iskm/wordfreq
1
0
Fork 0
mirror of https://github.com/rspeer/wordfreq.git synced 2024-12-23 17:31:41 +00:00
Code Issues Actions Packages Projects Releases Wiki Activity

add twitter-stems-2014 wordlist data

Browse Source
This commit is contained in:
Rob Speer 2015-02-11 13:29:32 -05:00
parent bf0071fd8b
commit 6ab72201cd
3 changed files with 2202970 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
wordfreq/build.py
View File

@ -189,6 +189,14 @@ def load_all_data(source_dir=None, filename=None, do_it_anyway=False):
)
save_wordlist_to_db(conn, 'twitter', 'xx', twitter_wordlist)
logger.info("Loading stemmed Twitter corpus.")
twitter_stems_wordlist = read_multilingual_csv(
os.path.join(source_dir, 'luminoso', 'twitter-stems-2014.csv')
)
for lang in twitter_stems_wordlist:
logger.info("\tLanguage: %s" % lang)
save_wordlist_to_db(conn, 'twitter-stems', lang, twitter_stems_wordlist[lang])
logger.info("Done loading.")

2
wordfreq/config.py
View File

@ -5,7 +5,7 @@ DB_DIR = (os.environ.get('WORDFREQ_DATA')
or os.path.expanduser('~/.cache/wordfreq'))
# When the minor version number increments, the data may change.
VERSION = '0.4.1'
VERSION = '0.5.0'
MINOR_VERSION = '.'.join(VERSION.split('.')[:2])
# Put these options together to make a database filename.

2202961
wordfreq_data/luminoso/twitter-stems-2014.csv Normal file
View File

File diff suppressed because it is too large Load Diff