Merge branch 'master' of https://github.uconn.edu/job13011/BigData

GlossCount.py

@@ -57,19 +57,23 @@ class GlossCount:
             neutral = set(newsets[2])
 
         # Learn Classifier
-        print len(negative)
-        print len(positive)
         trainfeats = [({word : True},"pos") for word in positive] + [({word : True},"neg") for word in negative]
         classifier = NaiveBayesClassifier.train(trainfeats)
+        print "cat"
         #print classifier.classify(dict([(word, True) for word in words]))
+<<<<<<< HEAD
         #print classifier.classify(dict([("bad",True),("bad",True)]))
 
 
+=======
+        print classifier.classify(dict([("bad",True),("bad",True)]))
+>>>>>>> parent of 47c6a2a... Bugfix
         # Iterate through all of the reviews and find sentiment
         count = 0.00
         correct = 0.00
-        for reviews in movie_reviews.fileids():     #For every review
+        for reviews in movie_reviews.fileids():
             score = 0;
+<<<<<<< HEAD
             tokens = nltk.pos_tag(nltk.word_tokenize(movie_reviews.raw(fileids=[reviews])))     #Tokenize all words with POS
             for token in tokens:
                 if (token[1]== "JJ" or token[1] == "JJR" or token[1] == "JJS"):         # If adjective, check value
@@ -78,14 +82,22 @@ class GlossCount:
                         score = score - 1
                     elif(sent_value is 'pos'):
                         score = score + 1
+=======
+            for words in movie_reviews.words(fileids=[reviews]):
+                if()
+                sent_value = classifier.classify(dict([(word, True)]))
+                if(sent_value is 'neg'):
+                    score = score - 1
+                elif(sent_value is 'pos'):
+                    score = score + 1
+>>>>>>> parent of 47c6a2a... Bugfix
             if (score < 0):
                 print "Negative at %d" % (score)
                 sentiment = 'neg'
             else:
                 sentiment = 'pos'
                 print "Positive at %d" % (score)
             if (sentiment == movie_reviews.categories(fileids=[reviews])[0]):
-                print "Correct"
                 correct = correct + 1.00
             count = count + 1.00
         print correct/count

cblexicon.py

@@ -0,0 +1,26 @@
+import math
+import nltk
+from nltk.corpus import wordnet as wn
+from nltk.corpus import brown as sc
+from collections import Counter
+from sets import Set
+
+class cblexicon:
+
+    def genSets(self):
+        f = open('words.txt', 'r+')
+        content = f.readlines()
+        positive = Set([])
+        negative = Set([])
+
+        for pair in content:
+            current = pair.split(' ')
+            if (current[1][0] == 'p'):
+                positive.add(current[0])
+            elif (current[1][0] == 'n'):
+                negative.add(current[0])
+
+        print len(positive)
+        print len(negative)
+
+cblexicon().genSets()

getAdjectives.py

@@ -0,0 +1,18 @@
+import math
+import nltk
+from nltk.corpus import brown as sc
+from collections import Counter
+
+
+f = open('words.txt', 'r+')
+list1 = []
+for word in sc.tagged_sents():
+    for w in word:
+        if(w[1] == "JJ" or w[1] == "JJR" or w[1] == "JJS" or w[1] == "JJT"):
+            list1.append(w[0])
+counts = Counter(list1)
+d = dict(counts)
+
+for n in d:
+    if( d[n] >= 20):
+        f.write(n+" \n")