From f4f6c976d67f499bf42381977b83369fcda1c173 Mon Sep 17 00:00:00 2001
From: Antonia Lewis <antonia.lewis@uconn.edu>
Date: Tue, 12 Apr 2016 23:17:03 -0400
Subject: [PATCH] Trying to optimize the optimizing.

---
 cblexicon.py | 83 ++++++++++++++++++++++++++++++++++++++++------------
 1 file changed, 64 insertions(+), 19 deletions(-)

diff --git a/cblexicon.py b/cblexicon.py
index b2375a8..a329d90 100644
--- a/cblexicon.py
+++ b/cblexicon.py
@@ -47,11 +47,48 @@ class cblexicon:
                         bestSwapWord = word
 
                 if(bestSwapWord in set1):
-                    set1.remove(word)
-                    set2.append(word)
+                    set1.remove(bestSwapWord)
+                    set2.append(bestSwapWord)
                 else:
-                    set2.remove(word)
-                    set1.append(word)
+                    set2.remove(bestSwapWord)
+                    set1.append(bestSwapWord)
+            # Return the optimized sets
+            return set1,set2
+
+        def optimize2(set1,set2,conjSet,defSet,dis):
+            i = 0
+            currentMin = 999999
+            consideredMin = calcScore(set1,conjSet,dis) + calcScore(set2,conjSet,dis)
+            bestSwapWord = ""
+            print consideredMin
+            # Calculate the best word to remove until no moves lessen the function
+            while( currentMin > consideredMin):
+                print i
+                i = i + 1
+                currentMin = consideredMin
+                currentS1 = calcScore(set1,conjSet,dis)
+                currentS2 = calcScore(set2,conjSet,dis)
+                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)
+                    if (test < consideredMin):
+                        print "found2"
+                        consideredMin = test
+                        bestSwapWord = word
+                print consideredMin
+
+                if(bestSwapWord in set1):
+                    set1.remove(bestSwapWord)
+                    set2.append(bestSwapWord)
+                else:
+                    set2.remove(bestSwapWord)
+                    set1.append(bestSwapWord)
+
             # Return the optimized sets
             return set1,set2
 
@@ -73,23 +110,31 @@ class cblexicon:
                     set1.append(word)
             return set1,set2
 
-        def calcScore(set1,set2,conjSet,dis):
-            score1 = 0
-            score2 = 0
-            for curr in set1:
-                for word in set1:
+        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]]
-                        score1 = score1 + cats
-            score1 = score1 * (1.0/len(set1))
+                        score = score + cats
+            return score * (1.0/len(set1))
 
-            for curr in set2:
-                for word in set2:
-                    if word != curr:
-                        cats = dis[conjSet[curr][0]][conjSet[word][0]]
-                        score2 = score2 + cats
-            score2 = score2 * (1.0/len(set2))
-            return score1 + score2
+        def calcSwap(word,currSet,opSet,currentCount,otherCount,conjSet,dis):
+            score1 = 0
+            score2 = 0
+            for w in currSet:
+                if word != w:
+                    cats = dis[conjSet[word][0]][conjSet[w][0]]
+                    score1 = score1 + cats
+            currentCount = ((currentCount* len(currSet)) - score1 ) * (1/(len(currSet)-1))
+
+            for word in set2:
+                if word != w:
+                    cats = dis[conjSet[word][0]][conjSet[w][0]]
+                    score2 = score2 + cats
+            otherCount = ((otherCount* len(opSet)) + score2 ) * (1/(len(opSet)-1))
+
+            return currentCount + otherCount
 
         def normalize_word(word):
             return SnowballStemmer("english").stem(word)
@@ -183,7 +228,7 @@ class cblexicon:
         set2 = defSet[:len(defSet)//2]
 
         # Optimize objective function
-        sets = optimize(set1,set2,conjSet,defSet,dis)
+        sets = optimize2(set1,set2,conjSet,defSet,dis)
         set1 = sets[0]
         set2 = sets[1]