hazza/docker-stacks
1
0
Fork 0
mirror of https://github.com/jupyter/docker-stacks.git synced 2025-10-17 06:52:56 +00:00
Code Issues Packages Projects Releases Wiki Activity

[Update] Spark updated to 2.1.1

Browse Source
This commit is contained in:
Pando85
2017-06-24 14:12:21 +02:00
parent d7b570a16d
commit 93683ee25f
2 changed files with 4 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
pyspark-notebook/Dockerfile
View File

@@ -7,7 +7,7 @@ MAINTAINER Jupyter Project <jupyter@googlegroups.com>
USER root
# Spark dependencies
ENV APACHE_SPARK_VERSION 2.1.0
ENV APACHE_SPARK_VERSION 2.1.1
ENV HADOOP_VERSION 2.7
# Temporarily add jessie backports to get openjdk 8, but then remove that source
@@ -19,7 +19,7 @@ RUN echo 'deb http://cdn-fastly.deb.debian.org/debian jessie-backports main' > /
rm -rf /var/lib/apt/lists/*
RUN cd /tmp && \
wget -q http://d3kbcqa49mib13.cloudfront.net/spark-${APACHE_SPARK_VERSION}-bin-hadoop${HADOOP_VERSION}.tgz && \
echo "3fc94096ae34f9a1a148d37e5ed640a7e5de1812f1f2ecd715d92bbf2901e895cf4b93e6d8ee0d64debb5df7c56d673c0a36e5fc49503ec0f4507eb0edf961a4 *spark-${APACHE_SPARK_VERSION}-bin-hadoop${HADOOP_VERSION}.tgz" | sha512sum -c - && \
echo "4b6427ca6dc6f888b21bff9f9a354260af4a0699a1f43caabf58ae6030951ee5fa8b976497aa33de7e4ae55609d47a80bfe66dfc48c79ea28e3e5b03bdaaba11 *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 && \
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

4
pyspark-notebook/README.md
View File

@@ -7,8 +7,8 @@
* Jupyter Notebook 5.0.x
* Conda Python 3.x and Python 2.7.x environments
* pyspark, pandas, matplotlib, scipy, seaborn, scikit-learn pre-installed
* Spark 2.1.0 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
* Spark 2.1.1 with Hadoop 2.7 for use in local mode or to connect to a cluster of Spark workers
* Mesos client 1.2 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