CSCI316.Dockerfile

FROM continuumio/anaconda3:2021.11

# Fetch Java, Scala, and Spark
RUN set -ex; \
    apt-get update; \
    apt-get install -y default-jre default-jdk scala gnupg; \
    wget -qO /tmp/spark.tgz https://dlcdn.apache.org/spark/spark-3.2.0/spark-3.2.0-bin-hadoop2.7.tgz; \
    wget -qO /tmp/spark.tgz.asc https://downloads.apache.org/spark/spark-3.2.0/spark-3.2.0-bin-hadoop2.7.tgz.asc; \
    wget -qO- https://downloads.apache.org/spark/KEYS | gpg --import -; \
    gpg --verify /tmp/spark.tgz.asc /tmp/spark.tgz; \
    apt-get purge -y gnupg; \
    rm -rf /var/lib/apt/lists/*; \
    tar -xzf /tmp/spark.tgz -C /usr/local/; \
    rm -rf /tmp/spark.tgz /tmp/spark.tgz.asc; \
    mv /usr/local/spark-3.2.0-bin-hadoop2.7 /usr/local/spark;

# Install essential packages
RUN set -ex; \
    pip install \
        findspark pyspark numpy pandas py4j \
        psutil cairocffi scikit-learn tensorflow; \
    conda install jupyter -y --quiet;

# Create user
RUN useradd -m -s /bin/bash -U user
USER user
WORKDIR /home/user

ENV JAVA_HOME=/usr/lib/jvm/java-11-openjdk-amd64 \
    SPARK_HOME=/usr/local/spark \
    HADOOP_HOME=/usr/local/spark \
    PYSPARK_PYTHON=/opt/conda/bin/python3 \
    PYSPARK_DRIVER_PYTHON=/opt/conda/bin/ipython3

CMD ["jupyter", "notebook", "--ip", "*"]