massquantity

Which algorithm are you using? If you are using a `pure` algorithm such as SVD or itemCF, you can pass users and items as list to the `predict` function. To...

Yes you can use the `evaluate` function to evaluate on the new data directly, see line 76 in [changing_feature_example.py](https://github.com/massquantity/LibRecommender/blob/master/examples/changing_feature_example.py). I do have a tf2.x plan, but certainly it's not my...

Unfortunately, SVD++ is a collaborative-filtering algorithm, which means it can't use any side information.

What do mean by expected value? All the prediction values are the same?

What's the range of your label, like 1 to 5?

Really no idea, unless you show some data examples.

I don't have multi-GPUs, so I didn't even consider it when writing the library. Even if I can write the multi-GPUs training code, I couldn't test it. But this is...

Sorry no plan for this. For now the top priority is adding some new algorithms.

See this [issue](https://github.com/massquantity/LibRecommender/issues/20). Possible cause is that your system is Windows... You can clone all the code and cd into the `LibRecommender` folder. Then maybe you can use the library...

Alright, I've released a new version, so you can give it a try. > pip install LibRecommender==0.2.2