QuantGov is an effort to expand the frontiers of economic and legal research by providing an open-source framework to uncover latent data in legal text. The QuantGov Python package captures this spirit by providing researchers and data scientists with an easy-to-use Python implementation of text extraction. Specifically, the QuantGov library specializes in helping individuals with building a corpus (a body of text to be examined), training an estimator (a trained algorithm that pulls latent data from text), and implementing pre-packaged Natural Language analyses.

The following interactive documentation is intended to help individuals of all skill levels use the QuantGov library. This documentation is interactive in the sense that it will allow users to directly run Python code within the documentation and on their own computer. In addition, the documentation will link to a variety of external sources that will help expand on topics and provide auxiliary information. After working through this documentation, users will be equipped with the knowledge, code, and resources needed to install and use Python, install and use the QuantGov library, build their own corpus of documents, develop their own custom machine learning algorithms, use data visualizations to explore data, and more.

Get the Code#

All code for official QuantGov projects is hosted on the QuantGov GitHub page. QuantGov currently maintains four repositories:

For additional information about GitHub and a step by step guide for obtaining code on GitHub, see the below guides: