search

benfred / implicit

Fast Python Collaborative Filtering for Implicit Feedback Datasets
https://benfred.github.io/implicit/
MIT License
3.57k stars 612 forks source link

Silent NaN's in implicit AlternatingLeastSquares while implementing Grid search #651

Closed milanABI closed 1 year ago

milanABI commented 1 year ago

@benfred @Focus Currently i am using 0.6.2 version and I am getting an error while implementing grid search. I've double checked there is no NaN's in the data.

clf = GridSearchCV(als_pipeline, parameters,cv = 2, verbose=True, error_score='raise') 
clf.fit(data_als,data_als)

below is the screenshot attached for the same.

Screenshot 2023-03-30 at 11 50 36 AM
benfred commented 1 year ago

Do you have a reproducer I can use here (dataset + ALS parameters that cause a NaN value)?

benfred commented 1 year ago

@milanABI - please re-open if this is still an issue for you