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

Merge branch 'develop' of https://github.com/explosion/spaCy into develop

Browse Source
This commit is contained in:
ines 2017-11-04 23:32:52 +01:00
commit 0a27afbf86
2 changed files with 9 additions and 16 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

15
examples/pipeline/multi_processing.py
View File

@ -35,21 +35,24 @@ def main(output_dir, model='en_core_web_sm', n_jobs=4, batch_size=1000,
texts, _ = zip(*data[-limit:])
print("Processing texts...")
partitions = partition_all(batch_size, texts)
items = ((i, [nlp(text) for text in texts], output_dir) for i, texts
in enumerate(partitions))
Parallel(n_jobs=n_jobs)(delayed(transform_texts)(*item) for item in items)
executor = Parallel(n_jobs=n_jobs)
do = delayed(transform_texts)
tasks = (do(nlp, i, batch, output_dir)
for i, batch in enumerate(partitions))
executor(tasks)
def transform_texts(batch_id, docs, output_dir):
def transform_texts(nlp, batch_id, texts, output_dir):
print(nlp.pipe_names)
out_path = Path(output_dir) / ('%d.txt' % batch_id)
if out_path.exists(): # return None in case same batch is called again
return None
print('Processing batch', batch_id)
with out_path.open('w', encoding='utf8') as f:
for doc in docs:
for doc in nlp.pipe(texts):
f.write(' '.join(represent_word(w) for w in doc if not w.is_space))
f.write('\n')
print('Saved {} texts to {}.txt'.format(len(docs), batch_id))
print('Saved {} texts to {}.txt'.format(len(texts), batch_id))
def represent_word(word):

10
spacy/language.py
View File

@ -135,10 +135,6 @@ class Language(object):
self.pipeline = []
self._optimizer = None
def __reduce__(self):
bytes_data = self.to_bytes(vocab=False)
return (unpickle_language, (self.vocab, self.meta, bytes_data))
@property
def path(self):
return self._path
@ -724,12 +720,6 @@ class DisabledPipes(list):
self[:] = []
def unpickle_language(vocab, meta, bytes_data):
lang = Language(vocab=vocab)
lang.from_bytes(bytes_data)
return lang
def _pipe(func, docs):
for doc in docs:
func(doc)