From: Tomas Musil <tomik.musil@gmail.com>
Date: Tue, 24 Jun 2014 13:13:30 +0000 (+0200)
Subject: comments for k_means
X-Git-Url: http://git.tomasm.cz/imago.git/commitdiff_plain/dfd21c7829d456a1c05db4fb0ef10c5994e2469a

comments for k_means
---

diff --git a/imago_pack/k_means.py b/imago_pack/k_means.py
index c5ddba5..f429824 100644
--- a/imago_pack/k_means.py
+++ b/imago_pack/k_means.py
@@ -19,6 +19,7 @@ def cluster(k, d, data, i_centers=None):
     return clusters
 
 def next_step(centers, data):
+    """Compute new clusters and centers."""
     clusters = [[] for _ in centers]
     for point in data:
         clusters[nearest(centers, point)].append(point)
@@ -26,12 +27,16 @@ def next_step(centers, data):
     return clusters, centers
 
 def nearest(centers, point):
+    """Find the nearest cluster *center* for *point*."""
     d, i = min(((sum((p - c) ** 2 for (p, c) in zip(point[0], center)) ** 0.5 ,
                 index) if center else (float('inf'), len(centers)))
                for (index, center) in enumerate(centers))
     return i
 
 def centroid(cluster):
+    """Find the centroid of the *cluster*."""
+    # TODO is this just a mean of coordinates?
+    # TODO should we try different definitions?
     l = float(len(cluster))
     try:
         d = len(cluster[0][0]) #TODO empty cluster error
@@ -40,5 +45,7 @@ def centroid(cluster):
     return [sum(c[0][i] for c in cluster) / l for i in range(d)]
 
 def delta(c1, c2):
+    """Find the absolute distance between two lists of points."""
+    # TODO rewrite this to a sane form
     return sum((sum(abs(cc1 - cc2) for (cc1, cc2) in zip (ccc1, ccc2)) if ccc2
                else 0.) for (ccc1, ccc2) in zip(c1, c2))