How does sklearn.cluster.KMeans handle an init ndarray parameter with missing centroids (available centroids less than n_clusters)?

问题

In Python sklearn KMeans (see documentation), I was wondering what happens internally when passing an ndarray of shape (n, n_features) to the init parameter, When n<n_clusters

1. Does it drop the given centroids and just starts a kmeans++ initialization which is the default choice for the init parameter ? (PDF paper kmeans++) (How does Kmeans++ work)
2. Does it consider the given centroids and fill accordingly the remaining centroids using kmeans++ ?
3. Does it consider the given centroids and fill the remaining centroids using random values ?

I didn't expect that this method returns no warning in this case. That's why I need to know how it manages this.

回答1:

If you give it a mismatching init it will adjust the number of clusters, as you can see from the source. This is not documented and I would consider it a bug. I'll propose to fix it.

来源：https://stackoverflow.com/questions/30169378/how-does-sklearn-cluster-kmeans-handle-an-init-ndarray-parameter-with-missing-ce