airflow.Dockerfile

# Airflow
FROM apache/airflow:2.2.2

ARG AIRFLOW_HOME=/opt/airflow

RUN pip install papermill==2.3.4
RUN pip install matplotlib
RUN pip install --upgrade pip ipython ipykernel
RUN ipython kernel install --name "python3" --user
RUN pip install pyspark==3.1.2
RUN pip install delta-spark==1.0.0

USER root
RUN apt update
RUN apt install -y git


# Java, Spark, PySpark
# Copyright (c) Jupyter Development Team.
# Distributed under the terms of the Modified BSD License.
LABEL maintainer="Jupyter Project <jupyter@googlegroups.com>"

# Fix DL4006
SHELL ["/bin/bash", "-o", "pipefail", "-c"]

USER root

# Spark dependencies
# Default values can be overridden at build time
# (ARGS are in lower case to distinguish them from ENV)
ARG spark_version="3.1.2"
ARG hadoop_version="3.2"
ARG spark_checksum="2385CB772F21B014CE2ABD6B8F5E815721580D6E8BC42A26D70BBCDDA8D303D886A6F12B36D40F6971B5547B70FAE62B5A96146F0421CB93D4E51491308EF5D5"
ARG openjdk_version="11"

ENV APACHE_SPARK_VERSION="${spark_version}" \
    HADOOP_VERSION="${hadoop_version}"

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


# Spark installation
WORKDIR /tmp
RUN wget -q "https://archive.apache.org/dist/spark/spark-${APACHE_SPARK_VERSION}/spark-${APACHE_SPARK_VERSION}-bin-hadoop${HADOOP_VERSION}.tgz" && \
    echo "${spark_checksum} *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"

WORKDIR /usr/local

# Configure Spark
ENV SPARK_HOME=/usr/local/spark
ENV SPARK_OPTS="--driver-java-options=-Xms1024M --driver-java-options=-Xmx4096M --driver-java-options=-Dlog4j.logLevel=info" \
    PATH=$PATH:$SPARK_HOME/bin

RUN ln -s "spark-${APACHE_SPARK_VERSION}-bin-hadoop${HADOOP_VERSION}" spark && \
    # Add a link in the before_notebook hook in order to source automatically PYTHONPATH
    mkdir -p /usr/local/bin/before-notebook.d && \
    ln -s "${SPARK_HOME}/sbin/spark-config.sh" /usr/local/bin/before-notebook.d/spark-config.sh

# Fix Spark installation for Java 11 and Apache Arrow library
# see: https://github.com/apache/spark/pull/27356, https://spark.apache.org/docs/latest/#downloading
RUN cp -p "$SPARK_HOME/conf/spark-defaults.conf.template" "$SPARK_HOME/conf/spark-defaults.conf" && \
    echo 'spark.driver.extraJavaOptions -Dio.netty.tryReflectionSetAccessible=true' >> $SPARK_HOME/conf/spark-defaults.conf && \
    echo 'spark.executor.extraJavaOptions -Dio.netty.tryReflectionSetAccessible=true' >> $SPARK_HOME/conf/spark-defaults.conf

USER $NB_UID

# # Install pyarrow
# RUN conda install --quiet --yes --satisfied-skip-solve \
#     'pyarrow=4.0.*' && \
#     conda clean --all -f -y && \
#     fix-permissions "${CONDA_DIR}" && \
#     fix-permissions "/home/${NB_USER}"

WORKDIR ${AIRFLOW_HOME}