course schedule

schedule, with links to slides and homeworks

The source code for these lectures is available at the github repository. Also please see the technical_notes for software and other troubleshooting tips.

Winter 2026

Week 1: Exploratory Data Analysis

Overview of the goals of the course: description, visualization, exploration, pattern discovery, and summarization. Introduction to different frameworks and goals, and relationship to preregistration and hypothesis testing. Types of data: tidy data, images, geospatial, words, time series.

• Reading: Chapter 2 (“Exploratory Data Analysis”) from Haig, The Philosophy of Quantitative Methods (see Canvas)
• Reading: Introduction from Tan, Steinbach, & Kumar, Introduction to Data Mining (see Canvas)
• Case study: the Youth Tobacco Survey
• Reading: NYTS report 2024
• Slides: Introduction (ipynb)
• Discussion: Exploratory Data Analysis
• Demo: Youth Tobacco Survey (ipynb)
• Assignment (due Monday 1/12): ipynb html
• Lab (for 1/9): ipynb html

Week 2: Visualization

Grammar of graphics. Overview of types of plot for uni- and multi-variate summarization, color pallettes, transformations. Output: bitmap, vector, and web-based interactive.

• Links: plotnine documentation
• Reading: A layered grammar of graphics, Wickham
• Slides: Graphics and visualization
• Demo: Grammar of Graphics
• Demo: Weather Data (completed version from class)
• Assignment (due Tuesday 1/20): ipynb html
• Lab (for 1/16): ipynb html

Week 3: Summarizing, smoothing, and outliers.

Split-apply-combine options. Types and goals of smoothers. Methods for outlier identification.

• Monday: no class (MLK day)
• Optional reading: The Split-Apply-Combine strategy for data analysis
• Slides: Split/apply/combine (completed version from class)
• Assignment (due Monday 1/26): ipynb html

Weeks 4-5: Dimension reduction.

What low-dimensional representations do and what they don’t. Overview of methods: similarity- and distance-based; examples: principal component analysis, t-SNE.

• Slides: PCA
• Slides: PCA and SVD
• Demo: penguin PCA (completed version from class)
• Assignment (due Monday 2/2): ipynb html
• Lab (for 1/30): ipynb html
• Slides: Generalizing: tSNE
• Slides: On ordination
• Assignment (due Monday 2/9): ipynb html
• Slides: Federalist papers (completed version from class)
• Lab (for 2/6): ipynb html (completed version from class)

Week 6: Working with words.

Bag of words, preprocessing, embeddings, latent Dirichlet allocation, other applications of dimension reduction. Finding n-grams, sentiment analysis.

• Slides: Working with text
• Assignment (due Monday 2/16): ipynb html
• Slides: Scraping, and plotting text
• Lab (for 2/13): ipynb html (semi-completed version from class)

Week 7: Case study.

Groundwater monitoring.

• Slides: Groundwater
• Assignment (due Monday 2/23): ipynb html

Week 8: Spatial data.

Spatial smoothing and prediction.

• Slides: Mapping
• Reference/reading: Geocomputation with Python
• Assignment (due Monday 3/2): ipynb html
• Slides: Mapping (edited notebook from class)
• Lab (for 2/27): ipynb html

Week 9: Working with images.

Formats; layers; types of image data. Normalization and pre-processing. Applications of dimension reduction.

• Slides: Landsat images (edited notebook from class)
• Assignment (due Monday 3/2): html

Week 10: More with images.

More with images; case study recap; student presentations.

• Slides: Galaxies
• Assignment (due Monday 3/9): html