explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2024-12-26 01:46:28 +03:00
Code Issues Packages Projects Releases Wiki Activity

Remove trailing whitespace

Browse Source
This commit is contained in:
Ines Montani 2016-12-18 16:54:52 +01:00
parent 4e95737c6c
commit bcc1d50d09
1 changed files with 9 additions and 9 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

18
spacy/language.py
View File

@ -53,7 +53,7 @@ class BaseDefaults(object):
else: else:
return Vocab.load(nlp.path, lex_attr_getters=cls.lex_attr_getters, return Vocab.load(nlp.path, lex_attr_getters=cls.lex_attr_getters,
tag_map=cls.tag_map, lemmatizer=lemmatizer) tag_map=cls.tag_map, lemmatizer=lemmatizer)
@classmethod @classmethod
def add_vectors(cls, nlp=None): def add_vectors(cls, nlp=None):
if nlp is None or nlp.path is None: if nlp is None or nlp.path is None:
@ -150,9 +150,9 @@ class BaseDefaults(object):
tag_map = {} tag_map = {}
tokenizer_exceptions = {} tokenizer_exceptions = {}
parser_features = get_templates('parser') parser_features = get_templates('parser')
entity_features = get_templates('ner') entity_features = get_templates('ner')
tagger_features = Tagger.feature_templates # TODO -- fix this tagger_features = Tagger.feature_templates # TODO -- fix this
@ -257,7 +257,7 @@ class Language(object):
path = util.match_best_version(self.lang, '', util.get_data_path()) path = util.match_best_version(self.lang, '', util.get_data_path())
self.path = path self.path = path
self.vocab = self.Defaults.create_vocab(self) \ self.vocab = self.Defaults.create_vocab(self) \
if 'vocab' not in overrides \ if 'vocab' not in overrides \
else overrides['vocab'] else overrides['vocab']
@ -299,7 +299,7 @@ class Language(object):
"""Apply the pipeline to some text. The text can span multiple sentences, """Apply the pipeline to some text. The text can span multiple sentences,
and can contain arbtrary whitespace. Alignment into the original string and can contain arbtrary whitespace. Alignment into the original string
is preserved. is preserved.
Args: Args:
text (unicode): The text to be processed. text (unicode): The text to be processed.
@ -327,9 +327,9 @@ class Language(object):
def pipe(self, texts, tag=True, parse=True, entity=True, n_threads=2, batch_size=1000): def pipe(self, texts, tag=True, parse=True, entity=True, n_threads=2, batch_size=1000):
'''Process texts as a stream, and yield Doc objects in order. '''Process texts as a stream, and yield Doc objects in order.
Supports GIL-free multi-threading. Supports GIL-free multi-threading.
Arguments: Arguments:
texts (iterator) texts (iterator)
tag (bool) tag (bool)
@ -352,7 +352,7 @@ class Language(object):
path = self.path path = self.path
elif isinstance(path, basestring): elif isinstance(path, basestring):
path = pathlib.Path(path) path = pathlib.Path(path)
if self.tagger: if self.tagger:
self.tagger.model.end_training() self.tagger.model.end_training()
self.tagger.model.dump(str(path / 'pos' / 'model')) self.tagger.model.dump(str(path / 'pos' / 'model'))
@ -362,7 +362,7 @@ class Language(object):
if self.entity: if self.entity:
self.entity.model.end_training() self.entity.model.end_training()
self.entity.model.dump(str(path / 'ner' / 'model')) self.entity.model.dump(str(path / 'ner' / 'model'))
strings_loc = path / 'vocab' / 'strings.json' strings_loc = path / 'vocab' / 'strings.json'
with strings_loc.open('w', encoding='utf8') as file_: with strings_loc.open('w', encoding='utf8') as file_:
self.vocab.strings.dump(file_) self.vocab.strings.dump(file_)