Olivier Sprangers

To partially answer my own question, by integrating the gradient it seems that taking the log of the score in the metric results in the difference between the differentiated metric...

@Zhylkaaa I think the answer is in [these lines](https://github.com/microsoft/LightGBM/blob/b857ee10cc9a913e6dedd15c2475765d1e923c7b/src/objective/regression_objective.hpp#L431). The Tweedie loss inherits from the RegressionPoissonLoss, so the LightGBM leaf values contain the raw score. To get the output, the...

For those stumbling upon this thread, below works for me: 1. Install [Build Tools for Visual Studio](https://visualstudio.microsoft.com/downloads/?q=build+tools) 2. Make sure you add compiler `cl` to your PATH environment variable (see...

Hi, `n_series` should indeed be the number of unique series in the dataset. Could you check whether this issue still persists on the latest version (1.7.1)? If not, can you...

Thanks for the suggestion, I think I understand the request. Feel free to file a PR with the request so that we can review.

> LGTM! Let's just please also wait for @cchallu's review as well. Thanks - it does not fix the default_config issue yet, so I'm changing a few things (converted to...

- Added a `get_default_config` method for all Auto* models - Fixed incompatible hyperparameter configurations in base models - Added unit tests to all auto models to ensure they all run...

Thanks for reporting - I think `input_size_multiplier` doesn't work in any case right now as a configurable hyperparameter so this is something that needs to be fixed too.

You can fix this (monkey patch) by: 1. Getting rid of `input_size_multiplier` in the config, i.e. `del config['input_size_multiplier']` 2. Getting rid of `inference_input_size_multiplier` in the config, i.e. `del config['inference_input_size_multiplier']` 3....

Thanks, good point. I think it should be `index.dt.isocalendar().week`, i.e. first need to access the `.dt` attribute. I'll have a pass through our code and see if there are other...