A Machine Learning Engineer is setting up Databricks Lakehouse Monitoring to issue alerts based on IoT sensors that monitor various water conditions at a high tech hydroponic farm.
Specifically:
- pH sensors
- Records acidity/alkalinity on a logarithmic scale from 0 to 14
- Pump status monitor
- Records the current status of the pump as "on", "off", "maintenance",
"fault", or "clean"
- Electrical Conductivity (EC) sensors
- Records nutrient level of the water as "very rich", "rich", "medium",
"poor", "very poor"
What are the appropriate drift metrics for each of the given sensor types?