Merge pull request #86 from paddymul/master

Add Jupyterlite
jvns · Oct 22, 2024 · ba8d1d3 · ba8d1d3
2 parents 7c4b573 + 304da8f
commit ba8d1d3
Show file tree

Hide file tree

Showing 21 changed files with 237 additions and 311 deletions.
diff --git a/.github/workflows/deploy.yml b/.github/workflows/deploy.yml
@@ -0,0 +1,57 @@
+name: Build and Deploy
+
+on:
+  push:
+    branches:
+      - main
+      - master
+  pull_request:
+    branches:
+      - '*'
+
+jobs:
+  build:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v3
+
+      - name: Setup Python
+        uses: actions/setup-python@v5
+        with:
+          python-version: '3.12'
+
+      - name: Install mamba
+        uses: mamba-org/setup-micromamba@v1
+        with:
+          micromamba-version: '1.5.8-0'
+          environment-file: build-environment.yml
+          cache-environment: true
+
+      - name: Build the JupyterLite site
+        shell: bash -l {0}
+        run: |
+          cp README.md content
+          jupyter lite build --contents cookbook --output-dir dist
+
+      - name: Upload artifact
+        uses: actions/upload-pages-artifact@v3
+        with:
+          path: ./dist
+
+  deploy:
+    needs: build
+    if: github.ref == 'refs/heads/master'
+    permissions:
+      pages: write
+      id-token: write
+
+    environment:
+      name: github-pages
+      url: ${{ steps.deployment.outputs.page_url }}
+
+    runs-on: ubuntu-latest
+    steps:
+      - name: Deploy to GitHub Pages
+        id: deployment
+        uses: actions/deploy-pages@v4
diff --git a/README.md b/README.md
@@ -1,7 +1,10 @@
 Pandas cookbook
 ===============
 
-[![Binder](https://mybinder.org/badge.svg)](https://mybinder.org/v2/gh/jvns/pandas-cookbook/master)
+
+Try it with Jupyter Lite
+[![lite-badge](https://jupyterlite.rtfd.io/en/latest/_static/badge.svg)](https://paddymul.github.io/pandas-cookbook/lab/index.html)
+
 
 [pandas](http://pandas.pydata.org/) is a Python library for doing
 data analysis. It's really fast and lets you do exploratory work
@@ -78,6 +81,13 @@ A tab should open up in your browser at `http://localhost:8888`
 
 Happy pandas!
 
+Running Jupyterlite locally
+===========================
+```bash
+#assuming you checked out into ~/code/pandas-cookbook
+cd ~/code/pandas-cookbook/  ; rm -rf _output ;  time jupyter lite build --contents ./cookbook/ && cd _output && python -m http.server
+```
+
 Running the cookbook inside a Docker container.
 ===============================================================
 This repository contains a Dockerfile and can be built into a docker container.

