I'm performing a PCA using the
It appears to work as it should. Acording to this question, I can get the eigenvalues like this:.
The eigenvalues represent the variance in the direction of the eigenvector. So you can get them through the pca.explained_variance_ attribute:
eigenvalues = pca.explained_variance_
If this is correct, the eigenvalues for my first few components seem to be way to high.
eigenvalues = pca.explained_variance_ eigenvalues # returns [1188.482427 760.26572144 581.29434167 325.56710676 267.10095401 219.49301802 155.1603308 107.8855256 76.17770897 64.09568959]
For every scree-plot I've seen and for example, when you google screeplot on google, the eigenvalues are usually much, much lower. Can eigenvalues be this high?