Interactive lab
Explore real K-Means clustering and PCA on generated 3D data.
Run each algorithm step by step.
K-Means starts with k-means++ centroids, assigns each point, and moves each centroid to its group's mean until stable. Labels are arbitrary, and results depend on K and starting centroids.
PCA finds the eigenvectors of the covariance matrix and projects data onto the most informative directions. It is linear, so some information is lost.
Interactive lab
Explore real K-Means clustering and PCA on generated 3D data.
Run each algorithm step by step.
K-Means starts with k-means++ centroids, assigns each point, and moves each centroid to its group's mean until stable. Labels are arbitrary, and results depend on K and starting centroids.
PCA finds the eigenvectors of the covariance matrix and projects data onto the most informative directions. It is linear, so some information is lost.
