[ENH] Rework ETS Forecaster

[TonyBagnall]

some adaptations of ETS to make it compliant. The basic structure of ETS is this

_fit
    _numba_fit
    self.forecast_ = _numba_predict


_numba_fit
    for t in range(n_timepoints):
            _update_states()
                _predict_value

_numba_predict
    _predict_value

predict_value makes a step ahead prediction (and also returns two other variables, so maybe poorly named)

1. Override iterative_forecasting
   the default method would result in refitting ETS each time. It now calls fit once then iterates numba_predict

        self.fit(y)
        preds = np.zeros(prediction_horizon)
        preds[0] = self.forecast_
        for i in range(1, prediction_horizon):
            preds[i] = _numba_predict(
                self._trend_type,
                self._seasonality_type,
                self.level_,
                self.trend_,
                self.seasonality_,
                self.phi,
                i + 1,
                self.n_timepoints_,
                self._seasonal_period,
            )

2. With no damping, now sets phi to the horizon

3. Not sure if I will make it "fit_is_empty" here, may be better to wait until we see how auto ets works.

[aeon-actions-bot]

Thank you for contributing to aeon

I have added the following labels to this PR based on the title: [ enhancement ].
I would have added the following labels to this PR based on the changes made: [ forecasting ], however some package labels are already present.

The Checks tab will show the status of our automated tests. You can click on individual test runs in the tab or "Details" in the panel below to see more information if there is a failure.

If our pre-commit code quality check fails, any trivial fixes will automatically be pushed to your PR unless it is a draft.

Don't hesitate to ask questions on the aeon Slack channel if you have any.

PR CI actions

These checkboxes will add labels to enable/disable CI functionality for this PR. This may not take effect immediately, and a new commit may be required to run the new configuration.

• Run pre-commit checks for all files
• Run mypy typecheck tests
• Run all pytest tests and configurations
• Run all notebook example tests
• Run numba-disabled codecov tests
• Stop automatic pre-commit fixes (always disabled for drafts)
• Disable numba cache loading
• Push an empty commit to re-run CI checks

[review-notebook-app]

Check out this pull request on 

See visual diffs & provide feedback on Jupyter Notebooks.

---

Powered by ReviewNB

[alexbanwell1]

Looks good to me, I've fixed the one bug that seemed to exist, so otherwise set up with the right parameters, produces similar forecasts to statsmodels

[TonyBagnall]

our next move is to auto set the parameters

    alpha : float, default=0.1
        Level smoothing parameter.
    beta : float, default=0.01
        Trend smoothing parameter.
    gamma : float, default=0.01
        Seasonal smoothing parameter.

in fit, it doesnt really make sense for the user to set them, other packages dont and the forecasts are very sensitive to them. So ETS will fit the parameters in train, AutoETS will set the hyper parameters (additive etc) in fit using ETS

[TonyBagnall]

test expected values changed because of the seasonality bug