Update public site

.github/workflows/deploy_main_preview.yml

@@ -22,6 +22,13 @@ jobs:
       packages: write
 
     steps:
+      - name: Get Actions user id
+        id: get_uid
+        run: |
+          actions_user_id=`id -u $USER`
+          echo $actions_user_id
+          echo "uid=$actions_user_id" >> $GITHUB_OUTPUT
+
       - name: checkout
         uses: actions/checkout@v2
         with:
@@ -30,6 +37,11 @@ jobs:
       - name: Build the book
         run: |
           ./build_html.sh
+
+      - name: Reset ownership of workspace after build
+        uses: peter-murray/reset-workspace-ownership-action@v1
+        with:
+          user_id: ${{ steps.get_uid.outputs.uid }}
 
        # Push the book's HTML to github-pages
       - name: GitHub Pages action

.github/workflows/deploy_pr_preview.yml

@@ -31,6 +31,13 @@ jobs:
           checkName: "Rebuild docker image"
           ref: ${{ github.event.pull_request.head.sha }}
           timeoutSeconds: 60000
+
+      - name: Get Actions user id
+        id: get_uid
+        run: |
+          actions_user_id=`id -u $USER`
+          echo $actions_user_id
+          echo "uid=$actions_user_id" >> $GITHUB_OUTPUT
 
       - name: Checkout the repo
         uses: actions/checkout@v2
@@ -42,6 +49,11 @@ jobs:
         run: |
           ./build_html.sh
 
+      - name: Reset ownership of workspace after build
+        uses: peter-murray/reset-workspace-ownership-action@v1
+        with:
+          user_id: ${{ steps.get_uid.outputs.uid }}
+
        # Push the book's HTML to github-pages
       - name: GitHub Pages action
         uses: peaceiris/[email protected]
@@ -52,11 +64,35 @@ jobs:
           destination_dir: pull${{ github.event.number }}
           # force_orphan: true # once peaceiris updates to v4, change this to true and keep_files: true for the PR / main branch deploy previews
 
+      - name: Checkout the gh-pages branch
+        uses: actions/checkout@v2
+        with:
+          fetch-depth: '0'
+          ref: 'gh-pages'
+
+      - name: Run website diff
+        run: |
+          rustup update
+          pip install --upgrade pip
+          pip install website_diff
+          rm -rf diff${{ github.event.number }}
+          website_diff --old dev --new pull${{ github.event.number }} --diff diff${{ github.event.number }}
+
+      - name: GitHub Pages action to push diff
+        uses: peaceiris/[email protected]
+        with:
+          github_token: ${{ secrets.GITHUB_TOKEN }}
+          publish_dir: diff${{ github.event.number }}
+          keep_files: true
+          destination_dir: diff${{ github.event.number }}
+          # force_orphan: true # once peaceiris updates to v4, change this to true and keep_files: true for the PR / main branch deploy previews
+
       - name: Post URLS to PR thread
         uses: mshick/[email protected]
         with:
           message: |
               Hello! I've built a preview of your PR so that you can compare it to the current `main` branch.
               * PR deploy preview available [here](https://datasciencebook.ca/pull${{ github.event.number }}/index.html)
+              * PR diff with `main` available [here](https://datasciencebook.ca/diff${{ github.event.number }}/index.html)
               * Current `main` deploy preview available [here](https://datasciencebook.ca/dev/index.html)
               * Public production build available [here](https://datasciencebook.ca)

.github/workflows/build_book.yml → .github/workflows/update_book.yml

@@ -22,21 +22,27 @@ jobs:
       packages: write
 
     steps:
-      - name: checkout
+      - name: checkout gh-pages
         uses: actions/checkout@v2
         with:
-          ref: 'production'
-          
-      - name: Build the book
+          ref: 'gh-pages'
+
+      - name: Copy contents of dev/ to home folder
         run: |
-          ./build_html.sh
+          yes | cp -rf dev ${{ runner.home }}
 
-       # Push the book's HTML to github-pages
-      - name: GitHub Pages action
+      # Push update website to dev/ and clean out old commits
+      - name: Update website to contents of dev, remove all old commits and subpages
         uses: peaceiris/[email protected]
         with:
           github_token: ${{ secrets.GITHUB_TOKEN }}
-          publish_dir: docs/
+          publish_dir: dev/
           force_orphan: true # this will clean up all previous PR previews / main branch preview
           cname: datasciencebook.ca
 
+      - name: copy dev/ website back in
+        run: |
+          yes | cp -rf ${{ runner.home }}/dev dev
+
+      - name: push the result to gh-pages
+        uses: stefanzweifel/git-auto-commit-action@v5

.github/workflows/update_build_environment.yml

@@ -2,6 +2,8 @@ name: Rebuild and publish new ubcdsci/intro-to-ds image on DockerHub
 on:
   pull_request:
     types: [opened, synchronize]
+    branches:
+      - 'main'
 jobs:
   rebuild-docker:
     name: Rebuild docker image

build_html.sh

@@ -1,2 +1,3 @@
 # Script to generate HTML book
 docker run --rm -m 8g -v $(pwd):/home/rstudio/introduction-to-datascience ubcdsci/intro-to-ds:202307130106229dd1c2 /bin/bash -c "cd /home/rstudio/introduction-to-datascience; Rscript -e 'bookdown::render_book(\"index.Rmd\", output_format=\"bookdown::gitbook\"); warnings(); problems()'"
+

