All of the examples I see for adding a test set to the databunch is from vision. There is the command add_test_folder
. But how do I add a test set from a tabular databunch:
data = (TabularList.from_df(df, cat_names=cat_vars, cont_names=cont_vars, procs=procs)
.split_by_idx(valid_idx)
.label_from_df(cols=dep_var, label_cls=CategoryList)
.databunch())
This just returns a train and valid set in the databunch, but no test set. Is there a similar command for tabular data?
I’m getting error for using add_test
data = (TabularList.from_df(df, cat_names=cat_vars, cont_names=cont_vars, procs=procs)
.split_by_idx(valid_idx)
.add_test(df_test, label='dep')
.label_from_df(cols=dep_var, label_cls=CategoryList)
.databunch())
AttributeError: 'TabularList' object has no attribute 'add_test'