We define production monitoring metrics and calculate Evidently results. We store them in PostgreSQL, then expose them through Grafana dashboards and debugging reports.

Separate service health, model performance, data quality, and drift indicators.

Create the Python and Docker Compose environment for metric calculation, PostgreSQL, Adminer, and Grafana.

Train a baseline model and save the reference dataset used for later comparisons.

Compare reference and current batches, then persist selected metrics for time-series monitoring.

Create a workspace for reports and model/data behavior.

Test the database and dashboard path with repeatable synthetic values before adding model metrics.

Add data-quality checks, schedule metric calculations, and choose thresholds with model owners.

Provision a saved Grafana dashboard from versioned JSON and configuration files.

Use Evidently reports and test suites to investigate a monitoring metric.

Run the local end-to-end monitoring stack with Docker Compose, PostgreSQL, and Grafana.

More information is available in the Module 5 homework.

The current requirements set Evidently to 0.6.7. Compare this code with the Evidently 0.7 example when updating the API.

• Monitoring services
• Metric calculation
• Dummy metric calculation
• Baseline model notebook
• Debugging notebook

Share community notes and resources below.

• Week 5 notes by M. Ayoub C.
• Week 5 monitoring notes by Ayoub B.
• Week 5 notes from 2023
• Why monitor models after deployment? by Hongfan
• Week 5 detailed notes by Muhammad Shifa
• Send a PR, add your notes above this line