Dockerfile 1022 Bytes
Newer Older
Martin Perdacher's avatar
Martin Perdacher committed
1 2 3 4 5 6 7 8
FROM debian:latest

LABEL maintainer="Martin Perdacher <martin.perdacher@univie.ac.at>"\
      lecture="Scientific Data Management (SDM), Data Mining (DM)" \
      description="Introduction into Spark"

RUN apt-get update -y --fix-missing && apt-get install -y wget curl git bzip2 ca-certificates gnupg gnupg2 apt-transport-https  \
          libglib2.0-0 libxext6 libsm6 libxrender1 \
Martin Perdacher's avatar
Martin Perdacher committed
9
          git mercurial subversion nano\
Martin Perdacher's avatar
Martin Perdacher committed
10
          build-essential \
Martin Perdacher's avatar
Martin Perdacher committed
11
          python3-pip python-pip python3-dev
Martin Perdacher's avatar
Martin Perdacher committed
12 13

RUN pip install pyspark --no-cache-dir
Martin Perdacher's avatar
Martin Perdacher committed
14 15
RUN pip3 install --upgrade pip
RUN pip install jupyter
Martin Perdacher's avatar
Martin Perdacher committed
16 17 18 19

# SPARK requires java runtime
RUN apt-get install -y openjdk-11-jre
RUN apt-get install -y openjdk-11-jdk openjdk-11-demo openjdk-11-doc openjdk-11-jre-headless openjdk-11-source
Martin Perdacher's avatar
Martin Perdacher committed
20
ENV JAVA_HOME=/usr/lib/jvm/java-11-openjdk-amd64
Martin Perdacher's avatar
Martin Perdacher committed
21 22 23 24 25 26

# SBT for the development of code in scala or java
RUN curl -L -o sbt-1.3.4.deb http://dl.bintray.com/sbt/debian/sbt-1.3.4.deb
RUN dpkg -i sbt-1.3.4.deb
RUN rm sbt-1.3.4.deb

Martin Perdacher's avatar
Martin Perdacher committed
27 28
EXPOSE 8888

Martin Perdacher's avatar
Martin Perdacher committed
29
COPY . .