s11_run_xgboost_only_test.py 文件源码

def read_test_train(train_size):
    print("Load train.csv")
    train = pd.read_hdf("../modified_data/train_original.csv.hdf", 'table')
    null_count = train.isnull().sum().sum()
    if null_count > 0:
        print('Nans:', null_count)
        cols = train.isnull().any(axis=0)
        print(cols[cols == True])
        rows = train.isnull().any(axis=1)
        print(rows[rows == True])
        print('NANs in train, please check it!')
        exit()
    split = round((1-train_size)*len(train.index))
    train = train[split:]
    print("Load test.csv")
    test = pd.read_hdf("../modified_data/test.hdf", 'table')
    null_count = test.isnull().sum().sum()
    if null_count > 0:
        print('Nans:', null_count)
        cols = test.isnull().any(axis=0)
        print(cols[cols == True])
        print('NANs in test, please check it!')
        exit()
    features = get_features(train, test)
    return train, test, features