willfuks

Hi @amitdingareNovelis , Not quite sure what's happening there. What might explain the error is that this package doesn't officially support the Windows OS (even though I thought it could...

That's good news. Those warnings are part of the Tensorflow packages and we didn't find how to turn them off.

Hi @shnaqawi , Not sure what's going on. If you could share some data (it could undergo transformations) so that I can replicate the issue here that'd be helpful. Also,...

Hi @sp-alicia-horsch , The default model does use `vi` method by default. This happens in the input processing when arranging the [arguments](https://github.com/WillianFuks/tfcausalimpact/blob/1951e7bf25f7cd7317ae0dad7ca2e9987450ff78/causalimpact/model.py#L112) for the model. Are you also observing unstable...

Hi @shnaqawi , I ran some simulations of your data with 'hcm' and also observed a higher variation for the relative effects. Unfortunately it does seem to be related to...

Hi @rangelrey , Just to confirm, are you using `vi` alg? Do you get the same when using `hcm`?

Hi @rangelrey , The results for the `vi` alg are expected to vary that much indeed (mainly because the algorithm works by surrogating the posterior distributions of each component with...

Hi @mc51 , In the README.md file there's a [section](https://github.com/WillianFuks/tfcausalimpact#google-r-package-vs-tensorflow-python) that discusses that. Overall results should be equivalent as far as values goes but regarding performance unfortunately the Python package...

Hi @mc51 , I suspect that the different algorithms (Gibbs vs HMC) are what explain the contrasting performances indeed. Notice that GPUs does help and are recommended for this package...

Hi @MichaelMitchellM , This does indeed happen. When developing this package I did look for ways to hide the warnings but they happen internally in TensorFlow Probability so I couldn't...