2014-07-05 18:49:34 +00:00
|
|
|
#!/usr/bin/env python
|
2016-01-15 17:57:01 +00:00
|
|
|
from __future__ import print_function
|
2016-10-18 22:27:57 +00:00
|
|
|
import io
|
2015-12-13 10:49:17 +00:00
|
|
|
import os
|
|
|
|
import subprocess
|
2014-07-05 18:49:34 +00:00
|
|
|
import sys
|
2015-12-13 22:32:23 +00:00
|
|
|
import contextlib
|
2015-10-12 22:31:59 +00:00
|
|
|
from distutils.command.build_ext import build_ext
|
2015-12-13 10:49:17 +00:00
|
|
|
from distutils.sysconfig import get_python_inc
|
2016-04-28 20:10:43 +00:00
|
|
|
from distutils import ccompiler, msvccompiler
|
2017-05-03 18:10:59 +00:00
|
|
|
from setuptools import Extension, setup, find_packages
|
2015-12-13 10:49:17 +00:00
|
|
|
|
|
|
|
|
2016-11-06 10:58:26 +00:00
|
|
|
PACKAGE_DATA = {'': ['*.pyx', '*.pxd', '*.txt', '*.tokens']}
|
|
|
|
|
|
|
|
|
2017-05-03 18:10:59 +00:00
|
|
|
PACKAGES = find_packages()
|
2015-12-13 10:49:17 +00:00
|
|
|
|
|
|
|
|
|
|
|
MOD_NAMES = [
|
2018-02-20 16:32:13 +00:00
|
|
|
'spacy._align',
|
2015-12-13 10:49:17 +00:00
|
|
|
'spacy.parts_of_speech',
|
|
|
|
'spacy.strings',
|
|
|
|
'spacy.lexeme',
|
|
|
|
'spacy.vocab',
|
|
|
|
'spacy.attrs',
|
|
|
|
'spacy.morphology',
|
2016-10-15 23:47:12 +00:00
|
|
|
'spacy.pipeline',
|
2015-12-13 10:49:17 +00:00
|
|
|
'spacy.syntax.stateclass',
|
2016-02-01 02:00:53 +00:00
|
|
|
'spacy.syntax._state',
|
2017-08-18 19:56:19 +00:00
|
|
|
'spacy.syntax._beam_utils',
|
2015-12-13 10:49:17 +00:00
|
|
|
'spacy.tokenizer',
|
2017-05-13 23:20:28 +00:00
|
|
|
'spacy.syntax.nn_parser',
|
2016-03-01 09:09:08 +00:00
|
|
|
'spacy.syntax.nonproj',
|
2015-12-13 10:49:17 +00:00
|
|
|
'spacy.syntax.transition_system',
|
|
|
|
'spacy.syntax.arc_eager',
|
|
|
|
'spacy.gold',
|
|
|
|
'spacy.tokens.doc',
|
|
|
|
'spacy.tokens.span',
|
|
|
|
'spacy.tokens.token',
|
|
|
|
'spacy.matcher',
|
|
|
|
'spacy.syntax.ner',
|
2016-03-10 12:01:34 +00:00
|
|
|
'spacy.symbols',
|
2017-06-05 10:32:22 +00:00
|
|
|
'spacy.vectors',
|
2017-06-05 10:45:29 +00:00
|
|
|
]
|
2015-12-13 10:49:17 +00:00
|
|
|
|
|
|
|
|
2016-11-06 10:58:26 +00:00
|
|
|
COMPILE_OPTIONS = {
|
2016-04-12 08:12:57 +00:00
|
|
|
'msvc': ['/Ox', '/EHsc'],
|
2018-01-14 13:34:36 +00:00
|
|
|
'mingw32' : ['-O2', '-Wno-strict-prototypes', '-Wno-unused-function'],
|
|
|
|
'other' : ['-O2', '-Wno-strict-prototypes', '-Wno-unused-function']
|
2016-02-05 13:43:52 +00:00
|
|
|
}
|
2015-10-12 22:31:59 +00:00
|
|
|
|
2016-02-05 13:43:52 +00:00
|
|
|
|
2016-11-06 10:58:26 +00:00
|
|
|
LINK_OPTIONS = {
|
2016-02-05 13:43:52 +00:00
|
|
|
'msvc' : [],
|
|
|
|
'mingw32': [],
|
|
|
|
'other' : []
