Probabilistic Time Series Forecasting with ๐Ÿค— Transformers

๐Ÿ“ฐ Hugging Face Blog

Use Transformers for probabilistic time series forecasting with Hugging Face's library

intermediate Published 1 Dec 2022
Action Steps
  1. Set up environment with required libraries
  2. Load and preprocess time series dataset
  3. Define and train a Time Series Transformer model
  4. Evaluate model performance using metrics such as mean absolute error and mean squared error
Who Needs to Know This

Data scientists and machine learning engineers can benefit from this approach to improve forecasting accuracy and uncertainty estimation in time series data

Key Insight

๐Ÿ’ก Transformers can be used for probabilistic time series forecasting, allowing for uncertainty estimation and improved accuracy

Share This
๐Ÿ“ˆ Use Transformers for probabilistic time series forecasting! ๐Ÿค–

Key Takeaways

Use Transformers for probabilistic time series forecasting with Hugging Face's library

Full Article

Published Time: 2022-12-01T00:00:00.154Z

# Probabilistic Time Series Forecasting with ๐Ÿค— Transformers

[![Image 1: Hugging Face's logo](https://huggingface.co/front/assets/huggingface_logo-noborder.svg)Hugging Face](https://huggingface.co/)

* [Models](https://huggingface.co/models)
* [Datasets](https://huggingface.co/datasets)
* [Spaces](https://huggingface.co/spaces)
* [Buckets new](https://huggingface.co/storage)
* [Docs](https://huggingface.co/docs)
* [Enterprise](https://huggingface.co/enterprise)
* [Pricing](https://huggingface.co/pricing)
*
*
* * *

* [Log In](https://huggingface.co/login)
* [Sign Up](https://huggingface.co/join)

[Back to Articles](https://huggingface.co/blog)

# [](https://huggingface.co/blog/time-series-transformers#probabilistic-time-series-forecasting-with-%F0%9F%A4%97-transformers) Probabilistic Time Series Forecasting with ๐Ÿค— Transformers

Published December 1, 2022

[Update on GitHub](https://github.com/huggingface/blog/blob/main/time-series-transformers.md)

[- [x] Upvote 43](https://huggingface.co/login?next=%2Fblog%2Ftime-series-transformers)
* [![Image 2](https://cdn-avatars.huggingface.co/v1/production/uploads/1617264212503-603d25b75f9d390ab190b777.jpeg)](https://huggingface.co/pcuenq "pcuenq")
* [![Image 3](https://cdn-avatars.huggingface.co/v1/production/uploads/620c70639e55c0fe782f7fc6/nokz7guK4l6b_woDl-XTM.jpeg)](https://huggingface.co/baiyinnamula "baiyinnamula")
* [![Image 4](https://huggingface.co/avatars/636fc0dc08d90474bf42ae1549dec252.svg)](https://huggingface.co/ridvan9 "ridvan9")
* [![Image 5](https://huggingface.co/avatars/9ceeeec72a1399a808ceaee1faea55e9.svg)](https://huggingface.co/arjoca "arjoca")
* [![Image 6](https://huggingface.co/avatars/8ab8f3e99ee3d96338ad9ea4d01bb8a1.svg)](https://huggingface.co/samjat2012cl "samjat2012cl")
* [![Image 7](https://cdn-avatars.huggingface.co/v1/production/uploads/6378821cdbe83216de43e4b6/YvJF2fPfGdF0Tu9fW7dg5.png)](https://huggingface.co/Ansh007 "Ansh007")
* +37

[![Image 8: Niels Rogge's avatar](https://cdn-avatars.huggingface.co/v1/production/uploads/1608042047613-5f1158120c833276f61f1a84.jpeg)](https://huggingface.co/nielsr)

[Niels Rogge nielsr Follow](https://huggingface.co/nielsr)

[![Image 9: Kashif Rasul's avatar](https://cdn-avatars.huggingface.co/v1/production/uploads/1669189789447-629f3b18ee05727ce328ccbe.jpeg)](https://huggingface.co/kashif)

[Kashif Rasul kashif Follow](https://huggingface.co/kashif)

[![Image 10: Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/huggingface/notebooks/blob/main/examples/time-series-transformers.ipynb)
## * [Introduction](https://huggingface.co/blog/time-series-transformers#introduction "Introduction")

* [Probabilistic Forecasting](https://huggingface.co/blog/time-series-transformers#probabilistic-forecasting "Probabilistic Forecasting")

* [The Time Series Transformer](https://huggingface.co/blog/time-series-transformers#the-time-series-transformer "The Time Series Transformer")

* [Set-up Environment](https://huggingface.co/blog/time-series-transformers#set-up-environment "Set-up Environment")

* [Load Dataset](https://huggingface.co/blog/time-series-transformers#load-dataset "Load Dataset")

* [Update `start` to `pd.Period`](https://huggingface.co/blog/time-series-transformers#update-start-to-pdperiod "Update <code>start</code> to <code>pd.Period</code>")

* [Define the Model](https://huggingface.co/blog/time-series-transformers#define-the-model "Define the Model")

* [Define Transformations](https://huggingface.co/blog/time-series-transformers#define-transformations "Define Transformations")

* [Define `InstanceSplitter`](https://huggingface.co/blog/time-series-transformers#define-instancesplitter "Define <code>InstanceSplitter</code>")

* [Create DataLoaders](https://huggingface.co/blog/time-series-transformers#create-dataloaders "Create DataLoaders")

* [Forwar
Read full article โ†’ โ† Back to Reads