scikit-learn: fetch_california_housing() URLError:
Description
I am unable to use fetch_california_housing() to download sample data set. Looks like certificate may have expired?
Steps/Code to Reproduce
print(‘The scikit-learn version is {}.’.format(sklearn.version)) from sklearn.datasets import fetch_california_housing housing = fetch_california_housing()
Actual Results
Downloading Cal. housing from https://ndownloader.figshare.com/files/5976036 to /Users/test/scikit_learn_data
The scikit-learn version is 0.19.1.
---------------------------------------------------------------------------
SSLError Traceback (most recent call last)
/Library/Frameworks/Python.framework/Versions/3.6/lib/python3.6/urllib/request.py in do_open(self, http_class, req, **http_conn_args)
1317 h.request(req.get_method(), req.selector, req.data, headers,
-> 1318 encode_chunked=req.has_header('Transfer-encoding'))
1319 except OSError as err: # timeout error
/Library/Frameworks/Python.framework/Versions/3.6/lib/python3.6/http/client.py in request(self, method, url, body, headers, encode_chunked)
1238 """Send a complete request to the server."""
-> 1239 self._send_request(method, url, body, headers, encode_chunked)
1240
/Library/Frameworks/Python.framework/Versions/3.6/lib/python3.6/http/client.py in _send_request(self, method, url, body, headers, encode_chunked)
1284 body = _encode(body, 'body')
-> 1285 self.endheaders(body, encode_chunked=encode_chunked)
1286
/Library/Frameworks/Python.framework/Versions/3.6/lib/python3.6/http/client.py in endheaders(self, message_body, encode_chunked)
1233 raise CannotSendHeader()
-> 1234 self._send_output(message_body, encode_chunked=encode_chunked)
1235
/Library/Frameworks/Python.framework/Versions/3.6/lib/python3.6/http/client.py in _send_output(self, message_body, encode_chunked)
1025 del self._buffer[:]
-> 1026 self.send(msg)
1027
/Library/Frameworks/Python.framework/Versions/3.6/lib/python3.6/http/client.py in send(self, data)
963 if self.auto_open:
--> 964 self.connect()
965 else:
/Library/Frameworks/Python.framework/Versions/3.6/lib/python3.6/http/client.py in connect(self)
1399 self.sock = self._context.wrap_socket(self.sock,
-> 1400 server_hostname=server_hostname)
1401 if not self._context.check_hostname and self._check_hostname:
/Library/Frameworks/Python.framework/Versions/3.6/lib/python3.6/ssl.py in wrap_socket(self, sock, server_side, do_handshake_on_connect, suppress_ragged_eofs, server_hostname, session)
400 server_hostname=server_hostname,
--> 401 _context=self, _session=session)
402
/Library/Frameworks/Python.framework/Versions/3.6/lib/python3.6/ssl.py in __init__(self, sock, keyfile, certfile, server_side, cert_reqs, ssl_version, ca_certs, do_handshake_on_connect, family, type, proto, fileno, suppress_ragged_eofs, npn_protocols, ciphers, server_hostname, _context, _session)
807 raise ValueError("do_handshake_on_connect should not be specified for non-blocking sockets")
--> 808 self.do_handshake()
809
/Library/Frameworks/Python.framework/Versions/3.6/lib/python3.6/ssl.py in do_handshake(self, block)
1060 self.settimeout(None)
-> 1061 self._sslobj.do_handshake()
1062 finally:
/Library/Frameworks/Python.framework/Versions/3.6/lib/python3.6/ssl.py in do_handshake(self)
682 """Start the SSL/TLS handshake."""
