optuna/optuna

Hi Team, I am using XGBoost 1.3.3 and Optuna 2.4.0. My dataset has 138k rows and 300 columns (after categorical encoding). I am trying to replicate the example as in - https://github.com/optuna/optuna/blob/master/examples/pruning/xgboost_integration.py (but only for booster='gbtree'). When I run the code , I get the message 'segmentation fault' and the program returns to the $prompt (I am using amazon linux). Can anyone please help to understand as to why am I getting the message 'segmentation fault' ?

The code that I am using is as given below:

# Import data into xgb.DMatrix form 
dtrain = xgb.DMatrix(X_train,label=y_train)
dtest = xgb.DMatrix(X_test,label=y_test)

# define the search space and the objecive function
def objective(trial):
    param_sp = {
        'base_score'            : 0.5, 
        'booster'               : 'gbtree', 
        'colsample_bylevel'     : trial.suggest_categorical('colsample_bylevel',[0.7,0.8,0.9]),        
        'colsample_bynode'      : trial.suggest_categorical('colsample_bynode',[0.7,0.8,0.9]),
        'colsample_bytree'      : trial.suggest_categorical('colsample_bytree',[0.7,0.8,0.9]),
        'gamma'                 : trial.suggest_categorical('gamma',[0.0000001,0.000001,0.00001,0.0001,0.001,0.01,0.1,0.3,0.5,0.7,0.9,1,2,3,4,5,6,7,8,9,10]),    
        'learning_rate'         : trial.suggest_categorical('learning_rate',[0.1]),
        'max_delta_step'        : trial.suggest_categorical('max_delta_step', [0,1,2,3,4,5,6,7,8,9,10]),     
        'max_depth'             : trial.suggest_categorical('max_depth', [10]),
        'min_child_weight'      : trial.suggest_categorical('min_child_weight', [1,3,5,7,9,11,13,15,17,19,21]),
        'objective'             : 'binary:logistic', 
        'reg_alpha'             : trial.suggest_categorical('reg_alpha', [0.000000001,0.00000001,0.0000001,0.000001,0.00001,0.0001,0.001,0.01,0.1,1,10,100]),
        'reg_lambda'            : trial.suggest_categorical('reg_lambda', [0.000000001,0.00000001,0.0000001,0.000001,0.00001,0.0001,0.001,0.01,0.1,1,10,100]),
        'scale_pos_weight'      : trial.suggest_categorical('scale_pos_weight', [ratio1,1,10,20,30,40,50,60,70,80,90,100,1000]),        
        'seed'                  : 42, 
        'subsample'             : trial.suggest_categorical('subsample', [0.5,0.6,0.7,0.8,0.9]),        
        'verbosity'             : 1, 
        'tree_method'           :'auto',            
        'predictor'             :'cpu_predictor', 
        'eval_metric'           :'error'
    }

    #Add the pruning Call Back
    pruning_callback = optuna.integration.XGBoostPruningCallback(trial, "validation-error")

    #Perform validation
    xgb_bst=xgb.train(param_sp,dtrain,num_boost_round=1000,evals=[(dtest, "validation")],early_stopping_rounds=100,verbose_eval=False,callbacks=[pruning_callback])    

    # Set n_estimators as a trial attribute
    trial.set_user_attr("n_estimators", xgb_bst.best_ntree_limit)

    # Extract the best score.
    preds = xgb_bst.predict(dtest)
    pred_labels = np.rint(preds)
    f1 = metrics.f1_score(y_test, pred_labels)
    return f1

pruner = optuna.pruners.MedianPruner(n_startup_trials=5, n_warmup_steps=20, interval_steps=10)
study = optuna.create_study(study_name='XGB_Optuna_0.1_max_depth_10_Error_Val_500_trials',direction='minimize',sampler=TPESampler(consider_magic_clip=True,seed=42,multivariate=False),pruner=pruner)

# perform the search
print('\nPerforming Bayesian Hyper Parameter Optimization..')
study.optimize(objective, n_trials=500,n_jobs=16)