Stress Testing with the RIME CLI

Let’s begin by stress testing a binary classification model using the RIME CLI! This example uses a modified version of the Adult Census Income Dataset from Kaggle that we’ve included in the rime_trial/ bundle provided during installation.

Before beginning, make sure that you’ve installed the RIME Python package. Installation instructions below:

• RIME Cloud

• RIME Enterprise (Local)

Be sure to run this example from the rime_trial/ directory so that local paths to datasets resolve correctly!

rime-engine run-stress-tests --config-path examples/income/stress_tests_model.json

NOTE: If you see "Missing option" errors, make sure you set up your environment variables (see Troubleshooting).

This command will run a batch of stress tests designed to detect vulnerabilities in your ML pipeline. The results will be uploaded to the “Default Project”, which comes pre-seeded in your environment.

Once the command completes, you should be able to see the test run in the Default Project (see table below for URL).

From there, you can open the test run “Income (With Model)” and start exploring the results!

You can continue the rest of this example in Running Stress Testing on the Income Example.