multi_input.py 文件源码

def fetch_data():
    """Download the data."""
    train_file = tempfile.NamedTemporaryFile()
    test_file = tempfile.NamedTemporaryFile()
    req.urlretrieve("http://mlr.cs.umass.edu/ml/machine-learning-databases"
                    "/adult/adult.data", train_file.name)
    req.urlretrieve("http://mlr.cs.umass.edu/ml/machine-learning-databases/"
                    "adult/adult.test", test_file.name)

    df_train = pd.read_csv(train_file, names=COLUMNS, skipinitialspace=True)
    df_test = pd.read_csv(test_file, names=COLUMNS, skipinitialspace=True,
                          skiprows=1)

    df_train[LABEL_COLUMN] = (df_train["income_bracket"]
                              .apply(lambda x: ">50K" in x)).astype(int)
    df_test[LABEL_COLUMN] = (df_test["income_bracket"]
                             .apply(lambda x: ">50K" in x)).astype(int)

    return df_train, df_test