The R package 'JACA' implements a joint statistical framework that performs association and classification analysis for multi-view data, where multi-view data refers to matched sets of measurements on the same subjects. The corresponding reference is
"Joint association and classification analysis of multi-view data" by Zhang and Gaynanova (2018+).
To install the latest version from Github, use
library(devtools)
devtools::install_github("Pennisetum/JACA")
```s library(JACA)
set.seed(1)
n = 100 Z=matrix(c(rep(1, n),rep(0, 2 * n)), byrow = FALSE, nrow = n) for(i in 1:n){ Z[i, ] = sample(Z[i, ]) }
d = 2 X_list = sapply(1:d, function(i) list(matrix(rnorm(n * 20), n, 20)))
W = jacaTrain(Z, X_list, lambda = rep(0.05, 2), verbose = FALSE, alpha= 0.5, rho = 0.2)
sapply(W, function(x) sum(rowSums(x) != 0))
Z[90:100, ] = rep(NA, 3) X_list[[1]][1:10, ] = NA X_list[[2]][11:20, ] = NA W = jacaTrain(Z, X_list, kmax = 200, eps = 1e-06, lambda = rep(0.05, 2),alpha = 0.5, rho = 0.2, missing = TRUE)
sapply(W, function(x) sum(rowSums(x) != 0))
Add the following code to your website.
For more information on customizing the embed code, read Embedding Snippets.