RDT is an open source Python library that's free to download and use under the MIT license.
If you'd like to use RDT for synthetic data, we recommend installing the sdv library. It will automatically download RDT, along with other libraries to support synthetic data generation and evaluation.

Colab Notebook

The fastest way to get started is through a Google Colab Notebook. Click the link below to view a pre-populated notebook with a sample dataset.
Create a copy of this notebook for your own use. You can upload your own data and run any of the code you see on this site.

Direct Download

You can also install the rdt package directly on your device.


  • The RDT has been developed and tested on Python 3.6, 3.7, 3.8 and 3.9.
  • We recommend using a virtual environment (such as virtualenv) to avoid conflicts with other software on your device

Download Instructions

These docs are for RDT version 1.2.0. If you are using a previous version, please update to see the new functionality.
We recommend downloading rdt using pip.
pip install rdt
This automatically downloads the most recent version from PyPi. You can also request a specific version.
pip install rdt==1.2.0
You can also download rdt using conda.
conda install -c conda-forge rdt
This automatically downloads the most recent version from conda. You can also request a specific version.
conda incstall -c conda-forge rdt=1.2.0


If you are having issues installing SDMetrics, please visit our GitHub. You can browse existing issues and raise a new one if you cannot find a solution.
You can also ask questions by joining the SDV Slack.