A step-by step tutorial for a kernel density estimation via the Parzen-window technique in Python and how to use it to classify patterns

This is not directly a question, but I went through some pain recently writing Python code to implement the Parzen-window technique for kernel density estimation using a hypercube. I wrote it up in a tutorial format and wanted to share it for those who find it useful.

Also, I am comparing it to the scipy.stats kde library class, which uses a Gaussian kernel and show how to use the estimated parameters for classifying some random 3-class 2-dimensional sample data via a Bayes' classifier.

I hope you find it useful and I am looking very much forward to your suggestions! And please let me know what you think!

Here is the link to the IPython notebook