Open Source Projects

District Data Labs produces and maintains several open source data science projects. Check out our project portfolio below or on Github

Cultivar: Multidimensional data explorer and visualization tool.

Cultivar: Multidimensional data explorer and visualization tool.

Yellowbrick: Visual diagnostics for machine learning. Install via PyPi

Yellowbrick: Visual diagnostics for machine learning. Install via PyPi

Baleen: An automated ingestion service for blogs to construct a corpus for NLP research. Install via PyPI.

Baleen: An automated ingestion service for blogs to construct a corpus for NLP research. Install via PyPI.

Partisan Discourse: A web application that identifies party in political discourse and an example of operationalized machine learning. View on Github

Partisan Discourse: A web application that identifies party in political discourse and an example of operationalized machine learning.
View on Github

Tribe extracts a network from an email mbox and writes it to a graphml file for visualization and analysis. Install via PyPI.

Tribe extracts a network from an email mbox and writes it to a graphml file for visualization and analysis. Install via PyPI.

Minimum Entropy is a DDL hosted question/answer site for beginners who need answers to Data Science questions. View on Github

Minimum Entropy is a DDL hosted question/answer site for beginners who need answers to Data Science questions. View on Github

Interested in Contributing?

 

We are always looking for additional contributors to our open source projects. If there is a project in our portfolio that you'd like to contribute to, let us know!

 
 
Name *
Name
Project(s) You're Interested In *
 

Data Product Incubator

Our incubator program is a structured 3-month project development program where teams of people work on building a data product. Team sizes are small (3-4 people) and are carefully assembled to contain a mix of quantitative and technical skills; and mentors are provided to the teams to offer assistance. Data products are assigned to the teams at the beginning of the program and typically target a pressing public or private need.