background preloader

A Programmer's Guide to Data Mining

A Programmer's Guide to Data Mining
Related:  NewEd

Academic Ranking of World Universities | ARWU | First World University Ranking | Shanghai Ranking The R Project for Statistical Computing java - Monotonic Pair - Codility How to Think Like a Computer Scientist Learning with Python by Allen Downey, Jeff Elkner and Chris Meyers. This book is now available for sale at How to Think... is an introduction to programming using Python, one of the best languages for beginners. How to Think... is a Free Book available under the GNU Free Documentation License. Please send suggestions, corrections and comments about the book to feedback{at}thinkpython{dot}com. Download The book is available in a variety of electronic formats: Precompiled copies of the book are available in PDF and Postscript . Translations Here are some translations of the book into other (natural) languages: Spanish translation by Gregorio Inda. Other Free Books by Allen Downey are available from Green Tea Press. If you are using this book and would like to make a contribution to support my work, please consider making a donation toward my web hosting bill by clicking on the icon below.

the museum of science, art and human perception Orange Data Mining Walking The Beat - Mining Seattle's Police Report Data This week marks the completion of Y Combinator for Bayes Impact! As our Fall 2014 Fellowship ramps up (250+ applicants!), we wanted to do a blog post illustrating how exactly we can use data to understand public services better. Tip 1: before analyzing the data we should understand when the events happened, and if the system that records the data, also known as the data generating mechanism, is biased to a particular period of time. Our natural intuition may want to ask does criminal activity vary according to the day of the week? First we will just check how many Mondays, Tuesdays, etc have data recorded in the dataset: Great! There are lots of different types of crimes here, some that are very similar to each other and some that are very different. Tip 2: We can simplify large categorical variables by binning them into a few major categories We solve this problem by defining a simpler category for crime type which can be "minor", "serious" or "violent".

A Course in Machine Learning What’s the “problem” with MOOCs? « EdTechDev In case the quotes didn’t clue you in, this post doesn’t argue against massive open online courses (MOOCs) such as the ones offered by Udacity, Coursera, and edX. I think they are very worthy ventures and will serve to progress our system of higher education. I do however agree with some criticisms of these courses, and that there is room for much more progress. I propose an alternative model for such massive open online learning experiences, or MOOLEs, that focuses on solving “problems,” but first, here’s a sampling of some of the criticisms of MOOCs. Criticisms of MOOCs Khan Academy The organization is unclear and it lacks sufficient learner support.The videos aren’t informed by research and theory on how people learn, and this may diminish the effectiveness of his videos. Are MOOCs a Horseless Carriage? In the book How People Learn (which can be read free online), John Bransford shared the story of Fish is Fish. MOOC or MMORPG? From MOOC to MOOLE Who’s the teacher in a MOOLE?