导入fetch_california_housing 加州房价数据集报错解决（HTTPError: HTTP Error 403: Forbidden）

报错

HTTPError                                 Traceback (most recent call last)
Cell In[3], line 5
      2 from sklearn.datasets import fetch_california_housing
      3 from sklearn.model_selection import train_test_split
----> 5 X, Y = fetch_california_housing(return_X_y=True)
      6 print(X.shape), # (20640, 8)
      7 print(Y.shape) #  (20640, )

File ~\miniconda3\lib\site-packages\sklearn\datasets\_california_housing.py:138, in fetch_california_housing(data_home, download_if_missing, return_X_y, as_frame)
    132     raise IOError("Data not found and `download_if_missing` is False")
    134 logger.info(
    135     "Downloading Cal. housing from {} to {}".format(ARCHIVE.url, data_home)
    136 )
--> 138 archive_path = _fetch_remote(ARCHIVE, dirname=data_home)
    140 with tarfile.open(mode="r:gz", name=archive_path) as f:
    141     cal_housing = np.loadtxt(
    142         f.extractfile("CaliforniaHousing/cal_housing.data"), delimiter=","
    143     )

File ~\miniconda3\lib\site-packages\sklearn\datasets\_base.py:1324, in _fetch_remote(remote, dirname)
   1302 """Helper function to download a remote dataset into path
   1303 
   1304 Fetch a dataset pointed by remote's url, save into path using remote's
   (...)
   1320     Full path of the created file.
   1321 """
   1323 file_path = remote.filename if dirname is None else join(dirname, remote.filename)
-> 1324 urlretrieve(remote.url, file_path)
   1325 checksum = _sha256(file_path)
   1326 if remote.checksum != checksum:

File ~\miniconda3\lib\urllib\request.py:241, in urlretrieve(url, filename, reporthook, data)
    224 """
    225 Retrieve a URL into a temporary location on disk.
    226 
   (...)
    237 data file as well as the resulting HTTPMessage object.
    238 """
    239 url_type, path = _splittype(url)
--> 241 with contextlib.closing(urlopen(url, data)) as fp:
    242     headers = fp.info()
    244     # Just return the local path and the "headers" for file://
    245     # URLs. No sense in performing a copy unless requested.

File ~\miniconda3\lib\urllib\request.py:216, in urlopen(url, data, timeout, cafile, capath, cadefault, context)
    214 else:
    215     opener = _opener
--> 216 return opener.open(url, data, timeout)

File ~\miniconda3\lib\urllib\request.py:525, in OpenerDirector.open(self, fullurl, data, timeout)
    523 for processor in self.process_response.get(protocol, []):
    524     meth = getattr(processor, meth_name)
--> 525     response = meth(req, response)
    527 return response

File ~\miniconda3\lib\urllib\request.py:634, in HTTPErrorProcessor.http_response(self, request, response)
    631 # According to RFC 2616, "2xx" code indicates that the client's
    632 # request was successfully received, understood, and accepted.
    633 if not (200 <= code < 300):
--> 634     response = self.parent.error(
    635         'http', request, response, code, msg, hdrs)
    637 return response

File ~\miniconda3\lib\urllib\request.py:563, in OpenerDirector.error(self, proto, *args)
    561 if http_err:
    562     args = (dict, 'default', 'http_error_default') + orig_args
--> 563     return self._call_chain(*args)

File ~\miniconda3\lib\urllib\request.py:496, in OpenerDirector._call_chain(self, chain, kind, meth_name, *args)
    494 for handler in handlers:
    495     func = getattr(handler, meth_name)
--> 496     result = func(*args)
    497     if result is not None:
    498         return result

File ~\miniconda3\lib\urllib\request.py:643, in HTTPDefaultErrorHandler.http_error_default(self, req, fp, code, msg, hdrs)
    642 def http_error_default(self, req, fp, code, msg, hdrs):
--> 643     raise HTTPError(req.full_url, code, msg, hdrs, fp)

HTTPError: HTTP Error 403: Forbidden

先手动下载数据（https://www.dcc.fc.up.pt/~ltorgo/Regression/cal_housing.tgz）

PS：

1. 报错文件 File ~\miniconda3\lib\site-packages\sklearn\datasets\_california_housing.py:138, in fetch_california_housing(data_home, download_if_missing, return_X_y, as_frame)

2. 找到文件打开，43行有下载地址

3. 复制下载后的cal_housing.tgz文件到指定文件夹，无需解压。需要复制到的文件夹需要从代码里获取，获取代码如下：
   
   4.更改 _california_housing.py文件,将def fetch_california_housing()这个函数内的archive_path这段代码更改为如下

重启 jupyter notebook即可，Windows系统也相同操作