Removed r

2017-11-07 16:44:32 -08:00 · 2017-11-07 16:44:32 -08:00 · 648a05aabc
--- a/aztk/constants.py
+++ b/aztk/constants.py
@ -5,7 +5,7 @@ import os
 """
 CLI_EXE = 'aztk'

-DEFAULT_DOCKER_REPO = "jiata/aztk-vanilla:0.1.0-spark2.2.0"
+DEFAULT_DOCKER_REPO = "jiata/aztk-base:0.1.0-spark2.2.0"
 DOCKER_SPARK_CONTAINER_NAME = "spark"

 # DOCKER
--- a/config/cluster.yaml
+++ b/config/cluster.yaml
@ -15,7 +15,7 @@ size: 2
 username: spark

 # docker_repo: <name of docker image repo (for more information, see https://github.com/Azure/aztk/blob/master/docs/12-docker-image.md)>
-docker_repo: jiata/aztk:0.1.0-spark2.2.0-python3.5.4
+docker_repo: jiata/aztk-base:0.1.0-spark2.2.0

 # # optional custom scripts to run on the Spark master, Spark worker or all nodes in the cluster
 # custom_scripts: 
--- a/custom-scripts/jupyter.sh
+++ b/custom-scripts/jupyter.sh
@ -3,9 +3,9 @@
 # This custom script only works on images where jupyter is pre-installed on the Docker image
 # 
 # This custom script has been tested to work on the following docker images:
-#  - jiata/aztk-python:0.1.0-spark2.2.0-anaconda3-5.0.0 (python3.6.2)
-#  - jiata/aztk-python:0.1.0-spark2.1.0-anaconda3-5.0.0 (python3.6.2)
-#  - jiata/aztk-python:0.1.0-spark1.6.3-anaconda3-5.0.0 (python3.6.2)
+#  - jiata/aztk-python:0.1.0-spark2.2.0-python3.6.2
+#  - jiata/aztk-python:0.1.0-spark2.1.0-python3.6.2
+#  - jiata/aztk-python:0.1.0-spark1.6.3-python3.6.2

 if  [ "$IS_MASTER" = "1" ]; then

--- a/docker-image/README.md
+++ b/docker-image/README.md
@ -10,7 +10,7 @@ On top of that, we also provide two flavors of Spark images, one geared towards

 Docker Image | Image Type | User Language(s) | What's Included? 
 :-- | :-- | :-- | :-- 
-[aztk-vanilla](https://hub.docker.com/r/jiata/aztk-vanilla/) | Vanilla | Java, Scala |  `Spark`
+[aztk-base](https://hub.docker.com/r/jiata/aztk-base/) | Base | Java, Scala |  `Spark`
 [aztk-python](https://hub.docker.com/r/jiata/aztk-python/) | Pyspark | Python | `Anaconda`</br>`Jupyter Notebooks` </br> `PySpark`
 [aztk-r](https://hub.docker.com/r/jiata/aztk-r/) | SparklyR | R | `CRAN`</br>`RStudio Server`</br>`SparklyR and SparkR`

@ -22,15 +22,15 @@ Today, all the AZTK images are hosted on Docker Hub under [jiata](https://hub.do

 Docker Repo (hosted on Docker Hub) | Spark Version | Python Version | R Version 
 :-- | :-- | :-- | :-- 
-jiata/aztk-vanilla:0.1.0-spark2.2.0 __(defaul)__ | v2.2.0 | -- | -- 
-jiata/aztk-vanilla:0.1.0-spark2.1.0 | v2.1.0 | -- | -- 
-jiata/aztk-vanilla:0.1.0-spark1.6.3 | v1.6.3 | -- | -- 
+jiata/aztk-base:0.1.0-spark2.2.0 __(defaul)__ | v2.2.0 | -- | -- 
+jiata/aztk-base:0.1.0-spark2.1.0 | v2.1.0 | -- | -- 
+jiata/aztk-base:0.1.0-spark1.6.3 | v1.6.3 | -- | -- 
 jiata/aztk-python:0.1.0-spark2.2.0-anaconda3-5.0.0 | v2.2.0 | v3.6.2 | -- 
 jiata/aztk-python:0.1.0-spark2.1.0-anaconda3-5.0.0 | v2.1.0 | v3.6.2 | -- 
 jiata/aztk-python:0.1.0-spark1.6.3-anaconda3-5.0.0 | v1.6.3 | v3.6.2 | -- 
-jiata/aztk-r:0.1.0-spark2.2.0-r3.4.1 | v2.2.0 | -- | v3.4.1 
-jiata/aztk-r:0.1.0-spark2.1.0-r3.4.1 | v2.1.0 | -- | v3.4.1 
-jiata/aztk-r:0.1.0-spark1.6.3-r3.4.1 | v1.6.3 | -- | v3.4.1 
+[coming soon] jiata/aztk-r:0.1.0-spark2.2.0-r3.4.1 | v2.2.0 | -- | v3.4.1 
+[coming soon] jiata/aztk-r:0.1.0-spark2.1.0-r3.4.1 | v2.1.0 | -- | v3.4.1 
+[coming soon] jiata/aztk-r:0.1.0-spark1.6.3-r3.4.1 | v1.6.3 | -- | v3.4.1 