diff --git a/build-environment.yml b/build-environment.yml
@@ -0,0 +1,9 @@
+name: build-env
+channels:
+  - conda-forge
+dependencies:
+  - python
+  - pip
+  - jupyter_server
+  - jupyterlite-core >=0.4.1,<0.5.0
+  - jupyterlite-xeus>=2.0.0,<3
diff --git a/cookbook/Chapter 1 - Reading from a CSV.ipynb b/cookbook/Chapter 1 - Reading from a CSV.ipynb
diff --git a/cookbook/Chapter 2 - Selecting data & finding the most common complaint type.ipynb b/cookbook/Chapter 2 - Selecting data & finding the most common complaint type.ipynb
@@ -36,7 +36,7 @@
    "outputs": [],
    "source": [
     "# because of mixed types we specify dtype to prevent any errors\n",
-    "complaints = pd.read_csv('../data/311-service-requests.csv', dtype='unicode')"
+    "complaints = pd.read_csv('./data/311-service-requests.csv', dtype='unicode')"
    ]
   },
   {
@@ -1693,7 +1693,7 @@
  ],
  "metadata": {
   "kernelspec": {
-   "display_name": "Python 3",
+   "display_name": "Python 3 (ipykernel)",
    "language": "python",
    "name": "python3"
   },
@@ -1707,9 +1707,16 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.8.5"
+   "version": "3.9.20"
+  },
+  "widgets": {
+   "application/vnd.jupyter.widget-state+json": {
+    "state": {},
+    "version_major": 2,
+    "version_minor": 0
+   }
   }
  },
  "nbformat": 4,
- "nbformat_minor": 1
+ "nbformat_minor": 4
 }
diff --git a/...k/Chapter 3 - Which borough has the most noise complaints (or, more selecting data).ipynb b/...k/Chapter 3 - Which borough has the most noise complaints (or, more selecting data).ipynb
@@ -36,7 +36,7 @@
    "outputs": [],
    "source": [
     "# because of mixed types we specify dtype to prevent any errors\n",
-    "complaints = pd.read_csv('../data/311-service-requests.csv', dtype='unicode')"
+    "complaints = pd.read_csv('./data/311-service-requests.csv', dtype='unicode')"
    ]
   },
   {
@@ -1607,7 +1607,7 @@
  ],
  "metadata": {
   "kernelspec": {
-   "display_name": "Python 3",
+   "display_name": "Python 3 (ipykernel)",
    "language": "python",
    "name": "python3"
   },
@@ -1621,9 +1621,16 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.8.5"
+   "version": "3.9.20"
+  },
+  "widgets": {
+   "application/vnd.jupyter.widget-state+json": {
+    "state": {},
+    "version_major": 2,
+    "version_minor": 0
+   }
   }
  },
  "nbformat": 4,
- "nbformat_minor": 1
+ "nbformat_minor": 4
 }
diff --git a/...apter 4 - Find out on which weekday people bike the most with groupby and aggregate.ipynb b/...apter 4 - Find out on which weekday people bike the most with groupby and aggregate.ipynb
@@ -70,7 +70,7 @@
     }
    ],
    "source": [
-    "bikes = pd.read_csv('../data/bikes.csv', sep=';', encoding='latin1', parse_dates=['Date'], dayfirst=True, index_col='Date')\n",
+    "bikes = pd.read_csv('./data/bikes.csv', sep=';', encoding='latin1', parse_dates=['Date'], dayfirst=True, index_col='Date')\n",
     "bikes['Berri 1'].plot()"
    ]
   },
@@ -628,7 +628,7 @@
     }
    ],
    "source": [
-    "bikes = pd.read_csv('../data/bikes.csv', \n",
+    "bikes = pd.read_csv('./data/bikes.csv', \n",
     "                    sep=';', encoding='latin1', \n",
     "                    parse_dates=['Date'], dayfirst=True, \n",
     "                    index_col='Date')\n",
@@ -652,7 +652,7 @@
  ],
  "metadata": {
   "kernelspec": {
-   "display_name": "Python 3",
+   "display_name": "Python 3 (ipykernel)",
    "language": "python",
    "name": "python3"
   },
@@ -666,9 +666,16 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.8.5"
+   "version": "3.9.20"
+  },
+  "widgets": {
+   "application/vnd.jupyter.widget-state+json": {
+    "state": {},
+    "version_major": 2,
+    "version_minor": 0
+   }
   }
  },
  "nbformat": 4,
- "nbformat_minor": 1
+ "nbformat_minor": 4
 }
diff --git a/cookbook/Chapter 5 - Combining dataframes and scraping Canadian weather data.ipynb b/cookbook/Chapter 5 - Combining dataframes and scraping Canadian weather data.ipynb
@@ -2,7 +2,7 @@
  "cells": [
   {
    "cell_type": "code",
-   "execution_count": 1,
+   "execution_count": 2,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -63,7 +63,7 @@
     }
    ],
    "source": [
