Skip to content
This repository was archived by the owner on Jan 3, 2023. It is now read-only.
Open
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
18 changes: 9 additions & 9 deletions elephantscale/docker/Dockerfile
Original file line number Diff line number Diff line change
@@ -1,7 +1,7 @@
## pick a specific version, to ensure predictability
FROM jupyter/pyspark-notebook@sha256:64420e4c348ab48fb806f42332109cbc205ae74cda67240c3e0974c5f7e6e969
FROM jupyter/pyspark-notebook@sha256:f5f1b391d3f6e94ae864690db1c5e0e9ffecf2f4a0a00f09c01c3e3a9230638e
## or latest
#FROM jupyter/pyspark-notebook@latest
#FROM jupyter/pyspark-notebook:latest

MAINTAINER Elephant Scale <[email protected]>

Expand All @@ -13,10 +13,9 @@ ARG SBT_VERSION=1.0.2
ARG INSTALL_DIR=/usr/local
ENV BIGDL_HOME ${INSTALL_DIR}/BigDL

#ARG BIGDL_URL=https://s3.amazonaws.com/elephantscale-public/BigDL/BigDL.zip
## Download BigDL from release page
## https://bigdl-project.github.io/0.3.0/#release-download/
ARG BIGDL_URL=https://repo1.maven.org/maven2/com/intel/analytics/bigdl/dist-spark-${SPARK_VERSION}-scala-2.11.8-linux64/0.3.0/dist-spark-${SPARK_VERSION}-scala-2.11.8-linux64-0.3.0-dist.zip
## https://repo1.maven.org/maven2/com/intel/analytics/bigdl/
ARG BIGDL_URL=https://repo1.maven.org/maven2/com/intel/analytics/bigdl/dist-spark-2.2.0-scala-2.11.8-all/0.4.0/dist-spark-2.2.0-scala-2.11.8-all-0.4.0-dist.zip
## --- end CONFIG

USER root
Expand All @@ -30,7 +29,7 @@ RUN apt-get install -yq --no-install-recommends \
atop \
curl \
less \
openjdk-8-jdk-headless \
openjdk-8-jdk \
rsync \
unzip \
wget \
Expand Down Expand Up @@ -76,6 +75,7 @@ RUN apt-get clean && \
rm -rf /var/lib/apt/lists/*

## ----- install BigDL
RUN echo "BIGDL_URL=$BIGDL_URL"
RUN \
mkdir -p ${BIGDL_HOME} && \
cd ${BIGDL_HOME} && \
Expand All @@ -96,15 +96,15 @@ RUN mkdir /work
USER $NB_USER

## update conda
# RUN conda update --all
#RUN conda update --all
## install NLTK
RUN conda install -y nltk

## python 3.5 env
RUN conda create -y -n py35 python=3.5 numpy scipy pandas scikit-learn matplotlib seaborn jupyter nltk tensorflow opencv pillow
RUN conda create -y -n py35 python=3.5 numpy scipy pandas scikit-learn matplotlib seaborn jupyter nltk opencv pillow tensorflow

## python 2.7 env
RUN conda create -y -n py27 python=2.7 numpy scipy pandas scikit-learn matplotlib seaborn jupyter nltk tensorflow opencv pillow
RUN conda create -y -n py27 python=2.7 numpy scipy pandas scikit-learn matplotlib seaborn jupyter nltk opencv pillow tensorflow

# list envs
RUN conda info -e
Expand Down
8 changes: 2 additions & 6 deletions elephantscale/run-bigdl-docker.sh
Original file line number Diff line number Diff line change
Expand Up @@ -3,7 +3,7 @@
## Usage
# ./run-bigdl-docker.sh <image name> [optional command]
#
# ./run-bigdl-docker.sh xxx/yyy
# ./run-bigdl-docker.sh elephantscale/bigdl-sandbox
#
# or during developing, give a local docker image id
# ./run-bigdl-docker.sh abcd1234
Expand All @@ -19,16 +19,12 @@ fi

image_id="$1"
cmd="$2"
name="bigdl"

## remove any previously running containers
docker rm -f "$name"

# mount the current directory at /work
this="${BASH_SOURCE-$0}"
mydir=$(cd -P -- "$(dirname -- "$this")" && pwd -P)

docker run -it --name "$name" \
docker run -it \
-p 8888:8888 \
-p 6006:6006 \
-v"$mydir:/work" \
Expand Down