Skip to main content
Cross Validated

Return to Revisions

1 of 2
user avatar
user avatar

Could not find a shorter way, than this one

import numpy as np
from scipy.cluster.vq import vq

X = np.array([[ 2.,  4.,  2.],
              [ 1.,  3.,  1.],
              [ 3.,  4.,  2.],
              [ 2.,  3.,  2.],
              [ 1.,  5.,  5.]])

codebook = np.array([[ 1.  ,  3.  ,  1.  ],
                     [ 2.33,  3.67,  2.  ],
                     [ 1.  ,  5.  ,  5.  ]])

partition, euc_distance_to_centroids = vq(X, codebook)

TSS = np.sum((X-X.mean(0))**2)
SSW = np.sum(euc_distance_to_centroids**2)
SSB = TSS - SSW

# The 'direct' way
B = []
c = X.mean(0)
for i in range(partition.max()+1):
    ci = X[partition == i].mean(0)
    B.append(np.bincount(partition)[i]*np.sum((ci - c)**2))
SSB_ = np.sum(B)

print(TSS, SSW, SSB, SSB_)
user35349