Description
PyData London 2016
Join Peadar as he talks you through how to do good statistical analysis with Statsmodels, scikit-learn and PyMC3
We'll compare and debug models (logistic regression and more advanced versions) in three different statistics packages in Python.
Peadar will show you how Python can help you fake statistics without having to open up your graduate textbook :)
Statistical inference is a fundamental tool in science and engineering, but it is often poorly understood. This tutorial will take you from first principles through how to do good statistical analysis in Python.
Both frequentist and Bayesian versions will be included, and attendees will leave the talk with a good understanding of statistical inference, how to use Scikit-learn, Statsmodels and PyMC3.
This will be an entire case study comparing three different libraries for solving the same regression problem.
Attendees should bring a Laptop with Anaconda installed and the latest version of Scikitlearn, PyMC3 and Scikit-Learn.
Slides available here: http://slides.com/springcoil/deck-17#/
GitHub Repo: https://github.com/springcoil/PyDataLondonTutorial