How to assign new data to validation

Hi all,

I’m working on tabular data at the moment
I was able to create the training data using TabularPandas function

to = TabularPandas(dfFULL, procs=[FillMissing, Categorify, Normalize],
                   cat_names = cat_names,
                   cont_names = cont_names,
                   y_names = dep_var)
dls = to.dataloaders(bs=3)

Now if we check the training data

And the valid data

This looks good to me, now I’m trying to add my own valid data, not using the split function
I tried 3 methods, non of them works?

Thanks you all your help

Why are you trying to do this? If you want to do predictions / add a test set you can use the DataLoaders .test_dl method. So:


If you’r doing it just for the sake of it, I guess you would create the two single ‘DataLoader’ objects with the appropriate sources and combine them to a ‘DataLoaders’ object (yes, those a two different things :smile:); the book should go into that, if I remember correctly. (edit: it does in chapter 19)

Thanks for your reply.
I just need to find a way to add valid data to the dataloaders.

Ah ok, I mistook that :slight_smile:. You do this by passing a splits parameter when creating the TabularPandas. Check the tutorial on tabular data here. Then dls.train holds the training and dls.valid the validation dataloader.