PySpark dockerfile

Dockerfile

# Source: https://hub.docker.com/r/jupyter/pyspark-notebook
# Copyright (c) Jupyter Development Team.
# Distributed under the terms of the Modified BSD License.
ARG BASE_CONTAINER=jupyter/scipy-notebook
FROM $BASE_CONTAINER

LABEL maintainer="Jupyter Project <[email protected]>"

USER root

# Spark dependencies
ENV APACHE_SPARK_VERSION 2.4.4
ENV HADOOP_VERSION 2.7

RUN apt-get -y update && \
    apt-get install --no-install-recommends -y openjdk-8-jre-headless ca-certificates-java && \
    rm -rf /var/lib/apt/lists/*

RUN cd /tmp && \
    wget -q http://mirrors.ukfast.co.uk/sites/ftp.apache.org/spark/spark-${APACHE_SPARK_VERSION}/spark-${APACHE_SPARK_VERSION}-bin-hadoop${HADOOP_VERSION}.tgz && \
    echo "2E3A5C853B9F28C7D4525C0ADCB0D971B73AD47D5CCE138C85335B9F53A6519540D3923CB0B5CEE41E386E49AE8A409A51AB7194BA11A254E037A848D0C4A9E5 *spark-${APACHE_SPARK_VERSION}-bin-hadoop${HADOOP_VERSION}.tgz" | sha512sum -c - && \
    tar xzf spark-${APACHE_SPARK_VERSION}-bin-hadoop${HADOOP_VERSION}.tgz -C /usr/local --owner root --group root --no-same-owner && \
    rm spark-${APACHE_SPARK_VERSION}-bin-hadoop${HADOOP_VERSION}.tgz
RUN cd /usr/local && ln -s spark-${APACHE_SPARK_VERSION}-bin-hadoop${HADOOP_VERSION} spark

# Mesos dependencies
# Install from the Xenial Mesosphere repository since there does not (yet)
# exist a Bionic repository and the dependencies seem to be compatible for now.
# COPY mesos.key /tmp/
# RUN apt-get -y update && \
#     apt-get install --no-install-recommends -y gnupg && \
#     apt-key add /tmp/mesos.key && \
#     echo "deb http://repos.mesosphere.io/ubuntu xenial main" > /etc/apt/sources.list.d/mesosphere.list && \
#     apt-get -y update && \
#     apt-get --no-install-recommends -y install mesos=1.2\* && \
#     apt-get purge --auto-remove -y gnupg && \
#     rm -rf /var/lib/apt/lists/*

# Spark and Mesos config
ENV JAVA_HOME /usr/lib/jvm/java-8-openjdk-amd64/
ENV SPARK_HOME /usr/local/spark
ENV PYTHONPATH $SPARK_HOME/python:$SPARK_HOME/python/lib/py4j-0.10.7-src.zip
ENV MESOS_NATIVE_LIBRARY /usr/local/lib/libmesos.so
ENV SPARK_OPTS --driver-java-options=-Xms1024M --driver-java-options=-Xmx4096M --driver-java-options=-Dlog4j.logLevel=info



### Set the working directory to /powershell
WORKDIR /powershell

# Download the Microsoft repository GPG keys, register, install powershell and finally start
# See also: https://docs.microsoft.com/en-us/powershell/scripting/install/installing-powershell-core-on-linux?view=powershell-6
RUN wget -q https://packages.microsoft.com/config/ubuntu/18.04/packages-microsoft-prod.deb  && \
    sudo dpkg -i packages-microsoft-prod.deb  && \
    sudo apt-get -o Acquire::Check-Valid-Until=false -o Acquire::Check-Date=false update  && \
    sudo apt-get install -y software-properties-common && \
    sudo apt-get -o Acquire::Check-Valid-Until=false -o Acquire::Check-Date=false update  && \
    sudo add-apt-repository universe  && \
    sudo apt-get install -y powershell && \
    rm packages-microsoft-prod.deb && \
    apt-get clean


# Switch from root/superuser to normal user and change directory
WORKDIR /home/$NB_USER
USER $NB_UID

# # Install and activate Jupyter extensions
RUN pip install jupyter_contrib_nbextensions && \
    jupyter contrib nbextension install --user && \
    jupyter nbextensions_configurator enable --user && \
    pip install RISE && \
    jupyter-nbextension enable rise --py --user && \
    jupyter-nbextension enable collapsible_headings/main --user && \
    jupyter-nbextension enable scratchpad/main --user && \
    jupyter-nbextension enable hide_input_all/main --user && \
    jupyter-nbextension enable hide_input/main --user && \
    jupyter-nbextension enable comment-uncomment/main --user && \
    jupyter-nbextension enable code_prettify/code_prettify --user && \
    jupyter-nbextension enable toc2/main --user && \
    fix-permissions $CONDA_DIR && \
    fix-permissions /home/$NB_USER

# # Install additional Python packages
RUN pip install pyarrow==0.12.1 && \
    pip install koalas && \
    pip install streamlit && \
    pip install pytest-cov && \
    pip install sphinx && \
    pip install requests-kerberos

# Add custom styling for Jupyter notebook - create folder, change to that folder and download custom.css from GitHub gist
RUN mkdir -p /home/$NB_USER/.jupyter/custom && \
    cd /home/$NB_USER/.jupyter/custom && \
    wget -q https://gist.githubusercontent.com/simicd/20d40cae61305aecdf372c4ac0cffc4a/raw/082096fe90fd58095f84aab9030fa8a643713ec3/custom.css