Merge pull request #33 from UBC-DSCI/dev

Update main

Author: trevorcampbell

.github/workflows/build_book.yml

@@ -1,11 +1,10 @@
 on:
   push:
     branches:
-      - myst
+      - main
     paths:
       - source/**
-  pull_request: null
-
+      
 jobs:
   deploy-book:
     runs-on: ${{ matrix.os }}
@@ -27,7 +26,7 @@ jobs:
       - name: checkout
         uses: actions/checkout@v2
         with:
-          ref: 'myst'
+          ref: 'main'
 
       - name: install from lockfile
         uses: mamba-org/provision-with-micromamba@main

install/environment.yml

@@ -2,7 +2,6 @@ name: dsci100
 channels:
   - eoas_ubc
   - conda-forge
-  - defaults
 dependencies:
   - altair
   - altair_data_server
@@ -12,17 +11,15 @@ dependencies:
   - git
   - jupyterlab
   - jupytext
-  - jupyter-book>0.12
   - jupyter_contrib_nbextensions
   - mamba
   - nodejs
   - notebook
   - numpy
   - pandas
   - pip
-  - pooch
   - python<3.10
   - jinja2==3.0.3
   - scikit-learn
-  - watchdog
+  - openpyxl
 # conda-lock --kind explicit --file environment.yml -p linux-64

notes/Readme_overview.md

@@ -0,0 +1,40 @@
+# OCESE summer notes
+
+## resource links
+
+### DSCI 100
+
+* the instructor repo (ubc enterprise github) https://github.ubc.ca/dsci-100-instructor  
+* the student repo) https://github.com/ubc-dsci/dsci-100-student  
+
+### python textbook repo and forks
+
+* https://github.com/ubc-dsci/introduction-to-datascience-python  
+* https://github.com/lheagy/introduction-to-datascience-python  
+* https://github.com/phaustin/introduction-to-datascience-python  
+
+#### textbook branches
+
+* dev: https://github.com/ubc-dsci/introduction-to-datascience-python/tree/dev
+* chapter 2 (reading,navya): https://github.com/ubc-dsci/introduction-to-datascience-python/tree/reading
+   * tutorial: https://github.ubc.ca/UBC-DSCI/dsci-100-instructor/tree/py_tutorial_reading
+   * worksheet: https://github.ubc.ca/UBC-DSCI/dsci-100-instructor/tree/py_worksheet_reading
+   * issue: https://github.com/UBC-DSCI/introduction-to-datascience-python/issues/4
+* chapter 5 (classification1, gloria): https://github.com/ubc-dsci/introduction-to-datascience-python/tree/classification1
+   * tutorial: https://github.ubc.ca/UBC-DSCI/dsci-100-instructor/tree/py_tutorial_classification1
+   * worksheet: https://github.ubc.ca/UBC-DSCI/dsci-100-instructor/tree/py_worksheet_classification1
+   * issue: https://github.com/UBC-DSCI/introduction-to-datascience-python/issues/3
+
+
+### R textbook
+
+* the R textbook repo: https://github.com/ubc-dsci/introduction-to-datascience  
+* rendered textbook (R version):  https://datasciencebook.ca/
+
+
+### nbgrader
+
+* rudaux: https://github.com/UBC-DSCI/rudaux  
+* autotest (private): https://github.com/ubc-dsci/autotest  
+
+

references.bib

@@ -280,7 +280,7 @@ @book{children2012
   publisher = {Public Works \& Government Services Canada}
 }
 
-@book{calls2015,
+@misc{calls2015,
   title={Calls to {A}ction},
   author={{Truth and Reconciliation Commission of Canada}},
   year={2015},
@@ -364,6 +364,13 @@ @book{wickham2016r
   url = {https://r4ds.had.co.nz/}
 }
 
