Skip to content

A web app to predict crowd levels on BART using historical trip data and various other features. Built as an individual project at Insight Data Science. (Note that this is for archival purposes. I am no longer hosting the web app). This work was done as part of my Data Science Fellowship with Insight Data Science.

Notifications You must be signed in to change notification settings

bkhurley/beat_the_crowd

Repository files navigation

Beat the Crowd

Analysis/Modeling Workflow:

  1. get_clean_data.ipynb
  • fetch ridership data from BART
  • scrape weather data from Weather Underground
  • clean data
  • build database and insert data
  1. explore.ipynb
  • exploratory graphics
  1. model.ipynb
  • build, assess, and refine predictive models
  • linear regression, random forest

Web App Pipeline

  • run.py
  • flask_app
    • connects random forest model to front-end UI using the Flask/Bootstrap framework

About

A web app to predict crowd levels on BART using historical trip data and various other features. Built as an individual project at Insight Data Science. (Note that this is for archival purposes. I am no longer hosting the web app). This work was done as part of my Data Science Fellowship with Insight Data Science.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published