explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2025-04-27 12:23:42 +03:00
Code Issues Packages Projects Releases Wiki Activity

* Add option to download script

Browse Source
This commit is contained in:
Matthew Honnibal 2015-01-31 13:51:56 +11:00
parent a3955fd8d5
commit e013555b25
1 changed files with 8 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

11
spacy/en/download.py
View File

@ -3,6 +3,7 @@ import os
import tarfile import tarfile
import shutil import shutil
import wget import wget
import plac
ALL_DATA_DIR_URL = 'http://s3-us-west-1.amazonaws.com/media.spacynlp.com/en_data_all-0.4.tgz' ALL_DATA_DIR_URL = 'http://s3-us-west-1.amazonaws.com/media.spacynlp.com/en_data_all-0.4.tgz'
@ -38,13 +39,17 @@ def install_dep_vectors(url, dest_dir):
filename = download_file(url, dest_dir) filename = download_file(url, dest_dir)
def main(): def main(data_size='all'):
if data_size == 'all':
data_url = ALL_DATA_DIR_URL
elif data_size == 'small':
data_url = SM_DATA_DIR_URL
if not path.exists(DEST_DIR): if not path.exists(DEST_DIR):
install_data(SM_DATA_DIR_URL, path.dirname(DEST_DIR)) install_data(data_url, path.dirname(DEST_DIR))
else: else:
install_parser_model(PARSER_URL, DEST_DIR) install_parser_model(PARSER_URL, DEST_DIR)
install_dep_vectors(DEP_VECTORS_URL, path.join(DEST_DIR, 'vocab')) install_dep_vectors(DEP_VECTORS_URL, path.join(DEST_DIR, 'vocab'))
if __name__ == '__main__': if __name__ == '__main__':
main() plac.call(main)