New Yes Energy datatypes

Myst Platform Release (2022-05-19)

Hello Myst Platform users,

We made one adjustment to the improvement over silent graph failures we released last week. We also added two datatypes to the Yes Energy Connector.

Please update your myst-alpha package at your earliest convenience to ensure you have access to this update (instructions here).

⚡️Enhancements:

• Model fit jobs will continue to fail if your model is asked to train on only missing data. However, if a model is asked to predict only on missing data (e.g., if a weather forecast feature is missing), the run job will complete but with masked outputs. Masked outputs differ from nulls: the platform interprets masked data as temporarily missing and attempts to replace it if missing features, for example, become available in the future. Null data is interpreted as permanently missing and is not updated in subsequent run jobs. We made this change to ensure that time series that contain predictions can fall back on lower priority layers, if they are available.
• We added two datatypes to the Yes Energy Connector: wind_forecast_bidclose and bidclose_solar_forecast.

As always, please do not hesitate to reach out via the chat embedded in the Myst Platform or email us at [email protected] with questions or feedback.

Thank you!
Ellery and the Myst team