Py4DS compiles with uv!

Author: aeturrell

.pre-commit-config.yaml

@@ -13,26 +13,18 @@ repos:
         entry: nbstripout
         language: python
         types: [jupyter]
-  - repo: https://github.com/psf/black
-    rev: 22.3.0
+  - repo: https://github.com/astral-sh/ruff-pre-commit
+    # Ruff version.
+    rev: v0.4.1
     hooks:
-      - id: black
-        name: black
-        description: 'applies black formatter to .py files'
-        entry: black
-        language: python
-        types: [python]
-      - id: black-jupyter
-        name: black-jupyter
-        description:
-          "Black: The uncompromising Python code formatter (with Jupyter Notebook support)"
-        entry: black
-        language: python
-        minimum_pre_commit_version: 2.9.2
-        require_serial: true
+      # Run the linter.
+      - id: ruff
+        types_or: [python, pyi, jupyter]
+        args: [ --fix ]
+      - id: ruff
+        types_or: [python, pyi, jupyter]
+        name: sort imports with ruff
+        args: [--select, I, --fix]
+      # Run the formatter.
+      - id: ruff-format
         types_or: [python, pyi, jupyter]
-        additional_dependencies: [".[jupyter]"]
-  - repo: https://github.com/pycqa/flake8
-    rev: 3.9.2  # pick a git hash / tag to point to
-    hooks:
-      -   id: flake8

Dockerfile

@@ -1,38 +1,31 @@
-# DOCKERFILE for Coding for Economists
-# Please note that you will need a lot of RAM dedicated to Docker to build this image (15Gb+, change this in your docker settings)
+# DOCKERFILE for Python for Data Science
 
-# Set base image (this also loads the Alpine Linux operating system)
-FROM continuumio/miniconda3:4.10.3-alpine
+# Set base image
+FROM python:3.10-slim-bookworm
 
 WORKDIR /app
 
 # Update Linux package list and install some key libraries, including latex
-RUN apk update && apk add openssl graphviz \
-    nano texlive alpine-sdk build-base graphviz-dev \
-    bash
+RUN apt-get -y update && apt-get install -y openssl graphviz \
+    nano texlive graphviz-dev \
+    bash build-essential git
 
 # change default shell from ash to bash
 RUN sed -i -e "s/bin\/ash/bin\/bash/" /etc/passwd
 
-# Install mamba
-RUN conda install mamba -n base -c conda-forge
+# Create the environment:
+COPY uv.lock .
+COPY pyproject.toml .
 
-# Ensure pip's setuptools is latest
-RUN pip install --upgrade setuptools wheel
+# Install uv
+COPY --from=ghcr.io/astral-sh/uv:0.5.14 /uv /bin/uv
 
-# Create the environment:
-COPY environment.yml .
 # Install everything at once:
-RUN mamba env create -f environment.yml
-# Do a debug or incremental env install (builds quickly):
-# RUN mamba create -n python4DS -c conda-forge python=3.9 numpy pandas -y
-
-# Make RUN commands use the new environment:
-SHELL ["conda", "run", "-n", "py4ds2e", "/bin/bash", "-c"]
+RUN uv sync --frozen
 
-RUN mamba list
+RUN uv pip list
 
 # Copy the current directory contents into the container at /app
 COPY . /app
 
-RUN echo "Success building the python4DS container!"
+RUN echo "Success building the Python4DS container!"

_config.yml

@@ -4,13 +4,16 @@
 title: Python for Data Science
 author: The Py4DS Community
 logo: logo.png
-
+exclude_patterns: [_build, Thumbs.db, .DS_Store, "**.ipynb_checkpoints", ".venv"]
 # Force re-execution of notebooks on each build.
 # See https://jupyterbook.org/content/execute.html
 execute:
   execute_notebooks: force
   timeout: 120
-  exclude_patterns: [README.md]
+  exclude_patterns: ["README.md"]
+  allow_errors: false
+  nb_output_stderr: show
+
 
 # Define the name of the latex output file for PDF builds
 latex:
@@ -32,9 +35,19 @@ html:
   use_issues_button: true
   use_repository_button: true
   favicon: "favicon.ico"  # A path to a favicon image
-  google_analytics_id: "G-LXJC37BJVX"  # A GA id that can be used to track book views.
+  analytics:
+    google_analytics_id: "G-LXJC37BJVX"  # A GA id that can be used to track book views.
 
 launch_buttons:
   colab_url: "https://colab.research.google.com"
   notebook_interface: "jupyterlab"  # or "classic"
-  binderhub_url: "https://mybinder.org"
+  binderhub_url: "https://mybinder.org"
+
+sphinx:
+  config:
+    html_js_files:
+    - https://cdnjs.cloudflare.com/ajax/libs/require.js/2.3.4/require.min.js
+    bibtex_reference_style: author_year
+    suppress_warnings: ["mystnb.unknown_mime_type"]
+    nb_execution_show_tb: true
+    nb_execution_raise_on_error: true  # Make build fail any content errors (don't want to publish if errors)

categorical-data.ipynb

@@ -25,8 +25,8 @@
    "outputs": [],
    "source": [
     "# remove cell\n",
-    "import matplotlib_inline.backend_inline\n",
     "import matplotlib.pyplot as plt\n",
+    "import matplotlib_inline.backend_inline\n",
     "\n",
     "# Plot settings\n",
     "plt.style.use(\"https://github.com/aeturrell/python4DS/raw/main/plot_style.txt\")\n",

