AI.Clustering.KMeans

Documentation

data KMeans a

Results from running kmeans

Constructors

KMeans

Fields

• membership :: Vector Int

  A vector of integers (0 ~ k-1) indicating the cluster to which each point is allocated.

• centers :: Matrix Double

  A matrix of cluster centers.

• clusters :: Maybe [[a]]
• sse :: Double

  the sum of squared error (SSE)

Instances

Show a => Show (KMeans a)

Defined in AI.Clustering.KMeans.Types

Methods

showsPrec :: Int -> KMeans a -> ShowS

show :: KMeans a -> String

showList :: [KMeans a] -> ShowS

data KMeansOpts

Constructors

KMeansOpts

Fields

• kmeansMethod :: Method
• kmeansSeed :: Vector Word32

  Seed for random number generation

• kmeansClusters :: Bool

  Wether to return clusters, may use a lot memory

• kmeansMaxIter :: Int

  Maximum iteration

defaultKMeansOpts :: KMeansOpts

Default options. > defaultKMeansOpts = KMeansOpts > { kmeansMethod = KMeansPP > , kmeansSeed = U.fromList [1,2,3,4,5,6,7] > , kmeansClusters = True > , kmeansMaxIter = 10 > }

kmeans

Arguments

:: Int

The number of clusters

-> Matrix Double

Input data stored as rows in a matrix

-> KMeansOpts

-> KMeans (Vector Double)

Perform K-means clustering

kmeansBy

Arguments

:: Vector v a

=> Int

The number of clusters

-> v a

Input data

-> (a -> Vector Double)

-> KMeansOpts

-> KMeans a

Perform K-means clustering, using a feature extraction function

Initialization methods

data Method

Different initialization methods

Constructors

Forgy

The Forgy method randomly chooses k unique observations from the data set and uses these as the initial means.

KMeansPP

K-means++ algorithm.

Centers (Matrix Double)

Provide a set of k centroids

decode :: Vector Int -> [a] -> [[a]]

Assign data to clusters based on KMeans result

References

Arthur, D. and Vassilvitskii, S. (2007). k-means++: the advantages of careful seeding. Proceedings of the eighteenth annual ACM-SIAM symposium on Discrete algorithms. Society for Industrial and Applied Mathematics Philadelphia, PA, USA. pp. 1027–1035.