Sam

Changes
- `predict` method from `sam.models.ConstantTimeseriesRegressor` now accepts kwargs for compatibility. Now, swapping models with `SamQuantileMLP` with `force_monotonic_quantiles` doesn't cause a failure.

Changes
- `sam.models.QuantileMLP` requires `predict_ahead` to be int or list, but always casts to lists. Change to tuples in version 2.6.0, but caused inconsistencies and incorrect if statements.

Changes
- `sam.visualization.sam_quantile_plot` now displays quantiles in 5 decimals, requirement from Aquasuite with larger quantiles.

Changes
- New (optional) parameters for `sam.validation.RemoveFlatlines`: `backfill` and `margin`
- Simplified `sam.validation.RemoveFlatlines` to use `pandas.DataFrame.rolling` functions

Changes
- `SamQuantileMLP.predict` now accepts `force_monotonic_quantiles` to force quantiles to be monotonic using a postprocessing step.

Changes
- Added a SPC model to SAM called `ConstantTimeseriesRegressor`, which uses the `SamQuantileRegressor` base class and can be used as a fall back or benchmark model

Fixes
- `SamQuantileMLP` now accepts Sequence types for some of its init parameters (like quantiles, time_cyclicals etc.) and the default value is changed to tuples to prevent the infamous "Mutable default argument" issue.