Random Forests and PyData – A Tutorial

I wanted to extend a (belated) thanks to @datakyle for inviting me to speak at the inagural Python Data Science Meetup graciously hosted by newhaven.io and Prometheus Research in New Haven on September 26th. I was delighted to have the opportunity to quickly dive into the PyData / Pandas /iPython data science stack. There is nothing like challenging oneself to present on a topic that you want to understand more deeply – on a short deadline. I was hoping to do some”learning-by-teaching” so I gave a short presentation and iPython notebook demo of the Random Forests approach for supervised classification. Thanks to newhaven.io, I gained a deeper understanding of how the random forest algorithm works, a keen interest in PyData, Pandas, scikit-learn.

Please take a look at the presentation and iPython notebook and let me know what you think:

Slides (pdf): http://bit.ly/1d1C3wK

iPython notebook demo: http://bit.ly/1d1C3wK