XGB_solver.py 文件源码

def generate_XGB_model(train_df):
    train_df.drop(['conversionTime'], axis=1, inplace=True)
    print 'Train And Fix Missing App Count Value...'
    train_df, xgb_appcount = train_model_for_appcounts(train_df)
    joblib.dump(xgb_appcount, 'XGB_missing.model')
    '''print 'Train And Fix Missing Age Value...'
    train_df, xgb_age = train_model_for_age(train_df)
    joblib.dump(xgb_age, 'XGB_age.model')'''
    train_df.drop(['marriageStatus','haveBaby','sitesetID', 'positionType'], axis=1, inplace=True)
    print 'Done'
    print train_df.info()
    print train_df.describe()
    print train_df.isnull().sum()
    train_np = train_df.as_matrix()
    y = train_np[:,0]
    X = train_np[:,1:]
    print 'Train Xgboost Model...'
    start_time  = datetime.datetime.now()
    xbg_clf = XGBRegressor(n_estimators=100, max_depth=6, objective="binary:logistic", silent=False)
    xbg_clf.fit(X,y)
    end_time = datetime.datetime.now()
    print 'Training Done..., Time Cost: %d' % ((end_time - start_time).seconds)
    model_df = pd.DataFrame({'columns':list(train_df.columns)[1:], 'values':xbg_clf.feature_importances_})
    print model_df
    return xbg_clf