aws / aws/sagemaker-python-sdk
How to change default values in constraints generated by baselines (`sagemaker.model_monitor.***.suggest_baseline()`)
- Dominant language
- Python
- Stars
- 2.3k
- Forks
- 1.3k
- Avg merge
- 2d 2h
- Merged PRs (30d)
- 32
Description
**What did you find confusing? Please describe.**
I have failed to find any documentation that let me change the default values in constraints.json that
[`sagemaker.model_monitor.DefaultModelMonitor.suggest_baseline()`](https://sagemaker.readthedocs.io/en/stable/api/inference/model_monitor.html?highlight=DefaultModelMonitor#sagemaker.model_monitor.model_monitoring.DefaultModelMonitor.suggest_baseline) saves to S3 after a processing job. one of the constraints that I would like to change are `domain_content_threshold` from `0.1` to `0.25`.
**Describe how documentation can be improved**
Provide documentation to change the default values of multiple constraints from [constraints.json file](https://docs.aws.amazon.com/sagemaker/latest/dg/model-monitor-byoc-constraints.html) in documentation for each of the `suggest_baseline` methods (I meant methods from `sagemaker.model_monitor.***`). And also let users use custom code(or a python function) for `comparison_method` in `distribution_constraints`. Having to bring custom container for one modification from sagemaker defaults is not optimal and time consuming for users to build. Moreover, sagemaker's model-analyzer images are not public anyway (or I haven't been able to pull pull them to local docker) for users to able to improve upon or change couple of things to suit their needs.
**Additional context**
Add any other context or screenshots about the documentation request here.
Contributor guide
Assessment
This issue has not been assessed yet.