databricks_tidymodels

FROM ubuntu:18.04

RUN apt-get update \
  && apt-get -y upgrade \
  && apt-get install --yes \
    build-essential \
    openjdk-8-jdk \
    iproute2 \
    bash \
    sudo \
    coreutils \
    procps \
  && /var/lib/dpkg/info/ca-certificates-java.postinst configure \
  && apt-get clean \
  && rm -rf /var/lib/apt/lists/* /tmp/* /var/tmp/*

RUN gcc --version

# Suppress interactive configuration prompts
ENV DEBIAN_FRONTEND=noninteractive

# Install python 3.8 and virtualenv for Spark and Notebooks
RUN apt-get update \
  && apt-get install -y \
  python3.8 \
    virtualenv

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/*

RUN virtualenv -p python3.8 --system-site-packages /databricks/python3

# 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(MRAN = 'https://mran.microsoft.com/snapshot/2022-04-08', CRAN = 'https://cran.microsoft.com/')); install.packages(c('hwriter', 'TeachingDemos', 'htmltools'), lib = '/usr/lib/R/library')" \
 && R -e "install.packages('https://cran.r-project.org/src/contrib/Archive/hwriterPlus/hwriterPlus_1.0-3.tar.gz', repos=NULL, type='source', lib = '/usr/lib/R/library')"

RUN sudo apt-get update &&  apt-get install -y zlib1g-dev \
    pandoc \
    make \
    libcurl4-openssl-dev \
    libssl-dev \          
    zlib1g-dev \
    pandoc-citeproc \
    libicu-dev  \
    curl \
    libxml2-dev \
    python-six

RUN R -e "install.packages('pak')"
RUN R -e "pak::pkg_install(c( 'htmltools', 'tidyverse', 'tidymodels',  'GGally',  'fable', 'tsibble', 'ranger', 'xgboost', 'modeltime', 'timetk'), lib = '/usr/lib/R/library')"
RUN R -e "pak::pkg_install('Rserve', lib = '/databricks/spark/R/lib')"

COPY Rprofile.site /usr/lib/R/etc/Rprofile.site