videos from PyCon 2014

Here (all of them).

Here are the stats-related ones:

Data intensive biology in the cloud: instrumenting ALL the things (Titus Brown)

Diving into Open Data with IPython Notebook & Pandas (Julia Evans)

Keynote (Fernando Pérez)

Know Thy Neighbor: Scikit and the K-Nearest Neighbor Algorithm (Portia Burton)

Bayesian statistics made simple (Allen Downey)

Beyond Defaults: Creating Polished Visualizations Using Matplotlib (Hannah Aizenman)

Data Wrangling for Kaggle Data Science Competitions – An etude (Krishna Sankar)

Enough Machine Learning to Make Hacker News Readable Again (Ned Jackson Lovely)

Hands-on with Pydata: how to build a minimal (Christian Fricke , Diego Maniloff , Zach Howard)

How to Get Started with Machine Learning (Melanie Warrick)

IPython in depth: high productivity interactive and parallel python (Fernando Perez)

Python for Social Scientists (Renee Chu)

Python + Geographic Data = BFFs (Mele Sax-Barnett)

Realtime predictive analytics using scikit-learn & RabbitMQ (Michael Becker)

Diving deeper into Machine Learning with Scikit-learn (Jake Vanderplas , Olivier Grisel)

Exploring Machine Learning with Scikit-learn (Jake Vanderplas , Olivier Grisel)

How to formulate a (science) problem and analyze it using Python code (Eric Ma)

And here are the webscraping/text_processing-related ones:

Character encoding and Unicode in Python (Esther Nam , Travis Fischer)

Introduction to Regular Expressions (Luke Sneeringer)

Introduction to Web (and data!) Scraping with Python (Katharine Jarmul)

Python Scraping Showdown: A performance and accuracy review (Katharine Jarmul)

Search 101: An Introduction to Information Retrieval (Christine Spang)

Mining Social Web APIs with IPython Notebook (Matthew Russell)

High Performance Scientific Computing - course starting today

Here.

will Julia become the new R?

Julia is turning two this month. It’s supposed to be as fast as C and as easy as Python. Here’s what people have been saying about it:

38-page Hacker News discussion of Julia’s pros and cons, comparisons to Python, R, Matlab/Octave, etc.

“Julia breaks down […] the wall between your high-level code and native assembly.”

“The Julia code takes around 8 milliseconds to complete, whereas the R code takes around 4000 milliseconds.”

Julia has powerful abstractions and good performance

If you are curious you can try Julia online before you install it.

Academic Torrents

Here. 1.6TB of data and counting.

programming for data analysis - two online courses starting today

Computing for Data Analysis (R-based) and Computational Methods for Data Analysis (Matlab-based, assumes stronger math background).