 If you have requests to add to the list of supported images, please file a Github issue.

--- a/docker-image/python/README.md
+++ b/docker-image/python/README.md
@ -1,7 +1,7 @@
 # Python
 This Dockerfile is used to build the __aztk-python__ Docker image used by this toolkit. This image uses Anaconda, providing access to a wide range of popular python packages.

-You can modify these Dockerfiles to build your own image. However, in mose cases, building on top of the __aztk-vanilla__ image is recommended.
+You can modify these Dockerfiles to build your own image. However, in mose cases, building on top of the __aztk-base__ image is recommended.

 NOTE: If you plan to use Jupyter Notebooks with your Spark cluster, we recommend using this image as Jupyter Notebook comes pre-installed with Anaconda. 

--- a/docker-image/python/spark2.1.0/Dockerfile
+++ b/docker-image/python/spark2.1.0/Dockerfile
@ -6,15 +6,7 @@ ARG ANACONDA_VERSION=anaconda3-5.0.0

 # install user specificed version of anaconda
 RUN pyenv install -f $ANACONDA_VERSION \
-    && pyenv global $ANACONDA_VERSION \
-    && apt-get install unzip \
-    # Fetch h2o_pysparkling 
-    && pip install http://h2o-release.s3.amazonaws.com/h2o/rel-weierstrass/7/Python/h2o-3.14.0.7-py2.py3-none-any.whl \
-    && pip install h2o_pysparkling_2.2 \
-    # Install Sparkling water 2.2.2
-    && cd /home \
-    && wget http://h2o-release.s3.amazonaws.com/sparkling-water/rel-2.2/2/sparkling-water-2.2.2.zip \
-    && unzip sparkling-water-2.2.2.zip 
+    && pyenv global $ANACONDA_VERSION 

 # set env vars
 ENV USER_PYTHON_VERSION $ANACONDA_VERSION
--- a/docker-image/python/spark2.2.0/Dockerfile
+++ b/docker-image/python/spark2.2.0/Dockerfile
@ -6,18 +6,9 @@ ARG ANACONDA_VERSION=anaconda3-5.0.0

 # install user specificed version of anaconda
 RUN pyenv install -f $ANACONDA_VERSION \
-    && pyenv global $ANACONDA_VERSION \
-    && apt-get install unzip \
-    # Fetch h2o_pysparkling 
-    && pip install http://h2o-release.s3.amazonaws.com/h2o/rel-weierstrass/7/Python/h2o-3.14.0.7-py2.py3-none-any.whl \
-    && pip install h2o_pysparkling_2.2 \
-    # Install Sparkling water 2.2.2
-    && cd /home \
-    && wget http://h2o-release.s3.amazonaws.com/sparkling-water/rel-2.2/2/sparkling-water-2.2.2.zip \
-    && unzip sparkling-water-2.2.2.zip 
+    && pyenv global $ANACONDA_VERSION 

 # set env vars
-ENV SPARKLING_WATER /home/sparkling-water-2.2.2/assembly/build/libs/sparkling-water-assembly_2.11-2.2.2-all.jar
 ENV USER_PYTHON_VERSION $ANACONDA_VERSION

