You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@ctakes.apache.org by dl...@apache.org on 2016/09/21 19:47:49 UTC
svn commit: r1761803 - /ctakes/trunk/ctakes-temporal/scripts/nn/predict.py
Author: dligach
Date: Wed Sep 21 19:47:49 2016
New Revision: 1761803
URL: http://svn.apache.org/viewvc?rev=1761803&view=rev
Log:
using 'none' for now to represent oov items
Modified:
ctakes/trunk/ctakes-temporal/scripts/nn/predict.py
Modified: ctakes/trunk/ctakes-temporal/scripts/nn/predict.py
URL: http://svn.apache.org/viewvc/ctakes/trunk/ctakes-temporal/scripts/nn/predict.py?rev=1761803&r1=1761802&r2=1761803&view=diff
==============================================================================
--- ctakes/trunk/ctakes-temporal/scripts/nn/predict.py (original)
+++ ctakes/trunk/ctakes-temporal/scripts/nn/predict.py Wed Sep 21 19:47:49 2016
@@ -34,10 +34,11 @@ def main(args):
feats=[]
for unigram in line.rstrip().split():
- if(unigram in word2int):
+ if unigram in word2int:
feats.append(word2int[unigram])
else:
- feats.append(word2int['oov_word'])
+ # TODO: 'none' is not in vocabulary!
+ feats.append(word2int['none'])
if len(feats) > maxlen:
feats=feats[0:maxlen]