ValueError: Test interactions matrix and train interactions matrix share 95786 interactions. This will cause incorrect evaluation, check your data split.
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 5.1k
- Forks
- 724
- PR merge metrics
- No merged PRs in 30d
Description
Hi
I am trying to create a hybrid recommender using item's features
I have a dataset with 478,930 interactions
I am quite sure that each user-item pairs available only once in my data,
so it should be no interactions shared between train and test sets
However, I keep getting the issue:
ValueError: Test interactions matrix and train interactions matrix share 95786 interactions. This will cause incorrect evaluation, check your data split.
How can I solve this?
What are the potential reasons for this?
Contributor guide
No contributing guide indexed for this repository
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
No file, test, or entry point is named. Start by reproducing the reported train/test split with the stated interaction data and inspect how LightFM validates overlap. Done would be identifying whether the overlap comes from the data split or a library defect and documenting a concrete fix or clarification.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- machine-learning
- Issue type
- Bug
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 30/100