datanugget (version 1.0.0)

WKmeans: Weighted K-means Clustering of Data Nuggets

Description

This function clusters data nuggets using a form of weighted K-means clustering.

Usage

WKmeans(dataset,
        k,
        cl.centers = NULL,
        obs.weights,
        num.init = 1,
        max.iterations = 10,
        print.progress = TRUE,
        seed = 291102,
        reassign.prop = .25)

Arguments

dataset

A data matrix (data frame, data table, matrix, etc) containing only entries of class numeric (i.e. matrix of data nugget centers).

k

Number of desired clusters. Must be of class numeric.

cl.centers

Chosen cluster centers. If not NULL, must be a k by ncol(dataset) matrix containing only entries of class numeric.

obs.weights

Vector of length nrow(dataset) of weights for each observation in the dataset. Must be of class numeric.

num.init

Number of initial clusters to attempt. Ignored if cl.centers is not NULL. Must be of class numeric.

max.iterations

Maximum number of iterations attempted for convergence before quitting. Must be of class numeric.

print.progress

Print progress of algorithm? Must be TRUE or FALSE.

seed

Random seed for replication. Must be of class numeric.

reassign.prop

Proportion of data to attempt to reassign during each iteration. Must be of class numeric and within (0,1].

Value

Cluster Assignments

Vector of length nrow(dataset) containing the cluster assignment for each observation.

Cluster Centers

k by ncol(dataset) matrix containing the cluster centers for each cluster.

Weighted WCSS

List containing the individual WWCSS for each cluster and the combined sum of all individual WWCSS's.

Details

Weighted K-means clustering can be used as an unsupervised learning technique to cluster observations contained in datasets that also have a measure of importance (e.g. weight) associated with them. In the case of data nuggets, this is the weight parameter associated with the data nuggets, so the centers of data nuggets are clustered using their weight parameters. The objective of the algorithm which performs this method of clustering is to minimize the weighted within cluster sum of squares (WWCSS). This function clusters data nuggets using Algorithm 3 provided in the reference.

Note that although this method was designed for use with data nuggets, there is no obvious reason to suggest that it cannot be used to perform clustering for other datasets which also have some weighting scheme.

References

Data Nuggets: A Method for Reducing Big Data While Preserving Data Structure (Submitted for Publication, 2019)

Examples

# NOT RUN {
    ## small example
    X = cbind.data.frame(rnorm(10^4),
                         rnorm(10^4),
                         rnorm(10^4))

    suppressMessages({

      my.DN = create.DN(x = X,
                        RS.num = 10^3,
                        DN.num1 = 500,
                        DN.num2 = 250,
                        no.cores = 0,
                        make.pbs = FALSE)

      my.DN2 = refine.DN(x = X,
                         DN = my.DN,
                         scale.tol = .9,
                         shape.tol = .9,
                         min.nugget.size = 2,
                         max.nuggets = 1000,
                         scale.max.splits = 5,
                         shape.max.splits = 5,
                         no.cores = 0,
                         make.pbs = FALSE)


      DN.clus = WKmeans(dataset = my.DN2$`Data Nuggets`[, c("Center1",
                                                            "Center2",
                                                            "Center3")],
                        k = 3,
                        obs.weights = my.DN2$`Data Nuggets`[, "Weight"],
                        num.init = 1,
                        max.iterations = 3,
                        reassign.prop = .33,
                        print.progress = FALSE)

    })

    DN.clus$`Cluster Assignments`
    DN.clus$`Cluster Centers`
    DN.clus$`Weighted WCSS`

    
# }
# NOT RUN {
      ## large example
      X = cbind.data.frame(rnorm(10^6),
                           rnorm(10^6),
                           rnorm(10^6),
                           rnorm(10^6),
                           rnorm(10^6))

      my.DN = create.DN(x = X,
                        RS.num = 10^5,
                        DN.num1 = 10^4,
                        DN.num2 = 2000)

      my.DN$`Data Nuggets`
      my.DN$`Data Nugget Assignments`

      my.DN2 = refine.DN(x = X,
                         DN = my.DN,
                         scale.tol = .9,
                         shape.tol = .9,
                         min.nugget.size = 2,
                         max.nuggets = 10000,
                         scale.max.splits = 5,
                         shape.max.splits = 5)

      my.DN2$`Data Nuggets`
      my.DN2$`Data Nugget Assignments`

      DN.clus = WKmeans(dataset = my.DN2$`Data Nuggets`[, c("Center1",
                                                            "Center2",
                                                            "Center3")],
                        k = 3,
                        obs.weights = my.DN2$`Data Nuggets`[, "Weight"],
                        num.init = 1,
                        max.iterations = 3,
                        reassign.prop = .33)

      DN.clus$`Cluster Assignments`
      DN.clus$`Cluster Centers`
      DN.clus$`Weighted WCSS`

    
# }
# NOT RUN {
# }