Hello, Sorry, this is not about scikit-learn. It is my method which I once offered here, and was told that it is too easy to code. Since then I have been talking to other people and learn that linguists do not understand enough math to work it out, and even people who are good at math would prefer a ready script. I wrote one and would like to share. I did a numeric implementation of the Elbow method for calculating the optimal cluster number. I will appecuat it greatly if you show my work here and people would give me feedback on it. https://github.com/Mathemilda/Numeric_ElbowMethod_For_K-means Best, Mya -- Maiia Bakhova Mathematician in Data Science http://myabakhova.blogspot.com https://www.linkedin.com/in/myabakhova