NEWS

---

modeltime.ensemble 1.0.4 (2024-07-19)

• #31 Fixes issue with metric argument not being specified:

Error in `tune::show_best()`:
! `...` must be empty.
✖ Problematic argument:
• ..1 = metric
ℹ Did you forget to name an argument?

modeltime.ensemble 1.0.3 (2023-04-18)

• Resubmit to CRAN (following timetk archival)

modeltime.ensemble 1.0.2 (2022-10-18)

• Update tests for workflows mode = "regression"

modeltime.ensemble 1.0.1 (2022-06-09)

Fixes

• Updates for hardhat 1.0.0

modeltime.ensemble 1.0.0 (2021-10-19)

NEW Nested Modeltime Ensembles

In modeltime 1.0.0, we introduced Nested Forecasting as a way to forecast many time series iteratively. In modeltime.ensemble 1.0.0, we introduce nested ensembles that can improve forecasting performance and be applied to many time series iteratively. We have added:

• ensemble_nested_average(): Apply average ensembles iteratively
• ensemble_nested_weighted(): Apply weighted ensembles iteratively

New Vignette (Nested Ensembles)

• Nested Ensembles

modeltime.ensemble 0.4.2 (2021-07-16)

Compatibility with modeltime 0.7.0.

• Calibration: Added "id" feature to enable accuracy and confidence intervals by time series ID.

modeltime.ensemble 0.4.1 (2021-05-31)

• Improvements for parallel processing during refitting (available in modeltime 0.6.0).
• Requires modeltime 0.6.0 and parsnip 0.1.6 to align with xgboost upgrades.

modeltime.ensemble 0.4.0 (2021-04-05)

Recursive Ensembles

• recursive() - The recursive() function is extended to recursive ensembles for both single time series and multiple time series models (panel data).
• "Forecasting with Recursive Ensembles" - A new forecasting vignette for using recurive() with ensembles.

Fixes

• modeltime_forecast() now returns NA when missing values are present in the sub-model predictions.

modeltime.ensemble 0.3.0 (2020-11-06)

Panel Data

• Improvements made to ensemble_average(), ensemble_weighted() and ensemble_model_spec() to support Panel Data (i.e. when data sets with multiple time series groups that have possibly overlapping time stamps).

Changes

• modeltime.ensemble now depends on modeltime.resample for the modeltime_fit_resamples() functionality.
• modeltime_fit_resamples() moved to a new package modeltime.resample.
• ensemble_weighted(): Now removes models that have no weight (e.g. loading = 0). This speeds up refitting.

modeltime.ensemble 0.2.0 (2020-10-09)

Stacked Ensembles (Breaking Changes)

The process for creating stacked ensembles is split into 2 steps:

• Step 1: Use modeltime_fit_resamples() to generate resampled predictions
• Step 2: Use ensemble_model_spec() to apply stacking using a model_spec

Note - modeltime_refit(stacked_ensemble) is still one step, which is the best way to handle refitting since multiple stacked models may have different submodel compositions. An additional argument, resamples can be provided to train stacked ensembles made with ensemble_model_spec().

modeltime.ensemble 0.1.0 (2020-10-07)

• Initial release of modeltime.ensemble.