You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
I am using "explain" with categorical dependent variables, predicted with random forests via nestcv.train . I found in one of nestedcv vignettes (https://cran.r-project.org/web/packages/nestedcv/vignettes/nestedcv_shap.html) that with multinomial classification I need to use pred_train_class1, pred_train_class2, etc as pred_wrapper. This works for pred_train_class1, pred_train_class2 and pred_train_class3, but not for pred_train_class4 and the following ones (I have 8 categories in total).
I can answer the question about the missing pred_train_class4 object (I'm the author of the nestedcv package). The source code for pred_train_class3 is as follows:
Hi @bgreenwell,
I am using "explain" with categorical dependent variables, predicted with random forests via nestcv.train . I found in one of nestedcv vignettes (https://cran.r-project.org/web/packages/nestedcv/vignettes/nestedcv_shap.html) that with multinomial classification I need to use pred_train_class1, pred_train_class2, etc as pred_wrapper. This works for pred_train_class1, pred_train_class2 and pred_train_class3, but not for pred_train_class4 and the following ones (I have 8 categories in total).
This is the code I am using:
And this is what I get:
Thank you.
The text was updated successfully, but these errors were encountered: