3.5. Monitoring text data [CODE PRACTICE]

A code example walkthrough of unstructured data evaluations using the open-source Evidently Python library.

Video 5. Monitoring text data [CODE PRACTICE]arrow-up-right, by Emeli Dral

In this video, we walk you through the code example of evaluations for unstructured data using the open-source Evidentlyarrow-up-right Python library.

Want to go straight to code? Here is the example notebookarrow-up-right to follow along.

Links to docs:

Outline: 00:00arrow-up-right Import libraries and datasets 02:26arrow-up-right Prepare a multimodal dataset with raw text 08:15arrow-up-right Text data overview report 11:18arrow-up-right Model-based text data drift detection 13:49arrow-up-right Adding custom text descriptors to report 17:50arrow-up-right Custom report with descriptor drift detection 23:55arrow-up-right Embedding drift detection

That’s it! We covered three use cases for evaluating unstructured data – multimodal data with raw text, detecting drift in text data with descriptors, and embedding drift detection – and learned to derive actionable metrics.

Last updated