R for data science
Undergraduate · Data science
Syllabus focus
Topics typically covered
Standard syllabus
R and tidyverse core
- RStudio/Posit workflow: scripts, projects, and packages
- Vectors, lists, factors, and data frames / tibbles
- dplyr verbs: filter, select, mutate, arrange, summarize, group_by
- Joins and relational data with dplyr
- tidyr pivots and nesting (intro)
- Importing CSV and reading from databases (DBI intro)
Visualization and reporting
- ggplot2 layers, aesthetics, and facets
- Themes, scales, and accessible color choices
- Quarto/R Markdown for reproducible reports
- Caching and knitting pitfalls
- Tables with gt or kable (survey)
- Exporting publication-ready figures
Modeling in R
- Formula interface with lm/glm (intro)
- tidymodels or caret survey (course-dependent)
- Train/test splits and resampling (intro)
- Model diagnostics and residual plots
- Classification metrics overview
- Communicating model results to non-R users
STEM / applied
Workflows
- renv or packrat for dependency lockfiles
- Style and lint (styler/lintr survey)
- Writing functions and avoiding copy-paste pipelines
- Parallel map over files (purrr intro)
- Connecting R to Python when required (reticulate survey)
- Version control for analysis projects
Applications
- Public health, business, or social-science case studies
- Shiny dashboard intro (optional)
- Survey weights awareness (intro)
- Missing-data reporting in papers
- Peer code review of tidy pipelines
- Capstone: Quarto analysis with tidyverse + model
Notes
Complements R under CS/math statistical computing when the focus is tidy DS workflows. Tutoring matches the course’s tidyverse vs base-R preference.