Files
docker-stacks/images/pyspark-notebook/Dockerfile
2025-05-30 09:11:31 +01:00

80 lines
2.7 KiB
Docker

# Copyright (c) Jupyter Development Team.
# Distributed under the terms of the Modified BSD License.
ARG REGISTRY=quay.io
ARG OWNER=jupyter
ARG BASE_IMAGE=$REGISTRY/$OWNER/scipy-notebook
FROM $BASE_IMAGE
LABEL maintainer="Jupyter Project <jupyter@googlegroups.com>"
# Fix: https://github.com/hadolint/hadolint/wiki/DL4006
# Fix: https://github.com/koalaman/shellcheck/wiki/SC3014
SHELL ["/bin/bash", "-o", "pipefail", "-c"]
USER root
# Spark dependencies
# Default values can be overridden at build time
# (ARGS are in lowercase to distinguish them from ENV)
ARG openjdk_version="17"
RUN apt-get update --yes && \
apt-get install --yes --no-install-recommends \
"openjdk-${openjdk_version}-jre-headless" \
ca-certificates-java && \
apt-get clean && rm -rf /var/lib/apt/lists/*
# If spark_version is not set, latest Spark will be installed
ARG spark_version
ARG hadoop_version="3"
# If scala_version is not set, Spark without Scala will be installed
ARG scala_version
# 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/"
# macOS Rosetta virtualization creates junk directory which gets owned by root further up.
# It'll get re-created, but as USER runner after the next directive so hopefully should not cause permission issues.
#
# More info: https://github.com/jupyter/docker-stacks/issues/2296
# hadolint ignore=DL3059
RUN rm -rf "/home/${NB_USER}/.cache/"
USER ${NB_UID}
# Install pyarrow
# NOTE: It's important to ensure compatibility between Pandas versions.
# The pandas version in this Dockerfile should match the version
# on which the Pandas API for Spark is built.
# To find the right version, check the pandas version being installed here:
# https://github.com/apache/spark/blob/<SPARK_VERSION>/dev/infra/Dockerfile
RUN mamba install --yes \
'grpcio-status' \
'grpcio' \
'pandas=2.2.3' \
'pyarrow' && \
mamba clean --all -f -y && \
fix-permissions "${CONDA_DIR}" && \
fix-permissions "/home/${NB_USER}"
WORKDIR "${HOME}"
EXPOSE 4040