问包含示例数据集但延迟下载的Python包？

EN

import os
import pandas as pd
from pandasgui.utility import get_logger
from appdirs import user_data_dir
from tqdm import tqdm

logger = get_logger(__name__)

__all__ = ["all_datasets",

           "country_indicators",
           "us_shooting_incidents",
           "diamonds",
           "pokemon",
           "anscombe",
           "attention",
           "car_crashes",
           "dots",
           "exercise",
           "flights",
           "fmri",
           "gammas",
           "geyser",
           "iris",
           "mpg",
           "penguins",
           "planets",
           "tips",
           "titanic",
           "gapminder",
           "stockdata"]

dataset_names = [x for x in __all__ if x != "all_datasets"]

all_datasets = {}

root_data_dir = os.path.join(user_data_dir(), "pandasgui", "dataset_files")

# Open local data CSVs if they exists
if all([os.path.exists(os.path.join(root_data_dir, f"{name}.csv")) for name in dataset_names]):
    for name in dataset_names:
        data_path = os.path.join(root_data_dir, f"{name}.csv")

        if os.path.isfile(data_path):
            all_datasets[name] = pd.read_csv(data_path)

# Download data if it doesn't exist locally
else:
    os.makedirs(root_data_dir, exist_ok=True)

    logger.info(f"Downloading PandasGui sample datasets into {root_data_dir}...")
    pbar = tqdm(dataset_names, bar_format='{percentage:3.0f}% {bar} | {desc}')
    for name in pbar:
        pbar.set_description(f"{name}.csv")

        data_path = os.path.join(root_data_dir, f"{name}.csv")

        if os.path.isfile(data_path):
            all_datasets[name] = pd.read_csv(data_path)
        else:
            all_datasets[name] = pd.read_csv(
                os.path.join("https://raw.githubusercontent.com/adamerose/datasets/master/",
                             f"{name}.csv"))

            all_datasets[name].to_csv(data_path, index=False)

# Add the datasets to globals so they can be imported like `from pandasgui.datasets import iris`
for name in all_datasets.keys():
    globals()[name] = all_datasets[name]