Backport PR #49981 on branch 1.5.x (Streamline docker usage) (#50421)

Backport PR #49981: Streamline docker usage

Co-authored-by: William Ayd <[email protected]>

Author: meeseeksmachine

.devcontainer.json

@@ -9,8 +9,7 @@
 	// You can edit these settings after create using File > Preferences > Settings > Remote.
 	"settings": {
 		"terminal.integrated.shell.linux": "/bin/bash",
-		"python.condaPath": "/opt/conda/bin/conda",
-		"python.pythonPath": "/opt/conda/bin/python",
+		"python.pythonPath": "/usr/local/bin/python",
 		"python.formatting.provider": "black",
 		"python.linting.enabled": true,
 		"python.linting.flake8Enabled": true,

.github/workflows/code-checks.yml

@@ -152,7 +152,7 @@ jobs:
         run: docker build --pull --no-cache --tag pandas-dev-env .
 
       - name: Show environment
-        run: docker run -w /home/pandas pandas-dev-env mamba run -n pandas-dev python -c "import pandas as pd; print(pd.show_versions())"
+        run: docker run --rm pandas-dev-env python -c "import pandas as pd; print(pd.show_versions())"
 
   requirements-dev-text-installable:
     name: Test install requirements-dev.txt

Dockerfile

@@ -1,42 +1,13 @@
-FROM quay.io/condaforge/mambaforge
+FROM python:3.10.8
+WORKDIR /home/pandas
 
-# if you forked pandas, you can pass in your own GitHub username to use your fork
-# i.e. gh_username=myname
-ARG gh_username=pandas-dev
-ARG pandas_home="/home/pandas"
+RUN apt-get update && apt-get -y upgrade
+RUN apt-get install -y build-essential
 
-# Avoid warnings by switching to noninteractive
-ENV DEBIAN_FRONTEND=noninteractive
+# hdf5 needed for pytables installation
+RUN apt-get install -y libhdf5-dev
 
-# Configure apt and install packages
-RUN apt-get update \
-    && apt-get -y install --no-install-recommends apt-utils git tzdata dialog 2>&1 \
-    #
-    # Configure timezone (fix for tests which try to read from "/etc/localtime")
-    && ln -fs /usr/share/zoneinfo/Etc/UTC /etc/localtime \
-    && dpkg-reconfigure -f noninteractive tzdata \
-    #
-    # cleanup
-    && apt-get autoremove -y \
-    && apt-get clean -y \
-    && rm -rf /var/lib/apt/lists/*
-
-# Switch back to dialog for any ad-hoc use of apt-get
-ENV DEBIAN_FRONTEND=dialog
-
-# Clone pandas repo
-RUN mkdir "$pandas_home" \
-    && git clone "https://github.com/$gh_username/pandas.git" "$pandas_home" \
-    && cd "$pandas_home" \
-    && git remote add upstream "https://github.com/pandas-dev/pandas.git" \
-    && git pull upstream main
-
-# Set up environment
-RUN mamba env create -f "$pandas_home/environment.yml"
-
-# Build C extensions and pandas
-SHELL ["mamba", "run", "--no-capture-output", "-n", "pandas-dev", "/bin/bash", "-c"]
-RUN cd "$pandas_home" \
-    && export \
-    && python setup.py build_ext -j 4 \
-    && python -m pip install --no-build-isolation -e .
+RUN python -m pip install --upgrade pip
+RUN python -m pip install --use-deprecated=legacy-resolver \
+    -r https://raw.githubusercontent.com/pandas-dev/pandas/main/requirements-dev.txt
+CMD ["/bin/bash"]

doc/source/development/contributing_environment.rst

@@ -216,34 +216,22 @@ with a full pandas development environment.
 
 Build the Docker image::
 
-    # Build the image pandas-yourname-env
-    docker build --tag pandas-yourname-env .
-    # Or build the image by passing your GitHub username to use your own fork
-    docker build --build-arg gh_username=yourname --tag pandas-yourname-env .
+    # Build the image
+    docker build -t pandas-dev .
 
 Run Container::
 
     # Run a container and bind your local repo to the container
-    docker run -it -w /home/pandas --rm -v path-to-local-pandas-repo:/home/pandas pandas-yourname-env
+    # This command assumes you are running from your local repo
+    # but if not alter ${PWD} to match your local repo path
+    docker run -it --rm -v ${PWD}:/home/pandas pandas-dev
 
-Then a ``pandas-dev`` virtual environment will be available with all the development dependencies.
+When inside the running container you can build and install pandas the same way as the other methods
 
-.. code-block:: shell
-
-    root@... :/home/pandas# conda env list
-    # conda environments:
-    #
-    base                  *  /opt/conda
-    pandas-dev               /opt/conda/envs/pandas-dev
-
-.. note::
-    If you bind your local repo for the first time, you have to build the C extensions afterwards.
-    Run the following command inside the container::
-
-        python setup.py build_ext -j 4
+.. code-block:: bash
 
-    You need to rebuild the C extensions anytime the Cython code in ``pandas/_libs`` changes.
-    This most frequently occurs when changing or merging branches.
+   python setup.py build_ext -j 4
+   python -m pip install -e . --no-build-isolation --no-use-pep517
 
 *Even easier, you can integrate Docker with the following IDEs:*