191 lines
5.9 KiB
Python
191 lines
5.9 KiB
Python
"""
|
|
Backports of fixes for joblib dependencies
|
|
"""
|
|
import os
|
|
import re
|
|
import time
|
|
|
|
from os.path import basename
|
|
from multiprocessing import util
|
|
|
|
# Prior to joblib 1.2, joblib used to import LooseVersion from
|
|
# distutils.version. This import had a side-effect with setuptools that was
|
|
# implicitly required in sklearn.show_versions() to work without raising an
|
|
# exception for scikit-learn 1.0 and earlier. This has been fixed in
|
|
# scikit-learn 1.1 (not yet released at the time of writing), see:
|
|
# https://github.com/scikit-learn/scikit-learn/issues/22614
|
|
#
|
|
# To avoid unnecessary disruption for users who might update to joblib 1.2
|
|
# prior to a release of scikit-learn that includes the fix, let's keep on
|
|
# importing distutils here. TODO: Remove this for a future release of joblib,
|
|
# e.g. 6 months after the release of scikit-learn 1.1.
|
|
import distutils # noqa
|
|
|
|
|
|
class Version:
|
|
"""Backport from deprecated distutils
|
|
|
|
We maintain this backport to avoid introducing a new dependency on
|
|
`packaging`.
|
|
|
|
We might rexplore this choice in the future if all major Python projects
|
|
introduce a dependency on packaging anyway.
|
|
"""
|
|
|
|
def __init__(self, vstring=None):
|
|
if vstring:
|
|
self.parse(vstring)
|
|
|
|
def __repr__(self):
|
|
return "%s ('%s')" % (self.__class__.__name__, str(self))
|
|
|
|
def __eq__(self, other):
|
|
c = self._cmp(other)
|
|
if c is NotImplemented:
|
|
return c
|
|
return c == 0
|
|
|
|
def __lt__(self, other):
|
|
c = self._cmp(other)
|
|
if c is NotImplemented:
|
|
return c
|
|
return c < 0
|
|
|
|
def __le__(self, other):
|
|
c = self._cmp(other)
|
|
if c is NotImplemented:
|
|
return c
|
|
return c <= 0
|
|
|
|
def __gt__(self, other):
|
|
c = self._cmp(other)
|
|
if c is NotImplemented:
|
|
return c
|
|
return c > 0
|
|
|
|
def __ge__(self, other):
|
|
c = self._cmp(other)
|
|
if c is NotImplemented:
|
|
return c
|
|
return c >= 0
|
|
|
|
|
|
class LooseVersion(Version):
|
|
"""Backport from deprecated distutils
|
|
|
|
We maintain this backport to avoid introducing a new dependency on
|
|
`packaging`.
|
|
|
|
We might rexplore this choice in the future if all major Python projects
|
|
introduce a dependency on packaging anyway.
|
|
"""
|
|
|
|
component_re = re.compile(r'(\d+ | [a-z]+ | \.)', re.VERBOSE)
|
|
|
|
def __init__(self, vstring=None):
|
|
if vstring:
|
|
self.parse(vstring)
|
|
|
|
def parse(self, vstring):
|
|
# I've given up on thinking I can reconstruct the version string
|
|
# from the parsed tuple -- so I just store the string here for
|
|
# use by __str__
|
|
self.vstring = vstring
|
|
components = [x for x in self.component_re.split(vstring)
|
|
if x and x != '.']
|
|
for i, obj in enumerate(components):
|
|
try:
|
|
components[i] = int(obj)
|
|
except ValueError:
|
|
pass
|
|
|
|
self.version = components
|
|
|
|
def __str__(self):
|
|
return self.vstring
|
|
|
|
def __repr__(self):
|
|
return "LooseVersion ('%s')" % str(self)
|
|
|
|
def _cmp(self, other):
|
|
if isinstance(other, str):
|
|
other = LooseVersion(other)
|
|
elif not isinstance(other, LooseVersion):
|
|
return NotImplemented
|
|
|
|
if self.version == other.version:
|
|
return 0
|
|
if self.version < other.version:
|
|
return -1
|
|
if self.version > other.version:
|
|
return 1
|
|
|
|
|
|
try:
|
|
import numpy as np
|
|
|
|
def make_memmap(filename, dtype='uint8', mode='r+', offset=0,
|
|
shape=None, order='C', unlink_on_gc_collect=False):
|
|
"""Custom memmap constructor compatible with numpy.memmap.
|
|
|
|
This function:
|
|
- is a backport the numpy memmap offset fix (See
|
|
https://github.com/numpy/numpy/pull/8443 for more details.
|
|
The numpy fix is available starting numpy 1.13)
|
|
- adds ``unlink_on_gc_collect``, which specifies explicitly whether
|
|
the process re-constructing the memmap owns a reference to the
|
|
underlying file. If set to True, it adds a finalizer to the
|
|
newly-created memmap that sends a maybe_unlink request for the
|
|
memmaped file to resource_tracker.
|
|
"""
|
|
util.debug(
|
|
"[MEMMAP READ] creating a memmap (shape {}, filename {}, "
|
|
"pid {})".format(shape, basename(filename), os.getpid())
|
|
)
|
|
|
|
mm = np.memmap(filename, dtype=dtype, mode=mode, offset=offset,
|
|
shape=shape, order=order)
|
|
if LooseVersion(np.__version__) < '1.13':
|
|
mm.offset = offset
|
|
if unlink_on_gc_collect:
|
|
from ._memmapping_reducer import add_maybe_unlink_finalizer
|
|
add_maybe_unlink_finalizer(mm)
|
|
return mm
|
|
except ImportError:
|
|
def make_memmap(filename, dtype='uint8', mode='r+', offset=0,
|
|
shape=None, order='C', unlink_on_gc_collect=False):
|
|
raise NotImplementedError(
|
|
"'joblib.backports.make_memmap' should not be used "
|
|
'if numpy is not installed.')
|
|
|
|
|
|
if os.name == 'nt':
|
|
# https://github.com/joblib/joblib/issues/540
|
|
access_denied_errors = (5, 13)
|
|
from os import replace
|
|
|
|
def concurrency_safe_rename(src, dst):
|
|
"""Renames ``src`` into ``dst`` overwriting ``dst`` if it exists.
|
|
|
|
On Windows os.replace can yield permission errors if executed by two
|
|
different processes.
|
|
"""
|
|
max_sleep_time = 1
|
|
total_sleep_time = 0
|
|
sleep_time = 0.001
|
|
while total_sleep_time < max_sleep_time:
|
|
try:
|
|
replace(src, dst)
|
|
break
|
|
except Exception as exc:
|
|
if getattr(exc, 'winerror', None) in access_denied_errors:
|
|
time.sleep(sleep_time)
|
|
total_sleep_time += sleep_time
|
|
sleep_time *= 2
|
|
else:
|
|
raise
|
|
else:
|
|
raise
|
|
else:
|
|
from os import replace as concurrency_safe_rename # noqa
|