 CMD ["/bin/bash"]
--- a/docker-image/r/README.md
+++ b/docker-image/r/README.md
@ -1,21 +0,0 @@
-# R
-This Dockerfile is used to build the __aztk-r__ Docker image used by this toolkit. This image uses R and RStudio Server, providing access to a wide range of popular R packages.
-
-You can modify these Dockerfiles to build your own image. However, in mose cases, building on top of the __aztk-vanilla__ image is recommended.
-
-## How to build this image
-This Dockerfile takes in two variables at build time that allow you to specify your desired Rstudio server versions and R versions: **RSTUDIO_SERVER_VERSION** and **R_VERSION**
-
-By default, we set **R_VERSION=3.4.2** and **RSTUDIO_SERVER_VERSION=1.1.383**.
-
-For example, if I wanted to use Rstudio Server v1.1.383 and R 3.2.1 with Spark v2.1.0, I would select the appropriate Dockerfile and build the image as follows:
-```sh
-# spark2.1.0/Dockerfile
-docker build \
-    --build-arg RSTUDIO_SERVER_VERSION=1.1.383 \
-    --build-arg R_VERSION=3.2.1 \
-    -t <my_image_tag> .
-```
-
-**R_VERSION** is used to set the version of R version for your cluster. 
-**RSTUDIO_SERVER_VERSION** is used to set the version of rstudio server for your cluster. 
--- a/docker-image/r/spark1.6.3/Dockerfile
+++ b/docker-image/r/spark1.6.3/Dockerfile
@ -1,150 +0,0 @@
-FROM jiata/aztk-base:0.1.0-spark1.6.3
-
-ARG R_VERSION=3.4.1
-ARG RSTUDIO_SERVER_VERSION=1.1.383
-ARG BUILD_DATE
-ENV BUILD_DATE ${BUILD_DATE:-}
-ENV R_VERSION=${R_VERSION:-3.4.2} \
-    LC_ALL=en_US.UTF-8 \
-    LANG=en_US.UTF-8 \
-    TERM=xterm
-
-ADD bootstrap.sh /bootstrap.sh
-
-RUN apt-get update \
-  && apt-get install -y --no-install-recommends \
-    bash-completion \
-    ca-certificates \
-    file \
-    fonts-texgyre \
-    g++ \
-    gfortran \
-    gsfonts \
-    libbz2-1.0 \
-    libcurl3 \
-    libopenblas-dev \
-    libpangocairo-1.0-0 \
-    libpcre3 \
-    libpng16-16 \
-    libtiff5 \
-    liblzma5 \
-    locales \
-    make \
-    unzip \
-    zip \
-    zlib1g \
-    libcurl4-openssl-dev \
-    libxml2-dev \
-    libapparmor1 \
-    gdebi-core \
-    lsb-release \
-    psmisc \
-    git \
-    libssl-dev \
-    sudo \
-    wget \
-  && echo "en_US.UTF-8 UTF-8" >> /etc/locale.gen \
-  && locale-gen en_US.utf8 \
-  && /usr/sbin/update-locale LANG=en_US.UTF-8 \
-  && BUILDDEPS="curl \
-    default-jdk \
-    libbz2-dev \
-    libcairo2-dev \
-    libcurl4-openssl-dev \
-    libpango1.0-dev \
-    libjpeg-dev \
-    libicu-dev \
-    libpcre3-dev \
-    libpng-dev \
-    libreadline-dev \
-    libtiff5-dev \
-    liblzma-dev \
-    libx11-dev \
-    libxt-dev \
-    perl \
-    tcl8.6-dev \
-    tk8.6-dev \
-    texinfo \
-    texlive-extra-utils \
-    texlive-fonts-recommended \
-    texlive-fonts-extra \
-    texlive-latex-recommended \
-    x11proto-core-dev \
-    xauth \
-    xfonts-base \
-    xvfb \
-    zlib1g-dev" \
-  && apt-get install -y --no-install-recommends $BUILDDEPS \
-  && cd tmp/ \
-  ## Download source code
-  && /bootstrap.sh ${R_VERSION} \
-  ## Extract source code
-  && tar -xf R-${R_VERSION}.tar.gz \
-  && cd R-${R_VERSION} \
-  ## Set compiler flags
-  && R_PAPERSIZE=letter \
-    R_BATCHSAVE="--no-save --no-restore" \
-    R_BROWSER=xdg-open \
-    PAGER=/usr/bin/pager \
-    PERL=/usr/bin/perl \
-    R_UNZIPCMD=/usr/bin/unzip \
-    R_ZIPCMD=/usr/bin/zip \
-    R_PRINTCMD=/usr/bin/lpr \
-    LIBnn=lib \
-    AWK=/usr/bin/awk \
-    CFLAGS="-g -O2 -fstack-protector-strong -Wformat -Werror=format-security -Wdate-time -D_FORTIFY_SOURCE=2 -g" \
