Revert "add a little fix to silhouette"

This reverts commit a6231bd.

DBSCAN_Main.py

@@ -96,25 +96,24 @@
 
 
 
-testArray = vectorsArray[0:50000]
+testArray = vectorsArray[0:100000]
 #====== Sklearn =================
 #the sklearn clustering takes 120 seconds to accomplish
 #return an array where each index is the vector(point) and value is it clustering
 #where -1 will represnt as a noise
 
 t = time.time()
-clustering = DBSCAN(eps=4, min_samples=2).fit(testArray)
+clustering = DBSCAN(eps=3, min_samples=2).fit(testArray)
 labels = clustering.labels_
 elapsed = time.time() - t
 print("optimal clustering time: ",elapsed)
 
-
 #=================================
 
 
 #============ my implementation =============
 t = time.time()
-dbscan = CMyDBSCAN(len(testArray), 4, 2)
+dbscan = CMyDBSCAN(len(testArray), 3, 2)
 myClusteringResult = dbscan.startClustering(testArray)
 elapsed = time.time() - t
 print("my clustering time: ",elapsed)
@@ -129,31 +128,13 @@
 
 #=================================
 
-"""
-for eps in range(1,6):
-    for minPts in range (2,6):
-        #t = time.time()
-        dbscan = CMyDBSCAN(len(testArray), eps, minPts)
-        myClusteringResult = dbscan.startClustering(testArray)
-        #elapsed = time.time() - t
-        #print("my clustering time: ",elapsed)
-
-        silhouette = Silhouette()
-
-        #t = time.time()
-        silhouetteValue = silhouette.calculateSilhouetteValue(testArray, np.array(myClusteringResult))
-        #elapsed = time.time() - t
-        #print("calculateSilhouetteValue time: ",elapsed)
-        print("value at (eps = ",eps,", minPts = ",minPts,") is: ",silhouetteValue)
-        
-"""
-"""
+
 #check correctness
 for i in range(len(labels)):
     if labels[i] != myClusteringResult[i]:
         print("different at: ",i)
 print("finish testing")
-"""
+
 
 #testing area
 

MyDBSCAN.py

@@ -145,36 +145,30 @@ def connectNodes(self, key, pIndex, qIndex):
 
     def initGraph(self, data):
         cnt = 0
-        cRow = 0
         for key in self.actualKeys:
-            cnt+=1
-            print("#",cnt)
-            t = time.time()
+            #cnt+=1
+            #print("#",cnt)
+            #t = time.time()
             result = self.dist(np.array(self.gridDictionaryVectors[key]))
-            elapsed = time.time() - t
-            print("dist calc : ",elapsed)
+            #elapsed = time.time() - t
+            #print("dist calc : ",elapsed)
 
             t = time.time()
             mat = result < self.eps
             pIndex = -1
             for row in mat:
-                cRow += 1
-                t__ = time.time()
                 pIndex += 1
                 trueAmounts = np.sum(row)
                 if trueAmounts >= self.minPoints:
-                    #try to modify here
                     for colom in range(len(row)):
                         if row[colom] == True:
                             self.connectNodes(key, pIndex, colom)
-                elapsed = time.time() - t__
-                print("time passed for row #" ,cRow, ": ",elapsed)
-
-            elapsed = time.time() - t
-            print("time passed for key" ,key, ": ",elapsed)
+
+            #elapsed = time.time() - t
+            #print("time passed for key" ,key, ": ",elapsed)
 
 
-        print("iterations = ",cnt)
+        #print("iterations = ",cnt)
 
 
 

silhouette.py

@@ -34,8 +34,6 @@ def calculateSilhouetteValue(self, dataset, clusters):
         self.createclustersDictionaryIndexes(dataset, clusters)
         #elapsed = time.time() - t
         #print("createclustersDictionaryIndexes time: ",elapsed)
-        if(len(self.listVectorsForDistanceMatrix) == 0):
-            return -1
         self.distances = dist(np.array(self.listVectorsForDistanceMatrix))
 
         for cluster in self.clustersDictionaryIndexes:
@@ -131,6 +129,25 @@ def calculateBValues(self, clusterNumber):
                     arrayBValues[arrayIndex] = bValue
         return arrayBValues
 
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+    def calcSumOfDistance(self, clusterNumber, pIndex):
+        x=0
+
+
 
 
 def dist(A):