X-Git-Url: http://git.tomasm.cz/imago.git/blobdiff_plain/841662dc25b40dce151a0bf7a024e55682028f18..966b2dcf6c734ffb729e2f8bab000d43586cf7eb:/src/k_means.py

diff --git a/src/k_means.py b/src/k_means.py
index f429824..5260601 100644
--- a/src/k_means.py
+++ b/src/k_means.py
@@ -4,19 +4,21 @@ import random
 
 def cluster(k, d, data, i_centers=None):
     """Find *k* clusters on *d* dimensional *data*."""
-    borders = [(min(p[0][i] for p in data), max(p[0][i] for p in data))
-               for i in range(d) ]
     if i_centers:
         old_centers = i_centers
     else:
+        borders = [(min(p[0][i] for p in data), max(p[0][i] for p in data))
+               for i in range(d)]
         old_centers = [[(h - l) * random.random() + l for (l, h) in borders]
                for _ in range(k)]
     clusters, centers = next_step(old_centers, data)
     while delta(old_centers, centers) > 0:
         old_centers = centers
         clusters, centers = next_step(old_centers, data)
-
-    return clusters
+    dst = lambda c, p: sum((a - b) ** 2 for (a, b) in zip(p, c)) ** 0.5
+    score = sum([sum(map(lambda p: dst(c, p[0]), clus)) for clus, c in
+                 zip(clusters, centers)])
+    return clusters, score
 
 def next_step(centers, data):
     """Compute new clusters and centers."""