Dockerfile

ARG REGISTRY=quay.io
ARG OWNER=jupyter
ARG BASE_CONTAINER=$REGISTRY/$OWNER/scipy-notebook
FROM $BASE_CONTAINER

# Fix: https://github.com/koalaman/shellcheck/wiki/SC3014
SHELL ["/bin/bash", "-o", "pipefail", "-c"]

USER root

# Spark dependencies
# Default values can be overridden at build time
# (ARGS are in lowercase to distinguish them from ENV)
ARG openjdk_version="17"

RUN apt-get update --yes && \
    apt-get install --yes --no-install-recommends \
    "openjdk-${openjdk_version}-jre-headless" \
    ca-certificates-java && \
    apt-get clean && rm -rf /var/lib/apt/lists/*

# If spark_version is not set, latest stable Spark will be installed
ARG spark_version="3.5.1"
ARG hadoop_version="3"
# If scala_version is not set, Spark without Scala will be installed
ARG scala_version="2.13"
# URL to use for Spark downloads
# You need to use https://archive.apache.org/dist/spark/ website if you want to download old Spark versions
# But it seems to be slower, that's why we use the recommended site for download
ARG spark_download_url="https://dlcdn.apache.org/spark/"

ENV SPARK_HOME=/usr/local/spark
ENV PATH="${PATH}:${SPARK_HOME}/bin"
ENV SPARK_OPTS="--driver-java-options=-Xms1024M --driver-java-options=-Xmx4096M --driver-java-options=-Dlog4j.logLevel=info"

COPY setup_spark.py /opt/setup-scripts/

# Setup Spark
RUN /opt/setup-scripts/setup_spark.py \
    --spark-version="${spark_version}" \
    --hadoop-version="${hadoop_version}" \
    --scala-version="${scala_version}" \
    --spark-download-url="${spark_download_url}"

# Configure IPython system-wide
COPY ipython_kernel_config.py "/etc/ipython/"
RUN fix-permissions "/etc/ipython/"

RUN curl -Lo /bin/coursier https://git.io/coursier-cli && \
    chmod +x /bin/coursier


USER ${NB_UID}

RUN coursier launch --fork almond:0.14.0-RC14 --scala 2.13.12 \
      -- --install --id scala2 --display-name "Scala 2" \
      --jupyter-path /opt/conda/share/jupyter/kernels \
      --global

# Install pyarrow
# NOTE: It's important to ensure compatibility between Pandas versions.
# The pandas version in this Dockerfile should match the version
# on which the Pandas API for Spark is built.
# To find the right version:
# 1. Check out the Spark branch you are on: <https://github.com/apache/spark>
# 2. Find the pandas version in the file `dev/infra/Dockerfile`.
RUN mamba install --yes \
    'grpcio-status' \
    'grpcio' \
    'pandas=2.0.3' \
    'pyarrow' && \
    mamba clean --all -f -y && \
    fix-permissions "${CONDA_DIR}" && \
    fix-permissions "/home/${NB_USER}"

WORKDIR "${HOME}"
EXPOSE 4040