|
|
|
|
}
|
|
|
|
|
2016-12-20 10:05:06 +00:00
|
|
|
|
2016-11-06 10:58:26 +00:00
|
|
|
# I don't understand this very well yet. See Issue #267
|
|
|
|
# Fingers crossed!
|
2017-10-27 10:16:58 +00:00
|
|
|
USE_OPENMP_DEFAULT = '0' if sys.platform != 'darwin' else None
|
2016-11-06 10:58:26 +00:00
|
|
|
if os.environ.get('USE_OPENMP', USE_OPENMP_DEFAULT) == '1':
|
|
|
|
if sys.platform == 'darwin':
|
|
|
|
COMPILE_OPTIONS['other'].append('-fopenmp')
|
|
|
|
LINK_OPTIONS['other'].append('-fopenmp')
|
|
|
|
PACKAGE_DATA['spacy.platform.darwin.lib'] = ['*.dylib']
|
|
|
|
PACKAGES.append('spacy.platform.darwin.lib')
|
|
|
|
|
|
|
|
elif sys.platform == 'win32':
|
|
|
|
COMPILE_OPTIONS['msvc'].append('/openmp')
|
|
|
|
|
|
|
|
else:
|
|
|
|
COMPILE_OPTIONS['other'].append('-fopenmp')
|
|
|
|
LINK_OPTIONS['other'].append('-fopenmp')
|
2015-01-06 01:34:55 +00:00
|
|
|
|
2017-05-07 16:36:35 +00:00
|
|
|
|
2016-04-19 17:50:42 +00:00
|
|
|
# By subclassing build_extensions we have the actual compiler that will be used which is really known only after finalize_options
|
|
|
|
# http://stackoverflow.com/questions/724664/python-distutils-how-to-get-a-compiler-that-is-going-to-be-used
|
2015-12-13 10:49:17 +00:00
|
|
|
class build_ext_options:
|
|
|
|
def build_options(self):
|
|
|
|
for e in self.extensions:
|
2016-11-06 10:58:26 +00:00
|
|
|
e.extra_compile_args += COMPILE_OPTIONS.get(
|
|
|
|
self.compiler.compiler_type, COMPILE_OPTIONS['other'])
|
2015-12-13 10:49:17 +00:00
|
|
|
for e in self.extensions:
|
2016-11-06 10:58:26 +00:00
|
|
|
e.extra_link_args += LINK_OPTIONS.get(
|
|
|
|
self.compiler.compiler_type, LINK_OPTIONS['other'])
|
2015-01-17 05:19:54 +00:00
|
|
|
|
|
|
|
|
2015-12-13 10:49:17 +00:00
|
|
|
class build_ext_subclass(build_ext, build_ext_options):
|
|
|
|
def build_extensions(self):
|
|
|
|
build_ext_options.build_options(self)
|
|
|
|
build_ext.build_extensions(self)
|
2015-01-17 05:19:54 +00:00
|
|
|
|
|
|
|
|
2015-12-13 22:32:23 +00:00
|
|
|
def generate_cython(root, source):
|
2015-12-13 10:49:17 +00:00
|
|
|
print('Cythonizing sources')
|
2015-12-13 11:51:23 +00:00
|
|
|
p = subprocess.call([sys.executable,
|
2015-12-13 22:32:23 +00:00
|
|
|
os.path.join(root, 'bin', 'cythonize.py'),
|
2017-02-16 18:01:25 +00:00
|
|
|
source], env=os.environ)
|
2015-12-13 10:49:17 +00:00
|
|
|
if p != 0:
|
|
|
|
raise RuntimeError('Running cythonize failed')
