Interactive Visualizations for Chicago ‘L’ Station Ridership

Jelena Hui Ling Neo

22 | Singapore | Computer Engineering


This project aims to help the Chicago Transit Authority visualize ‘L’ station metro ridership so that they can better plan resources, maintenance and train frequency based on ridership data. Charts are built using Plotly which allows the user to zoom, pan and save the chart. Plotly charts also have the feature of comparing data on hover. This project breaks down ridership data into three granular levels: year, month and day and station levels. Various charts were used such as custom calendar heat maps and box plots to help users extract the most information from the data at one glance. Calendar heat maps allow comparison of ridership across the year on station-level to see which station has more traffic during different months. Also, by sorting the mean number of rides for each station by day type (weekday, saturday, sunday/holiday), we can see the top 5 stations for each day type. This information can help Chicago Transit Authority redirect resources to the station that needs it more. Overall, this project provides the statistics and correlation of ridership data in the form of various charts which would be extremely useful when organised into a dashboard.


I am a final year student majoring in Computer Engineering at the National University of Singapore. I mainly focus on software engineering but started learning more about data science through a friend by joining his team for a datathon. My first machine learning/ data science project was for a dance wearble project where I worked on machine learning section to detect dance moves. I gained more interest in data science after that and am currently enrolled in a data science for IoT module right now.


Ridership Counts / Chicago Transit Authority ‘L’ Stations, Chicago, Illinois, United States / 2017