main_CV.py 文件源码

def LoadParseData(filename):

    data_name = filename.split('_')[0]
    pd_data = pd.read_hdf(CODE_FOLDER + "data/" + filename)
    cols_features = pd_data.drop(['ID', 'target'], 1).columns.tolist()

    pd_train = pd_data[pd_data.target >= 0]
    pd_test = pd_data[pd_data.target == -1]

    Y = pd_train['target'].values.astype(int)
    test_idx = pd_test['ID'].values.astype(int)

    X = np.array(pd_train.drop(['ID', 'target'],1))
    X_test = np.array(pd_test.drop(['ID','target'], 1))

    return X, Y, X_test, test_idx, pd_data, data_name, cols_features