This workshop will cover dimension reduction techniques for data analysis in Python, focusing on Principal Component Analysis (PCA), factor analysis, and canonical correlation analysis (CCA).  Depending on audience interest, dimension reduction regression (e.g. SIR), and kernel versions of the classical dimension reduction techniques can also be discussed.

The presentation will begin by covering the conceptual basis of these methods, then we will discuss several case studies.  The Statsmodels, Sklearn, Numpy, and Scipy Python libraries will be used to conduct the analyses.  Visualization of results using Matplotlib and Seaborn will also be covered.