NYC Traffic Centrality

Project Overview

Built as part of an Object/IoT Technologies workshop, this project offers dynamic traffic analysis by leveraging modern mapping tools and the AGNES clustering algorithm to visualize traffic flows in New York City. Users can explore traffic data through interactive maps, filter by time slots, and uncover insights about central traffic patterns.

Features

• ✓Interactive map visualization — zoom and pan through traffic maps for detailed NYC traffic patterns
• ✓Advanced data filters — filter by year, month, day, and time slots to explore trends
• ✓Color-coded clusters — visual representation of congestion areas and smooth traffic zones
• ✓Clickable map markers revealing detailed traffic information and centrality scores
• ✓Responsive design with multi-language support for a global audience
• ✓AGNES hierarchical clustering for meaningful traffic pattern classification

Challenges

• •Processing and clustering large NYC traffic datasets efficiently
• •Rendering thousands of map markers without degrading UI performance
• •Designing meaningful cluster visualizations for non-technical users

Solution

Used Python with AGNES hierarchical clustering to pre-process traffic data into meaningful clusters. React + Leaflet renders color-coded markers, with filtering applied client-side for responsive interaction.

Architecture

Python script pre-processes NYC traffic dataset and outputs clustered JSON. React SPA consumes the JSON and renders it on an interactive Leaflet map with dynamic filtering by time and date.

Results & Impact

• ✓Interactive map handles thousands of data points smoothly
• ✓AGNES clustering surfaces non-obvious traffic centrality patterns
• ✓Multi-language support for a broader audience