BUG: print function fails

[vandenman]

Consider the following example:

library(BDgraph)
library(easybgm)
packageVersion("BDgraph")
#> [1] '2.72'
packageVersion("easybgm")
#> [1] '0.1.1'

n <- 100
p <- 7

# simulate a true graph structure
set.seed(126)
g_obj <- graph.sim(p)
g_obj[5, 6] <- g_obj[6, 5] <- 1
g <- unclass(g_obj)

# simulate a true precision matrix
K <- rgwish(1, adj = g)
print(zapsmall(K))
#>          [,1]     [,2]      [,3]      [,4]      [,5]      [,6]     [,7]
#> [1,] 9.549353 0.000000  0.000000  0.000000  0.321668  0.000000 1.700633
#> [2,] 0.000000 6.022439  0.000000  0.000000  2.067669  0.000000 0.000000
#> [3,] 0.000000 0.000000  4.974015 -2.421315  0.000000  0.000000 0.000000
#> [4,] 0.000000 0.000000 -2.421315  3.206202  0.706456  0.000000 0.000000
#> [5,] 0.321668 2.067669  0.000000  0.706456  6.848114 -0.501471 0.000000
#> [6,] 0.000000 0.000000  0.000000  0.000000 -0.501471  7.512933 0.000000
#> [7,] 1.700633 0.000000  0.000000  0.000000  0.000000  0.000000 4.854756

# invert it to obtain the true covariance matrix
Sigma <- solve(K)

# simulate the data
X <- mvtnorm::rmvnorm(n = n, mean = rep(0, p), sigma = Sigma)

# fit easybgm
fit <- easybgm(X, type = "continuous")
#> 10000 MCMC sampling ... in progress: 
#> 10%->20%->30%->40%->50%->60%->70%->80%->90%-> done
print(fit)
#> Error in matrix(rep(names, each = p), ncol = p): 'data' must be of a vector type, was 'NULL'

# the object still contains useful stuff
str(fit)
#> List of 8
#>  $ parameters             : num [1:7, 1:7] 0 -0.021598 0.000403 0.040694 -0.017792 ...
#>  $ inc_probs              : num [1:7, 1:7] 0 0.33 0.18 0.36 0.37 0.34 1 0.33 0 0.23 ...
#>   ..- attr(*, "dimnames")=List of 2
#>   .. ..$ : NULL
#>   .. ..$ : NULL
#>  $ inc_BF                 : num [1:7, 1:7] 0 0.493 0.22 0.562 0.587 ...
#>   ..- attr(*, "dimnames")=List of 2
#>   .. ..$ : NULL
#>   .. ..$ : NULL
#>  $ structure              : num [1:7, 1:7] 0 0 0 0 0 0 1 0 0 0 ...
#>   ..- attr(*, "dimnames")=List of 2
#>   .. ..$ : NULL
#>   .. ..$ : NULL
#>  $ structure_probabilities: num [1:1818] 2e-04 8e-04 6e-04 2e-04 4e-04 6e-04 2e-04 2e-04 4e-04 2e-04 ...
#>  $ graph_weights          : num [1:1818] 1 4 3 1 2 3 1 1 2 1 ...
#>  $ sample_graphs          : chr [1:1818] "100011011100100100010" "000011011100100100010" "000111011100100100010" "000111111100100100010" ...
#>  $ model                  : chr "ggm"
#>  - attr(*, "class")= chr [1:2] "package_bdgraph" "easybgm"

^{Created on 2023-11-22 with reprex v2.0.2}

Here, print(fit) throws an error, but it should not.

In addition, I noticed that the samples from BDgraph are weighted. Is this accounted for in e.g., the centrality measures?

[KarolineHuth]

the issue was the lack of column names of the dataframe. fixed it to now impute column names

[KarolineHuth]

fixed with 66e5bd1