Pipeline fails with "Training and / or test set is empty, verify that training / test split is correctly set in split.csv" .
Issue Description
Pipeline fails with:
File "", line 140, in train
File "", line 139, in __init__
File "", line 26, in __init__
File "", line 527, in preprocess_data
AssertionError: Training and / or test set is empty, verify that training / test split is correctly set in split.csv
File "", line 139, in __init__
File "", line 26, in __init__
File "", line 527, in preprocess_data
AssertionError: Training and / or test set is empty, verify that training / test split is correctly set in split.csv
Root Cause: This can occur when the file names in the dataset folder are too long. There may be other causes for this issue.
Diagnosing / Resolving Steps
- Look at the dataset and check to see if there are any files with name greater than 260 characters
- If there is a file name that is longer than 260, the file name needs to be reduced and any references to it need to be changed to the updated name
- Other causes could be that the wrong folder was selected for the pipeline
- If the above does not resolve the issue, raise a ticket with UiPath.