José Morales

@fengshansi can you try using the same parameters in both? For example you're setting 0.3 as the learning rate for LightGBM and 0.7 for CatBoost, which should converge faster. Also...

Hey @ravibrock, thanks for the contribution. Unfortunately, this breaks the documentation, for example for the `SimpleExponentialSmoothing` this is the [current documentation](https://nixtlaverse.nixtla.io/statsforecast/src/core/models.html#simpleexponentialsmoothing):  and these are the docs rendered locally from...

Seems like we can just use raw strings for our docstrings, would you like to make that change @ravibrock?

Also, can you please export the changes to the source code? You can find a detailed guide [here](https://github.com/Nixtla/statsforecast/blob/main/CONTRIBUTING.md)

I think there was a recent breaking change in setuptools 70, it should be fixed by downgrading (e.g. `pip install "setuptools

Just spitballing here but since we're [getting conda's libgomp](https://dev.azure.com/lightgbm-ci/lightgbm-ci/_build/results?buildId=16481&view=logs&j=7a417b3a-6502-5a0d-1db8-7ef6155c93de&t=380f8b13-0b2d-5f03-5de0-8353018c7351&l=217), we could also try installing [conda's c++ compiler](https://anaconda.org/conda-forge/cxx-compiler/) in that job and that'd link against that libgomp, which is the one...

Oh sorry, I didn't realize that job was building wheels. We could also go the other way and drop conda from that job, I've used [uv](https://github.com/astral-sh/uv) a lot lately and...

> would you support commenting out this CI job for now so that we can keep making progress in the repo while we investigate this? Sure! That shouldn't block our...

The book uses `fill_gaps` which creates `NaN`s for times that were missing. `plot_series` behaves the same way, i.e. ```python import pandas as pd from utilsforecast.plotting import plot_series from utilsforecast.preprocessing import...

Closing due to lack of response.