This app provides real-time predictions of the number of bikes that will be available at the stations of Washington DC’s docked bike share, Capital Bikeshare. Creating and visualizing those predicitons takes advantage of many different types of R content and the ability to deploy them on RStudio Connect.
Background Like many metropolitan areas, the Washington DC area has bicycles available for short-term rental to commuters and tourists at docks around the city. The number of bikes at each of these docks ebbs and flows throughout the day, and the Capital Bikeshare program provides real-time data on the number of bikes available at each dock via an API.
Goal The goal of this app is to provide a prediction of the number of bikes at a station in the near future based on real-time streaming data from an API. These predictions will be made available in a web application and to other services via an API. Furthermore, continuous monitoring of the predictions will be enabled to watch for model drift and changes in goodness-of-fit over time.
The source code and more detail on this project can be found on the Github Repository.
Here are links to all the content in the project
|Content||Content Description||Code||Pin||Refresh Frequency|
|Raw Data Ingest Script||Writes data from API calls into
||Code||NA||Every 20 Minutes|
|Clean Data Script||Cleans
||Code||NA||Daily (4 am)|
|Clean Station Metadata Script||Ingests station metadata and saves to a pin (names, lat/long).||Code||bike_station_info||Weekly (Sundays)|
|Data Split Script||Creates a training/test split for the data for models to use, saves to a pin.||Code||bike_model_params||Daily (5 am)|
|R XGB Model Train||Retrains model based on training/test split indicated by Data Split Script, writes into pin.||Code||bike_rxgb||Daily (6 am)|
|Model Metrics Script||Writes
||Code||bike_err_dat||Daily (8 am)|
|Model Performance App||Displays model performance metrics.||Code||NA||NA|
|Model API||Serves model predictions via Plumber API.||Code||NA||NA|
|Bike Prediction App||Displays predictions from App.||Code||NA||NA|
|Dev Bike Prediction App||Dev version of Bike Prediction App||Code||NA||NA|
|bikeHelpR Package||An R package of helper functions, built in internal repo on demo.rstudiopm.com.||Code||NA||Tags|