LAB2

import requests
from pathlib import Path

def fetch_and_cache(data_url, file, data_dir="data", force=False):
    """
    Download and cache a url and return the file object.
    
    data_url: the web address to download
    file: the file in which to save the results.
    data_dir: (default="data") the location to save the data
    force: if true the file is always re-downloaded 
    
    return: The pathlib.Path to the file.
    """
    data_dir = Path(data_dir)
    data_dir.mkdir(exist_ok=True)
    file_path = data_dir/Path(file)
    if force and file_path.exists():
        file_path.unlink()
    if force or not file_path.exists():
        print('Downloading...', end=' ')
        resp = requests.get(data_url)
        with file_path.open('wb') as f:
            f.write(resp.content)
        print('Done!')
    else:
        import time 
        created = time.ctime(file_path.stat().st_ctime)
        print("Using cached version downloaded at", created)
    return file_path

In Python, a `Path` object represents the filesystem paths to files (and other resources). The `pathlib` module is effective for writing code that works on different operating systems and filesystems. 

To check if a file exists at a path, use `.exists()`. To create a directory for a path, use `.mkdir()`. To remove a file that might be a [symbolic link](https://en.wikipedia.org/wiki/Symbolic_link), use `.unlink()`. 

This function creates a path to a directory that will contain data files. It ensures that the directory exists (which is required to write files in that directory), then proceeds to download the file based on its URL.

The benefit of this function is that not only can you force when you want a new file to be downloaded using the `force` parameter, but in cases when you don't need the file to be re-downloaded, you can use the cached version and save download time.

import zipfile
zf = zipfile.ZipFile(namesbystate_path, 'r')

column_labels = ['State', 'Sex', 'Year', 'Name', 'Count']

def load_dataframe_from_zip(zf, f):
    with zf.open(f) as fh: 
        return pd.read_csv(fh, header=None, names=column_labels)

states = [
    load_dataframe_from_zip(zf, f)
    for f in sorted(zf.filelist, key=lambda x:x.filename) 
    if f.filename.endswith('.TXT')
]

baby_names = states[0]
for state_df in states[1:]:
    baby_names = pd.concat([baby_names, state_df])
baby_names = baby_names.reset_index().iloc[:, 1:]

for n, g in elections.query("Year >= 1980").groupby("Party"):
    print(f"Name: {n}") # by the way this is an "f string", a relatively new and great feature of Python
    display(g)

(
elections.query("Year >= 1980").groupby("Party") 
                               .mean()            ## computes the mean values by party
                               .reset_index()     ## reset to a numerical index
)
# 或者 用 \ 分隔开来

elections.query("Year >= 1980").groupby("Party") \
                               .mean() \
                               .reset_index()