Improve courseware robustness

.gitignore

@@ -2,13 +2,13 @@
 .Rhistory
 .RData
 .Ruserdata
-downloading-course-materials.qmd 
+downloading-course-materials.qmd
 notes.txt
 /.quarto/
 .DS_Store
-docs/site_libs/
 lab-notes
 census-key.R
 *_cache
 election-comp.R
-canvas-to-my-harvard.R
+canvas-to-my-harvard.R
+**/*.quarto_ipynb

Makefile

@@ -0,0 +1,47 @@
+.PHONY: render preview clean precheck check-cran check-legacy check-urls check-years
+
+# Verify all R packages used in course materials are installed
+precheck:
+	@Rscript check_packages.R
+
+# Verify CRAN packages are still listed on CRAN (catches archiving between course iterations)
+# Requires internet access.  GitHub-sourced packages (ThemePark, excessmort) are excluded.
+check-cran:
+	@Rscript -e "\
+	  source('check_packages.R', echo=FALSE); \
+	  cat('Checking CRAN availability...\n'); \
+	  avail <- rownames(available.packages(repos='https://cloud.r-project.org')); \
+	  gone  <- setdiff(cran_build_pkgs, avail); \
+	  also  <- setdiff(c('gganimate','gsheet'), avail); \
+	  all_gone <- c(gone, also); \
+	  if (length(all_gone) == 0) { \
+	    cat('OK: all CRAN packages are still listed on CRAN.\n') \
+	  } else { \
+	    cat('WARNING: these packages no longer appear on CRAN:\n'); \
+	    for (p in all_gone) cat('  ', p, '\n'); \
+	    quit(status=1) \
+	  }"
+
+render:
+	quarto render
+
+preview:
+	quarto preview
+
+clean:
+	rm -rf docs/
+
+# Find any remaining datasciencelabs.github.io references
+check-legacy:
+	@echo "=== datasciencelabs.github.io references ==="
+	@grep -rn "datasciencelabs.github.io" --include="*.qmd" --include="*.yml" . | grep -v "^\./docs/" || echo "None found."
+
+# Frequency-sorted list of all external URLs (for audits)
+check-urls:
+	@echo "=== External absolute URLs ==="
+	@grep -rohE "https?://[^)\"'> ]+" --include="*.qmd" . | grep -v "^\./docs/" | sort | uniq -c | sort -rn
+
+# Find hardcoded year references to update at annual course refresh
+check-years:
+	@echo "=== Year references (may need updating) ==="
+	@grep -rn "2025\|2024" --include="*.qmd" . | grep -v "^\./docs/" | grep -v "rafalab\|github\.com\|census\.gov\|cdc\.gov"

_quarto.yml

@@ -3,9 +3,9 @@ project:
   output-dir: docs
 
 website:
-  title: "BST 260: Introduction to Data Science"
-  site-url: "https://datasciencelabs.github.io/2025/"
-  repo-url: "https://github.com/datasciencelabs/2025"
+  title: "DRAFT FOR 2026 fall of BST 260: Introduction to Data Science"
+  site-url: "https://vjcitn.github.io/2026vjc/"
+  repo-url: "https://github.com/vjcitn/2026vjc/"
   repo-branch: main
   repo-actions: [source]
   sidebar:
@@ -15,7 +15,7 @@ website:
     align: center
     tools:
       - icon: github
-        href: "https://github.com/datasciencelabs/2025"
+        href: "https://github.com/vjcitn/2026vjc"
         text: GitHub
     style: docked
     contents:
@@ -38,4 +38,4 @@ format:
     css: style.css
     toc: true
 
-editor: source
+editor: source

_variables.yml

@@ -0,0 +1,9 @@
+# Course infrastructure
+site_url: "https://vjcitn.github.io/2026vjc/"
+canvas_url: "https://canvas.harvard.edu/courses/158943"
+slack_url: "https://bst-260-f25-7j2.slack.com/"
+course_github: "https://github.com/vjcitn/2026vjc/"
+
+# Textbook base URLs
+dsbook1: "http://rafalab.dfci.harvard.edu/dsbook-part-1/"
+dsbook2: "http://rafalab.dfci.harvard.edu/dsbook-part-2/"

