-
Hi, I was hoping to extend the create_transform function in the DeepAR estimator, is there anyway to do this? I haven't found the extended [tutorial](https://gluon-ts.mxnet.io/examples/extended_foreca…
-
I am a beginner at Deepar. The Deepar example code of sagemaker is different from GluonTS. Sagemaker uses "dynamic_feat" and "cat" as extension features.But GluonTS use "feat_dynamic_real" and "feat_s…
-
I am using DeepStateEstimator for forecasting purposes with Hourly data .But if I set prediction length=1,means prediction for next hour ,it gives me error and if I set prediction length>=2,its workin…
-
Hi Team,
I am working on a daily time series dataset with different lengths (a mix of short and long time series with different start dates). Following is a subset of the dataset (2 time series out…
-
I've got a few questions around using feat_static_cat for time series with more than one category.
My data set that I'm wanting to create forecasts on includes both a store id and a product id, per…
-
## Description
Data loading seems to hang when `num_workers` is set to `1` or more. The same doesn't seem to happen if `num_workers=None` or `num_workers=0` (I'm not sure what the latter implies).
…
-
(Please state your question in the title, and add here any relevant details,
like a description of the problem, code snippets, examples, and so on.)
Hi,
I am curious to add covariates(day of the …
-
In https://github.com/QuantConnect/Lean/issues/4930 I already flagged that a docker image can not be build out of the box. I now have managed to do so by moving some packages from conda to pip for ins…
-
I upgraded `gluon-ts` from `0.4.2` to `0.5.0` and now I am experiencing some inconsistent logging behaviour when **training on SageMaker** (when running locally without SageMaker, I am not experiencin…
-
I am trying to model NPTS using Gluonts. Please guide me on how to get the probabilistic forecasting results using NPTSEstimator.
```python
'from gluonts.model.npts import NPTSEstimator
from gluo…