This function sums up SHAP values (or SHAP interaction values) of feature groups. Typical application: SHAP values have been generated by a model with one or multiple one-hot encoded variables, but the explanations should be done using the original factor.
collapse_shap(S, collapse = NULL, ...)Either a (n x p) matrix of SHAP values or a (n x p x p) array of SHAP interaction values.
A named list of character vectors. Each vector specifies the feature names whose SHAP values need to be summed up. The names determine the resulting collapsed column/dimension names.
Currently unused.
A matrix of SHAP values, or an array of SHAP interaction values.
S <- cbind(
x = c(0.1, 0.1, 0.1),
`age low` = c(0.2, -0.1, 0.1),
`age mid` = c(0, 0.2, -0.2),
`age high` = c(1, -1, 0)
)
collapse <- list(age = c("age low", "age mid", "age high"))
collapse_shap(S, collapse)
#> x age
#> [1,] 0.1 1.2
#> [2,] 0.1 -0.9
#> [3,] 0.1 -0.1
# Arrays (as with SHAP interactions)
S_inter <- array(1, dim = c(2, 4, 4), dimnames = list(NULL, letters[1:4], letters[1:4]))
collapse_shap(S_inter, collapse = list(cd = c("c", "d"), ab = c("a", "b")))
#> , , cd
#>
#> cd ab
#> [1,] 4 4
#> [2,] 4 4
#>
#> , , ab
#>
#> cd ab
#> [1,] 4 4
#> [2,] 4 4
#>