Introduction to Python

Instructor(s):

  • John Poe, University of Kentucky

Python has become one of the most popular languages for statistics and machine learning on the planet. Python’s flexibility to handle virtually any kind of data combined with the truly astounding range of analytical techniques that it offers means that it provides enormous value to academics. Despite this fact, it is rarely if ever taught to people in the social and behavioral sciences or public policy. Most courses and textbooks that do teach Python at an introductory level are designed by people with computer science backgrounds who tend to hide the value Python provides for the social sciences.

In this 3-day intermediate workshop, we will highlight some of the more astoundingly impressive and useful tools that Python offers that are of particular use to social scientists. Note that this is not the standard list of libraries that one would learn in an introductory workshop on Python. It is designed explicitly for the typical ICPSR audience and so ignores most of the computer science-oriented libraries. This workshop cannot make you an expert in Python. It can and will give you a sense of some of the tools Python makes available and how to learn more about them.

Day 1 offers a basic introduction to Python 3 and the Anaconda distribution with a focus on pandas, NumPy, and data management. Day 2 provides an overview of the incredibly powerful scikit-learn library for a range of analysis from linear regression to classification to dimensionality reduction. Day 3 introduces web scraping and text analysis features available in Python and ways to use things like R packages and other programs through Python.

Fees: Consult the fee structure.

Tags: Python, computing

Course Sections

Section 1

Location: ICPSR -- Ann Arbor, MI

Date(s): August 12 - August 14

Time: 5:30 PM - 7:00 PM

Instructor(s):

  • John Poe, University of Kentucky