Jonathan Mallia

> > I added '-DCMAKE_GENERATOR_PLATFORM=x64' flag to the setup.py and the problem solved in Win64 (Win10) and Python 3.5.4. > > if 0 != execute(['cmake', > > '-DCMAKE_GENERATOR_PLATFORM=x64', > '-DCMAKE_BUILD_TYPE={}'.format(build_type),...

Is there a solution to fix the gap between CPU and GPU training performance?

Bayesian time SVD++? Thank you Thanks, It's referred as Bayesian time SVD++ https://arxiv.org/pdf/1905.01395v1.pdf mentioned also here: Koren, Y. Collaborative filtering with temporal dynamics. In Proceedings of the 15th ACM SIGKDD...

Hello, Is there any update on this feature? Would be great as it would speed up processing even more.

This would be a great implementation as it proves to be very effective for non-subscription based scenarios.

Yes would like to know more on best approach on predicting on completely new data set? Do we need to recreate a graph network for this each time we have...

Hi @ita9naiwa , Can you please advise how to build and install the package from source, in order to have GPU working on Windows? Thanks

This errors comes from the latest update of Polars. Returns: `ModuleNotFoundError: No module named 'polars.utils'` Stack: `import polars as pl [7](file:///C:/Users/ia/.conda/envs/env/Lib/site-packages/functime/feature_extractors.py:7) from polars.type_aliases import ClosedInterval ----> [8](file:///C:/Users/ia/.conda/envs/env/Lib/site-packages/functime/feature_extractors.py:8) from polars.utils.udfs import...

Hi, Is there an update on when the final merge to master going to happen? Thank you

> You should edit into the title that the issue is reading from cloud. Please run this and post full output, maybe that'll help. > > ``` > import os...