main_load_data_DiDi.py 文件源码

def cluster_map_sheet_pre():
    print("------ load cluster_map data ----------")
    cluster_map_sheet_path = os.path.join(LOAD_DATA_DIR, CONCRETE_DIR, CLUSTER_MAP_SHEET_DIR)
    print("load data from: ", cluster_map_sheet_path)
    save_path = os.path.join(SAVE_DATA_DIR, CONCRETE_DIR, CLUSTER_MAP_SHEET_DIR)
    print("save data to: ", save_path)
    file = "cluster_map"

    cluster_sheet = os.path.join(cluster_map_sheet_path, file)
    data = pd.read_csv(cluster_sheet,header=-1)
    data.columns = ["raw"]
    data["district_hash"] = data["raw"].map(lambda x: x.split("\t")[0])
    data["district_map"] = data['raw'].map(lambda x: x.split("\t")[1])

    del data["raw"]

    save_df_to_file(data, save_path, file)


# handle the order_info sheet