Automatically assess data quality and explore your data. Lens can fix common data format errors, infer column types, and calculate and visualise correlations between features. You can explore the results through a web UI or directly in a Jupyter Notebook.
Never have to worry about data storage. With the elasticity of the cloud, SherlockML is capable of handling peta-byte datasets.
With data and code versioing, SherlockML allows the creation of a fully reproducible data processing pipeline.
Deploy models and code in a single click and never worry about scaling your application.
Publish and share beautiful reports directly from SherlockML without having to leave your workflow.
Ingest data from production databases such as PostgreSQL, SQL Server, or Redshift as well as processing data in real-time.