azul

[FEAT] Fitted values for intermittent models

1

**Is your feature request related to a problem? Please describe.** Intermittent models don't have in-sample predictions (or fitted values) implemented. See, for example, https://github.com/Nixtla/statsforecast/blob/e24068ebe456c8eb6fe68265caf9d60afaa8b60d/statsforecast/models.py#L2253-L2254 **Describe the solution you'd like** Add...

Some methods and functionality (bootstrapped prediction intervals) need the fitted values of the models. But the following iteration omits to request them. https://github.com/Nixtla/hierarchicalforecast/blob/0c5cc368875589c65244364516374d577875627f/hierarchicalforecast/core.py#L128-L146 The above leads to unintelligible bugs.

**Is your feature request related to a problem? Please describe.** Update `nbdev` to `nbdev2`.

**Is your feature request related to a problem? Please describe.** Pipelines in `neuralforecast.experiments.utils` should be migrated to a general class named `NeuralForecast` as in `StastForecast`.

**Is your feature request related to a problem? Please describe.** The `neuralforecast.data.datasets` must be migrated to [`datasetsforecast`](https://github.com/Nixtla/datasetsforecast).

[MODELS DOCS] Change ETS to AutoETS

1

### Description We are deprecating `ETS` in favor of `AutoETS`. We have to update the documentation accordingly. ### Link _No response_

[FEAT] Add M5 and M4-Daily experiments (Amazon Forecast)

1

This PR includes an experiment comparing `AmazonForecast` and `StatsForecast` using the M5 and M4-Daily datasets.

[Bug] Prompt request prevents installing openbb SDK for CI

2

**Describe the bug** I'm trying to use `openbb` SDK as a dependency in our library and use it inside our continuous integration. But during CI, importing `openbb` requests a prompt...

The tutorials can be opened using Colab, but the installation must still be included.

[FEAT] Add recommendations when a 413 error is returned

2

Related to size of data. It should suggest using `num_partitions`. See #176.