GBDT_solver.py 文件源码

def generate_GBDT_model(file_name):
    train_df = read_from_file(file_name)
    #featrue 18
    selected_train_df = train_df.filter(regex='label|creativeID|positionID|connectionType|telecomsOperator|adID|camgaignID|advertiserID|appID|appPlatform|sitesetID|positionType|age|gender|education|marriageStatus|haveBaby|hometown|residence')
    train_np = selected_train_df.as_matrix()
    y = train_np[:,0]
    X = train_np[:,1:]
    print 'Train Gradient Boosting Regression Model...'
    start_time  = datetime.datetime.now()
    gbdt = GradientBoostingRegressor(n_estimators=120, max_depth=10) #, class_weight='balanced')
    gbdt.fit(X,y)
    end_time = datetime.datetime.now()
    print 'Training Done..., Time Cost: '
    print (end_time - start_time).seconds

    print 'Save Model...'
    joblib.dump(gbdt, 'GBDT.model')
    return gbdt