--> 683 self._sslobj.do_handshake()
684 if self.context.check_hostname:
SSLError: [SSL: CERTIFICATE_VERIFY_FAILED] certificate verify failed (_ssl.c:749)
During handling of the above exception, another exception occurred:
URLError Traceback (most recent call last)
<ipython-input-18-dc07bc139b51> in <module>()
1 print('The scikit-learn version is {}.'.format(sklearn.__version__))
2 from sklearn.datasets import fetch_california_housing
----> 3 housing = fetch_california_housing()
/Library/Frameworks/Python.framework/Versions/3.6/lib/python3.6/site-packages/sklearn/datasets/california_housing.py in fetch_california_housing(data_home, download_if_missing)
99 ARCHIVE.url, data_home))
100
--> 101 archive_path = _fetch_remote(ARCHIVE, dirname=data_home)
102
103 with tarfile.open(mode="r:gz", name=archive_path) as f:
/Library/Frameworks/Python.framework/Versions/3.6/lib/python3.6/site-packages/sklearn/datasets/base.py in _fetch_remote(remote, dirname)
872 file_path = (remote.filename if dirname is None
873 else join(dirname, remote.filename))
--> 874 urlretrieve(remote.url, file_path)
875 checksum = _sha256(file_path)
876 if remote.checksum != checksum:
/Library/Frameworks/Python.framework/Versions/3.6/lib/python3.6/urllib/request.py in urlretrieve(url, filename, reporthook, data)
246 url_type, path = splittype(url)
247
--> 248 with contextlib.closing(urlopen(url, data)) as fp:
249 headers = fp.info()
250
/Library/Frameworks/Python.framework/Versions/3.6/lib/python3.6/urllib/request.py in urlopen(url, data, timeout, cafile, capath, cadefault, context)
221 else:
222 opener = _opener
--> 223 return opener.open(url, data, timeout)
224
225 def install_opener(opener):
/Library/Frameworks/Python.framework/Versions/3.6/lib/python3.6/urllib/request.py in open(self, fullurl, data, timeout)
524 req = meth(req)
525
--> 526 response = self._open(req, data)
527
528 # post-process response
/Library/Frameworks/Python.framework/Versions/3.6/lib/python3.6/urllib/request.py in _open(self, req, data)
542 protocol = req.type
543 result = self._call_chain(self.handle_open, protocol, protocol +
--> 544 '_open', req)
545 if result:
546 return result
/Library/Frameworks/Python.framework/Versions/3.6/lib/python3.6/urllib/request.py in _call_chain(self, chain, kind, meth_name, *args)
502 for handler in handlers:
503 func = getattr(handler, meth_name)
--> 504 result = func(*args)
505 if result is not None:
506 return result
/Library/Frameworks/Python.framework/Versions/3.6/lib/python3.6/urllib/request.py in https_open(self, req)
1359 def https_open(self, req):
1360 return self.do_open(http.client.HTTPSConnection, req,
-> 1361 context=self._context, check_hostname=self._check_hostname)
1362
1363 https_request = AbstractHTTPHandler.do_request_
/Library/Frameworks/Python.framework/Versions/3.6/lib/python3.6/urllib/request.py in do_open(self, http_class, req, **http_conn_args)
1318 encode_chunked=req.has_header('Transfer-encoding'))
1319 except OSError as err: # timeout error
-> 1320 raise URLError(err)
1321 r = h.getresponse()
1322 except:
URLError: <urlopen error [SSL: CERTIFICATE_VERIFY_FAILED] certificate verify failed (_ssl.c:749)>
About this issue
- Original URL
- State: closed
- Created 7 years ago
- Comments: 16 (5 by maintainers)
UGH!
I found the problem. python 3.6 on mac requires a post install step
$ less /Applications/Python\ 3.6/ReadMe.rtf
" Unlike previous releases, the deprecated Apple-supplied OpenSSL libraries are no longer used. This also means that the trust certificates in system and user keychains managed by the Keychain Access application and the security command line utility are no longer used as defaults"
The solution is
$ sudo /Applications/Python\ 3.6/Install\ Certificates.command
Found solution here: http://blog.pengyifan.com/how-to-fix-python-ssl-certificate_verify_failed/
On Mac with Python 3.10, a similar solution as suggested by @AEDWIP worked:
% sudo /Applications/Python\ 3.10/Install\ Certificates.command
Worked for me on Google Colab as well.