You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Using a variety of machine learning methods, we predict the individual daily demand on routes within the Capital Bikeshare network. Featured models include deep neural net classifier, random forest regressor, ridge regression, & gradient tree boosted regression. Originally submitted on 6/7/2020 as a class project for UC Davis' STA 208.
This is a data analysis project from Dicoding to pass the Learning Data Analysis with Python class. This project aims to analyse and create a simple dashboard based on data from Capital Bikeshare.
Prediction of bike rental count hourly or daily based on the environmental and seasonal settings using data set from two-years historical log corresponding to years 2011 and 2012 from Capital Bikeshare system, Washington D.C., USA
Predict near-term Capital Bikeshare availability using a random forest and Poisson regression. Display current status and predictions with leaflet.js map visualization.