Adding self-adjusting label size to SpectralCluster in scikit-learn.

Which clustering method?

The sample dataset.

Spectral Clustering - how does it work?

Nearest 10 neighbour graph from the sample data.

How many clusters?

n_auto : bool, optional, default=False
If not False (or zero), an eigenvalue evaluation is undergone to
better fit/reduce the maximum number of clusters based on the
work in `A Tutorial on Spectral Clustering, 2007 Ulrike von
Luxburg
http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.165.9323`.

Code

Analysis and testing

Greatest Change

eigenvalues [-0.002 -0.002 -0.001 -0.001 -0.001 -0.001 -0.000 -0.000]

Eigenvalue Split

eigenvalues [-0.000 -0.000 -0.000 0.000 0.000] @ threshold 1e-3

All zeros

eigenvalues [-0.008 -0.008 -0.007 -0.006 -0.006 -0.005 -0.005 -0.003 -0.003 -0.002–0.002 -0.002 -0.002 -0.001 -0.001 -0.001 -0.000 -0.000 -0.000 0.000] @ threshold 1e-4

Overfitting

Conclusions

References

Research Software Engineer specialising in Data Visualisation with a touch of HPC. — PhD in Atmospheric Chemistry and Masters in Theoretical Physics.

Get the Medium app

A button that says 'Download on the App Store', and if clicked it will lead you to the iOS App store
A button that says 'Get it on, Google Play', and if clicked it will lead you to the Google Play store