Install numpy on all spark images

This commit is contained in:
Matthew Farrellee 2015-11-20 16:05:47 -05:00
parent fc8f5672cb
commit fb4afda2bf

View File

@ -26,6 +26,13 @@ RUN mkdir -p /opt && \
# Add the GCS connector.
RUN wget -O /opt/spark/lib/gcs-connector-latest-hadoop2.jar https://storage.googleapis.com/hadoop-lib/gcs/gcs-connector-latest-hadoop2.jar
# if numpy is installed on a driver it needs to be installed on all
# workers, so install it everywhere
RUN apt-get update && \
apt-get install -y python-numpy && \
apt-get clean && \
rm -rf /var/lib/apt/lists/*
ADD log4j.properties /opt/spark/conf/log4j.properties
ADD start-common.sh /
ADD core-site.xml /opt/spark/conf/core-site.xml