Sample Notebooks

Amazon SageMaker Clarify provides the following sample notebooks for post-training bias detection and model explainability:

• Fairness and Explainability with SageMaker Clarify – Use SageMaker Clarify to create a processing job for detecting bias and explaining model predictions with feature attributions. You can also see an example notebook to read a dataset in JSON Lines format.

• Additional example notebooks using SageMaker Clarify include the following

  • Bringing your own container

  • Running processing jobs with Spark

  • Partial dependence plots (PDPs)

  • Natural language processing (NLP) explainability with text sentiment analysis

  • Computer vision (CV) explainability with image classification and object detection

These notebooks have been verified to run in Amazon SageMaker Studio. If you need instructions on how to open a notebook in Studio, see Create or Open an Amazon SageMaker Studio Notebook. If you're prompted to choose a kernel, choose Python 3 (Data Science).