Merge pull request #163 from parente/unify-pyspark-all-spark

Rebase all-spark-notebook on pyspark-notebook

all-spark-notebook/Dockerfile

 # Copyright (c) Jupyter Development Team.
 # Distributed under the terms of the Modified BSD License.
-FROM jupyter/minimal-notebook
+FROM jupyter/pyspark-notebook
 
 MAINTAINER Jupyter Project <jupyter@googlegroups.com>
 
 USER root
 
-# Util to help with kernel spec later
-RUN apt-get -y update && apt-get -y install jq && apt-get clean && rm -rf /var/lib/apt/lists/*
-
-# Spark dependencies
-ENV APACHE_SPARK_VERSION 1.6.0
-RUN apt-get -y update && \
-    apt-get install -y --no-install-recommends openjdk-7-jre-headless && \
-    apt-get clean && \
-    rm -rf /var/lib/apt/lists/*
-RUN cd /tmp && \
-        wget -q http://d3kbcqa49mib13.cloudfront.net/spark-${APACHE_SPARK_VERSION}-bin-hadoop2.6.tgz && \
-        echo "439fe7793e0725492d3d36448adcd1db38f438dd1392bffd556b58bb9a3a2601 *spark-${APACHE_SPARK_VERSION}-bin-hadoop2.6.tgz" | sha256sum -c - && \
-        tar xzf spark-${APACHE_SPARK_VERSION}-bin-hadoop2.6.tgz -C /usr/local && \
-        rm spark-${APACHE_SPARK_VERSION}-bin-hadoop2.6.tgz
-RUN cd /usr/local && ln -s spark-${APACHE_SPARK_VERSION}-bin-hadoop2.6 spark
-
-RUN apt-key adv --keyserver keyserver.ubuntu.com --recv E56151BF && \
-    DISTRO=debian && \
-    CODENAME=jessie && \
-    echo "deb http://repos.mesosphere.io/${DISTRO} ${CODENAME} main" > /etc/apt/sources.list.d/mesosphere.list && \
-    apt-get -y update && \
-    apt-get --no-install-recommends -y --force-yes install mesos=0.25.0-0.2.70.debian81 && \
-    apt-get clean && \
-    rm -rf /var/lib/apt/lists/*
-
-# Spark and Mesos pointers
-ENV SPARK_HOME /usr/local/spark
+# RSpark config
 ENV R_LIBS_USER $SPARK_HOME/R/lib
-ENV PYTHONPATH $SPARK_HOME/python:$SPARK_HOME/python/lib/py4j-0.9-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
 
 # R pre-requisites
 RUN apt-get update && \
@@ -48,28 +19,6 @@ RUN apt-get update && \
 
 USER jovyan
 
-# Install Python 3 packages
-RUN conda install --quiet --yes \
-    'ipywidgets=4.1*' \
-    'pandas=0.17*' \
-    'matplotlib=1.5*' \
-    'scipy=0.17*' \
-    'seaborn=0.7*' \
-    'scikit-learn=0.17*' \
-    && conda clean -tipsy
-
-# Install Python 2 packages and kernel spec
-RUN conda create --quiet --yes -p $CONDA_DIR/envs/python2 python=2.7 \
-    'ipython=4.1*' \
-    'ipywidgets=4.1*' \
-    'pandas=0.17*' \
-    'matplotlib=1.5*' \
-    'scipy=0.17*' \
-    'seaborn=0.7*' \
-    'scikit-learn=0.17*' \
-    pyzmq \
-    && conda clean -tipsy
-
 # R packages
 RUN conda config --add channels r && \
     conda install --quiet --yes \
@@ -78,17 +27,6 @@ RUN conda config --add channels r && \
     'r-ggplot2=1.0*' \
     'r-rcurl=1.95*' && conda clean -tipsy
 
-# Toree kernel
+# Apache Toree kernel
 RUN pip install toree==0.1.0.dev4
 RUN jupyter toree install --user --kernel_name='Apache_Toree'
-
-# Install Python 2 kernel spec into the Python 3 conda environment which
-# runs the notebook server
-RUN bash -c '. activate python2 && \
-    python -m ipykernel.kernelspec --prefix=$CONDA_DIR && \
-    . deactivate'
-# Set PYSPARK_HOME in the python2 spec
-RUN jq --arg v "$CONDA_DIR/envs/python2/bin/python" \
-        '.["env"]["PYSPARK_PYTHON"]=$v' \
-        $CONDA_DIR/share/jupyter/kernels/python2/kernel.json > /tmp/kernel.json && \
-        mv /tmp/kernel.json $CONDA_DIR/share/jupyter/kernels/python2/kernel.json

pyspark-notebook/Dockerfile

@@ -36,10 +36,11 @@ RUN apt-key adv --keyserver keyserver.ubuntu.com --recv E56151BF && \
     apt-get clean && \
     rm -rf /var/lib/apt/lists/*
 
-# Spark and Mesos pointers
+# Spark and Mesos config
 ENV SPARK_HOME /usr/local/spark
 ENV PYTHONPATH $SPARK_HOME/python:$SPARK_HOME/python/lib/py4j-0.9-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
 
 USER jovyan