check_packages.R

@@ -0,0 +1,91 @@
+## check_packages.R
+##
+## Verifies R packages used in course materials are installed.
+## Run via:  make precheck
+##
+## PACKAGE PROVENANCE
+## ------------------
+## The vast majority of packages below are from CRAN and can be installed with
+## install.packages().  Two packages come from GitHub and carry a sustainability
+## risk: if the author's repository is removed or renamed, the package becomes
+## unavailable and course materials that reference it will need to be updated.
+##
+## GitHub dependencies (non-CRAN):
+##   ThemePark  -- MatthewBJane/ThemePark (BUILD-CRITICAL: used in 08-ggplot2 slides)
+##                 remotes::install_github("MatthewBJane/ThemePark")
+##   excessmort -- rafalab/excessmort      (STUDENT-ONLY:  eval:false in pset-08)
+##                 remotes::install_github("rafalab/excessmort")
+##
+## All other packages are from CRAN.  Use `make check-cran` to verify they are
+## still listed on CRAN (catches archiving/removal between course iterations).
+##
+## TWO TIERS
+## ---------
+##   build_pkgs   packages executed during `quarto render`; missing = broken build
+##   student_pkgs packages in eval:false exercise templates; students need them,
+##                the site renders without them
+
+## --- CRAN packages (build-critical) -----------------------------------------
+cran_build_pkgs <- c(
+  "broom", "caret", "data.table", "devtools", "doParallel",
+  "dplyr", "dslabs", "emmeans", "forcats", "geomtextpath",
+  "ggplot2", "ggrepel", "ggridges", "ggthemes", "gridExtra",
+  "gtools", "HistData", "httr2", "janitor", "jsonlite",
+  "kableExtra", "knitr", "Lahman", "lattice", "lpSolve",
+  "lubridate", "maps", "MASS", "matrixStats", "NHANES",
+  "purrr", "randomForest", "RColorBrewer", "readr", "readxl",
+  "remotes", "reshape2", "rpart", "rvest", "scales",
+  "shiny", "tidyr", "tidyverse", "VennDiagram"
+)
+
+## --- GitHub packages (build-critical) ----------------------------------------
+github_build_pkgs <- c(
+  "ThemePark"   # MatthewBJane/ThemePark -- risk: author-hosted, not on CRAN
+)
+
+## --- Packages only needed by students (eval:false in QMD sources) -------------
+student_pkgs <- c(
+  "gganimate",  # CRAN -- dataviz slide (eval:false demo)
+  "gsheet",     # CRAN -- pset-07 (eval:false)
+  "excessmort"  # GitHub: rafalab/excessmort -- pset-08 (eval:false)
+)
+
+build_pkgs <- c(cran_build_pkgs, github_build_pkgs)
+
+## --- Check function ----------------------------------------------------------
+missing_pkgs <- function(pkgs) {
+  pkgs[!vapply(pkgs, requireNamespace, logical(1), quietly = TRUE)]
+}
+
+missing_build   <- missing_pkgs(build_pkgs)
+missing_student <- missing_pkgs(student_pkgs)
+
+## --- Report ------------------------------------------------------------------
+if (length(missing_student) > 0) {
+  cat("NOTE: student-exercise packages not installed (site will still render):\n")
+  for (pkg in missing_student) cat("  ", pkg, "\n")
+  cat("\n")
+}
+
+if (length(missing_build) == 0) {
+  cat("OK: all", length(build_pkgs), "build-critical packages are available.\n")
+  cat("   (", length(cran_build_pkgs), "from CRAN,",
+      length(github_build_pkgs), "from GitHub:", paste(github_build_pkgs, collapse = ", "), ")\n")
+} else {
+  cat("ERROR: build-critical packages missing (", length(missing_build),
+      ") -- render will fail:\n", sep = "")
+  for (pkg in missing_build) cat("  ", pkg, "\n")
+  cat("\nInstall CRAN packages with:\n")
+  cran_missing <- intersect(missing_build, cran_build_pkgs)
+  if (length(cran_missing))
+    cat('  install.packages(c(', paste0('"', cran_missing, '"', collapse = ", "), '))\n')
+  gh_missing <- intersect(missing_build, github_build_pkgs)
+  if (length(gh_missing)) {
+    cat("Install GitHub packages with:\n")
+    for (pkg in gh_missing) {
+      src <- switch(pkg, ThemePark = "MatthewBJane/ThemePark")
+      cat('  remotes::install_github("', src, '")\n', sep = "")
+    }
+  }
+  quit(status = 1)
+}