Oskar Triebe

Excellent @quant-exchange! Looking forward to your PR.

Addressing this will also require https://github.com/ourownstory/neural_prophet/issues/828

Hi @catherinening Thank you for raising this issue with detailed description. Could you please include a minimal toy/synthetic dataset that triggers the same issue, so I can reproduce and debug...

@catherinening Please excuse the late follow-up. Did you find a solution to this? I suspect, that some of your series still had no or insufficient observations in the training data...

Thank you for sharing your solution to the issue you observed @quant-exchange

@MaiBe-ctrl Do you mind checking if you get the same error with the dummy dataset?

@quant-exchange Has your work-around held up with no further issues? I would be happy to add a page with tips on using NP in production. Would you like to contribute...

@MaiBe-ctrl Let's consider freeing up the upward range of `tensorboard` and other dependencies. Edit: Done.

@MaiBe-ctrl This seems to stem from one of the semi-modularized components, future-regressors, more recent support for NN modeling. We should have a closer look at this error.

It appears that after an initial request to add a package to `conda-forge`, which was [done here](https://github.com/conda-forge/staged-recipes/pull/23383) by @VaTupuri, they will pull subsequent releases from PyPI, [based on this resource](https://www.pyopensci.org/python-package-guide/tutorials/publish-conda-forge.html)....