Skip to content

This repository contains the sample code to benchmark popular time series forecast algorithms using Gluonts in AWS Sagemaker Notebook Instance.

License

Notifications You must be signed in to change notification settings

pinak-p/amazon-sagemaker-forecast-algorithms-benchmark-using-gluonts

 
 

Repository files navigation

amazon-sagemaker-forecast-algorithms-benchmark-using-gluonts

Sample Code for use of the Gluonts Python library in AWS Sagemaker Notebook Instance to benchmark popular time series forecast Algorithms, including

amazon-sagemaker-forecast-algorithms-benchmark-using-gluonts.ipynb gives an example on how to compare forecast algorithms on a dataset by only using the Gluonts library.

  • The Jupyter notebook should be run in a AWS Sagemker Notebook Instance (ml.m5.4xlarge is recommended)
  • Pls use the conda_python3 kernel.

The example charts below visualize the comparison of different algorithms on prediction the same time series.

mean naive seasonal arima prophet deepar

License

This library is licensed under the MIT-0 License. See the LICENSE file.

About

This repository contains the sample code to benchmark popular time series forecast algorithms using Gluonts in AWS Sagemaker Notebook Instance.

Resources

License

Code of conduct

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • Jupyter Notebook 100.0%