search

NicolasHug / Surprise

A Python scikit for building and analyzing recommender systems
http://surpriselib.com
BSD 3-Clause "New" or "Revised" License
6.34k stars 1.01k forks source link

Using Surprise on more than 3 columns #409

Open sumit-mandal opened 2 years ago

sumit-mandal commented 2 years ago

Description

I want to use surprise for more than 3 columns but the Reader only takes 3 columns _userid, _itemid and ratings. How to use surprise on few more columns?

Steps/Code to Reproduce

Expected Results

Actual Results

Versions

VishnuBhaarath commented 2 years ago

Description

I want to use surprise for more than 3 columns but the Reader only takes 3 columns _userid, _itemid and ratings. How to use surprise on few more columns?

Steps/Code to Reproduce

Expected Results

Actual Results

Versions

Hi sumit, I too was looking out for the same to apply for more than 3 columns did you figure it out. @NicolasHug is it possible to go for more than 3 columns. Thanks

NicolasHug commented 2 years ago

If by column you mean additional "features" for items or users, then no, this isn't something that surprise can support

ayanatherate commented 1 year ago

Use solitary algorithms like NearestNeighbors and fit the model to your dataset according to your own problem statement. I ran into the same problem days ago and it's much better curating your own recommendation system than trying to fit it to the architecture supported by Surprise and other libraries.