index.Rmd

@@ -35,10 +35,16 @@ You can read the web version of the book on this site. Click a section in the ta
 on the left side of the page to navigate to it. If you are on a mobile device,
 you may need to open the table of contents first by clicking the menu button on 
 the top left of the page. You can purchase a PDF or print copy of the book 
-on the [CRC Press website](https://www.routledge.com/Data-Science-A-First-Introduction/Timbers-Campbell-Lee/p/book/9780367524685) or on [Amazon](https://www.amazon.com/Data-Science-First-Introduction-Chapman/dp/0367532174/ref=sr_[…]qid=1644637450&sprefix=data+science+timber%2Caps%2C166&sr=8-1).
+on the [CRC Press website](https://www.routledge.com/Data-Science-A-First-Introduction/Timbers-Campbell-Lee/p/book/9780367524685) or on [Amazon](https://www.amazon.com/Data-Science-First-Introduction-Chapman/dp/0367532174).
 
 For the python version of the textbook, visit [https://python.datasciencebook.ca](https://python.datasciencebook.ca).
 
+This book is listed in a number of open educational resource (OER) collections:
+
+- [The University of British Columbia OER collection](https://oer.open.ubc.ca/data-science-a-first-introduction/)
+- [The OER Commons](https://oercommons.org/courses/data-science-a-first-introduction-with-r)
+- [MERLOT](https://merlot.org/merlot/viewMaterial.htm?id=773420156)
+
 ```{r bookcover, echo = FALSE, fig.retina = 2, out.width = "45%"}
 knitr::include_graphics("img/frontmatter/ds-a-first-intro-cover.jpg")
 ```

source/reading.Rmd

@@ -547,7 +547,7 @@ communication channel that R can use to send SQL commands to the database.
 ```{r}
 library(DBI)
 
-conn_lang_data <- dbConnect(RSQLite::SQLite(), "data/can_lang.db")
+canlang_conn <- dbConnect(RSQLite::SQLite(), "data/can_lang.db")
 ```
 
 Often relational databases have many tables; thus, in order to retrieve
@@ -557,7 +557,7 @@ all the tables in the database using the `dbListTables` \index{database!tables}
 function:
 
 ```{r}
-tables <- dbListTables(conn_lang_data)
+tables <- dbListTables(canlang_conn)
 tables
 ```
 
@@ -573,7 +573,7 @@ into SQL queries!
 ```{r}
 library(dbplyr)
 
-lang_db <- tbl(conn_lang_data, "lang")
+lang_db <- tbl(canlang_conn, "lang")
 lang_db
 ```
 
@@ -596,15 +596,15 @@ image_read("img/reading/ref_vs_tibble.001.jpeg") |>
 ```
 
 We can look at the SQL commands that are sent to the database when we write
-`tbl(conn_lang_data, "lang")` in R with the `show_query` function from the
+`tbl(canlang_conn, "lang")` in R with the `show_query` function from the
 `dbplyr` package. \index{database!show\_query}
 
 ```{r}
-show_query(tbl(conn_lang_data, "lang"))
+show_query(tbl(canlang_conn, "lang"))
 ```
 
 The output above shows the SQL code that is sent to the database. When we
-write `tbl(conn_lang_data, "lang")` in R, in the background, the function is
+write `tbl(canlang_conn, "lang")` in R, in the background, the function is
 translating the R code into SQL, sending that SQL to the database, and then translating the
 response for us. So `dbplyr` does all the hard work of translating from R to SQL and back for us;
 we can just stick with R!
@@ -704,7 +704,7 @@ be able to connect to a database using this information.
 
 ```{r, eval = FALSE}
 library(RPostgres)
-conn_mov_data <- dbConnect(RPostgres::Postgres(), dbname = "can_mov_db",
+canmov_conn <- dbConnect(RPostgres::Postgres(), dbname = "can_mov_db",
                         host = "fakeserver.stat.ubc.ca", port = 5432,
                         user = "user0001", password = "abc123")
 ```
@@ -714,7 +714,7 @@ to when we were using an SQLite database in R. For example, we can again use
 `dbListTables` to find out what tables are in the `can_mov_db` database:
 
 ```{r, eval = FALSE}
-dbListTables(conn_mov_data)
+dbListTables(canmov_conn)
 ```
 
 ```
@@ -727,7 +727,7 @@ We see that there are 10 tables in this database. Let's first look at the
 database:
 
 ```{r, eval = FALSE}
-ratings_db <- tbl(conn_mov_data, "ratings")
+ratings_db <- tbl(canmov_conn, "ratings")
 ratings_db
 ```
 

source/version-control.Rmd

@@ -941,10 +941,9 @@ and guidance that the worksheets provide will function as intended.
 Now that you've picked up the basics of version control with Git and GitHub,
 you can expand your knowledge through the resources listed below:
 
-- GitHub's [guides website](https://guides.github.com/) and [YouTube
-  channel](https://www.youtube.com/githubguides), and [*Happy Git and GitHub
-  for the useR*](https://happygitwithr.com/) are great resources to take the next steps in
-  learning about Git and GitHub.
+- GitHub's [guides website](https://docs.github.com/) and [*Happy Git and GitHub
+  for the useR*](https://happygitwithr.com/) are great resources for
+  learning more about Git and GitHub.
 - [Good enough practices in scientific
   computing](https://journals.plos.org/ploscompbiol/article?id=10.1371/journal.pcbi.1005510#sec014)
   [@wilson2014best] provides more advice on useful workflows and "good enough"