-
**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 …
-
Would it also be possible for the package to support confidence and prediction intervals for gls models?
-
- As a developer, I want to calculate the residuals per training fold. To do that, i need the true target values along with the training predictions. I can not find anything in the documentation relat…
-
Hi Zhendong,
I tried to adapt your amazing PCP framework to a model agnostic PCP-framework, --> SLCP-PCP.
To do this, I replaced your QRF-PCP framework (uniform) with a nonconformis agnostic wra…
-
Thanks for a fantastic series about conformal prediction. I am working on a model that outputs predictions for 100s-1000s of variables. Is it possible to use conformal predictors in that case?
Doe…
vitkl updated
8 months ago
-
Define You:
- [ ] DWOC 2023 Participant
- [x] Contributor
Hey OS participants, good to see you.
This project will help us in predicting the moisture of the soil to check if it's wet or dry
…
-
The new count models have many `which`, prediction of nonlinear functions of parameters.
But we do not have `get_prediction` for them.
Getting standard errors and confidence intervals requires del…
-
As of now, `ThetaForecaster` generates probabilistic forecasts by adding white noise to point forecasts in `sktime`. Given that it inherits from `_StatsModelsAdapter` and `statsmodels` does have a met…
-
The way the `rfinterval` method is currently set up, the only way to get predictions for new data is to input them as `test_data` while training the model. This makes it much more difficult to use in …
-
Would it be possible by any chance for investr to also support scam (https://cran.r-project.org/web/packages/scam/index.html) and mgcv::gam (https://cran.r-project.org/web/packages/mgcv/index.html) mo…