Skip to main content

Creates the complete Tox21 dataset

Project description

This is a Tox21-like dataset created from the raw NIH assay data. The Tox21 dataset we know and love only includes 12 assays. This one includes 64 different assays!

Simply by using this dataset you can train machine learning models with metrics you never thought was possible.

Downloads NIH raw assay data and creates a clean CSV.GZ file ready for import into pandas:

tox21full ~/Downloads/tox21full.csv.gz

You can also create it as a parquet file (more efficent):

tox21full --format parquet ~/Downloads/tox21full.parquet

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

tox21full-0.1.0.tar.gz (5.7 kB view hashes)

Uploaded Source

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page