I created a command line utility that allows the user to view a tagcloud of the terms used in the EDGAR documents for the annual reports. This utility creates a visualization that shows the most common terms, ignoring outliers with the color darkness relating directly to the relationship that term has to the argument. For example, if 'manufacturing' is the argument, the terms most related to manufacturing will be the brightest while the terms less important will be faded out.

Built With

  • cortical.io
  • edgar-dataset
  • finra
  • python
Share this project:
×

Updates