Skip to content

Releases: davidusb-geek/emhass-add-on

EMHASS add-on v0.3.7

17 Mar 07:53
Compare
Choose a tag to compare

Fix

  • Fixed to correct index length for ML forecaster prediction series.

Full Changelog: v0.3.6...v0.3.7

EMHASS add-on v0.3.6

16 Mar 23:04
Compare
Choose a tag to compare

Fix

  • Fixed wrong path for saved ML forecaster model.
  • Fixed wrong column name for var_load when using predict with ML forecaster.

Full Changelog: v0.3.5...v0.3.6

EMHASS add-on v0.3.5

10 Mar 18:20
Compare
Choose a tag to compare

Fix

  • Fixed default behavior for passed data.
  • Added a new graph for tune results.

Full Changelog: v0.3.4...v0.3.5

EMHASS add-on v0.3.4

10 Mar 06:42
Compare
Choose a tag to compare

Fix

  • Fixed missing emhass moddule

EMHASS add-on v0.3.3

09 Mar 22:25
Compare
Choose a tag to compare

Fix

  • Added missing possibility to set the method for load forecast to 'mlforecaster'.
  • Fixed logging formatting.

Full Changelog: v0.3.2...v0.3.3

EMHASS add-on v0.3.2

08 Mar 23:19
Compare
Choose a tag to compare

Some bug fixes

Fix

  • Fixed logging.
  • Fixed missing module on docker standalone mode.

Full Changelog: v0.3.1...v0.3.2

EMHASS add-on v0.3.1

07 Mar 10:50
Compare
Choose a tag to compare

Some bug fixes.

Full Changelog: v0.3.0...v0.3.1

EMHASS add-on v0.3.0

06 Mar 22:44
Compare
Choose a tag to compare

The new machine learning forecast module is here! Check the updated documentation with the dedicated section here: https://emhass.readthedocs.io/en/latest/mlforecaster.html

Improvement

  • A brand new load forecast module and more... The new forecast module can actually be used to foreast any Home Assistant variable. The API provides fit, predict and tune methods. By the default it provides a more efficient way to forecast the power load consumption. It is based on the skforecast module that uses scikit-learn regression models considering auto-regression lags as features. The hyperparameter optimization is proposed using bayesian optimization from the optuna module.
  • A new documentation section covering the new forecast module.
  • Improved the documentation and the in-code docstrings.
  • Added the possibility to save the optimized model after a tuning routine.
  • Added the possibility to publish predict results to a Home Assistant sensor.
  • Added the possibility to provide custom entity_id, unit_of_measurement and friendly_name for each published data.

Fix

  • Fixed Solar.Forecast issues with lists of parameters.
  • Fixed latex equations rendering on documentation, dropped Mathjax.
  • Refactored images in documentation, now using only SVG for plotly figures.
  • Bumped requirements to latest non-conflicting versions.

Full Changelog: v0.2.29...v0.3.0

EMHASS add-on v0.2.29

31 Jan 10:52
Compare
Choose a tag to compare

Fix

  • Fixed access to injection_dict for the first time that emhass is used.
  • Fixed message handling from request module.

Full Changelog: v0.2.28...v0.2.29

EMHASS add-on v0.2.28

30 Jan 22:39
Compare
Choose a tag to compare

Fix

  • Fixed bugs with paths again, now using the official pathlib everywhere.

Full Changelog: v0.2.27...v0.2.28