DataHandler.py 文件源码

def create_codes(df, column_name, revive=False, model_code=0):
    print('Encoding', column_name, '...')
    # get unique data
    nms_unique = df[column_name].unique().tolist()

    # fit model

    if not revive:
        print('Creating new Label Encoder...')
        le = LabelEncoder()
        le.fit(nms_unique)
    else:
        # Reload LE
        le_file_name = "LE_" + str(model_code)
        le = load_pickle(ROOT_PATH + '\\Data\\PickleJar\\' + le_file_name + '.pkl')
    # get all data
    nms = df[column_name].tolist()

    return le.transform(nms), le