fixed anias code

cblexicon.py

@@ -59,35 +59,36 @@ class cblexicon:
             i = 0
             currentMin = 999999
             consideredMin = calcScore(set1,conjSet,dis) + calcScore(set2,conjSet,dis)
-            bestSwapWord = ""
+            bestSwapWord = None
             print consideredMin
             # Calculate the best word to remove until no moves lessen the function
             while( currentMin > consideredMin):
-                print i
-                i = i + 1
+                print "Iteration #%d: (%d, %d)" % (i, len(set1), len(set2))
                 currentMin = consideredMin
                 currentS1 = calcScore(set1,conjSet,dis)
                 currentS2 = calcScore(set2,conjSet,dis)
+                consideredMin = currentS1 + currentS2 #
                 for word in set1:
                     test = calcSwap(word,set1,set2,currentS1,currentS2,conjSet,dis)
                     if (test < consideredMin):
                         print "found1"
                         consideredMin = test
                         bestSwapWord = word
                 for word in set2:
-                    test = calcSwap(word,set2,set1,currentS1,currentS2,conjSet,dis)
+                    test = calcSwap(word,set2,set1,currentS2,currentS1,conjSet,dis)
                     if (test < consideredMin):
                         print "found2"
                         consideredMin = test
                         bestSwapWord = word
-                print consideredMin
+                print "New min: %f" % consideredMin
 
                 if(bestSwapWord in set1):
                     set1.remove(bestSwapWord)
                     set2.append(bestSwapWord)
-                else:
+                elif(bestSwapWord in set2):
                     set2.remove(bestSwapWord)
                     set1.append(bestSwapWord)
+                i = i + 1
 
             # Return the optimized sets
             return set1,set2
@@ -112,12 +113,13 @@ class cblexicon:
 
         def calcScore(set,conjSet,dis):
             score = 0
-            for curr in set:
-                for word in set:
-                    if word != curr:
-                        cats = dis[conjSet[curr][0]][conjSet[word][0]]
-                        score = score + cats
-            return score * (1.0/len(set1))
+            for i in range(len(set)):
+                w1 = set[i]
+                for j in range(i, len(set)):
+                    w2 = set[j]
+                    cats = dis[conjSet[w1][0]][conjSet[w2][0]]
+                    score = score + cats
+            return score / len(set)
 
         def calcSwap(word,currSet,opSet,currentCount,otherCount,conjSet,dis):
             score1 = 0
@@ -126,13 +128,14 @@ class cblexicon:
                 if word != w:
                     cats = dis[conjSet[word][0]][conjSet[w][0]]
                     score1 = score1 + cats
-            currentCount = ((currentCount* len(currSet)) - score1 ) * (1/(len(currSet)-1))
+            currentCount = ((currentCount* len(currSet)) - score1 )/(len(currSet)-1)
 
-            for word in set2:
+            #for word in set2:
+            for w in opSet:
                 if word != w:
                     cats = dis[conjSet[word][0]][conjSet[w][0]]
                     score2 = score2 + cats
-            otherCount = ((otherCount* len(opSet)) + score2 ) * (1/(len(opSet)-1))
+            otherCount = ((otherCount* len(opSet)) + score2 )/(len(opSet)+1)
 
             return currentCount + otherCount
 
@@ -202,10 +205,12 @@ class cblexicon:
             return d
 
         #Get the Data#
+        """
         negids = movie_reviews.fileids('neg')
         posids = movie_reviews.fileids('pos')
         training = set(negids[:500] + posids[:500])
         testing = set(negids[500:] + posids[500:])
+        """
         # Generate positive and negative initial sets
         sets = genSets()
         positive = random.sample(sets[0], min(len(sets[0]), len(sets[1])))
@@ -223,25 +228,29 @@ class cblexicon:
         # Generate dissimilarity matrix
         dis = vectorize(conjSet,defSet)
 
+        """
         # Its Cluster time
         set1 = defSet[len(defSet)//2:]
         set2 = defSet[:len(defSet)//2]
-
+        """
+        set1 = random.sample(defSet, len(defSet)//4)
+        set2 = [x for x in defSet if x not in set1]
+
         # Optimize objective function
         sets = optimize2(set1,set2,conjSet,defSet,dis)
         set1 = sets[0]
         set2 = sets[1]
-
+        
         print(set1)
         print(set2)
-
+        """
         f = open('set1.txt', 'w+')
         f2 = open('set1.txt', 'w+')
         for word in set1:
             f.write(word + "/n")
         for word in set2:
             f2.write(word + "/n")
-
+        """
 
 
         # Can we classify and then run bag of words?