8000 [MRG] Uses gzip when caching in fetch_openml by thomasjpfan · Pull Request #11830 · scikit-learn/scikit-learn · GitHub
[go: up one dir, main page]
Skip to content

[MRG] Uses gzip when caching in fetch_openml #11830

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 5 commits into from
Sep 2, 2018
Merged

[MRG] Uses gzip when caching in fetch_openml #11830

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
5 commits
Select commit Hold shift + click to select a range
97dd729
ENH: Uses gzip when caching
thomasjpfan Aug 15, 2018
e8a713c
TST: Adjusts mocks to work with Requests
thomasjpfan Aug 16, 2018
96c9da8
Merge remote-tracking branch 'upstream/master' into fetch_openml_gzip
thomasjpfan Aug 25, 2018
74f00e3
ENH: Uses content-encoding
thomasjpfan Aug 31, 2018
b6ae1f9
BUG: Fixes for python2
thomasjpfan Sep 1, 2018
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
27 changes: 19 additions & 8 deletions sklearn/datasets/openml.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -7,18 +7,18 @@

try:
# Python 3+
from urllib.request import urlopen
from urllib.request import urlopen, Request
except ImportError:
# Python 2
from urllib2 import urlopen
from urllib2 import urlopen, Request


import numpy as np
import scipy.sparse

from sklearn.externals import _arff
from .base import get_data_home
from ..externals.six import string_types, PY2
from ..externals.six import string_types, PY2, BytesIO
from ..externals.six.moves.urllib.error import HTTPError
from ..utils import Bunch

Expand Down Expand Up @@ -50,8 +50,18 @@ def _open_openml_url(openml_path, data_home):
result : stream
A stream to the OpenML resource
"""
req = Request(_OPENML_PREFIX + openml_path)
req.add_header('Accept-encoding', 'gzip')
fsrc = urlopen(req)
is_gzip = fsrc.info().get('Content-Encoding', '') == 'gzip'

if data_home is None:
return urlopen(_OPENML_PREFIX + openml_path)
if is_gzip:
if PY2:
fsrc = BytesIO(fsrc.read())
return gzip.GzipFile(fileobj=fsrc, mode='rb')
return fsrc

local_path = os.path.join(data_home, 'openml.org', openml_path + ".gz")
if not os.path.exists(local_path):
try:
Expand All @@ -61,15 +71,16 @@ def _open_openml_url(openml_path, data_home):
pass

try:
with gzip.GzipFile(local_path, 'wb') as fdst:
fsrc = urlopen(_OPENML_PREFIX + openml_path)
with open(local_path, 'wb') as fdst:
shutil.copyfileobj(fsrc, fdst)
fsrc.close()
except Exception:
os.unlink(local_path)
raise
# XXX: unnecessary decompression on first access
return gzip.GzipFile(local_path, 'rb')
if is_gzip:
return gzip.GzipFile(local_path, 'rb')
return fsrc


def _get_json_content_from_openml_api(url, error_message, raise_if_error,
Expand Down Expand Up @@ -308,7 +319,7 @@ def _download_data_arff(file_id, sparse, data_home, encode_nominal=True):
retur 5DA0 n_type = _arff.DENSE

if PY2:
arff_file = _arff.load(response, encode_nominal=encode_nominal,
arff_file = _arff.load(response.read(), encode_nominal=encode_nominal,
return_type=return_type, )
else:
arff_file = _arff.loads(response.read().decode('utf-8'),
Expand Down
Loading
0