Use Apache Toree 0.2.0dev1 for Spark 2.0.2

all-spark-notebook/Dockerfile

@@ -29,5 +29,5 @@ RUN conda config --add channels r && \
     'r-rcurl=1.95*' && conda clean -tipsy
 
 # Apache Toree kernel
-RUN pip --no-cache-dir install toree==0.1.0.dev7
+RUN pip --no-cache-dir install https://dist.apache.org/repos/dist/dev/incubator/toree/0.2.0/snapshots/dev1/toree-pip/toree-0.2.0.dev1.tar.gz
 RUN jupyter toree install --user

all-spark-notebook/README.md

@@ -11,8 +11,8 @@
 * Scala 2.10.x
 * pyspark, pandas, matplotlib, scipy, seaborn, scikit-learn pre-installed for Python
 * ggplot2, rcurl preinstalled for R
-* Spark 1.6.0 for use in local mode or to connect to a cluster of Spark workers
-* Mesos client 0.22 binary that can communicate with a Mesos master
+* Spark 2.0.2 with Hadoop 2.7 for use in local mode or to connect to a cluster of Spark workers
+* Mesos client 0.25 binary that can communicate with a Mesos master
 * Unprivileged user `jovyan` (uid=1000, configurable, see options) in group `users` (gid=100) with ownership over `/home/jovyan` and `/opt/conda`
 * [tini](https://github.com/krallin/tini) as the container entrypoint and [start-notebook.sh](../base-notebook/start-notebook.sh) as the default command
 * A [start-singleuser.sh](../base-notebook/start-singleuser.sh) script useful for running a single-user instance of the Notebook server, as required by JupyterHub
@@ -112,8 +112,8 @@ conf = pyspark.SparkConf()
 # point to mesos master or zookeeper entry (e.g., zk://10.10.10.10:2181/mesos)
 conf.setMaster("mesos://10.10.10.10:5050")
 # point to spark binary package in HDFS or on local filesystem on all slave
-# nodes (e.g., file:///opt/spark/spark-1.6.0-bin-hadoop2.6.tgz)
-conf.set("spark.executor.uri", "hdfs://10.10.10.10/spark/spark-1.6.0-bin-hadoop2.6.tgz")
+# nodes (e.g., file:///opt/spark/spark-2.0.2-bin-hadoop2.7.tgz)
+conf.set("spark.executor.uri", "hdfs://10.10.10.10/spark/spark-2.0.2-bin-hadoop2.7.tgz")
 # set other options as desired
 conf.set("spark.executor.memory", "8g")
 conf.set("spark.core.connection.ack.wait.timeout", "1200")
@@ -145,10 +145,10 @@ library(SparkR)
 # point to mesos master or zookeeper entry (e.g., zk://10.10.10.10:2181/mesos)\
 # as the first argument
 # point to spark binary package in HDFS or on local filesystem on all slave
-# nodes (e.g., file:///opt/spark/spark-1.6.0-bin-hadoop2.6.tgz) in sparkEnvir
+# nodes (e.g., file:///opt/spark/spark-2.0.2-bin-hadoop2.7.tgz) in sparkEnvir
 # set other options in sparkEnvir
 sc <- sparkR.init("mesos://10.10.10.10:5050", sparkEnvir=list(
-    spark.executor.uri="hdfs://10.10.10.10/spark/spark-1.6.0-bin-hadoop2.6.tgz",
+    spark.executor.uri="hdfs://10.10.10.10/spark/spark-2.0.2-bin-hadoop2.7.tgz",
     spark.executor.memory="8g"
     )
 )
@@ -172,7 +172,7 @@ The Apache Toree kernel automatically creates a `SparkContext` when it starts ba
 For instance, to pass information about a Mesos master, Spark binary location in HDFS, and an executor options, you could start the container like so:
 
 `docker run -d -p 8888:8888 -e SPARK_OPTS '--master=mesos://10.10.10.10:5050 \
-    --spark.executor.uri=hdfs://10.10.10.10/spark/spark-1.6.0-bin-hadoop2.6.tgz \
+    --spark.executor.uri=hdfs://10.10.10.10/spark/spark-2.0.2-bin-hadoop2.7.tgz \
     --spark.executor.memory=8g' jupyter/all-spark-notebook`
 
 Note that this is the same information expressed in a notebook in the Python case above. Once the kernel spec has your cluster information, you can test your cluster in an Apache Toree notebook like so:

pyspark-notebook/Dockerfile

@@ -7,39 +7,36 @@ MAINTAINER Jupyter Project <jupyter@googlegroups.com>
 USER root
 
