kmeans-clusterer 0.11.1 → 0.11.2

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 266be0ce63154b6d9dd3928ae7901b42795be4eb
-  data.tar.gz: 4be98d5b084e2d27473ca3bee802b442d2b7690a
+  metadata.gz: 5074292fdb3b22c58c295514f9f80c255bd9c38b
+  data.tar.gz: a2ed2f4c4d288755d551444ac279e57762e14dd3
 SHA512:
-  metadata.gz: 4afc940658e70c7c0871fe3694d8e220f0048a66191b235ca179695c1366f61ce50b8793d5f107e95cd074110e97903ba3ff36f7116655b9cb047c94193ada6c
-  data.tar.gz: 24a9be6db3a93a5a64c71f6820f62bcc96aa44adbfb35fd7007c882242e82edd4fec9151bc1bf7eaa13cd763f9a9170f382c2ffab6e226f1850d631105871045
+  metadata.gz: 896ab8eae01c177a4c70550ee73ce22fd57d044c03e099d1148cf017adf1b9be1d9663571a9dcfc23b744776d0d4689e36e5967a3a4fd794a34d08b8026c5e84
+  data.tar.gz: d19418742a21b6d7302d2be7cca6701553c82f3cd2b5cfc6e4289948b2c4f32cc1f05e7861af88f3014538b0faf1f7430e39482732c23b8a0ff9924144a74e65

data/lib/kmeans-clusterer.rb

@@ -255,13 +255,15 @@ class KMeansClusterer
   def silhouette
     return 1.0 if @k < 2
 
+    # calculate all point-to-point distances at once
+    # uses more memory, but much faster
+    point_distances = Distance.euclidean @data, @data
+
     scores = @points.map do |point|
       sort_index = point.centroid_distances.sort_index
-      c1_points = get_points_for_cluster sort_index[0]
-      c2_points = get_points_for_cluster sort_index[1]
-
-      a = dissimilarity(c1_points, point.data)
-      b = dissimilarity(c2_points, point.data)
+      c1, c2 = sort_index[0], sort_index[1]
+      a = dissimilarity point.id, c1, point_distances
+      b = dissimilarity point.id, c2, point_distances
       (b - a) / [a,b].max
     end
 
@@ -274,9 +276,10 @@ class KMeansClusterer
 
   private
 
-    def dissimilarity points, point
-      distances = Distance.euclidean points, point
-      distances.sum / distances.length.to_f
+    def dissimilarity point_id, cluster_id, point_distances
+      cluster_point_ids = @cluster_assigns.eq(cluster_id).where
+      cluster_point_distances = point_distances[cluster_point_ids, point_id]
+      cluster_point_distances.sum / cluster_point_distances.length
     end
 
     def init_centroids

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: kmeans-clusterer
 version: !ruby/object:Gem::Version
-  version: 0.11.1
+  version: 0.11.2
 platform: ruby
 authors:
 - Geoff Buesing
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2015-04-02 00:00:00.000000000 Z
+date: 2015-04-03 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: narray