StatRed ass4: Added some comments.

statred/ass4/k-means.py

 from pylab import loadtxt, array, scatter, figure, show, mean, argmin, \
         append, savefig
-from random import random, seed, randint
+from random import random, seed
 from sys import argv, exit
 
 def init(X, k):
@@ -9,18 +9,21 @@ def init(X, k):
 
 def init_pp(X, k):
     """Use the k-means++ algorithm to find initial means."""
-    # Choose first center at random
+    # Choose first mean at random
     N = X.shape[0]
     indices = [int(N * random())]
     m = [X[indices[0]]]
+    # Initial distances
     D = [((x - m[0])**2).sum() for x in X]
     while len(m) < k:
+        # Find new best mean
         best_sum = new = -1
         for i in range(N):
             if i not in indices:
                 Dsum = sum([min(D[j], ((X[j] - X[i])**2).sum()) for j in range(N)])
                 if best_sum == -1 or best_sum < Dsum:
                     best_sum, new = Dsum, i
+        # Add new mean and update distances
         m.append(X[new])
         indices.append(new)
         D = [min(D[i], ((X[i] - X[new])**2).sum()) for i in range(N)]