Martin Walter
Martin Walter
**Is your feature request related to a problem? Please describe.** I would recommend to introduce soft-dependency machanism that gives the user a proper exception and hinting to that multiple install...
**Is your feature request related to a problem? Please describe.** The current `sktime` interface to `hcrystalball` is going to be deprecated soon. A solution to still use `hcrystalball` with `sktime`...
**Describe the bug** `make_reduction` does not work with `sktime` forecasters aka `scitype="time-series-regressor"` ``` TypeError: Invalid `fh`. The type of the passed `fh` values is not supported. Please use one of...
**Describe the bug** related discussion: #3220 grid search is trying to predict on `self.best_forecaster_ = self.forecaster.clone().set_params(**self.best_params_)` which was not fitted and raises therefore a `NotFittedError`. The problem is that` evaluate()...
**Is your feature request related to a problem? Please describe.** I got the idea to add `sktime` as a package to `mlflow` like the following packages that are already included:...
**Is your feature request related to a problem? Please describe.** We currently have only simple dummy panel data like this: ```python from sktime.datatypes import get_examples y_hier = get_examples("pd_multiindex_hier")[1] ``` **Describe...
**Describe the bug** Exception: ```python The above exception was the direct cause of the following exception: NotImplementedError Traceback (most recent call last) ~\AppData\Local\Temp/ipykernel_27188/715707699.py in 30 verbose=1, 31 ) ---> 32...
#### Reference Issues/PRs closes #3439
**Describe the bug** ```python --------------------------------------------------------------------------- ValueError Traceback (most recent call last) ~\AppData\Local\Temp\ipykernel_10704\2624273533.py in 15 ("forecaster", NaiveForecaster())]) 16 pipe.fit(y_train) ---> 17 pipe.predict(fh=3) c:\Users\mf-wa\Desktop\sktime\sktime\sktime\forecasting\base\_base.py in predict(self, fh, X) 356 # we call...
**Is your feature request related to a problem? Please describe.** We have currently three sequential pipeline classes `TransformedTragetForecaster`, `ForecastingPipeline` and `TransformerPipeline`. Having several transformers chained raises the question which is...