How to make Optuna get replicable results?

Question

I'm using optuna to tune LGBM. Random seeds had been set but each time Optuna got different set of best params.

Here's my optuna code:

def get_hpo_params(opt_X_train, opt_X_val, opt_y_train, opt_y_val, n_trials=180, cat_features=""):

def objective(trial):
    dtrain = lgb.Dataset(opt_X_train, opt_y_train, categorical_feature=cat_features)
    dval = lgb.Dataset(opt_X_val, opt_y_val, categorical_feature=cat_features)
    upper = min(32768, int(opt_X_train.shape[0]))

    params = {
        "objective": "binary",
        "metric": "auc",
        "random_state": 10,
        "verbosity": -1,
        "boosting": "gbdt",
        "num_threads": 4,

        "num_leaves": trial.suggest_int("num_leaves", 4, 30),
        "learning_rate": trial.suggest_loguniform("learning_rate", 0.005, 1.0),
        "bagging_fraction": trial.suggest_uniform("bagging_fraction", 0.1, 1.0),
        "feature_fraction": trial.suggest_uniform("feature_fraction", 0.1, 1.0),
        "bagging_freq": trial.suggest_int("bagging_freq", 10, 30),
        "min_data_in_leaf": trial.suggest_int("min_data_in_leaf", 1000, 3000),
        "num_iterations": trial.suggest_int("num_iterations", 1000, 3000)
    }

    pruning_callback = optuna.integration.LightGBMPruningCallback(trial, "auc")
    clf = lgb.train(
        params, dtrain, valid_sets=[dval], verbose_eval=False, callbacks=[pruning_callback]
    )

    y_val_pred = clf.predict(opt_X_val)
    auc = roc_auc_score(opt_y_val, y_val_pred)
    return auc


start = timeit.default_timer()
study = optuna.create_study(direction="maximize", pruner=optuna.pruners.HyperbandPruner(),
                           sampler=optuna.samplers.TPESampler(seed=10), study_name='lgbm_hpo')
study.optimize(objective, n_trials=n_trials)

print("Number of finished trials: {}".format(len(study.trials)))
best_trial = study.best_trial
print(f"Best trial performance: {best_trial.value}")
stop = timeit.default_timer()
print('Time (min): ', (stop - start)/60)

return best_trial.params

If I restart my ipython notebook kernel, the results will be different. Is there anyway to make optuna output reproducable?

Answer 1

Ohh, I finally solved the problem. Need to set hash seed on my laptop using this method: https://gerrychain.readthedocs.io/en/latest/topics/reproducibility.html#set-pythonhashseed-0

This solution is mentioned in optuna for reproducing pruning behaviour: https://optuna.readthedocs.io/en/stable/reference/generated/optuna.pruners.HyperbandPruner.html