view tabpfn.xml @ 1:5112462f2dd3 draft

planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/tabpfn commit 0544107f87c3df249ecc89a64dfd390f8708b736
author bgruening
date Wed, 15 Jan 2025 20:34:13 +0000
parents 3dc3c7443c8e
children c081e5e1d7ce
line wrap: on
line source

<tool id="tabpfn" name="Tabular data prediction using TabPFN" version="@TOOL_VERSION@+galaxy@VERSION_SUFFIX@" profile="23.0">
    <description>with PyTorch</description>
    <macros>
        <token name="@TOOL_VERSION@">2.0.3</token>
        <token name="@VERSION_SUFFIX@">0</token>
    </macros>
    <creator>
        <organization name="European Galaxy Team" url="https://galaxyproject.org/eu/" />
        <person givenName="Anup" familyName="Kumar" email="kumara@informatik.uni-freiburg.de" />
        <person givenName="Frank" familyName="Hutter" email="fh@cs.uni-freiburg.de" />
    </creator>
    <requirements>
	<requirement type="package" version="@TOOL_VERSION@">tabpfn</requirement>
	<requirement type="package" version="2.2.2">pandas</requirement>
	<requirement type="package" version="3.9.2">matplotlib</requirement>
    </requirements>
    <version_command>echo "@VERSION@"</version_command>
    <command detect_errors="aggressive">
    <![CDATA[
        python '$__tool_directory__/main.py'
            --train_data '$train_data'
            --test_data '$test_data'
    ]]>
    </command>
    <inputs>
	<param name="train_data" type="data" format="tabular" label="Train data" help="Please provide training data for training model."/>
        <param name="test_data" type="data" format="tabular" label="Test data" help="Please provide test data for evaluating model."/>
    </inputs>
    <outputs>
        <data format="tabular" name="output_predicted_data" from_work_dir="output_predicted_data" label="Predicted data"></data>
        <data format="png" name="output_prec_recall_curve" from_work_dir="output_prec_recall_curve.png" label="Precision-recall curve"></data>
    </outputs>
    <tests>
        <test>
	    <param name="train_data" value="local_train_rows.tabular" ftype="tabular" />
	    <param name="test_data" value="local_test_rows.tabular" ftype="tabular" />
            <output name="output_predicted_data">
	        <assert_contents>
		    <has_n_columns n="42" />
                    <has_n_lines n="3" />
	        </assert_contents>
	    </output>
        </test>
	<test>
	    <param name="train_data" value="local_train_rows.tabular" ftype="tabular" />
	    <param name="test_data" value="local_test_rows.tabular" ftype="tabular" />
	    <output name="output_prec_recall_curve" file="pr_curve.png" compare="sim_size" />
	</test>
    </tests>
    <help>
        <![CDATA[
            **What it does**

            Classification on tabular data by TabPFN

            **Input files**
            - Training data: the training data should contain features and the last column should be the class labels. It could either be tabular or in CSV format.
            - Test data: the test data should also contain the same features as the training data and the last column should be the class labels. It could either be tabular or in CSV format.

            **Output files**
            - Predicted data along with predicted labels
        ]]>
    </help>
    <citations>
        <citation type="doi">10.1038/s41586-024-08328-6</citation>
    </citations>
</tool>