basic stuff

modules/extractor.py

@@ -3,8 +3,8 @@
 
 import nltk
 
-sample = open("para.txt").read()
-
+#sample = open("para.txt").read()
+sample = 'I like Harvard and partitions'
 sentences = nltk.sent_tokenize(sample)
 tokenized_sentences = [nltk.word_tokenize(sentence) for sentence in sentences]
 tagged_sentences = [nltk.pos_tag(sentence) for sentence in tokenized_sentences]
@@ -43,4 +43,4 @@ def extract_entity_names(t):
 for (x,y) in tagged_sentences[0]:
   if y in wantset:
     entity_names.append(x)
-print entity_names
+#print entity_names

modules/sourceContentSelector.py

@@ -73,15 +73,15 @@ def ngramWeight(question, sentence):
 
   #get all bigram overlaps, rolls around end of sentence
   if len(uniQ) > 1 and len(uniS) > 1:
-    bigramQ = {uniQ[i-1]+uniQ[i] for i,word in enumerate(uniQ)}
-    bigramS = {uniS[i-1]+uniS[i] for i,word in enumerate(uniS)}
+    bigramQ = set([uniQ[i-1]+uniQ[i] for i,word in enumerate(uniQ)])
+    bigramS = set([uniS[i-1]+uniS[i] for i,word in enumerate(uniS)])
     bigram = bigramQ.intersection(bigramS)
   else:
       bigram = {}
 
-  if len(uniQ) > 2 and len(uniS) > 1:
-    trigramQ = {uniQ[i-2]+uniQ[i-1]+uniQ[i] for i,word in enumerate(uniQ)}
-    trigramS = {uniS[i-2]+uniS[i-1]+uniS[i] for i,word in enumerate(uniS)}
+  if len(uniQ) > 2 and len(uniS) > 2:
+    trigramQ = set([uniQ[i-2]+uniQ[i-1]+uniQ[i] for i,word in enumerate(uniQ)])
+    trigramS = set([uniS[i-2]+uniS[i-1]+uniS[i] for i,word in enumerate(uniS)])
     trigram = trigramQ.intersection(trigramS)
   else:
       trigram = {}