Closed PeruBhardwaj closed 5 years ago
fb15k-237 and wn18rr datasets have some entities in test and validation set that are not in train set. So we need to remove them before fitting/evaluation. That's why you are getting this error.
Will the train_test_split_no_unseen() function work for this?
Just checked. There is a clean_data method in predictive_performance.py which can be used. You can also refer that file for more details.
I think we must move the clean_data to model_utils. I will create a separate issue for that.
Closing this issue and creating a separate issue for moving clean_data to a meaningful location
Description
I am trying to replicate the performance results from the documentation but getting a runtime error when using early stopping with FB15k-237.
I have used early stopping with other datasets like FB15k, WN18 and there is no runtime error with these.
Steps to Reproduce