CentrePerGroup: Centre a data matrix to mean zero (per group)

In btaschler/mcap: Model-Based Clustering in High Dimensions via Adaptive Projections

Description

Mean centering of an input matrix. When true labels are provided, the groups/clusters are centred individually.

Usage

CentrePerGroup(xx, true_labels = numeric(nrow(xx)))

Arguments

xx	The data matrix (n x p).
true_labels	Vector of true cluster assignments. Default: 0 (all elements are treated as belonging to one group).

Value

xx_centred

Mean centred data matrix.

See Also

colMeans, scale

Examples

  ## 10x5 matrix, 1 group:
  CentrePerGroup(xx=matrix(rnorm(50),10,5))
  
  ## 2 groups:
  CentrePerGroup(xx=matrix(rnorm(50),10,5), true_labels=round(runif(10)))
  
  ## 10 groups:
  CentrePerGroup(xx=matrix(rnorm(5000),100,50), true_labels=round(runif(100)*10))

btaschler/mcap documentation built on May 26, 2019, 1:31 a.m.