<metapackage xmlns:os="http://opensuse.org/Standards/One_Click_Install" xmlns="http://opensuse.org/Standards/One_Click_Install">
  <group>
    <repositories>
      <repository recommended="true">
        <name>devel:languages:R:autoCRAN</name>
        <summary>Large parts of CRAN (cran.r-project.org) mirrored to OBS in a fully automatic way.</summary>
        <description>This repo contains a large part of CRAN automatically converted to rpm packages.
*ALL* packages in the repo are created and kept uptodate(!) in a fully automatic way using the R package CRAN2OBS (gitlab.com/dsteuer/CRAN2OBS).
At the moment CRAN2OBS is still subject to many changes, but it already works well enough to bring about 15k packages from CRAN to Suse.
If you find packages not working, please contact me. Do not push packages here by hand after manually altering anything in a spec file, please. If you find an important package still missing, send a note, please. May be it is easy to add fitting rules to the scripts. 

Attention: there are Prefer: lines in the project config. Should be rechecked from time to time.</description>
        <url>https://download.opensuse.org/repositories/devel:/languages:/R:/autoCRAN/15.5/</url>
      </repository>
      <repository recommended="true">
        <name>deleted</name>
        <summary>INTERNAL PROJECT</summary>
        <description>don't delete this project, it's used for internal purposes</description>
        <url>https://download.opensuse.org/repositories/deleted/deleted/</url>
      </repository>
      <repository recommended="true">
        <name>openSUSE:Leap:15.5</name>
        <summary></summary>
        <description>openSUSE Leap borrows packages from SLE. The content of the build media is almost the same as Leap:15.2, but the development is drastic different. It includes the binaries (instead of the sources) directly from SLE. https://lists.opensuse.org/opensuse-factory/2020-04/msg00165.html</description>
        <url>https://download.opensuse.org/repositories/openSUSE:/Leap:/15.5/standard/</url>
      </repository>
      <repository recommended="true">
        <name>openSUSE:Backports:SLE-15-SP5</name>
        <summary>Backports project for SLE-15-SP5</summary>
        <description>Backports project for SLE-15-SP5</description>
        <url>https://download.opensuse.org/repositories/openSUSE:/Backports:/SLE-15-SP5/standard/</url>
      </repository>
      <repository recommended="true">
        <name>SUSE:SLE-15-SP5:GA</name>
        <summary></summary>
        <description></description>
        <url>https://download.opensuse.org/repositories/SUSE:/SLE-15-SP5:/GA/pool/</url>
      </repository>
      <repository recommended="true">
        <name>SUSE:SLE-15-SP4:Update</name>
        <summary>SLE 15 SP4</summary>
        <description>SLE 15 SP4</description>
        <url>https://download.opensuse.org/distribution/leap/15.5/repo/oss/</url>
      </repository>
      <repository recommended="true">
        <name>SUSE:SLE-15-SP4:GA</name>
        <summary></summary>
        <description></description>
        <url>https://download.opensuse.org/repositories/SUSE:/SLE-15-SP4:/GA/pool/</url>
      </repository>
      <repository recommended="true">
        <name>SUSE:SLE-15-SP3:Update</name>
        <summary>SLE 15 SP3</summary>
        <description>SLE 15 SP3</description>
        <url>https://download.opensuse.org/distribution/leap/15.5/repo/oss/</url>
      </repository>
      <repository recommended="true">
        <name>SUSE:SLE-15-SP3:GA</name>
        <summary></summary>
        <description></description>
        <url>https://download.opensuse.org/repositories/SUSE:/SLE-15-SP3:/GA/pool/</url>
      </repository>
      <repository recommended="true">
        <name>SUSE:SLE-15-SP2:Update</name>
        <summary>SLE 15 SP2</summary>
        <description>SLE 15 SP2</description>
        <url>https://download.opensuse.org/distribution/leap/15.5/repo/oss/</url>
      </repository>
      <repository recommended="true">
        <name>SUSE:SLE-15-SP2:GA</name>
        <summary>SLE 15 SP2</summary>
        <description>SLE 15 SP2</description>
        <url>https://download.opensuse.org/repositories/SUSE:/SLE-15-SP2:/GA/pool/</url>
      </repository>
      <repository recommended="true">
        <name>SUSE:SLE-15-SP1:Update</name>
        <summary>SLE 15 SP1</summary>
        <description>SLE 15 SP1</description>
        <url>https://download.opensuse.org/distribution/leap/15.5/repo/oss/</url>
      </repository>
      <repository recommended="true">
        <name>SUSE:SLE-15-SP1:GA</name>
        <summary>SLE 15 SP1</summary>
        <description>SLE 15 SP1</description>
        <url>https://download.opensuse.org/repositories/SUSE:/SLE-15-SP1:/GA/pool/</url>
      </repository>
      <repository recommended="true">
        <name>SUSE:SLE-15:Update</name>
        <summary>SLE 15</summary>
        <description>SLE 15</description>
        <url>https://download.opensuse.org/distribution/leap/15.5/repo/oss/</url>
      </repository>
      <repository recommended="false">
        <name>SUSE:SLE-15:GA</name>
        <summary>SLE 15</summary>
        <description>SLE 15</description>
        <url>https://download.opensuse.org/repositories/SUSE:/SLE-15:/GA/pool/</url>
      </repository>
    </repositories>
    <software>
      <item>
        <name>R-cito</name>
        <summary>Building and Training Neural Networks</summary>
        <description>The 'cito' package provides a user-friendly interface for training and
interpreting deep neural networks (DNN). 'cito' simplifies the fitting
of DNNs by supporting the familiar formula syntax, hyperparameter
tuning under cross-validation, and helps to detect and handle
convergence problems.  DNNs can be trained on CPU, GPU and MacOS GPUs.
In addition, 'cito' has many downstream functionalities such as various
explainable AI (xAI) metrics (e.g. variable importance, partial
dependence plots, accumulated local effect plots, and effect estimates)
to interpret trained DNNs. 'cito' optionally provides confidence
intervals (and p-values) for all xAI metrics and predictions. At the
same time, 'cito' is computationally efficient because it is based on
the deep learning framework 'torch'. The 'torch' package is native to
R, so no Python installation or other API is required for this package.</description>
      </item>
    </software>
  </group>
</metapackage>
