fitted.gpca: Fitted values using generalized PCA

In andland/generalizedPCA: Generalized PCA

Description

Fit a lower dimentional representation of the exponential family matrix using generalized PCA

Usage

## S3 method for class 'gpca'
fitted(object, type = c("link", "response"), ...)

Arguments

object	generalized PCA object
type	the type of fitting required. type = "link" gives output on the natural parameter scale and type = "response" gives output on the response scale
...	Additional arguments

Examples

# construct a low rank matrix in the natural parameter space
rows = 100
cols = 10
set.seed(1)
mat_np = outer(rnorm(rows), rnorm(cols))

# generate a count matrix
mat = matrix(rpois(rows * cols, c(exp(mat_np))), rows, cols)

# run Poisson PCA on it
gpca = generalizedPCA(mat, k = 1, M = 4, family = "poisson")

# construct fitted expected value of counts matrix
fit = fitted(gpca, type = "response")

andland/generalizedPCA documentation built on May 12, 2019, 2:42 a.m.