communicate-plots.ipynb

@@ -37,8 +37,8 @@
    "outputs": [],
    "source": [
     "# remove cell\n",
-    "import matplotlib_inline.backend_inline\n",
     "import matplotlib.pyplot as plt\n",
+    "import matplotlib_inline.backend_inline\n",
     "\n",
     "# Plot settings\n",
     "plt.style.use(\"https://github.com/aeturrell/python4DS/raw/main/plot_style.txt\")\n",
@@ -52,10 +52,9 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "from lets_plot import *\n",
-    "from lets_plot.mapping import as_discrete\n",
-    "import pandas as pd\n",
     "import numpy as np\n",
+    "import pandas as pd\n",
+    "from lets_plot import *\n",
     "\n",
     "LetsPlot.setup_html()"
    ]
@@ -1326,17 +1325,14 @@
   }
  ],
  "metadata": {
-  "interpreter": {
-   "hash": "9d7534ecd9fbc7d385378f8400cf4d6cb9c6175408a574f1c99c5269f08771cc"
-  },
   "jupytext": {
    "cell_metadata_filter": "-all",
    "encoding": "# -*- coding: utf-8 -*-",
    "formats": "md:myst",
    "main_language": "python"
   },
   "kernelspec": {
-   "display_name": "Python 3 (ipykernel)",
+   "display_name": ".venv",
    "language": "python",
    "name": "python3"
   },
@@ -1350,7 +1346,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.10.13"
+   "version": "3.10.0"
   },
   "toc-showtags": true
  },

data-import.ipynb

@@ -181,8 +181,6 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "import numpy as np\n",
-    "\n",
     "students[\"age\"] = students[\"age\"].replace(\"five\", 5)\n",
     "students[\"age\"]"
    ]

data-tidy.ipynb

@@ -29,8 +29,8 @@
    "outputs": [],
    "source": [
     "# remove cell\n",
-    "import matplotlib_inline.backend_inline\n",
     "import matplotlib.pyplot as plt\n",
+    "import matplotlib_inline.backend_inline\n",
     "\n",
     "# Plot settings\n",
     "plt.style.use(\"https://github.com/aeturrell/python4DS/raw/main/plot_style.txt\")\n",

data-visualise.ipynb

@@ -68,9 +68,8 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "import pandas as pd\n",
-    "from palmerpenguins import load_penguins\n",
     "from lets_plot import *\n",
+    "from palmerpenguins import load_penguins\n",
     "\n",
     "LetsPlot.setup_html()"
    ]

databases.ipynb

@@ -453,47 +453,39 @@
     "import ibis\n",
     "\n",
     "ibis.options.interactive = True\n",
-    "connection = ibis.sqlite.connect(Path(\"data/Chinook.sqlite\"))\n",
+    "connection = ibis.sqlite.connect(\"data/Chinook.sqlite\")\n",
     "track = connection.table(\"track\")\n",
     "track.head()"
    ]
   },
   {
    "cell_type": "markdown",
-   "id": "965cc983",
+   "id": "6dcd7d71",
    "metadata": {},
    "source": [
-    "As an aside, you can list the available tables using"
+    "Okay, now let's reproduce the following query: \"SELECT albumid, AVG(milliseconds)/1e3/60 FROM track GROUP BY albumid ORDER BY AVG(milliseconds) ASC LIMIT 5;\". We'll use a groupby, a mutate (which you can think of like **pandas**' assign statement), a sort, and then `limit()` to only show the first five entries."
    ]
   },
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "58369c80",
+   "id": "5e5a482b",
    "metadata": {},
    "outputs": [],
    "source": [
-    "connection.list_tables()"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "6dcd7d71",
-   "metadata": {},
-   "source": [
-    "Okay, now let's reproduce the following query: \"SELECT albumid, AVG(milliseconds)/1e3/60 FROM track GROUP BY albumid ORDER BY AVG(milliseconds) ASC LIMIT 5;\". We'll use a groupby, a mutate (which you can think of like **pandas**' assign statement), a sort, and then `limit()` to only show the first five entries."
+    "track.group_by(\"AlbumId\").mutate(\n",
+    "    mean_mins_track=track.Milliseconds.mean() / 1e3 / 60\n",
+    ").order_by(\"mean_mins_track\").limit(5)"
    ]
   },
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "5e5a482b",
+   "id": "39c80365",
    "metadata": {},
    "outputs": [],
    "source": [
-    "track.group_by(\"AlbumId\").mutate(\n",
-    "    mean_mins_track=track.Milliseconds.mean() / 1e3 / 60\n",
-    ").order_by(\"mean_mins_track\").limit(5)"
+    "track.group_by(\"AlbumId\").mutate(mean_mins_track=track.Milliseconds.mean() / 1e3 / 60)"
    ]
   },
   {
@@ -788,7 +780,7 @@
    "main_language": "python"
   },
   "kernelspec": {
-   "display_name": "Python 3.9.12 ('python4DS')",
+   "display_name": ".venv",
    "language": "python",
    "name": "python3"
   },
@@ -802,14 +794,9 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.10.12"
+   "version": "3.10.0"
   },
-  "toc-showtags": true,
-  "vscode": {
-   "interpreter": {
-    "hash": "9d7534ecd9fbc7d385378f8400cf4d6cb9c6175408a574f1c99c5269f08771cc"
-   }
-  }
+  "toc-showtags": true
  },
  "nbformat": 4,
  "nbformat_minor": 5