-    CXXFLAGS="-g -O2 -fstack-protector-strong -Wformat -Werror=format-security -Wdate-time -D_FORTIFY_SOURCE=2 -g" \
-  ## Configure options
-  ./configure --enable-R-shlib \
-               --enable-memory-profiling \
-               --with-readline \
-               --with-blas="-lopenblas" \
-               --disable-nls \
-               --without-recommended-packages \
-  ## Build and install
-  && make \
-  && make install \
-  ## Add a default CRAN mirror
-  && echo "options(repos = c(CRAN = 'https://cran.rstudio.com/'), download.file.method = 'libcurl')" >> /usr/local/lib/R/etc/Rprofile.site \
-  ## Add a library directory (for user-installed packages)
-  && mkdir -p /usr/local/lib/R/site-library \
-  && chown root:staff /usr/local/lib/R/site-library \
-  && chmod g+wx /usr/local/lib/R/site-library \
-  ## Fix library path
-  && echo "R_LIBS_USER='/usr/local/lib/R/site-library'" >> /usr/local/lib/R/etc/Renviron \
-  && echo "R_LIBS=\${R_LIBS-'/usr/local/lib/R/site-library:/usr/local/lib/R/library:/usr/lib/R/library'}" >> /usr/local/lib/R/etc/Renviron \
-  ## install packages from date-locked MRAN snapshot of CRAN
-  && [ -z "$BUILD_DATE" ] && BUILD_DATE=$(TZ="America/Los_Angeles" date -I) || true \
-  && MRAN=https://mran.microsoft.com/snapshot/${BUILD_DATE} \
-  && echo MRAN=$MRAN >> /etc/environment \
-  && export MRAN=$MRAN \
-  && echo "options(repos = c(CRAN='$MRAN'), download.file.method = 'libcurl')" >> /usr/local/lib/R/etc/Rprofile.site \
-  ## Use littler installation scripts
-  && Rscript -e "install.packages(c('littler', 'docopt'), repo = '$MRAN')" \
-  && ln -s /usr/local/lib/R/site-library/littler/examples/install2.r /usr/local/bin/install2.r \
-  && ln -s /usr/local/lib/R/site-library/littler/examples/installGithub.r /usr/local/bin/installGithub.r \
-  && ln -s /usr/local/lib/R/site-library/littler/bin/r /usr/local/bin/r \
-  ## TEMPORARY WORKAROUND to get more robust error handling for install2.r prior to littler update
-  && curl -O /usr/local/bin/install2.r https://github.com/eddelbuettel/littler/raw/master/inst/examples/install2.r \
-  && chmod +x /usr/local/bin/install2.r \
-  ## Clean up from R source install
-  && cd / \
-  && rm -rf /tmp/* \
-  && apt-get remove --purge -y $BUILDDEPS \
-  && apt-get autoremove -y \
-  && apt-get autoclean -y \
-  && rm -rf /var/lib/apt/lists/* \
-
-## Downloading and Installing RStudio Server
-RUN Rscript -e "install.packages(c('tidyverse', 'sparklyr'))" \
-  && wget https://download2.rstudio.org/rstudio-server-$RSTUDIO_SERVER_VERSION-amd64.deb \
-  && gdebi rstudio-server-1.1.383-amd64.deb --non-interactive \
-  && echo "server-app-armor-enabled=0" | tee -a /etc/rstudio/rserver.conf \
-  && echo "Sys.setenv(SPARK_HOME ='"$SPARK_HOME"')" >> ${R_HOME}/etc/Rprofile.site \
-  ## Preparing default user for Rstudio Server
-  && set -e \
-  && useradd -m -d /home/rstudio rstudio \
-  && echo rstudio:rstudio | chpasswd
-
-CMD ["R"]
-EXPOSE 8787
--- a/docker-image/r/spark1.6.3/bootstrap.sh
+++ b/docker-image/r/spark1.6.3/bootstrap.sh
@ -1,3 +0,0 @@
-#!/bin/bash
-IFS='.' read -r -a baseVersion << $1
-curl -O https://cran.r-project.org/src/base/R-${baseVersion[0]}/R-$1.tar.gz \
--- a/docker-image/r/spark2.1.0/Dockerfile
+++ b/docker-image/r/spark2.1.0/Dockerfile
@ -1,148 +0,0 @@
-FROM jiata/aztk-base:0.1.0-spark2.1.0
-
-ARG R_VERSION=3.4.1
-ARG RSTUDIO_SERVER_VERSION=1.1.383
-ARG BUILD_DATE
-ENV BUILD_DATE ${BUILD_DATE:-}
-ENV R_VERSION=${R_VERSION:-3.4.2} \
-    LC_ALL=en_US.UTF-8 \