|
|
|
|
|
|
|
|
|
2015-12-13 22:32:23 +00:00
|
|
|
def is_source_release(path):
|
|
|
|
return os.path.exists(os.path.join(path, 'PKG-INFO'))
|
|
|
|
|
|
|
|
|
|
|
|
def clean(path):
|
2015-12-13 10:49:17 +00:00
|
|
|
for name in MOD_NAMES:
|
|
|
|
name = name.replace('.', '/')
|
|
|
|
for ext in ['.so', '.html', '.cpp', '.c']:
|
2015-12-13 22:32:23 +00:00
|
|
|
file_path = os.path.join(path, name + ext)
|
|
|
|
if os.path.exists(file_path):
|
|
|
|
os.unlink(file_path)
|
2015-01-25 03:49:10 +00:00
|
|
|
|
|
|
|
|
2015-12-13 22:32:23 +00:00
|
|
|
@contextlib.contextmanager
|
|
|
|
def chdir(new_dir):
|
|
|
|
old_dir = os.getcwd()
|
2015-12-13 10:49:17 +00:00
|
|
|
try:
|
2015-12-13 22:32:23 +00:00
|
|
|
os.chdir(new_dir)
|
|
|
|
sys.path.insert(0, new_dir)
|
|
|
|
yield
|
2015-12-13 10:49:17 +00:00
|
|
|
finally:
|
|
|
|
del sys.path[0]
|
2015-12-13 22:32:23 +00:00
|
|
|
os.chdir(old_dir)
|
|
|
|
|
|
|
|
|
|
|
|
def setup_package():
|
|
|
|
root = os.path.abspath(os.path.dirname(__file__))
|
|
|
|
|
|
|
|
if len(sys.argv) > 1 and sys.argv[1] == 'clean':
|
|
|
|
return clean(root)
|
|
|
|
|
|
|
|
with chdir(root):
|
2016-10-18 22:05:53 +00:00
|
|
|
with io.open(os.path.join(root, 'spacy', 'about.py'), encoding='utf8') as f:
|
2016-03-13 17:12:32 +00:00
|
|
|
about = {}
|
2016-01-15 17:57:01 +00:00
|
|
|
exec(f.read(), about)
|
2015-12-13 22:32:23 +00:00
|
|
|
|
2016-10-18 22:05:53 +00:00
|
|
|
with io.open(os.path.join(root, 'README.rst'), encoding='utf8') as f:
|
2016-03-13 17:12:32 +00:00
|
|
|
readme = f.read()
|
|
|
|
|
2015-12-13 22:32:23 +00:00
|
|
|
include_dirs = [
|
|
|
|
get_python_inc(plat_specific=True),
|
|
|
|
os.path.join(root, 'include')]
|
|
|
|
|
2016-04-28 20:10:43 +00:00
|
|
|
if (ccompiler.new_compiler().compiler_type == 'msvc'
|
2016-11-06 10:58:26 +00:00
|
|
|
and msvccompiler.get_build_version() == 9):
|
2016-04-28 20:10:43 +00:00
|
|
|
include_dirs.append(os.path.join(root, 'include', 'msvc9'))
|
|
|
|
|
2015-12-13 22:32:23 +00:00
|
|
|
ext_modules = []
|
|
|
|
for mod_name in MOD_NAMES:
|
|
|
|
mod_path = mod_name.replace('.', '/') + '.cpp'
|
2016-11-06 10:58:26 +00:00
|
|
|
extra_link_args = []
|
|
|
|
# ???
|
|
|
|
# Imported from patch from @mikepb
|
|
|
|
# See Issue #267. Running blind here...
|
|
|
|
if sys.platform == 'darwin':
|
|
|
|
dylib_path = ['..' for _ in range(mod_name.count('.'))]
