Spectral clustering warning

7.6k views Asked by At

I want to know the meaning of this warning which occurs when i run spectral clustering code in Python.

I extracted the connected components and then again apply spectral method on each component, but still getting the same warning!

the warning is:

Calinski-Harabasz Score with gamma= 1 n_clusters= 12 score: 29.6079084919

Calinski-Harabasz Score with gamma= 1 n_clusters= 13 score: 28.0773430337

Calinski-Harabasz Score with gamma= 1 n_clusters= 14 score: 29.2831696856

Calinski-Harabasz Score with gamma= 1 n_clusters= 15 score: 28.8945479231

User Warning: Graph is not fully connected, spectral embedding may not work as expected. warnings.warn("Graph is not fully connected, spectral embedding"

1

There are 1 answers

2
Has QUIT--Anony-Mousse On

Fully connected means every node needs to have a distance to every other node.

Connected components finds subset such that every element is connected to every other with a path, but not necessarily directly.