Setting stopping criteria into H2O K-means

Sometime you may be looking for k-means stopping criteria, based off of “Number of Reassigned Observations Within Cluster”. H2O K-means implementation has following 2 stopping criteria in k-means: Outer loop for estimate_k – stop when relative reduction of sum-of-within-centroid-sum-of-squares is small enough lloyds iteration – stops when relative fraction of reassigned points is small enough In […]

Continue reading