Étienne Marcotte

Thanks for your interest in TACTiS. Sadly, its current architecture doesn't allow for variable length predictions in the decoder. I don't think reasonable tweaks could allow you to get around...

Hi, We sadly do not have an example where we add covariates to the data when doing the forecasting. We haven't tested that functionality, although theoretically the model should be...

It would indeed be a possible method to implement covariates. However, it would require some refactoring, since you would have to make sure that the mask for these covariates is...

The dataset in Hugging Face format, converted to JSON is available here: https://github.com/ServiceNow/context-is-key-forecasting/blob/main/results/all_tasks.json We still plan still plan to have it available on Hugging Face directly, but there are a...

Here is the link to the HuggingFace version of the dataset: https://huggingface.co/datasets/ServiceNow/context-is-key The dataset contains the same information as the JSON (the JSON was created from it).

> Ok thanks! Feel free to link it in the README of this Github repo Good point, I add it to the header.

The `aggregate_success` method is imported and used in the notebook, but is not defined where it is being imported from: ```ImportError: cannot import name 'aggregate_success' from 'agentlab.analyze.covariate_std_err'```

Hi rozhix, could you tell me a little more about what your input and label represent in your example? TACTiS has been designed for mostly multivariate timeseries forecasting problems, where...

Sadly, this kind of problem wouldn't work with TACTiS. TACTiS assumes that both your input (the discharging process in your case) and the output (the battery capacity) comes from the...

Hello Benny, Thanks for your interest in our benchmark dataset. We are planning on releasing a compiled version of the dataset (which won't require executing the code from this repo)...