Clustering refresher

less than 1 minute read

Below is a sample notebook on my kaggle dashboard which showcases how clustering was implemented to group the states in the US using different crime numbers.

Various aspects of the notebook:

  1. Data normalization
  2. Fit K-means model
  3. Get scree plot and decide on the number of clusters
  4. Fit final K-means model and get clusters
  5. Write clusters column along with others into a CSV
  6. Visualize clusters for different crimes on a scatter plot and among states on tableau

https://www.kaggle.com/akshayreddykotha/us-crime-rate-k-means-clustering

Leave a comment