Chris Lo

[ENH] predictive variance and quantiles for naive forecaster

5

#### Reference Issues/PRs Closes #1905 #### What does this implement/fix? Explain your changes. - Implements `predict_var` and `predict_quantile` for `NaiveForecaster` - We apply the following algorithm from FPP3 Chapter 5....

[ENH] Predicted variance for `STLForecaster`

1

#### Reference Issues/PRs Closes #3437 #### What does this implement/fix? Explain your changes. - Implements `_predict_var` for `STLForecaster` - Adds conditional tagging logic under `__init__` #### Does your contribution introduce...

[ENH] Prediction intervals for `EnsembleForecaster`

4

**Is your feature request related to a problem? Please describe.** - `EnsembleForecaster` does not have`_predict_interval capabilities **Describe the solution you'd like** - Add a check that all underlying forecasters have...

[ENH] Predict variance / quantiles for `STLForecaster`

5

**Is your feature request related to a problem? Please describe.** - `STLForecaster` does not have `predict_var` or `predict_quantile` capabilities **Describe the solution you'd like** Since the current implementation already assumes...

**Tools** - https://docs.pydantic.dev/latest/integrations/datamodel_code_generator/ - https://github.com/ghandic/jsf

**User Story:** I want to build automated investigations given findings from Datadog security products. Datadog's key security features can be grouped in the following: - CSPM findings - SIEM signals...

**Is your feature request related to a problem? Please describe.** I would like to support Excel-like formulas to perform complex piecemeal transformations directly within the input field. **Describe the solution...

Add ta-lib to feature extraction

3

For the financial forecasting use-case, instead of implementing technical indicators from scratch, we can leverage talib's native integration with polars. https://github.com/ta-lib/ta-lib-python

Add `plot_interval_forecasts` function

3

## Rationale We currently have `plot_forecasts` function in `functime.plotting`. However, we also support probablistic forecasts (see `forecaster.conformalize`. We need to do a better job promoting this functionality. The best way...

Explain why forecasters drop very short time series

3

## Problem Time series with counts less than the number of lags are silently dropped at predict time. For example, during M5 benchmarking, time series with lengths less than `lags=24`...