Skip to content

Release 0.8.22

Need Help?

The SuperCowPowers team is happy to give any assistance needed when setting up AWS and SageWorks. So please contact us at sageworks@supercowpowers.com or on chat us up on Discord

The SageWorks framework continues to flex to support different real world use cases when operating a set of production machine learning pipelines.

Note: These release notes cover the changes from 0.8.20 to 0.8.22

General

Mostly bug fixes and minor API changes.

API Changes

  • Removing target_column arg when creating FeatureSets

    When creating a FeatureSet via DataSource or Pandas Dataframe there was an optional argument for the target_column after some discussion we decided to remove this argument. In general FeatureSets are often used to create multiple models with different targets, so it doesn't make sense to specify a target at the FeatureSet level.

    Changed for both DataSource.to_features() and the PandasToFeatures() classes.

Minor Bug Fixes

Fixed: The SHAP computation was occasionally complaining about the additivity check so we flipped that flag to False

shap_vals = explainer.shap_values(X_pred, check_additivity=False)

Improvements

The optional requirements for [UI] now include matplotlib since it will probably be useful in the future.

Questions?

The SuperCowPowers team is happy to answer any questions you may have about AWS and SageWorks. Please contact us at sageworks@supercowpowers.com or on chat us up on Discord