SWKM-package: Sparse Weighted K-Means

In cuhklinlab/SWKM: Sparse Weighted K-Means

Sparse Weighted K-Means

Description

An implementation of (sparse) weighted K-Means clustering algorithm on observations with weights.

Details

Main Functions:

kmeans.weight: Perform weighted K-Means algorithm on data.

kmeans.weight.tune: Choose weight parameter for (sparse) weighted K-Means algorithm. Usually used before kmeans.weight or KMeansSparseCluster.weight.

KMeansSparseCluster.weight: Perform sparse weighted K-Means algorithm on data.

KMeansSparseCluster.permute.weight: Choose sparsity parameter for sparse weighted K-Means algorithm. Usually used before KMeansSparseCluster.weight, and after weight parameter is tuned or known.

ChooseK: Choose the number of clusters K for (sparse) weighted K-Means clustering. Usually used before clustering method is performed.

Please refer to the vigenette for more details.

Author(s)

Wenyu ZHANG.

Maintainer: Wenyu ZHANG <[e-mail]>

References

Daniela M Witten and Robert Tibshirani (2010). A framework for feature selection in clustering. Journal of the American Statistical Association, 105(490), 713-726.

Robert, T. et al. (2001). Estimating the number of clusters in a data set via the gap statistic. Journal of the Royal Statistical Society: Series B (Statistical Methodology), 63(2), 411-423.

cuhklinlab/SWKM documentation built on Aug. 5, 2022, 2:27 a.m.