Neighbors get added to the live Set during blob expansion

Signed-off-by: James Ketrenos <james_git@ketrenos.com>

ketrface/ketrface/dbscan.py

@@ -8,13 +8,13 @@ Undefined = 0
 Edge = -1
 Noise = -2
 
-# Union of two lists of dicts
+# Union of two lists of dicts, adding unique elements of B to
+# end of A
 def Union(A, B):
-  C = A
   for key in B:
-    if key not in C:
-      C.append(key)
-  return C    
+    if key not in A:
+      A.append(key)
+  return A    
 
 # https://en.wikipedia.org/wiki/DBSCAN
 #
@@ -53,32 +53,39 @@ def DBSCAN(points, eps = MAX_DISTANCE, minPts = MIN_PTS, verbose = True):
     S.remove(P)
 
     sub_perc = -1
-    sub_total = len(S)
-    T = S.copy()
-    for j, Q in enumerate(S):                       # Process every seed point
+    sub_last = 0
+
+    for j, Q in enumerate(S):        # Process every seed point
+
       if verbose == True:
+        sub_total = len(S)
         sub_new_perc = int(100 * (j+1) / sub_total)
-        now = time.time()
-        if sub_new_perc != sub_perc or now - last > 5:
+        sub_now = time.time()
+        if sub_new_perc != sub_perc or sub_now - sub_last > 5:
           sub_perc = sub_new_perc
-          print(f'... points {sub_perc}% ({j}/{sub_total} processed) complete with {len(clusters)} identities ({now - start}s).')
-          last = now
+          print(f'... points {sub_perc}% ({j}/{sub_total} processed [{perc}% total]) complete with {len(clusters)} identities ({now - start}s).')
+          sub_last = sub_now
+
       if Q['cluster'] == Noise:       # Change Noise to border point
         Q['cluster'] = C
         C['faces'].append(Q)
+
       if Q['cluster'] != Undefined:   # Previously processed (border point)
         continue
+
       Q['cluster'] = C                # Label neighbor
       C['faces'].append(Q)
+      
       N = RangeQuery(points, Q, eps)  # Find neighbors
       if len(N) >= minPts:            # Density check (if Q is a core point)
-        T = Union(T, N)               # Add new neighbors to seed set
-    S = T
+        S = Union(S, N)               # Add new neighbors to seed set
   return clusters
         
 def RangeQuery(points, Q, eps):
   neighbors = []
   for P in points:                    # Scan all points in the database
+    if P == Q:
+      continue
     if P in neighbors:
       continue       
     distance = findCosineDistance(    # Compute distance and check epsilon