param, dtrain, valid_sets=[dvalid], callbacks=[pruning_callback, evals_result_callback])

    preds = gbm.predict(valid_x)
    accuracy = sklearn.metrics.roc_auc_score(valid_y, preds)
    return accuracy
    # return max(evals_result['valid_0']['auc'])


if __name__ == "__main__":
    study = optuna.create_study(
        study_name="lightGBM 01", storage="sqlite:///db.sqlite3",
        pruner=optuna.pruners.MedianPruner(n_warmup_steps=10), direction="maximize"
    )
    # study = optuna.create_study(pruner=optuna.pruners.MedianPruner(n_warmup_steps=10), direction="maximize")
    study.optimize(objective, n_trials=500)
    # study.optimize(objective)

    print("Number of finished trials: {}".format(len(study.trials)))

    print("Best trial:")
    trial = study.best_trial

    print("  Value: {}".format(trial.value))

    print("  Params: ")
    for key, value in trial.params.items():
        print("    {}: {}".format(key, value))