-    "weather_2012_final = pd.read_csv('../data/weather_2012.csv', index_col='Date/Time')\n",
+    "weather_2012_final = pd.read_csv('./data/weather_2012.csv', index_col='Date/Time')\n",
     "weather_2012_final['Temp (C)'].plot(figsize=(15, 6))"
    ]
   },
@@ -85,6 +85,15 @@
     "Here's an URL template you can use to get data in Montreal. "
    ]
   },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "#downloading via URLS doesn't work in Jupyterlite"
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": 15,
@@ -103,15 +112,15 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 17,
+   "execution_count": 3,
    "metadata": {},
    "outputs": [],
    "source": [
     "#url = url_template.format(month=3, year=2012)\n",
     "#weather_mar2012 = pd.read_csv(url, skiprows=15, index_col='Date/Time', parse_dates=True, encoding='latin1', header=True)\n",
     "\n",
     "# because the url is broken, we use our saved dataframe for now\n",
-    "weather_mar2012 = pd.read_csv('../data/weather_2012.csv')"
+    "weather_mar2012 = pd.read_csv('./data/weather_2012.csv')"
    ]
   },
   {
@@ -1905,7 +1914,7 @@
  ],
  "metadata": {
   "kernelspec": {
-   "display_name": "Python 3",
+   "display_name": "Python 3 (ipykernel)",
    "language": "python",
    "name": "python3"
   },
@@ -1919,9 +1928,16 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.8.5"
+   "version": "3.9.20"
+  },
+  "widgets": {
+   "application/vnd.jupyter.widget-state+json": {
+    "state": {},
+    "version_major": 2,
+    "version_minor": 0
+   }
   }
  },
  "nbformat": 4,
- "nbformat_minor": 1
+ "nbformat_minor": 4
 }
diff --git a/cookbook/Chapter 6 - String Operations- Which month was the snowiest.ipynb b/cookbook/Chapter 6 - String Operations- Which month was the snowiest.ipynb
@@ -156,7 +156,7 @@
     }
    ],
    "source": [
-    "weather_2012 = pd.read_csv('../data/weather_2012.csv', parse_dates=True, index_col='Date/Time')\n",
+    "weather_2012 = pd.read_csv('./data/weather_2012.csv', parse_dates=True, index_col='Date/Time')\n",
     "weather_2012[:5]"
    ]
   },
@@ -717,7 +717,7 @@
  ],
  "metadata": {
   "kernelspec": {
-   "display_name": "Python 3",
+   "display_name": "Python 3 (ipykernel)",
    "language": "python",
    "name": "python3"
   },
@@ -731,9 +731,16 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.8.5"
+   "version": "3.9.20"
+  },
+  "widgets": {
+   "application/vnd.jupyter.widget-state+json": {
+    "state": {},
+    "version_major": 2,
+    "version_minor": 0
+   }
   }
  },
  "nbformat": 4,
- "nbformat_minor": 1
+ "nbformat_minor": 4
 }
diff --git a/cookbook/Chapter 7 - Cleaning up messy data.ipynb b/cookbook/Chapter 7 - Cleaning up messy data.ipynb
@@ -39,7 +39,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "requests = pd.read_csv('../data/311-service-requests.csv', dtype='unicode')"
+    "requests = pd.read_csv('./data/311-service-requests.csv', dtype='unicode')"
    ]
   },
   {
@@ -149,7 +149,7 @@
    "outputs": [],
    "source": [
     "na_values = ['NO CLUE', 'N/A', '0']\n",
-    "requests = pd.read_csv('../data/311-service-requests.csv', na_values=na_values, dtype={'Incident Zip': str})"
+    "requests = pd.read_csv('./data/311-service-requests.csv', na_values=na_values, dtype={'Incident Zip': str})"
    ]
   },
   {
@@ -1194,7 +1194,7 @@
    "outputs": [],
    "source": [
     "na_values = ['NO CLUE', 'N/A', '0']\n",
-    "requests = pd.read_csv('../data/311-service-requests.csv', \n",
+    "requests = pd.read_csv('./data/311-service-requests.csv', \n",
     "                       na_values=na_values, \n",
     "                       dtype={'Incident Zip': str})"
    ]
@@ -1337,7 +1337,7 @@
  ],
  "metadata": {
   "kernelspec": {
-   "display_name": "Python 3",
+   "display_name": "Python 3 (ipykernel)",
    "language": "python",
    "name": "python3"
   },
@@ -1351,9 +1351,16 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.8.5"
+   "version": "3.9.20"
+  },
+  "widgets": {
+   "application/vnd.jupyter.widget-state+json": {
+    "state": {},
+    "version_major": 2,
+    "version_minor": 0
+   }
   }
  },
  "nbformat": 4,
- "nbformat_minor": 1
+ "nbformat_minor": 4
 }