A code example walkthrough of creating a live ML monitoring dashboard for online architecture using Evidently.
Last updated
Video 3. ML model monitoring dashboard with Evidently. Online architecture [CODE PRACTICE], by Emeli Dral
In this video, we create a live ML monitoring dashboard for an ML model deployed as a service. We imitate sending the live data directly from the machine learning service to the ML monitoring service and update the dashboard in near real-time.
Want to go straight to code? Here is the code example to follow along.
Outline: 00:00 Introduction 00:30 Script overview and imports 01:59 Define Collector, Workspace, and Project variables 03:31 Load data and create mini-batches to simulate production usage 04:39 Implement the function to generate Test Suites 06:38 Create the Workspace, Project and add Dashboard panels 09:25 Set up and configure the Collector service 13:00 Simulate sending data to the Collector 15:48 Implement the main function, run and debug the script 18:32 Run the Collector and view the online Dashboard updates 20:46 Recap and next steps
