This project is an indivisual project.
The purpose of this project is to understand bike riders behaviour, station traffic and popular routes in order to help bike management and operation to improve bike sharing system efficiency and accessibility, so more and more people cycling indtead of driving, our city become greener.
- Inferential Statistics
- Data Visualization
- Python
- Pandas, jupyter
- Matplotlib and Seaborn
- Googlemaps with Google Distance Matrix API
- Tableau
In this project, I am going to analyze Oslo City Bike historical tripdata from 2019/01 to 2021/08. The primary goal is to understand riders behavior, usage of stations and existing rouotes by answering following questions:
- 😷 How have the riding changed since pandemic?
- 📅 When do they ride? at different granularity levels of date, such as year, season, month, day and hour.
- 🏞️ Where do riders go?
- 💼 Map out the "rush hour" of different stations
- 📈 What are the most popular cycling routes in Oslo?
- 🚴 How far do they go?
In addition, we want to find insights to encourage more people to ride bikes instead of driving cars. The idea could be to show people how efficient it is to ride a bike and how much carbon emission is saved if taking a bike instead of a car based on the historical data. So in this project, we will also look into:
- ⚡️ Compare the efficiency between cycling and driving?
- ♻️ How much CO2 emission has cycling saved?
- data exploration/descriptive statistics
- data processing/cleaning
- data visualization
- Interactive map viz.
- Clone this repo (for help see this tutorial).
- Raw Data is from Oslo City Bike website, code for data import can be found in the jupyter notebook.
- Routes data
route_dfwith distance/duration by driving from Google Distance Matrix API can be found in this repo also.
@ Hongxia Hou --Licensed under MIT License