Feature/drift monitor

[renjith-digicat]

Pull Request

Checklist

• Have you read Digital Catapult's Code of Conduct?
• I have performed a self-review of my own code.
• I have commented my code, particularly in hard-to-understand areas.
• I have made corresponding changes to the documentation.
• My changes generate no new warnings.
• I have added tests that prove my fix is effective or that my feature works.
• New and existing unit tests pass locally with my changes.

PR Type

Please delete options that are irrelevant.

• Feature
• Documentation Update

Linked tickets

https://digicatapult.atlassian.net/browse/BRID-19

High level description

This PR implements the drift detection on the data and model used for the bridgeai regression model

Detailed description

The steps are as follows;

• Fetch the data - historical data(on which the model was trained on) as well as new data (the data which will be used to test if there is any drift. The data versions are specified in the config file and the data is pulled from the versioned data kept in the dvc.
• Get the predictions on the both sets of data using the deployed model endpoint provided in the config file.
• Get a drift detection report using evidently, which compares the two sets of data and the models predictions on those two sets of data.
• Push the generated report, an html file to the specified s3 bucket.

Describe alternatives you've considered

Operational impact

Additional context

[dblane-digicatapult]

Good stuff, There are some separation of concerns that we should think about here.