Rooba
/
spaCy
mirror of https://github.com/explosion/spaCy.git
1
1
Fork 0
Code Issues Packages Projects Releases Wiki Activity

Merge branch 'master' of ssh://github.com/explosion/spaCy

This commit is contained in:
Matthew Honnibal 2016-12-18 23:19:45 +01:00
parent 5a6328a5a4 13a0b31279
commit 4e68abebc4
1 changed files with 9 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

9
spacy/en/__init__.py
View File

@ -4,6 +4,7 @@ from __future__ import unicode_literals, print_function
from os import path from os import path
from ..util import match_best_version from ..util import match_best_version
from ..util import get_data_path
from ..language import Language from ..language import Language
from ..lemmatizer import Lemmatizer from ..lemmatizer import Lemmatizer
from ..vocab import Vocab from ..vocab import Vocab
@ -36,11 +37,14 @@ class English(Language):
def _fix_deprecated_glove_vectors_loading(overrides): def _fix_deprecated_glove_vectors_loading(overrides):
if 'data_dir' in overrides and 'path' not in overrides: if 'data_dir' in overrides and 'path' not in overrides:
raise ValueError("The argument 'data_dir' has been renamed to 'path'") raise ValueError("The argument 'data_dir' has been renamed to 'path'")
if overrides.get('path') is None: if overrides.get('path') is False:
return overrides return overrides
if overrides.get('path') in (None, True):
data_path = get_data_path()
else:
path = overrides['path'] path = overrides['path']
if 'add_vectors' not in overrides:
data_path = path.parent data_path = path.parent
if 'add_vectors' not in overrides:
if 'vectors' in overrides: if 'vectors' in overrides:
vec_path = match_best_version(overrides['vectors'], None, data_path) vec_path = match_best_version(overrides['vectors'], None, data_path)
if vec_path is None: if vec_path is None:
@ -50,5 +54,6 @@ def _fix_deprecated_glove_vectors_loading(overrides):
vec_path = match_best_version('en_glove_cc_300_1m_vectors', None, data_path) vec_path = match_best_version('en_glove_cc_300_1m_vectors', None, data_path)
if vec_path is not None: if vec_path is not None:
vec_path = vec_path / 'vocab' / 'vec.bin' vec_path = vec_path / 'vocab' / 'vec.bin'
if vec_path is not None:
overrides['add_vectors'] = lambda vocab: vocab.load_vectors_from_bin_loc(vec_path) overrides['add_vectors'] = lambda vocab: vocab.load_vectors_from_bin_loc(vec_path)
return overrides return overrides