|
|
|
|
dylib_path = '/'.join(dylib_path)
|
|
|
|
dylib_path = '@loader_path/%s/spacy/platform/darwin/lib' % dylib_path
|
|
|
|
extra_link_args.append('-Wl,-rpath,%s' % dylib_path)
|
2015-12-13 22:32:23 +00:00
|
|
|
ext_modules.append(
|
|
|
|
Extension(mod_name, [mod_path],
|
2016-11-06 10:58:26 +00:00
|
|
|
language='c++', include_dirs=include_dirs,
|
|
|
|
extra_link_args=extra_link_args))
|
2015-12-13 22:32:23 +00:00
|
|
|
|
|
|
|
if not is_source_release(root):
|
|
|
|
generate_cython(root, 'spacy')
|
|
|
|
|
|
|
|
setup(
|
2016-02-15 00:33:39 +00:00
|
|
|
name=about['__title__'],
|
2016-01-15 17:01:02 +00:00
|
|
|
zip_safe=False,
|
2015-12-13 22:32:23 +00:00
|
|
|
packages=PACKAGES,
|
2016-11-06 10:58:26 +00:00
|
|
|
package_data=PACKAGE_DATA,
|
2016-01-15 17:57:01 +00:00
|
|
|
description=about['__summary__'],
|
2016-03-13 17:12:32 +00:00
|
|
|
long_description=readme,
|
2016-01-15 17:57:01 +00:00
|
|
|
author=about['__author__'],
|
|
|
|
author_email=about['__email__'],
|
|
|
|
version=about['__version__'],
|
|
|
|
url=about['__uri__'],
|
|
|
|
license=about['__license__'],
|
2015-12-13 22:32:23 +00:00
|
|
|
ext_modules=ext_modules,
|
2017-08-09 10:17:30 +00:00
|
|
|
scripts=['bin/spacy'],
|
2016-03-13 17:12:32 +00:00
|
|
|
install_requires=[
|
2016-04-19 17:50:42 +00:00
|
|
|
'numpy>=1.7',
|
2017-06-01 07:56:12 +00:00
|
|
|
'murmurhash>=0.28,<0.29',
|
2016-04-19 17:50:42 +00:00
|
|
|
'cymem>=1.30,<1.32',
|
2017-03-11 18:33:56 +00:00
|
|
|
'preshed>=1.0.0,<2.0.0',
|
2018-03-25 17:29:36 +00:00
|
|
|
'thinc>=6.11.1.dev10,<6.12.0',
|
2017-03-18 14:14:02 +00:00
|
|
|
'plac<1.0.0,>=0.9.6',
|
2016-10-13 12:19:57 +00:00
|
|
|
'pathlib',
|
2017-03-08 13:11:54 +00:00
|
|
|
'ujson>=1.35',
|
2017-03-15 16:39:08 +00:00
|
|
|
'dill>=0.2,<0.3',
|
2017-04-07 13:43:34 +00:00
|
|
|
'requests>=2.13.0,<3.0.0',
|
2017-04-20 11:34:51 +00:00
|
|
|
'regex==2017.4.5',
|
2017-05-29 11:47:29 +00:00
|
|
|
'ftfy>=4.4.2,<5.0.0',
|
2018-02-22 12:25:52 +00:00
|
|
|
'msgpack-python==0.5.4',
|
2017-12-06 02:24:24 +00:00
|
|
|
'msgpack-numpy==0.4.1'],
|
Improve label management in parser and NER (#2108)
This patch does a few smallish things that tighten up the training workflow a little, and allow memory use during training to be reduced by letting the GoldCorpus stream data properly.
Previously, the parser and entity recognizer read and saved labels as lists, with extra labels noted separately. Lists were used becaue ordering is very important, to ensure that the label-to-class mapping is stable.
We now manage labels as nested dictionaries, first keyed by the action, and then keyed by the label. Values are frequencies. The trick is, how do we save new labels? We need to make sure we iterate over these in the same order they're added. Otherwise, we'll get different class IDs, and the model's predictions won't make sense.
To allow stable sorting, we map the new labels to negative values. If we have two new labels, they'll be noted as having "frequency" -1 and -2. The next new label will then have "frequency" -3. When we sort by (frequency, label), we then get a stable sort.
Storing frequencies then allows us to make the next nice improvement. Previously we had to iterate over the whole training set, to pre-process it for the deprojectivisation. This led to storing the whole training set in memory. This was most of the required memory during training.
To prevent this, we now store the frequencies as we stream in the data, and deprojectivize as we go. Once we've built the frequencies, we can then apply a frequency cut-off when we decide how many classes to make.
