Examples

Sample notebooks and tutorials

Quick start

This is the best place to start.

Title	Guide
Evaluation Tutorial: Tabular Data	Tutorial
Evaluation Tutorial: LLMs	Tutorial
Set up Cloud ML monitoring Dashboard	Tutorial
Self-host ML monitoring Dashboard	Tutorial

Sample notebooks

Simple examples show different Metrics, Tests and Presets. Head to Colab examples to see the pre-rendered visuals.

Title	Code example	Contents
Evidently Test Presets	Jupyter notebook Colab	Pre-built Test Suites on tabular data: Data Drift Data Stability Data Quality NoTargetPerformance Regression Classification (Multi-class, binary, binary top-K)
Evidently Tests	Jupyter notebook Colab	All individual Tests (50+) that one can use to create a custom Test Suite. Tabular data examples. How to set test conditions and parameters.
Evidently Metric Presets	Jupyter notebook Colab	All pre-built Reports: Data Drift Target Drift Data Quality Regression Classification
Evidently Metrics	Jupyter notebook Colab	All individual metrics (30+) that one can use to create a custom Report. How to set simple metric parameters.
Evidently LLM Metrics	Jupyter notebook	Evaluations for Text Data and LLMs

For more examples showing specific features, including text data support, head to the "How to" examples.

How-to guides

Tutorials

To better understand the Evidently use cases, refer to the detailed tutorials accompanied by the blog posts.

Title	Code example	Blog post
Understand ML model decay in production (regression example)	Jupyter notebook	How to break a model in 20 days. A tutorial on production model analytics.
Compare two ML models before deployment (classification example)	Jupyter notebook	What Is Your Model Hiding? A Tutorial on Evaluating ML Models.
Evaluate and visualize historical data drift	Jupyter notebook	How to detect, evaluate and visualize historical drifts in the data.
Monitor NLP models in production	Colab	Monitoring NLP models in production: a tutorial on detecting drift in text data
Create ML model cards	Jupyter notebook	A simple way to create ML Model Cards in Python
Use descriptors to monitor text data	Jupyter notebook	Monitoring unstructured data for LLM and NLP with text descriptors

You can find more examples in the Community Examples repository.

Integrations

To see how to integrate Evidently in your prediction pipelines and use it with other tools, refer to the integrations.

Evidently integrations