FROM python:3.7.3 USER root ARG NB_USER=jovyan ENV NB_USER $NB_USER ENV NB_UID 1000 ENV HOME /home/$NB_USER ENV NB_PREFIX / ENV PATH $HOME/.local/bin:$PATH # RUN /usr/bin/python3 -m pip3 install --upgrade pip3 RUN pip3 install awscli pyspark findspark # Install base python3 packages RUN pip3 --no-cache-dir install jupyter-console==6.0.0 jupyterlab RUN wget http://archive.apache.org/dist/spark/spark-3.0.0/spark-3.0.0-bin-hadoop3.2.tgz RUN tar xvzf spark-3.0.0-bin-hadoop3.2.tgz RUN mv spark-3.0.0-bin-hadoop3.2 /opt/spark-3.0.0 RUN ln -s /opt/spark-3.0.0 /opt/spark RUN rm spark-3.0.0-bin-hadoop3.2.tgz ENV SPARK_HOME=/opt/spark ENV PATH=$SPARK_HOME/bin:$PATH RUN apt-get update -y RUN apt-get install -y openjdk-8-jre gcc \ python3 python-dev python3-dev \ build-essential libssl-dev libffi-dev \ libxml2-dev libxslt1-dev zlib1g-dev \ python-pip EXPOSE 8888 CMD ["sh","-c", "jupyter notebook --notebook-dir=/home/${NB_USER} --ip=0.0.0.0 --no-browser --allow-root --port=8888 --NotebookApp.token='' --NotebookApp.password='' --NotebookApp.allow_origin='*' --NotebookApp.base_url=${NB_PREFIX}"]