THE SPARKS FOUNDATION - DATA SCIENCE AND BUSINESS ANALYTICS INTERNSHIP
Task 2 - Prediction using Unsupervised ML
This task requires to predict the optimum number of clusters and represent it visually, from the ‘Iris’ dataset.
Name - Shreya Nair
K means works through the following iterative process:
- Pick a value for k the number of clusters to create.
- Initialize k (starting points) in your data
- Create your clusters. Assign each point to the nearest centroid.
- Make your clusters better. Move each centroid to the center of its cluster.
- Repeat steps 3–4 until your centroids converge.