Finally, to allow proper data streaming, we also have to have some way of shuffling the iterator. This is awkward if the training files have multiple documents in them. To solve this, the GoldCorpus class now writes the training data to disk in msgpack files, one per document. We can then shuffle the data by shuffling the paths.
This is a squash merge, as I made a lot of very small commits. Individual commit messages below.
* Simplify label management for TransitionSystem and its subclasses
* Fix serialization for new label handling format in parser
* Simplify and improve GoldCorpus class. Reduce memory use, write to temp dir
* Set actions in transition system
* Require thinc 6.11.1.dev4
* Fix error in parser init
* Add unicode declaration
* Fix unicode declaration
* Update textcat test
* Try to get model training on less memory
* Print json loc for now
* Try rapidjson to reduce memory use
* Remove rapidjson requirement
* Try rapidjson for reduced mem usage
* Handle None heads when projectivising
* Stream json docs
* Fix train script
* Handle projectivity in GoldParse
* Fix projectivity handling
* Add minibatch_by_words util from ud_train
* Minibatch by number of words in spacy.cli.train
* Move minibatch_by_words util to spacy.util
* Fix label handling
* More hacking at label management in parser
* Fix encoding in msgpack serialization in GoldParse
* Adjust batch sizes in parser training
* Fix minibatch_by_words
* Add merge_subtokens function to pipeline.pyx
* Register merge_subtokens factory
* Restore use of msgpack tmp directory
* Use minibatch-by-words in train
* Handle retokenization in scorer
* Change back-off approach for missing labels. Use 'dep' label
* Update NER for new label management
* Set NER tags for over-segmented words
* Fix label alignment in gold
* Fix label back-off for infrequent labels
* Fix int type in labels dict key
* Fix int type in labels dict key
* Update feature definition for 8 feature set
* Update ud-train script for new label stuff
* Fix json streamer
* Print the line number if conll eval fails
* Update children and sentence boundaries after deprojectivisation
* Export set_children_from_heads from doc.pxd
* Render parses during UD training
* Remove print statement
* Require thinc 6.11.1.dev6. Try adding wheel as install_requires
* Set different dev version, to flush pip cache
* Update thinc version
* Update GoldCorpus docs
* Remove print statements
* Fix formatting and links [ci skip]
2018-03-19 01:58:08 +00:00
|
|
|
setup_requires=['wheel'],
|
2016-03-12 12:47:10 +00:00
|
|
|
classifiers=[
|
|
|
|
'Development Status :: 5 - Production/Stable',
|
|
|
|
'Environment :: Console',
|
|
|
|
'Intended Audience :: Developers',
|
|
|
|
'Intended Audience :: Science/Research',
|
|
|
|
'License :: OSI Approved :: MIT License',
|
|
|
|
'Operating System :: POSIX :: Linux',
|
|
|
|
'Operating System :: MacOS :: MacOS X',
|
|
|
|
'Operating System :: Microsoft :: Windows',
|
2016-03-14 00:46:33 +00:00
|
|
|
'Programming Language :: Cython',
|
2017-11-26 17:46:24 +00:00
|
|
|
'Programming Language :: Python :: 2',
|
2016-03-12 12:47:10 +00:00
|
|
|
'Programming Language :: Python :: 2.7',
|
2017-11-26 17:46:24 +00:00
|
|
|
'Programming Language :: Python :: 3',
|
2016-03-12 12:47:10 +00:00
|
|
|
'Programming Language :: Python :: 3.4',
|
|
|
|
'Programming Language :: Python :: 3.5',
|
2017-03-19 00:40:24 +00:00
|
|
|
'Programming Language :: Python :: 3.6',
|
2016-03-12 12:47:10 +00:00
|
|
|
'Topic :: Scientific/Engineering'],
|
2015-12-13 22:32:23 +00:00
|
|
|
cmdclass = {
|
|
|
|
'build_ext': build_ext_subclass},
|
|
|
|
)
|
2015-01-04 18:30:56 +00:00
|
|
|
|
|
|
|
|
|
|
|
if __name__ == '__main__':
|
2015-12-13 22:32:23 +00:00
|
|
|
setup_package()
|