GBDT_solver.py 文件源码

def select_model(file_name):
    train_df = read_from_file(file_name)
    #featrue 16
    selected_train_df = train_df.filter(regex='label|creativeID|positionID|connectionType|telecomsOperator|adID|camgaignID|advertiserID|appID|appPlatform|sitesetID|positionType|age|gender|education|marriageStatus|haveBaby')
    train_np = selected_train_df.as_matrix()
    y = train_np[:,0]
    X = train_np[:,1:]

    print 'Select Model...'
    start_time  = datetime.datetime.now()
    gbdt = GradientBoostingRegressor() 
    parameters = {'n_estimators': [10000, 12000], 'max_depth':[16,15, 14]}
    grid_search = GridSearchCV(estimator=gbdt, param_grid=parameters, cv=10, n_jobs=-1)
    print("parameters:")
    pprint.pprint(parameters)
    grid_search.fit(X, y)
    print("Best score: %0.3f" % grid_search.best_score_)
    print("Best parameters set:")
    best_parameters=grid_search.best_estimator_.get_params()
    for param_name in sorted(parameters.keys()):
        print("\t%s: %r" % (param_name, best_parameters[param_name]))
    end_time = datetime.datetime.now()
    print 'Select Done..., Time Cost: %d' % ((end_time - start_time).seconds)