Skip to content
Clustering geolocation data using Amazon SageMaker and the k-means algorithm
Jupyter Notebook
Branch: master
Clone or download
Fetching latest commit…
Cannot retrieve the latest commit at this time.
Permalink
Type Name Latest commit message Commit time
Failed to load latest commit information.
Hong_Kong_18_Districts
images
.gitignore
LICENSE
README.md
Traffic_Camera_Locations_En.csv
traffic-cameras-k-means.ipynb

README.md

Clustering locations of traffic cameras in Hong Kong using Amazon SageMaker and the k-means algorithm

This project contains a Jupyter notebook, together with the relevant geospatial data, that demonstrates how to use Amazon SageMaker and the k-means alogrithm to determine clusters for the locations of traffic cameras in Hong Kong.

Below is an example visualisation for k = 15, with red dots representing traffic camera locations, and blue triangles representing cluster centroids.

Traffic camera locations and cluster centroids in Hong Kong

For instructions on how to run this using a SageMaker Notebook, see here. Note that you will need to ensure that the notebook instance is using a role that has permission to write to the S3 bucket specified using the bucket_name variable.

You can’t perform that action at this time.