Flow Forecast Release 0.956

We are excited to announce that today we are releasing Flow Forecast version 0.95 (if you are unfamiliar with Flow Forecast please see the introductory article). Although we are still somewhat far away from version 1.0 there are a lot of cool new features now available. To get the latest version please run pip install flood_forecast --upgrade.

Improvements

  • Fixes a bug related to Weights and Biases dependency issue.

  • Allows not including dataset_params in inference_params . This should save a lot time spent moving between the configuration file and copying parts.

  • Removes need to have datetime column in your CSV file. Just specify a sort_column in your parameters.

  • Informer model (SOTA model from AAAI added)

Next release (0.957)

  • Informer support for SHAP

  • Support for specifying a series_id in order to train model with several different series at once.

  • Additional support for multitask learning with SHAP.

 

Flow Forecast will be hosting a May Sprint. If you have free-time and would like to contribute please consider joining the sprint. We have a lot of issues to resolve and new features to add so we can use all the help we can get! Sign up here