colWeightedMads,dgCMatrix-method {sparseMatrixStats}R Documentation

Calculates the weighted median absolute deviation for each row (column) of a matrix-like object

Description

Calculates the weighted median absolute deviation for each row (column) of a matrix-like object.

Usage

## S4 method for signature 'dgCMatrix'
colWeightedMads(
  x,
  w = NULL,
  rows = NULL,
  cols = NULL,
  na.rm = FALSE,
  constant = 1.4826,
  center = NULL,
  useNames = NA
)

## S4 method for signature 'dgCMatrix'
rowWeightedMads(
  x,
  w = NULL,
  rows = NULL,
  cols = NULL,
  na.rm = FALSE,
  constant = 1.4826,
  center = NULL,
  useNames = NA
)

Arguments

x

An NxK matrix-like object.

w

A numeric vector of length K (N) that specifies by how much each element is weighted.

rows

A vector indicating the subset of rows (and/or columns) to operate over. If NULL, no subsetting is done.

cols

A vector indicating the subset of rows (and/or columns) to operate over. If NULL, no subsetting is done.

na.rm

If TRUE, NAs are excluded first, otherwise not.

constant

A scale factor. See stats::mad() for details.

center

Not supported at the moment.

useNames

If NA, the default behavior of the function about naming support is remained. If FALSE, no naming support is done. Else if TRUE, names attributes of result are set.

Details

The S4 methods for x of type matrix, array, or numeric call matrixStats::rowWeightedMads / matrixStats::colWeightedMads.

Value

Returns a numeric vector of length N (K).

See Also

Examples

  mat <- matrix(0, nrow=10, ncol=5)
  mat[sample(prod(dim(mat)), 25)] <- rpois(n=25, 5)
  sp_mat <- as(mat, "dgCMatrix")
  weights <- rnorm(10, mean=1, sd=0.1)

  # sparse version
  sparseMatrixStats::colWeightedMads(sp_mat, weights)

  # Attention the result differs from matrixStats
  # because it always uses 'interpolate=FALSE'.
  matrixStats::colWeightedMads(mat, weights)


[Package sparseMatrixStats version 1.5.3 Index]