mv_plot: Overview plot of multi-view data

In andreamrau/maskmeans: Multi-view Aggregation and Splitting for K-Means Clustering

Description

Global graphical representation of multi-view data.

Usage

mv_plot(
  mv_data,
  scale = TRUE,
  mv = NULL,
  mv_names = NULL,
  labels = NULL,
  include_default_caption = TRUE,
  ...
)

Arguments

mv_data	Multi-view data, either in the form of a concatenated matrix (where the columns of the views have been combined) or in the form of a list, where each element contains one of the views. In the former case, the argument mv should also be provided to indicate the dimension of each of the views (sum(mv) should be equal to the number of columns in the matrix). In the latter case, each matrix in the list should have observations (rows) sorted in the same order, as matrices will be combined by columns within the function; note that mv will be detected automtically based on the number of columns in each matrix.
scale	If TRUE, data will be scaled so that all variables are normalized and views are standardized according to their size.
mv	(Optional unless X is a matrix.) If X is a matrix, vector corresponding to the size of each data view.
mv_names	If desired, a vector of multiview names to be used for the plot.
labels	If points should be colored by a hard cluster membership, a vector providing cluster assigments should be provided. If points should be colored by a soft cluster membership (where the transparency of points reflects the maximum conditional probability of cluster membership), a matrix providing conditional probabilities of cluster membership should be provided.
include_default_caption	If TRUE, include default caption.
...	Additional optional parameters.

Value

A multi-facetted plot, with one facet per view. Univariate views are represented as densities, bivariate views are represented as scatterplots, and multivariate views are represented by plotting scatterplots of the first two principal components.

andreamrau/maskmeans documentation built on Nov. 13, 2021, 7:44 a.m.