kmeans (empty) → 0.1

raw patch · 4 files changed

+93/−0 lines, 4 filesdep +basesetup-changed

Dependencies added: base

Files

• Data/KMeans.hs +40/−0
• LICENSE +30/−0
• Setup.lhs +4/−0
• kmeans.cabal +19/−0

@@ -0,0 +1,40 @@+module Data.KMeans (kmeans, kmeans')+    where++import Data.List (transpose, sort, groupBy, minimumBy)+import Data.Function (on)+import Data.Ord (comparing)++type Vector a = [a]++dist a b = sqrt . sum $ zipWith (\x y-> (x-y) ^ 2) a b++centroid points = map (flip (/) l . sum) $ transpose points+    where l = fromIntegral $ length points++closest points point = minimumBy (comparing $ dist point) points++recluster' centroids points = map (map snd) $ groupBy ((==) `on` fst) reclustered+    where reclustered = sort [(closest centroids a, a) | a <- points]++recluster clusters = recluster' centroids $ concat clusters+    where centroids = map centroid clusters++part x ys+     | zs' == [] = [zs]+     | otherwise = zs : part x zs'+    where (zs, zs') = splitAt x ys++-- | Recluster points+kmeans' :: (Floating a, Ord a) => [[Vector a]] -> [[Vector a]]+kmeans' clusters+    | clusters == clusters' = clusters+    | otherwise             = kmeans' clusters'+    where clusters' = recluster clusters++-- | Cluster points into k clusters.+-- |+-- | The initial clusters are chosen arbitrarily+kmeans :: (Floating a, Ord a) => Int -> [Vector a] -> [[Vector a]]+kmeans k points = kmeans' $ part l points+    where l = (length points + k - 1) `div` k

@@ -0,0 +1,30 @@+Copyright (c) Keegan Carruthers-Smith++All rights reserved.++Redistribution and use in source and binary forms, with or without+modification, are permitted provided that the following conditions+are met:++1. Redistributions of source code must retain the above copyright+   notice, this list of conditions and the following disclaimer.++2. Redistributions in binary form must reproduce the above copyright+   notice, this list of conditions and the following disclaimer in the+   documentation and/or other materials provided with the distribution.++3. Neither the name of the author nor the names of his contributors+   may be used to endorse or promote products derived from this software+   without specific prior written permission.++THIS SOFTWARE IS PROVIDED BY THE CONTRIBUTORS ``AS IS'' AND ANY EXPRESS+OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED+WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE+DISCLAIMED.  IN NO EVENT SHALL THE AUTHORS OR CONTRIBUTORS BE LIABLE FOR+ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL+DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS+OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)+HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT,+STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN+ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE+POSSIBILITY OF SUCH DAMAGE.

@@ -0,0 +1,4 @@+#! /usr/bin/env runhaskell++> import Distribution.Simple+> main = defaultMain

@@ -0,0 +1,19 @@+Name:               kmeans+Version:            0.1+Description:+    A simple library for k-means clustering+Category:           algorithms, clustering, data mining+Synopsis:           Hidden Markov Model algorithms+License:            BSD3+License-file:       LICENSE+Author:             Keegan Carruthers-Smith+Maintainer:         max.rabkin@gmail.com+Stability:          Alpha+Build-Type:         Simple+Cabal-Version:      >= 1.2++Library+    Build-Depends:  base >= 3 && < 5++    Exposed-Modules:+        Data.KMeans