Re: [Scikit-learn-general] Help with line in example

Thanks Gael. I guess I have some reading up to do. On Sun, Feb 16, 2014 at 9:54 AM, Gael Varoquaux < gael.varoqu...@normalesup.org> wrote: > On Sat, Feb 15, 2014 at 08:03:53PM -0500, Adam Hughes wrote: > > graph.data = np.exp(-graph.data / graph.data.std()) > > > Can someone offer an explanatio

Re: [Scikit-learn-general] Help with line in example

On Sat, Feb 15, 2014 at 08:03:53PM -0500, Adam Hughes wrote: > graph.data = np.exp(-graph.data / graph.data.std()) > Can someone offer an explanation of what this step is doing for a novice? This is the 'heat kernel', it turns a real-valued difference into a positive-only affinity, as spectral cl

[Scikit-learn-general] Help with line in example

Hello, I'm trying to follow the spectral clustering example and am not very skilled in machine learning. From reading about normalized cuts, I understand most of what is going on, but am confused particularly in this