massquantity
massquantity
You may need instances of at least 16GB memory.
Maybe there is a name conflict. Please provide your code. You can also print [data](https://github.com/massquantity/LibRecommender/blob/master/libserving/sanic_serving/tf_deploy.py#L177) here to check if it has the correct format.
After splitting, you can manually move all the oov(out-of-vocabulary) users/items from eval_data to train_data. ```python train_data, eval_data = split_by_ratio(...) train_data, eval_data = move_oov_to_train(train_data, eval_data) def move_oov_to_train(train_data: pd.DataFrame, eval_data: pd.DataFrame): unique_users...
OK, I'll consider adding this extension. "retrain" in this library means incremental training, which is used when one gets some new data potentially several days later. So the previous trained...
The embeddings of users/items with no transaction can't be learned, since they have no data to be trained. The library applies mean embedding, so all these users will have the...
OK, i get it. You didn't mention that you can use other features in your data. This is supported by using [Dynamic Embedding Generation](https://librecommender.readthedocs.io/en/latest/user_guide/embedding.html#dynamic-embedding-generation). However, this approach only supports new...
Do you want to recommend items that a user has not interacted with before? This is the default case since the `filter_consumed` parameter in the [`recommend_user`](https://librecommender.readthedocs.io/en/latest/api/algorithms/pinsage.html#libreco.algorithms.PinSage.recommend_user) method is True by...
OK, i get it. This is basically an item cold-start problem, but this library can't deal with this since the algorithms require some kind of interaction for items. The common...
This is highly related to your specific scenario, so I don't think general-purpose open-source libraries can help with that...
The error shows the new model only has 106 items. You can use `print("new n_items: ", model.data_info.n_items)` to verify it. I suspect you used the previous data_info in the new...