explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2024-11-10 19:57:17 +03:00
Code Issues Packages Projects Releases Wiki Activity

Delete gather_freqs.py

Browse Source 
This script was in a broken state, and should be unnecessary. The functionality is subsumed by `get_freqs.py`
This commit is contained in:
Matthew Honnibal 2016-03-02 00:42:55 +11:00
parent ae2b479312
commit 9d51e4d13c
1 changed files with 0 additions and 29 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

29
bin/gather_freqs.py
View File

@ -1,29 +0,0 @@
from __future__ import unicode_literals
import plac
import io
def main(in_loc, out_loc):
this_key = None
this_freq = 0
df = 0
with io.open(out_loc, 'w', encoding='utf8') as out_file:
for line in io.open(in_loc, encoding='utf8'):
line = line.strip()
if not line:
continue
freq, key = line.split('\t', 1)
freq = int(freq)
if this_key is not None and key != this_key:
out_file.write('%d\t%d\t%s\n' % (this_freq, df, this_key))
this_key = key
this_freq = freq
df = 1
else:
this_freq += freq
df += 1
this_key = key
out_file.write('%d\t%d\t%s\n' % (this_freq, df, this_key))
if __name__ == '__main__':
plac.call(main)