-    LANG=en_US.UTF-8 \
-    TERM=xterm
-
-RUN apt-get update \
-  && apt-get install -y --no-install-recommends \
-    bash-completion \
-    ca-certificates \
-    file \
-    fonts-texgyre \
-    g++ \
-    gfortran \
-    gsfonts \
-    libbz2-1.0 \
-    libcurl3 \
-    libopenblas-dev \
-    libpangocairo-1.0-0 \
-    libpcre3 \
-    libpng16-16 \
-    libtiff5 \
-    liblzma5 \
-    locales \
-    make \
-    unzip \
-    zip \
-    zlib1g \
-    libcurl4-openssl-dev \
-    libxml2-dev \
-    libapparmor1 \
-    gdebi-core \
-    lsb-release \
-    psmisc \
-    git \
-    libssl-dev \
-    sudo \
-    wget \
-  && echo "en_US.UTF-8 UTF-8" >> /etc/locale.gen \
-  && locale-gen en_US.utf8 \
-  && /usr/sbin/update-locale LANG=en_US.UTF-8 \
-  && BUILDDEPS="curl \
-    default-jdk \
-    libbz2-dev \
-    libcairo2-dev \
-    libcurl4-openssl-dev \
-    libpango1.0-dev \
-    libjpeg-dev \
-    libicu-dev \
-    libpcre3-dev \
-    libpng-dev \
-    libreadline-dev \
-    libtiff5-dev \
-    liblzma-dev \
-    libx11-dev \
-    libxt-dev \
-    perl \
-    tcl8.6-dev \
-    tk8.6-dev \
-    texinfo \
-    texlive-extra-utils \
-    texlive-fonts-recommended \
-    texlive-fonts-extra \
-    texlive-latex-recommended \
-    x11proto-core-dev \
-    xauth \
-    xfonts-base \
-    xvfb \
-    zlib1g-dev" \
-  && apt-get install -y --no-install-recommends $BUILDDEPS \
-  && cd tmp/ \
-  ## Download source code
-  && IFS='.' read -r -a baseVersion << ${R_VERSION} \
-  && curl -O https://cran.r-project.org/src/base/R-${baseVersion[0]}/R-${R_VERSION}.tar.gz \
-  ## Extract source code
-  && tar -xf R-${R_VERSION}.tar.gz \
-  && cd R-${R_VERSION} \
-  ## Set compiler flags
-  && R_PAPERSIZE=letter \
-    R_BATCHSAVE="--no-save --no-restore" \
-    R_BROWSER=xdg-open \
-    PAGER=/usr/bin/pager \
-    PERL=/usr/bin/perl \
-    R_UNZIPCMD=/usr/bin/unzip \
-    R_ZIPCMD=/usr/bin/zip \
-    R_PRINTCMD=/usr/bin/lpr \
-    LIBnn=lib \
-    AWK=/usr/bin/awk \
-    CFLAGS="-g -O2 -fstack-protector-strong -Wformat -Werror=format-security -Wdate-time -D_FORTIFY_SOURCE=2 -g" \
-    CXXFLAGS="-g -O2 -fstack-protector-strong -Wformat -Werror=format-security -Wdate-time -D_FORTIFY_SOURCE=2 -g" \
-  ## Configure options
-  ./configure --enable-R-shlib \
-               --enable-memory-profiling \
-               --with-readline \
-               --with-blas="-lopenblas" \
-               --disable-nls \
-               --without-recommended-packages \
-  ## Build and install
-  && make \
-  && make install \
-  ## Add a default CRAN mirror
-  && echo "options(repos = c(CRAN = 'https://cran.rstudio.com/'), download.file.method = 'libcurl')" >> /usr/local/lib/R/etc/Rprofile.site \
-  ## Add a library directory (for user-installed packages)
-  && mkdir -p /usr/local/lib/R/site-library \
-  && chown root:staff /usr/local/lib/R/site-library \
-  && chmod g+wx /usr/local/lib/R/site-library \
-  ## Fix library path
-  && echo "R_LIBS_USER='/usr/local/lib/R/site-library'" >> /usr/local/lib/R/etc/Renviron \
-  && echo "R_LIBS=\${R_LIBS-'/usr/local/lib/R/site-library:/usr/local/lib/R/library:/usr/lib/R/library'}" >> /usr/local/lib/R/etc/Renviron \
-  ## install packages from date-locked MRAN snapshot of CRAN
-  && [ -z "$BUILD_DATE" ] && BUILD_DATE=$(TZ="America/Los_Angeles" date -I) || true \
-  && MRAN=https://mran.microsoft.com/snapshot/${BUILD_DATE} \
-  && echo MRAN=$MRAN >> /etc/environment \
-  && export MRAN=$MRAN \
-  && echo "options(repos = c(CRAN='$MRAN'), download.file.method = 'libcurl')" >> /usr/local/lib/R/etc/Rprofile.site \
