个人笔记

# Credits: https://linuxhandbook.com/clear-pip-cache/
pip cache info # 查看缓存信息
pip cache list # 查找各个包的缓存
pip cache dir # 查找缓存所在的目录
pip cache remove [package_name] # 从缓存中删除特定包
pip cache remove * # 从缓存中删除每个包
pip cache purge # 从 pip 缓存中删除所有内容
sudo rm -rf /root/.cache/pip # 手动删除 pip 缓存
pip install package_name --no-cache-dir # 安装没有缓存的包

xgboost 2.0.1: 436.63 MB
----------------------------------------
catboost 1.2.2: 298.30 MB
----------------------------------------
httpstan 4.10.1: 214.71 MB
----------------------------------------
llvmlite 0.41.1: 134.52 MB
----------------------------------------
scipy 1.11.3: 96.34 MB

# Credits: https://stackoverflow.com/a/67914559/11067496
sort_in_descending = True   # Show packages in descending order

import os
import pkg_resources
from tqdm import tqdm

def calc_container(path):
    total_size = 0
    for dirpath, _, filenames in os.walk(path):
        for f in filenames:
            fp = os.path.join(dirpath, f)
            total_size += os.path.getsize(fp)
    return total_size

dists = [d for d in pkg_resources.working_set]
dists_with_size = {}

for dist in tqdm(dists):
    try:
        path = os.path.join(dist.location, dist.project_name)
        size = calc_container(path)
        dists_with_size[size] = dist
    except OSError:
        '{} no longer exists'.format(dist.project_name)

# Sort packages size
dists_with_size = dict(sorted(dists_with_size.items(), reverse=sort_in_descending))

for size, dist in dists_with_size.items():
    if size/1000 > 1.0:
        print (f"{dist}: {size/1000000:.2f} MB")
        print("-"*40)

def foo():
    print("foo() from module.py")

if __name__ == '__main__':
    print("module.py is being run directly")
else:
    print("module.py is being imported into another module")