In this workshop we will cover the most common CTA task: supervised classification. Using the Python library scikit-learn, we will implement Logistic Regression and Random Forest methods to perform sentiment analysis. Optional: introduction to word vector representations with Word2Vec.

Prior knowledge: Basic familiarity with Python is required if you wish to follow along with the tutorial. Completion of D-Lab's Python FUN!damentals workshop series will be sufficient.

This hands-on workshop presents a broad overview of the existing methods to use text as data, with a focus on applications in social sciences and humanities. After a brief theoretical discussion, we will go through the common “preprocessing recipe” that is used as the foundation for a variety of other applications as well as some basic natural language processing techniques.  These include: a) tokenization b) removal of stopwords, numbers, punctuation, c) calculation of word frequencies / proportions, d) part of speech tagging.  

For this workshop, we'll provide an introduction to visualization with Python. We'll cover visualization theory and plotting with Matplotlib and Seaborn, working through examples in a Jupyter (formerly IPython) notebook. The following plot types will be covered:

• line
• bar
• scatter
• boxplot

We'll also learn about styles and customizing plots.

Throughout the workshop, we'll discuss the plot types best suited for particular kinds of data.

This four-part, interactive workshop series is your complete introduction to programming Python for people with little or no previous programming experience. By the end of the series, you will be able to apply your knowledge of basic principles of programming and data manipulation to a real-world social science application.

Part 4 Topics: We will applying the skills learned during previous sessions to a real world social science example.