-  ## Use littler installation scripts
-  && Rscript -e "install.packages(c('littler', 'docopt'), repo = '$MRAN')" \
-  && ln -s /usr/local/lib/R/site-library/littler/examples/install2.r /usr/local/bin/install2.r \
-  && ln -s /usr/local/lib/R/site-library/littler/examples/installGithub.r /usr/local/bin/installGithub.r \
-  && ln -s /usr/local/lib/R/site-library/littler/bin/r /usr/local/bin/r \
-  ## TEMPORARY WORKAROUND to get more robust error handling for install2.r prior to littler update
-  && curl -O /usr/local/bin/install2.r https://github.com/eddelbuettel/littler/raw/master/inst/examples/install2.r \
-  && chmod +x /usr/local/bin/install2.r \
-  ## Clean up from R source install
-  && cd / \
-  && rm -rf /tmp/* \
-  && apt-get remove --purge -y $BUILDDEPS \
-  && apt-get autoremove -y \
-  && apt-get autoclean -y \
-  && rm -rf /var/lib/apt/lists/* \
-  ## Downloading and Installing RStudio Server
-  && Rscript -e "install.packages(c('tidyverse', 'sparklyr'))" \
-  && wget https://download2.rstudio.org/rstudio-server-$RSTUDIO_SERVER_VERSION-amd64.deb \
-  && gdebi rstudio-server-1.1.383-amd64.deb --non-interactive \
-  && echo "server-app-armor-enabled=0" | tee -a /etc/rstudio/rserver.conf \
-  && echo "Sys.setenv(SPARK_HOME ='"$SPARK_HOME"')" >> ${R_HOME}/etc/Rprofile.site \
-  ## Preparing default user for Rstudio Server
-  && set -e \
-  && useradd -m -d /home/rstudio rstudio \
-  && echo rstudio:rstudio | chpasswd
-
-CMD ["R"]
-EXPOSE 8787
--- a/docker-image/r/spark2.2.0/Dockerfile
+++ b/docker-image/r/spark2.2.0/Dockerfile
@ -1,148 +0,0 @@
-FROM jiata/aztk-base:0.1.0-spark2.2.0
-
-ARG R_VERSION=3.4.1
-ARG RSTUDIO_SERVER_VERSION=1.1.383
-ARG BUILD_DATE
-ENV BUILD_DATE ${BUILD_DATE:-}
-ENV R_VERSION=${R_VERSION:-3.4.2} \
-    LC_ALL=en_US.UTF-8 \
-    LANG=en_US.UTF-8 \
-    TERM=xterm
-
-RUN apt-get update \
-  && apt-get install -y --no-install-recommends \
-    bash-completion \
-    ca-certificates \
-    file \
-    fonts-texgyre \
-    g++ \
-    gfortran \
-    gsfonts \
-    libbz2-1.0 \
-    libcurl3 \
-    libopenblas-dev \
-    libpangocairo-1.0-0 \
-    libpcre3 \
-    libpng16-16 \
-    libtiff5 \
-    liblzma5 \
-    locales \
-    make \
-    unzip \
-    zip \
-    zlib1g \
-    libcurl4-openssl-dev \
-    libxml2-dev \
-    libapparmor1 \
-    gdebi-core \
-    lsb-release \
-    psmisc \
-    git \
-    libssl-dev \
-    sudo \
-    wget \
-  && echo "en_US.UTF-8 UTF-8" >> /etc/locale.gen \
-  && locale-gen en_US.utf8 \
-  && /usr/sbin/update-locale LANG=en_US.UTF-8 \
-  && BUILDDEPS="curl \
-    default-jdk \
-    libbz2-dev \
-    libcairo2-dev \
-    libcurl4-openssl-dev \
-    libpango1.0-dev \
-    libjpeg-dev \
-    libicu-dev \
-    libpcre3-dev \
-    libpng-dev \
-    libreadline-dev \
-    libtiff5-dev \
-    liblzma-dev \
-    libx11-dev \
-    libxt-dev \
-    perl \
-    tcl8.6-dev \
-    tk8.6-dev \
-    texinfo \
-    texlive-extra-utils \
-    texlive-fonts-recommended \
-    texlive-fonts-extra \
-    texlive-latex-recommended \
-    x11proto-core-dev \
-    xauth \
-    xfonts-base \
-    xvfb \
-    zlib1g-dev" \
-  && apt-get install -y --no-install-recommends $BUILDDEPS \
-  && cd tmp/ \
-  ## Download source code
-  && IFS='.' read -r -a baseVersion << ${R_VERSION} \
-  && curl -O https://cran.r-project.org/src/base/R-${baseVersion[0]}/R-${R_VERSION}.tar.gz \
-  ## Extract source code
-  && tar -xf R-${R_VERSION}.tar.gz \
-  && cd R-${R_VERSION} \