 # Spark dependencies
-ENV APACHE_SPARK_VERSION 2.0.0
+ENV APACHE_SPARK_VERSION 2.0.2
+ENV HADOOP_VERSION 2.7
 
 # Temporarily add jessie backports to get openjdk 8, but then remove that source
-RUN echo 'deb http://ftp.debian.org/debian jessie-backports main' > /etc/apt/sources.list.d/jessie-backports.list && \
+RUN echo 'deb http://cdn-fastly.deb.debian.org/debian jessie-backports main' > /etc/apt/sources.list.d/jessie-backports.list && \
     apt-get -y update && \
     apt-get install -y --no-install-recommends openjdk-8-jre-headless && \
     rm /etc/apt/sources.list.d/jessie-backports.list && \
     apt-get clean && \
     rm -rf /var/lib/apt/lists/*
 RUN cd /tmp && \
-        wget -q http://d3kbcqa49mib13.cloudfront.net/spark-${APACHE_SPARK_VERSION}-bin-hadoop2.6.tgz && \
-        echo "e17d9da4b3ac463ea3ce42289f2a71cefb479d154b1ffd00310c7d7ab207aa2c *spark-${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-${APACHE_SPARK_VERSION}-bin-hadoop2.6 spark
+        wget -q http://d3kbcqa49mib13.cloudfront.net/spark-${APACHE_SPARK_VERSION}-bin-hadoop${HADOOP_VERSION}.tgz && \
+        echo "e6349dd38ded84831e3ff7d391ae7f2525c359fb452b0fc32ee2ab637673552a *spark-${APACHE_SPARK_VERSION}-bin-hadoop${HADOOP_VERSION}.tgz" | sha256sum -c - && \
+        tar xzf spark-${APACHE_SPARK_VERSION}-bin-hadoop${HADOOP_VERSION}.tgz -C /usr/local && \
+        rm spark-${APACHE_SPARK_VERSION}-bin-hadoop${HADOOP_VERSION}.tgz
+RUN cd /usr/local && ln -s spark-${APACHE_SPARK_VERSION}-bin-hadoop${HADOOP_VERSION} spark
 
 # Mesos dependencies
-# Currently, Mesos is not available from Debian Jessie.
-# So, we are installing it from Debian Wheezy. Once it
-# becomes available for Debian Jessie. We should switch
-# over to using that instead.
 RUN apt-key adv --keyserver keyserver.ubuntu.com --recv E56151BF && \
     DISTRO=debian && \
-    CODENAME=wheezy && \
+    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=0.22.1-1.0.debian78 && \
+    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 config
 ENV SPARK_HOME /usr/local/spark
-ENV PYTHONPATH $SPARK_HOME/python:$SPARK_HOME/python/lib/py4j-0.10.1-src.zip
+ENV PYTHONPATH $SPARK_HOME/python:$SPARK_HOME/python/lib/py4j-0.10.3-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
 

pyspark-notebook/README.md

@@ -7,8 +7,8 @@
 * Jupyter Notebook 4.2.x
 * Conda Python 3.x and Python 2.7.x environments
 * pyspark, pandas, matplotlib, scipy, seaborn, scikit-learn pre-installed
-* Spark 1.6.0 for use in local mode or to connect to a cluster of Spark workers
-* Mesos client 0.22 binary that can communicate with a Mesos master
+* Spark 2.0.2 with Hadoop 2.7 for use in local mode or to connect to a cluster of Spark workers
+* Mesos client 0.25 binary that can communicate with a Mesos master
 * Unprivileged user `jovyan` (uid=1000, configurable, see options) in group `users` (gid=100) with ownership over `/home/jovyan` and `/opt/conda`
 * [tini](https://github.com/krallin/tini) as the container entrypoint and [start-notebook.sh](../base-notebook/start-notebook.sh) as the default command
 * A [start-singleuser.sh](../base-notebook/start-singleuser.sh) script useful for running a single-user instance of the Notebook server, as required by JupyterHub
@@ -68,8 +68,8 @@ conf = pyspark.SparkConf()
 # point to mesos master or zookeeper entry (e.g., zk://10.10.10.10:2181/mesos)
 conf.setMaster("mesos://10.10.10.10:5050")
 # point to spark binary package in HDFS or on local filesystem on all slave
-# nodes (e.g., file:///opt/spark/spark-1.6.0-bin-hadoop2.6.tgz)
-conf.set("spark.executor.uri", "hdfs://10.122.193.209/spark/spark-1.6.0-bin-hadoop2.6.tgz")
+# nodes (e.g., file:///opt/spark/spark-2.0.2-bin-hadoop2.7.tgz)
+conf.set("spark.executor.uri", "hdfs://10.122.193.209/spark/spark-2.0.2-bin-hadoop2.7.tgz")
 # set other options as desired
 conf.set("spark.executor.memory", "8g")
 conf.set("spark.core.connection.ack.wait.timeout", "1200")