AWS Pyspark Docker Container

Dockerfile

# Copyright (c) Jupyter Development Team.
# Distributed under the terms of the Modified BSD License.
ARG OWNER=jupyter
ARG BASE_CONTAINER=$OWNER/scipy-notebook
FROM $BASE_CONTAINER

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"
ARG aws_hadoop_version="3.2.0"
ARG aws_sdk_version="1.11.375"


ENV APACHE_SPARK_VERSION="${spark_version}" \
    HADOOP_VERSION="${hadoop_version}" \
    AWS_SDK_VERSION="${aws_sdk_version}" \
    AWS_HADOOP_VERSION="${aws_hadoop_version}"
ENV JUPYTER_ENABLE_LAB=yes
RUN apt-get update --yes && \
    apt-get install --yes --no-install-recommends \
    "openjdk-${openjdk_version}-jre-headless" \
    ca-certificates-java  \
    curl \
    awscli && \
    apt-get clean && rm -rf /var/lib/apt/lists/*


# Install requirements
COPY requirements.txt ./
RUN pip3 install --upgrade pip  && pip3 install --no-cache-dir -r requirements.txt
RUN apt-get clean && rm requirements.txt


# 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"

# Add hadoop-aws and aws-sdk
RUN wget https://repo1.maven.org/maven2/org/apache/hadoop/hadoop-aws/${AWS_HADOOP_VERSION}/hadoop-aws-${AWS_HADOOP_VERSION}.jar -P "${SPARK_HOME}/jars/" && \
    wget https://repo1.maven.org/maven2/com/amazonaws/aws-java-sdk-bundle/${AWS_SDK_VERSION}/aws-java-sdk-bundle-${AWS_SDK_VERSION}.jar -P "${SPARK_HOME}/jars/"
# Adding JetS3t libary
RUN wget https://repo1.maven.org/maven2/net/java/dev/jets3t/jets3t/0.9.4/jets3t-0.9.4.jar -P "${SPARK_HOME}/jars/"


# Install pyarrow
RUN mamba install --quiet --yes \
    'pyarrow' && \
    mamba clean --all -f -y && \
    fix-permissions "${CONDA_DIR}" && \
    fix-permissions "/home/${NB_USER}"
USER ${NB_UID}


WORKDIR "${HOME}"

requirements.txt

boto3
s3fs
botocore