explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2025-06-29 09:23:12 +03:00
Code Issues Packages Projects Releases Wiki Activity

* Write a supersenses.json fil into a wsd directory in init_model

Browse Source
This commit is contained in:
Matthew Honnibal 2015-07-04 17:24:32 +02:00
parent 00c9acbf42
commit 4c6533a019
1 changed files with 10 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

10
bin/init_model.py
View File

@ -22,6 +22,7 @@ from shutil import copyfile
from shutil import copytree from shutil import copytree
import codecs import codecs
from collections import defaultdict from collections import defaultdict
import json
from spacy.en import get_lex_props from spacy.en import get_lex_props
from spacy.en.lemmatizer import Lemmatizer from spacy.en.lemmatizer import Lemmatizer
@ -31,6 +32,7 @@ from spacy.vocab import write_binary_vectors
from spacy.parts_of_speech import NOUN, VERB, ADJ, ADV from spacy.parts_of_speech import NOUN, VERB, ADJ, ADV
import spacy.senses import spacy.senses
from spacy.munge import read_wordnet
def setup_tokenizer(lang_data_dir, tok_dir): def setup_tokenizer(lang_data_dir, tok_dir):
@ -127,6 +129,7 @@ def setup_vocab(src_dir, dst_dir):
vocab.strings.dump(str(dst_dir / 'strings.txt')) vocab.strings.dump(str(dst_dir / 'strings.txt'))
def main(lang_data_dir, corpora_dir, model_dir): def main(lang_data_dir, corpora_dir, model_dir):
model_dir = Path(model_dir) model_dir = Path(model_dir)
lang_data_dir = Path(lang_data_dir) lang_data_dir = Path(lang_data_dir)
@ -142,6 +145,13 @@ def main(lang_data_dir, corpora_dir, model_dir):
setup_vocab(corpora_dir, model_dir / 'vocab') setup_vocab(corpora_dir, model_dir / 'vocab')
if not (model_dir / 'wordnet').exists(): if not (model_dir / 'wordnet').exists():
copytree(str(corpora_dir / 'wordnet'), str(model_dir / 'wordnet')) copytree(str(corpora_dir / 'wordnet'), str(model_dir / 'wordnet'))
ss_probs = read_wordnet.make_supersense_dict(str(corpora_dir / 'wordnet'))
wsd_dir = Path(model_dir, 'wsd')
if not wsd_dir.exists():
wsd_dir.mkdir()
with codecs.open(str(wsd_dir / 'supersenses.json'), 'w', 'utf8') as file_:
json.dump(ss_probs, file_)
if __name__ == '__main__': if __name__ == '__main__':