comparison ensemble.xml @ 22:2e69c6ca6e91 draft

planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/sklearn commit c64ccc5850c8e061a95fb64e07ed388384e82393

21:9ce3e347506c

            <param name="infile_model" value="gbc_model01" ftype="zip"/>
            <param name="infile_data" value="test.tabular" ftype="tabular"/>
            <param name="selected_task" value="load"/>
            <output name="outfile_predict" file="gbc_result01" compare="sim_size" delta="500"/>
        </test>
    </tests>
    <help><![CDATA[
***What it does***
The goal of ensemble methods is to combine the predictions of several base estimators built with a given learning algorithm in order to improve generalizability / robustness over a single estimator. This tool offers two sets of ensemble algorithms for classification and regression: random forests and ADA boosting which are based on sklearn.ensemble library from Scikit-learn. Here you can find out about the input, output and methods presented in the tools. For information about ensemble methods and parameters settings please refer to `Scikit-learn ensemble`_.

22:2e69c6ca6e91

            <param name="infile_model" value="gbc_model01" ftype="zip"/>
            <param name="infile_data" value="test.tabular" ftype="tabular"/>
            <param name="selected_task" value="load"/>
            <output name="outfile_predict" file="gbc_result01" compare="sim_size" delta="500"/>
        </test>
        <test>
            <param name="infile1" value="train.tabular" ftype="tabular"/>
            <param name="infile2" value="train.tabular" ftype="tabular"/>
            <param name="col1" value="1,2,3,4"/>
            <param name="col2" value="5"/>
            <param name="selected_task" value="train"/>
            <param name="selected_algorithm" value="AdaBoostClassifier"/>
            <param name="random_state" value="10"/>
            <output name="outfile_fit" file="abc_model01" compare="sim_size" delta="500"/>
        </test>
        <test>
            <param name="infile_model" value="abc_model01" ftype="zip"/>
            <param name="infile_data" value="test.tabular" ftype="tabular"/>
            <param name="selected_task" value="load"/>
            <output name="outfile_predict" file="abc_result01" compare="sim_size" delta="500"/>
        </test>
        <test>
            <param name="infile1" value="regression_train.tabular" ftype="tabular"/>
            <param name="infile2" value="regression_train.tabular" ftype="tabular"/>
            <param name="col1" value="1,2,3,4,5"/>
            <param name="col2" value="6"/>
            <param name="selected_task" value="train"/>
            <param name="selected_algorithm" value="AdaBoostRegressor"/>
            <param name="random_state" value="10"/>
            <output name="outfile_fit" file="abr_model01" compare="sim_size" delta="500"/>
        </test>
        <test>
            <param name="infile_model" value="abr_model01" ftype="zip"/>
            <param name="infile_data" value="regression_test.tabular" ftype="tabular"/>
            <param name="selected_task" value="load"/>
            <output name="outfile_predict" file="abr_result01" compare="sim_size" delta="500"/>
        </test>
    </tests>
    <help><![CDATA[
***What it does***
The goal of ensemble methods is to combine the predictions of several base estimators built with a given learning algorithm in order to improve generalizability / robustness over a single estimator. This tool offers two sets of ensemble algorithms for classification and regression: random forests and ADA boosting which are based on sklearn.ensemble library from Scikit-learn. Here you can find out about the input, output and methods presented in the tools. For information about ensemble methods and parameters settings please refer to `Scikit-learn ensemble`_.