Merge pull request #222 from UBC-DSCI/main

Production push pre-fall 2023

Author: trevorcampbell

.github/workflows/build_book.yml

@@ -30,4 +30,6 @@ jobs:
           github_token: ${{ secrets.GITHUB_TOKEN }}
           publish_dir: source/_build/html
           force_orphan: true
+          cname: python.datasciencebook.ca
+
 

.github/workflows/update_build_environment.yml

@@ -34,6 +34,15 @@ jobs:
         chmod u+x build_html.sh
         git add build_html.sh
         git commit -m "update build_html.sh script with new docker image"
+    - name: Update build_pdf.sh script
+      run: |
+        git config --local user.email "[email protected]"
+        git config --local user.name "GitHub Action"
+        git pull origin main
+        sed 's/ubcdsci\/py-intro-to-ds:[[:alnum:]]\+/ubcdsci\/py-intro-to-ds:${{ steps.rebuild.outputs.snapshot-tag }}/g' build_pdf.sh > build_pdf.tmp && mv build_pdf.tmp build_pdf.sh
+        chmod u+x build_pdf.sh
+        git add build_pdf.sh
+        git commit -m "update build_pdf.sh script with new docker image"
     - name: Push changes to build scripts
       uses: ad-m/github-push-action@master
       with:

.gitignore

@@ -8,3 +8,4 @@ source/*.ipynb
 source/*.py
 *.swp
 *.swo
+source/__pycache__

Dockerfile

@@ -3,8 +3,8 @@ FROM jupyter/scipy-notebook
 
 USER root
 
-# install vim
-RUN apt-get update && apt-get install -y vim
+# install vim and a few packages for PDF builds
+RUN apt-get update && apt-get install -y vim texlive-latex-extra texlive-fonts-extra texlive-xetex latexmk xindy imagemagick
 
 USER ${NB_UID}
 
@@ -13,19 +13,36 @@ WORKDIR "${HOME}"
 # remove the "work/" directory added in an earlier layer...
 RUN rm -rf work
 
-# Install R packages
-RUN mamba install --quiet --yes \
-        'numpy' \
-        'jinja2' \
-        'altair_data_server' \
-        'altair_saver' \
-        'click' \
-        'ibis-framework' \
-        'ghp-import' \
-        'jupytext' \
-        'jupyter-book' \
-        'nodejs' \
-    && mamba clean --all -f -y \
-    && fix-permissions "${CONDA_DIR}" \
-    && fix-permissions "/home/${NB_USER}" 
+
+RUN pip install docutils==0.17.1 # Need to pin docutils to an old version for now, due to https://github.com/executablebooks/jupyter-book/issues/2022
+RUN pip install referencing
+RUN pip install jupyter-book
+# Pinning pandas until altair 5.1.2 to avoid future warning https://github.com/altair-viz/altair/issues/3181
+RUN pip install numpy jinja2 pandas"<2.1" altair">=5.1.1" "vegafusion[embed]" vl-convert-python">=0.13" click ibis-framework ghp-import jupytext nodejs
+
+# forces scikit-learn to grab latest to avoid bug in 1.3.0 related to checking for c-contiguity breaking figures in classification 2. See https://github.com/scikit-learn/scikit-learn/pull/26772
+# TODO: remove this once scikit-learn 1.4.x or beyond releases and is incorporated into jupyter/scipy-notebook
+RUN pip install -U git+https://github.com/scikit-learn/scikit-learn.git@main
+
+# disable warnings that pollute build logs; seems to be related to the update to python 3.11
+# https://discourse.jupyter.org/t/debugger-warning-it-seems-that-frozen-modules-are-being-used-python-3-11-0/16544/12
+ENV PYDEVD_DISABLE_FILE_VALIDATION=1
+
+## Install various python packages
+# commented out for now due to various package version conflicts
+# installing via pip instead above
+#RUN mamba install --quiet --yes \
+#        'numpy' \
+#        'jinja2' \
+#        'altair_data_server' \
+#        'altair_saver' \
+#        'click' \
+#        'ibis-framework' \
+#        'ghp-import' \
+#        'jupytext' \
+#        'jupyter-book' \
+#        'nodejs' \
+#    && mamba clean --all -f -y \
+#    && fix-permissions "${CONDA_DIR}" \
+#    && fix-permissions "/home/${NB_USER}" 
 

README.md

@@ -1,8 +1,10 @@
 ## Data Science: A First Introduction (Python Edition)
 This is the source for the python edition of the *Data Science: A First Introduction* textbook.
 
+The book is available online at: https://python.datasciencebook.ca/
+
 For the R version of the textbook, please visit https://datasciencebook.ca or the github repository
-at https://github.com/ubc-dsci/introduction-to-datascience .
+at https://github.com/ubc-dsci/introduction-to-datascience.
 
 ## License Information
 
@@ -24,12 +26,18 @@ The `production` branch contains the source material for the live, publicly view
 
 ### Build locally
 
-You can build the book on your own machine by running
+You can build the HTML version of the book on your own machine by running
 ```
 ./build_html.sh
 ```
 in the root directory of this repository. The book can be viewed in your browser by opening the `source/_build/html/index.html` file.
 
+You can build the PDF version of the book on your own machine by running
+```
+./build_pdf.sh
+```
+in the root directory of this repository. The book can be viewed in a PDF reader by opening `source/_build/latex/python.pdf`.
+
 ### Update build environment
 
 You can update the build environment for the book by making changes to `Dockerfile` in the root of the repository in the `main` branch.

build_html.sh

@@ -1,2 +1,3 @@
 chmod -R o+w source/
-docker run --rm -v $(pwd):/home/jovyan ubcdsci/py-intro-to-ds:20230104230634037f38 /bin/bash -c "jupyter-book build source"
+docker run --rm -v $(pwd):/home/jovyan ubcdsci/py-intro-to-ds:20230831171718ddf538 /bin/bash -c "jupyter-book build source"
+chmod -R o-w source/

build_pdf.sh

@@ -0,0 +1,3 @@
+chmod -R o+w source/
+docker run --rm -v $(pwd):/home/jovyan ubcdsci/py-intro-to-ds:20230831171718ddf538 /bin/bash -c "export BOOK_BUILD_TYPE='PDF'; jupyter-book build source --builder pdflatex"
+chmod -R o-w source/