Evidently OSS Quickstart
Run your first evaluation using Evidently open-source, for tabular data.
You can launch this hello-world example in Jupyter notebook, Colab or other Python environment.
Installation
MAC OS and Linux, Jupyter notebook
Install Evidently using the pip package manager:
Colab
Install Evidently:
Imports
Import the Evidently components and a toy “Iris” dataset:
Run a Test Suite
Split the data into two batches. Run a set of pre-built data quality Tests to compare them:
This will automatically generate tests on share of nulls, out-of-range values, etc. – with test conditions generated based on the first "reference" dataset.
Get a Report
Get a Data Drift Report to see if the data distributions shifted between two datasets:
Want to see more?
Take the complete Report & Test Suite Tutorial to learn how to run checks like this in detail (15 minutes). You can also evaluate ML model quality, e.g., for classification, regression, and ranking models, and work with text data.
Start with ML monitoring. Go through the Evidently Cloud Quickstart (2 min) to get a dashboard to track metrics over time.
Working with LLMs? See an LLM Evaluation Quicktart to see how to run checks for text data.
Last updated