Skip to content

don't turn sparse matrix into dense matrix for glmnet prediction #1210

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 6 commits into from
Jan 29, 2025
Merged

don't turn sparse matrix into dense matrix for glmnet prediction #1210

Show file tree
Hide file tree
Changes from 3 commits
Commits
Show all changes
6 commits
Select commit Hold shift + click to select a range
517ecfb
don't turn sparse matrix into dense matrix for glmnet prediction
EmilHvitfeldt Sep 30, 2024
6904644
remember to do subsetting
EmilHvitfeldt Sep 30, 2024
6a22f85
don't add random newlines
EmilHvitfeldt Sep 30, 2024
ba56e2a
test glmnet predict doesn't remove sparseness
EmilHvitfeldt Oct 2, 2024
dbe666f
Merge branch 'main' into sparse-glmnet-predict
topepo Jan 29, 2025
645a2fc
regenerate snapshots to resolve merge conflicts
topepo Jan 29, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
10 changes: 10 additions & 0 deletions R/glmnet-engines.R
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -138,6 +138,16 @@ predict_raw._glmnetfit <- predict_raw_glmnet
unname(x[, 1])
}

organize_glmnet_pre_pred <- function(x, object) {
x <- x[, rownames(object$fit$beta), drop = FALSE]
if (is_sparse_matrix(x)) {
return(x)
}

as.matrix(x)
}


organize_glmnet_class <- function(x, object) {
prob_to_class_2(x[, 1], object)
}
Expand Down
2 changes: 1 addition & 1 deletion R/linear_reg_data.R
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -249,7 +249,7 @@ set_pred(
args =
list(
object = expr(object$fit),
newx = expr(as.matrix(new_data[, rownames(object$fit$beta), drop = FALSE])),
Copy link
Member Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

before we would call as.matrix() on anything before passing it to the predict method for the engine.

However if the data is a sparse matrix, we don't want to do that as {glmnet} is happy to receive it

newx = expr(organize_glmnet_pre_pred(new_data, object)),
type = "response",
s = expr(object$spec$args$penalty)
)
Expand Down
Loading