explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2025-01-26 17:24:41 +03:00
Code Issues Packages Projects Releases Wiki Activity

* Fix init_model script

Browse Source
This commit is contained in:
Matthew Honnibal 2015-07-25 22:35:52 +02:00
parent ef448649b3
commit 6076213c16
1 changed files with 2 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
bin/init_model.py
View File

@ -91,7 +91,7 @@ def _read_probs(loc):
def _read_freqs(loc): def _read_freqs(loc):
counts = PreshCounter() counts = PreshCounter()
total = 0 total = 0
for line in open(loc): for line in loc.open():
freq, doc_freq, key = line.split('\t', 2) freq, doc_freq, key = line.split('\t', 2)
freq = int(freq) freq = int(freq)
counts[hash_string(key)] = freq counts[hash_string(key)] = freq
@ -99,7 +99,7 @@ def _read_freqs(loc):
counts.smooth() counts.smooth()
log_total = math.log(total) log_total = math.log(total)
probs = {} probs = {}
for line in open(loc): for line in loc.open():
freq, doc_freq, key = line.split('\t', 2) freq, doc_freq, key = line.split('\t', 2)
if int(doc_freq) >= 2 and int(freq) >= 5 and len(key) < 200: if int(doc_freq) >= 2 and int(freq) >= 5 and len(key) < 200:
word = literal_eval(key) word = literal_eval(key)