We can define similarity between two clusters using MIN, MAX, group average, distance between centroids, other methods driven by an objective function like ward’s method that uses squared error. This Project showcase variants of k-means which uses an alternative distance measure . Also different K-Mean algorithms are also show cased various distribution of dataset to compare their outcomes
Algorithms to use:
i) kmeans Elkan
ii) kmeans Lloyd
iii) kmeans Manhatten
iv) MiniBatch KMeans
v) Affinity Propagation
vi) Spectral Clustering
vii) Agglomerative Clustering
viii) DBSCAN
ix) OPTICS
x) BIRCH
xi) Gaussian Mixture
Distance Measurement techniques to use:
i) euclidean
ii) squared euclidean
iii) manhattan
iv) chebyshev
v) canberra
vi) chi-square