-  ## Set compiler flags
-  && R_PAPERSIZE=letter \
-    R_BATCHSAVE="--no-save --no-restore" \
-    R_BROWSER=xdg-open \
-    PAGER=/usr/bin/pager \
-    PERL=/usr/bin/perl \
-    R_UNZIPCMD=/usr/bin/unzip \
-    R_ZIPCMD=/usr/bin/zip \
-    R_PRINTCMD=/usr/bin/lpr \
-    LIBnn=lib \
-    AWK=/usr/bin/awk \
-    CFLAGS="-g -O2 -fstack-protector-strong -Wformat -Werror=format-security -Wdate-time -D_FORTIFY_SOURCE=2 -g" \
-    CXXFLAGS="-g -O2 -fstack-protector-strong -Wformat -Werror=format-security -Wdate-time -D_FORTIFY_SOURCE=2 -g" \
-  ## Configure options
-  ./configure --enable-R-shlib \
-               --enable-memory-profiling \
-               --with-readline \
-               --with-blas="-lopenblas" \
-               --disable-nls \
-               --without-recommended-packages \
-  ## Build and install
-  && make \
-  && make install \
-  ## Add a default CRAN mirror
-  && echo "options(repos = c(CRAN = 'https://cran.rstudio.com/'), download.file.method = 'libcurl')" >> /usr/local/lib/R/etc/Rprofile.site \
-  ## Add a library directory (for user-installed packages)
-  && mkdir -p /usr/local/lib/R/site-library \
-  && chown root:staff /usr/local/lib/R/site-library \
-  && chmod g+wx /usr/local/lib/R/site-library \
-  ## Fix library path
-  && echo "R_LIBS_USER='/usr/local/lib/R/site-library'" >> /usr/local/lib/R/etc/Renviron \
-  && echo "R_LIBS=\${R_LIBS-'/usr/local/lib/R/site-library:/usr/local/lib/R/library:/usr/lib/R/library'}" >> /usr/local/lib/R/etc/Renviron \
-  ## install packages from date-locked MRAN snapshot of CRAN
-  && [ -z "$BUILD_DATE" ] && BUILD_DATE=$(TZ="America/Los_Angeles" date -I) || true \
-  && MRAN=https://mran.microsoft.com/snapshot/${BUILD_DATE} \
-  && echo MRAN=$MRAN >> /etc/environment \
-  && export MRAN=$MRAN \
-  && echo "options(repos = c(CRAN='$MRAN'), download.file.method = 'libcurl')" >> /usr/local/lib/R/etc/Rprofile.site \
-  ## Use littler installation scripts
-  && Rscript -e "install.packages(c('littler', 'docopt'), repo = '$MRAN')" \
-  && ln -s /usr/local/lib/R/site-library/littler/examples/install2.r /usr/local/bin/install2.r \
-  && ln -s /usr/local/lib/R/site-library/littler/examples/installGithub.r /usr/local/bin/installGithub.r \
-  && ln -s /usr/local/lib/R/site-library/littler/bin/r /usr/local/bin/r \
-  ## TEMPORARY WORKAROUND to get more robust error handling for install2.r prior to littler update
-  && curl -O /usr/local/bin/install2.r https://github.com/eddelbuettel/littler/raw/master/inst/examples/install2.r \
-  && chmod +x /usr/local/bin/install2.r \
-  ## Clean up from R source install
-  && cd / \
-  && rm -rf /tmp/* \
-  && apt-get remove --purge -y $BUILDDEPS \
-  && apt-get autoremove -y \
-  && apt-get autoclean -y \
-  && rm -rf /var/lib/apt/lists/* \
-  ## Downloading and Installing RStudio Server
-  && Rscript -e "install.packages(c('tidyverse', 'sparklyr'))" \
-  && wget https://download2.rstudio.org/rstudio-server-$RSTUDIO_SERVER_VERSION-amd64.deb \
-  && gdebi rstudio-server-1.1.383-amd64.deb --non-interactive \
-  && echo "server-app-armor-enabled=0" | tee -a /etc/rstudio/rserver.conf \
-  && echo "Sys.setenv(SPARK_HOME ='"$SPARK_HOME"')" >> ${R_HOME}/etc/Rprofile.site \
-  ## Preparing default user for Rstudio Server
-  && set -e \
-  && useradd -m -d /home/rstudio rstudio \
-  && echo rstudio:rstudio | chpasswd
-
-CMD ["R"]
-EXPOSE 8787
--- a/docs/12-docker-image.md
+++ b/docs/12-docker-image.md
@ -1,25 +1,25 @@
 # Docker
 Azure Distributed Data Engineering Toolkit runs Spark on Docker.

