Heatmap visualization of nmfae.signed factor matrices

Displays the factor blocks of a nmfae.signed fit as side-by-side heatmaps. Non-negative blocks (\(X_1, C_{+}, C_{-}, X_2\)) use the white-orange-red palette; the signed combined bottleneck \(C = C_{+} - C_{-}\) is rendered with a diverging blue-white-red palette so positive and negative weights are visually distinguishable.

Usage

nmfae.signed.heatmap(
  x,
  Y1.label = NULL,
  X1.label = NULL,
  X2.label = NULL,
  Y2.label = NULL,
  palette.pos = NULL,
  palette.signed = NULL,
  show.C = TRUE,
  ...
)

Arguments

x: An object of class "nmfae.signed".
Y1.label: Character vector for rows of \(X_1\).
X1.label: Decoder basis labels.
X2.label: Encoder basis labels.
Y2.label: Input variable labels.
palette.pos: Palette for non-negative blocks. Default white-orange-red.
palette.signed: Palette for signed \(C\). Default blue-white-red.
show.C: Logical. If TRUE (default), shows the combined signed \(C = C_{+} - C_{-}\) as a separate panel.
...: Not used.

Value

Invisible NULL. Called for its side effect (plot).

Lifecycle

This function is experimental. The interface may change in future versions.

References

Ding, C. H. Q., Li, T., & Jordan, M. I. (2010). Convex and semi-nonnegative matrix factorizations. IEEE Transactions on Pattern Analysis and Machine Intelligence, 32(1), 45–55.

Examples

# \donttest{
set.seed(1)
Y1 <- matrix(abs(rnorm(12)), 3, 4)
Y2 <- matrix(abs(rnorm(20)), 5, 4)
res <- nmfae.signed(Y1, Y2, rank = 2, rank.encoder = 2, maxit = 200)
#> Warning: maximum iterations (200) reached...
nmfae.signed.heatmap(res)

# }