Skip to content

On-premise users: click in-app to access the full platform documentation for your version of DataRobot.

DataRobot Model Metrics

The datarobot-model-metrics (DMM) library provides the tools necessary to compute model metrics over time and produce aggregated metrics. It provides a framework to perform the following operations:

Topic Description
Configure an environment for DMM Configure an environment to develop custom metrics with the DataRobot Model Metrics library.
Configure data sources Connect to DataRobot to fetch selected data from the DataRobot platform.
Define custom metrics Define custom metrics using the provided default classes.
Calculate metric values Calculate custom metric values over time, by batch, or without data aggregation.
Use the DR Custom Metrics module Facilitate synchronization with existing metrics in DataRobot.
Notebook: Create a hosted custom metric from a template with code Follow a tutorial to create a hosted custom metric using the Python SDK.

Installation

The DMM library is published to PyPI. To install it, run the following command:

pip install datarobot-model-metrics

Updated March 19, 2025