Dockerfile

FROM databricksruntime/minimal:experimental

# Suppress interactive configuration prompts
ENV DEBIAN_FRONTEND=noninteractive

# Install python 3.10 and virtualenv for Spark and Notebooks
RUN apt-get update \
  && apt-get install -y \
    python3.10 \
    virtualenv

# We add RStudio's debian source to install the latest r-base version (4.1)
# We are using the more secure long form of pgp key ID of marutter@gmail.com
# based on these instructions (avoiding firewall issue for some users):
# https://cran.rstudio.com/bin/linux/ubuntu/#secure-apt
RUN apt-get update \
  && apt-get install --yes software-properties-common apt-transport-https \
  && gpg --keyserver hkp://keyserver.ubuntu.com:80 --recv-keys E298A3A825C0D65DFD57CBB651716619E084DAB9 \
  && gpg -a --export E298A3A825C0D65DFD57CBB651716619E084DAB9 | sudo apt-key add - \
  && add-apt-repository -y "deb [arch=amd64,i386] https://cran.rstudio.com/bin/linux/ubuntu $(lsb_release -cs)-cran40/" \
  && apt-get update \
  && apt-get install --yes \
    libssl-dev \
    r-base \
    r-base-dev \
  && add-apt-repository -r "deb [arch=amd64,i386] https://cran.rstudio.com/bin/linux/ubuntu $(lsb_release -cs)-cran40/" \
  && apt-key del E298A3A825C0D65DFD57CBB651716619E084DAB9 \
  && apt-get clean \
  && rm -rf /var/lib/apt/lists/* /tmp/* /var/tmp/*

# hwriterPlus is used by Databricks to display output in notebook cells
# hwriterPlus is removed for newer version of R, so we hardcode the dependency to archived version
# Rserve allows Spark to communicate with a local R process to run R code
RUN R -e "options(repos = list(CRAN = 'https://packagemanager.posit.co/cran/latest')); install.packages(c('hwriter', 'TeachingDemos', 'htmltools'))" \
 && R -e "install.packages('https://cran.r-project.org/src/contrib/Archive/hwriterPlus/hwriterPlus_1.0-3.tar.gz', repos=NULL, type='source')" \
 && R -e "install.packages('Rserve', repos='http://rforge.net/')"

# Additional instructions to setup rstudio. If you dont need rstudio, you can 
# omit the below commands in your docker file. Even after this you need to use
# an init script to start the RStudio daemon (See README.md for details.)

# Databricks configuration for RStudio sessions.
COPY Rprofile.site /usr/lib/R/etc/Rprofile.site

# Rstudio installation.
RUN apt-get update \
 # Install gdebi-core.
 && apt-get install -y gdebi-core \
 # Download rstudio and install it.
 && apt-get install -y wget \
 && apt-get install -y gdebi-core \
 && wget https://download2.rstudio.org/server/jammy/amd64/rstudio-server-2022.12.0-353-amd64.deb \
 && gdebi -n rstudio-server-2022.12.0-353-amd64.deb && rstudio-server version

# Initialize the default environment that Spark and notebooks will use
RUN virtualenv -p python3.10 --system-site-packages /databricks/python3