-Supported Azure Distributed Data Engineering Toolkit images are hosted publicly on [Docker Hub](https://hub.docker.com/r/jiata/aztk/tags).
+Supported Azure Distributed Data Engineering Toolkit images are hosted publicly on [Docker Hub](https://hub.docker.com/r/jiata/aztk-base/tags).

 ## Versioning with Docker
-The default image that this package uses is a the __aztk-vanilla__ Docker image that comes with **Spark v2.2.0**.
+The default image that this package uses is a the __aztk-base__ Docker image that comes with **Spark v2.2.0**.

-You can use several versions of the __aztk-vanilla__ image:
- Spark 2.2.0 - jiata/aztk-vanilla:0.1.0-spark2.2.0 (default)
- Spark 2.1.0 - jiata/aztk-vanilla:0.1.0-spark2.1.0
- Spark 1.6.3 - jiata/aztk-vanilla:0.1.0-spark1.6.3
+You can use several versions of the __aztk-base__ image:
+- Spark 2.2.0 - jiata/aztk-base:0.1.0-spark2.2.0 (default)
+- Spark 2.1.0 - jiata/aztk-base:0.1.0-spark2.1.0
+- Spark 1.6.3 - jiata/aztk-base:0.1.0-spark1.6.3

 We also provide two other image types tailored for the Python and R users: __aztk-r__ and __aztk-python__. You can choose between the following:
- Anaconda3-5.0.0 (Python 3.6.2) / Spark 2.2.0 - jiata/aztk-python:0.1.0-spark2.2.0-anaconda3-5.0.0
- Anaconda3-5.0.0 (Python 3.6.2) / Spark 2.1.0 - jiata/aztk-python:0.1.0-spark2.1.0-anaconda3-5.0.0
- Anaconda3-5.0.0 (Python 3.6.2) / Spark 1.6.3 - jiata/aztk-python:0.1.0-spark1.6.3-anaconda3-5.0.0
- R 3.4.0 / Spark v2.2.0 - jiata/aztk-r:0.1.0-spark2.2.0-r3.4.0
- R 3.4.0 / Spark v2.1.0 - jiata/aztk-r:0.1.0-spark2.1.0-r3.4.0
- R 3.4.0 / Spark v1.6.3 - jiata/aztk-r:0.1.0-spark1.6.3-r3.4.0
+- Anaconda3-5.0.0 (Python 3.6.2) / Spark 2.2.0 - jiata/aztk-python:0.1.0-spark2.2.0-python3.6.2
+- Anaconda3-5.0.0 (Python 3.6.2) / Spark 2.1.0 - jiata/aztk-python:0.1.0-spark2.1.0-python3.6.2
+- Anaconda3-5.0.0 (Python 3.6.2) / Spark 1.6.3 - jiata/aztk-python:0.1.0-spark1.6.3-python3.6.2
+- [coming soon] R 3.4.0 / Spark v2.2.0 - jiata/aztk-r:0.1.0-spark2.2.0-r3.4.1
+- [coming soon] R 3.4.0 / Spark v2.1.0 - jiata/aztk-r:0.1.0-spark2.1.0-r3.4.1
+- [coming soon] R 3.4.0 / Spark v1.6.3 - jiata/aztk-r:0.1.0-spark1.6.3-r3.4.1

-*Today, these supported images are hosted on Docker Hub under the repo ["jiata/aztk-vanilla/r/python:<tag>"](https://hub.docker.com/r/jiata).*
+*Today, these supported images are hosted on Docker Hub under the repo ["jiata/aztk-base/r/python:<tag>"](https://hub.docker.com/r/jiata).*

 To select an image other than the default, you can set your Docker image at cluster creation time with the optional **--docker-repo** parameter:

@ -29,7 +29,7 @@ aztk spark cluster create ... --docker-repo <name_of_docker_image_repo>

 For example, if I am using the image version 0.1.0, and wanted to use Spark v1.6.3, I could run the following cluster create command:
 ```sh
-aztk spark cluster create ... --docker-repo jiata/aztk:0.1.0-spark1.6.3
+aztk spark cluster create ... --docker-repo jiata/aztk-base:0.1.0-spark1.6.3
 ```

 ## Using a custom Docker Image