Added random restart to CB lexicon

cblexicon.py

@@ -5,6 +5,7 @@ import nltk.stem
 from nltk.corpus import brown
 import random
 from nltk.stem import *
+import time
 
 from sets import Set
 
@@ -47,12 +48,13 @@ def optimize(set1,set2,conjSet,defSet,dis):
     return set1,set2
 
 def optimize2(set1,set2,conjSet,defSet,dis):
-    i = 0
     currentMin = 999999
     consideredMin = calcScore(set1,conjSet,dis) + calcScore(set2,conjSet,dis)
     bestSwapWord = None
     # Calculate the best word to remove until no moves lessen the function
+    i = 1
     while( currentMin > consideredMin):
+        t1 = time.time()
         currentMin = consideredMin
         currentS1 = calcScore(set1,conjSet,dis)
         currentS2 = calcScore(set2,conjSet,dis)
@@ -74,7 +76,9 @@ def optimize2(set1,set2,conjSet,defSet,dis):
         elif(bestSwapWord in set2):
             set2.remove(bestSwapWord)
             set1.append(bestSwapWord)
-        i = i + 1
+        t2 = time.time()
+        print "Iteration: %d\tScore: %f\tTime: %f sec" % (i, consideredMin, t2-t1)
+        i += 1
 
     # Return the optimized sets
     return set1,set2
@@ -275,39 +279,41 @@ def returnCBLexicon():
     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
-    (set1,set2) = optimize2(set1,set2,conjSet,defSet,dis)
-    # Check the constraint
-    #(set1,set2) = constraintSwap(set1,set2,conjSet,defSet,dis)
-
-    #f1 = open('set1.txt', 'w+')
-    #f2 = open('set2.txt', 'w+')
-    #for word in set1:
-    #    f1.write(word + "\n")
-    #for word in set2:
-    #    f2.write(word + "\n")
-    #f1.close()
-    #f2.close()
+    bestSet1 = []
+    bestSet2 = []
+    bestScore = 999999
+    numIterations = 10
+    for i in range(numIterations):
+      set1 = random.sample(defSet, len(defSet)//2)
+      set2 = [x for x in defSet if x not in set1]
+
+      # Optimize objective function
+      (set1,set2) = optimize2(set1,set2,conjSet,defSet,dis)
+      # Check the constraint
+      (set1,set2) = constraintSwap(set1,set2,conjSet,defSet,dis)
+      score = calcScore(set1,conjSet,dis) + calcScore(set2,conjSet,dis)
+      print "*** score = %f, bestScore = %f ***" % (score, bestScore)
+      if score < bestScore:
+        bestSet1 = set1
+        bestSet2 = set2
+        bestScore = score
 
     #Find which set has a higher frequency in the training set
     (set1Freq,set2Freq) = findFrequency(set1,set2)
 
     positive = set1 if (set1Freq>set2Freq) else set2
     negative = set1 if (set1Freq<set2Freq) else set2
 
-    print "Positive set of length %d" % len(positive)
-    #print positive
-    print "Negative set of length %d" % len(negative)
-
     conjunctionData(set1,set2)
 
     # Generate Dictionary in correct format
     lexicon = dict([(word,1) for word in positive])
     lexicon.update(dict([(word,-1) for word in negative]))
     return lexicon
+
+lex = returnCBLexicon()
+f = open("cblex.txt", "w")
+for key in lex.keys():
+  f.write("%s, %d\n" % (key, lex[key]))
+
+f.close()