Python for Data Analysis: Machine Learning Using Scikit-Learn

1. Overview

This 2-session workshop is a gentle introduction to the practical applications of machine learning, primarily using the Python package scikit-learn. The workshop is taught using JupyterLab in the Interactive Data Analytics Service (IDAS).

2. Prerequisites

Participants are expected to be familiar with Python and JupyterLab. Theoretical (mathematical) knowledge of machine learning concepts is not required but may be helpful.

3. Eligibility

This workshop is available to current University of Iowa faculty, staff, and students, who are employed by the University or enrolled in a class at the University at the time of the workshop. 

4. How to register

Click HERE then log in with your HawkID and password. Click “Register now” at the bottom of the page to register. After registering successfully, an automated email with a Zoom link will be sent to your University of Iowa email. Registration will close at 10 a.m. on Monday, April 15, 2024.

5. Additional information         

If you have any questions, please see the workshop FAQs or contact research-computing@uiowa.edu.

6. Workshop agenda

This workshop is taught in 2 sessions over 2 days. The later session builds on the previous one. Participants are encouraged to attend all sessions in order to learn the complete contents of the workshop.

This is not a theoretical (mathematical) introduction to machine learning, nor is it a comprehensive introduction to all machine learning algorithms. The workshop focuses on the practical aspects of using Python for machine learning, primarily with the package scikit-learn. If you are already familiar with the concepts below, please see the workshop FAQs for a list of additional, free learning resources.

Tentative topics to be covered:

Day 1

• Introduction and log in to the workshop computing environment
• Overview of categories of machine learning
• Introducing scikit-learn, a Python package commonly used for machine learning
• Training set and test set
• Supervised learning – Linear Regression
• Supervised learning – Gaussian Naive Bayes Classification

Day 2

• Log in to the workshop computing environment
• Supervised learning – Gaussian Naive Bayes Classification (continued)
• Supervised learning – Nearest Neighbors Classification
• Unsupervised learning – K-means Clustering
• Unsupervised learning – Spectral Clustering (when time permits)
• Resources for after the workshop