+@book{mckinney2012python,
+  title={Python for data analysis: Data wrangling with Pandas, NumPy, and IPython},
+  author={McKinney, Wes},
+  year={2012},
+  publisher={" O'Reilly Media, Inc."}
+}
+
 @book{wickham2019advanced,
   title={Advanced {R}},
   author={Wickham, Hadley},
@@ -429,3 +436,71 @@ @book{openintro
   year = {2019},
   publisher = {OpenIntro, Inc.},
   url = {https://openintro.org/book/os/}}
+
+@inproceedings{sklearn_api,
+  author    = {Lars Buitinck and Gilles Louppe and Mathieu Blondel and
+               Fabian Pedregosa and Andreas Mueller and Olivier Grisel and
+               Vlad Niculae and Peter Prettenhofer and Alexandre Gramfort
+               and Jaques Grobler and Robert Layton and Jake VanderPlas and
+               Arnaud Joly and Brian Holt and Ga{\"{e}}l Varoquaux},
+  title     = {{API} design for machine learning software: experiences from the scikit-learn
+               project},
+  booktitle = {ECML PKDD Workshop: Languages for Data Mining and Machine Learning},
+  year      = {2013},
+  pages = {108--122},
+}
+
+@Manual{reback2020pandas,
+    author       = {The pandas development team},
+    title        = {pandas-dev/pandas: Pandas},
+    month        = feb,
+    year         = 2020,
+    publisher    = {Zenodo},
+    version      = {latest},
+    doi          = {10.5281/zenodo.3509134},
+    url          = {https://doi.org/10.5281/zenodo.3509134}
+}
+
+@InProceedings{ mckinney-proc-scipy-2010,
+  author    = { {W}es {M}c{K}inney },
+  title     = { {D}ata {S}tructures for {S}tatistical {C}omputing in {P}ython },
+  booktitle = { {P}roceedings of the 9th {P}ython in {S}cience {C}onference },
+  pages     = { 56 - 61 },
+  year      = { 2010 },
+  editor    = { {S}t\'efan van der {W}alt and {J}arrod {M}illman },
+  doi       = { 10.25080/Majora-92bf1922-00a }
+}
+
+@Manual{pep8-style-guide,
+  year = {2001},
+  author = {Guido van Rossum, Barry Warsaw, Nick Coghlan},
+  title = {PEP 8 – Style Guide for Python Code},
+  url = {https://peps.python.org/pep-0008/}
+}
+
+@article{altair,
+    doi = {10.21105/joss.01057},
+    url = {https://doi.org/10.21105/joss.01057},
+    year = {2018},
+    publisher = {The Open Journal},
+    volume = {3},
+    number = {32},
+    pages = {1057},
+    author = {Jacob VanderPlas and Brian Granger and Jeffrey Heer and Dominik Moritz and Kanit Wongsuphasawat and Arvind Satyanarayan and Eitan Lees and Ilia Timofeev and Ben Welsh and Scott Sievert},
+    title = {Altair: Interactive Statistical Visualizations for Python},
+    journal = {Journal of Open Source Software}
+}
+
+@article{beautifulsoup,
+  title={Beautiful soup documentation},
+  author={Richardson, Leonard},
+  journal={April},
+  year={2007}
+}
+
+@article{tweepy,
+  title={Tweepy: Twitter for Python!},
+  author={Roesslein, Joshua},
+  journal={URL: https://github.com/tweepy/tweepy},
+  year={2020}
+}

source/_config.yml

@@ -65,14 +65,14 @@ latex:
   latex_engine: pdflatex # one of 'pdflatex', 'xelatex' (recommended for unicode), 'luatex', 'platex', 'uplatex'
   use_jupyterbook_latex: true # use sphinx-jupyterbook-latex for pdf builds as default
 
+  
 #######################################################################################
+
 # Launch button settings
 launch_buttons:
-  notebook_interface: classic # The interface interactive links will activate ["classic", "jupyterlab"]
-  binderhub_url: https://mybinder.org # The URL of the BinderHub (e.g., https://mybinder.org)
-  jupyterhub_url: "https://eosc211.jupyterhub.eoas.ubc.ca/jupyter" # The URL of the JupyterHub (e.g., https://datahub.berkeley.edu)
-  thebe: false # Add a thebe button to pages (requires the repository to run on Binder)
-  colab_url: "" # The URL of Google Colab (https://colab.research.google.com)
+  binderhub_url: ""
+
+
 
 repository:
   url: https://github.com/phaustin/eosc211_students # The URL to your book's repository
@@ -85,3 +85,8 @@ sphinx:
   extra_extensions: # A list of extra extensions to load by Sphinx (added to those already used by JB).
   local_extensions: # A list of local extensions to load by sphinx specified by "name: path" items
   config: # key-value pairs to directly over-ride the Sphinx configuration
+    bibtex_reference_style: author_year
+
+#######################################################################################
+bibtex_bibfiles:
+    - ../references.bib

source/_toc.yml

@@ -1,22 +1,24 @@
 format: jb-book
-root: intro.md
+root: index.md
+options:
+  numbered: true
 parts:
 - caption: First draft
   chapters:
-    - file: preface-text
-    - file: setup
-    - file: reading
-    - file: wrangling
-    - file: viz
-    - file: version-control
-    - file: classification1
-    - file: classification2
-    - file: regression1
-    - file: regression2
-    - file: clustering
-    - file: inference
-    - file: references
-    - file: acknowledgements
-    - file: authors
-    - file: appendixA
-
+    - file: preface-text.md
+    - file: foreword-text.md
+    - file: acknowledgements.md
+    - file: authors.md
+    - file: setup.md
+    - file: intro.md
+    - file: reading.md
+    - file: wrangling.md
+    - file: viz.md
+    - file: classification1.md
+    - file: classification2.md
+    - file: regression1.md
+    - file: regression2.md
+    - file: clustering.md
+    - file: inference.md
+    - file: references.md
+    - file: appendixA.md

source/acknowledgements.md

@@ -13,7 +13,7 @@ kernelspec:
   name: python3
 ---
 
-# Acknowledgments {-}
+# Acknowledgments -- TBD
 
 We'd like to thank everyone that has contributed to the development of 
 [*Data Science: A First Introduction*](https://datasciencebook.ca).

source/appendixA.md

@@ -13,7 +13,7 @@ kernelspec:
   name: python3
 ---
 
-# (APPENDIX) Appendix {-}
+# Appendix
 
 # Downloading files from JupyterHub {#appendixA}
 

source/authors.md

@@ -13,7 +13,7 @@ kernelspec:
   name: python3
 ---
 
-# About the authors {-}
+# About the authors -- TBD
 
 **Tiffany Timbers** is an Assistant Professor of Teaching in the Department of
 Statistics and Co-Director for the Master of Data Science program (Vancouver