v0.5.4

What's Changed

• feat: add issues template by @FedericoGarza in #93
• refactor: use Pool instead of ProcessPoolExecutor by @FedericoGarza in #96
• Feat: add ray integration by @FedericoGarza in #98
• fix: add automatic n_jobs behavior by @FedericoGarza in #99
• Creation of forecast dates improvement by @FedericoGarza in #101
• Ray experiment by @FedericoGarza in #103
• Update README.md by @mergenthaler in #104

Full Changelog: v0.5.3...v0.5.4

v0.5.3

What's Changed

New features

• summary method for the AutoARIMA class requested in #31.
• representational string for the AutoARIMA fitted model, requested in #83.

Bug Fixes

• [BUG] croston_sba #88 fixed in #89.

AutoARIMA predict_in_sample

• Added predict_in_sample method for AutoARIMA.
• Users can now compute in sample forecasts including prediction intervals.

AutoARIMA class

• Now: Good Ol' sklearn syntax with model = AutoARIMA(); model.fit(y); model.predict(10).
• Bug fixes.

Prediction intervals for AutoARIMA

Notable changes

• Inclusion of prediction intervals for auto_arima.
• statsforecast is now installable from conda-forge (conda install -c conda-forecast statsforecast, thanks to @sugatoray).

Exogenous variables for AutoARIMA

Notable changes

• Inclusion of exogenous variables for auto_arima.
• The StatsForecast class now handles exogenous variables.
• This release allows developers to include more models that use exogenous variables.
• Bug fixes.