You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Centroid Index is used to evaluate the clustering solution if the ground truth is available. CI=0 means that you have found the optimal partitioning with your clustering solution.
You need two arrays. The first one LABELS contains the partition labels generated by your clustering solution and the other array GT contains the ground truth.
LABELS = np.asarray([1, 2, 3, 1, 2, 3, 3, 4, 4, 4])
GT = np.asarray([1, 2, 3, 1, 4, 2, 2, 4, 3, 1])
Whereas the k=3 is the number of clusters.
CI = CentroidIndex(LABELS1,GT)
print("Centroid Index: "+str(CI))
CI=0 means that you have found optimal partitions, CI>0 shows the number of cluster having mismatch with the ground truth.
Please report it if you find any bug.
The text was updated successfully, but these errors were encountered:
Centroid Index is used to evaluate the clustering solution if the ground truth is available. CI=0 means that you have found the optimal partitioning with your clustering solution.
You need two arrays. The first one LABELS contains the partition labels generated by your clustering solution and the other array GT contains the ground truth.
LABELS = np.asarray([1, 2, 3, 1, 2, 3, 3, 4, 4, 4])
GT = np.asarray([1, 2, 3, 1, 4, 2, 2, 4, 3, 1])
Whereas the k=3 is the number of clusters.
CI = CentroidIndex(LABELS1,GT)
print("Centroid Index: "+str(CI))
CI=0 means that you have found optimal partitions, CI>0 shows the number of cluster having mismatch with the ground truth.
Please report it if you find any bug.
The text was updated successfully, but these errors were encountered: