comparison pre_process.xml @ 36:ff2a7f89069e draft

"planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/sklearn commit 208a8d348e7c7a182cfbe1b6f17868146428a7e2"

35:f40b6759fc1d

<tool id="sklearn_data_preprocess" name="Preprocess" version="@VERSION@">
    <description>raw feature vectors into standardized datasets</description>
    <macros>
        <import>main_macros.xml</import>
    </macros>
    <expand macro="python_requirements"/>
    <expand macro="macro_stdio"/>
    <version_command>echo "@VERSION@"</version_command>
    <command>
        <![CDATA[
        python "$pre_processor_script" '$inputs'
        ]]>

            </param>
            <when value="tabular">
                <param name="infile" type="data" format="tabular" label="Select a tabular file you want to train your preprocessor on its data:" />
                <param name="header1" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolfalse" checked="false" label="Does the dataset contain header:" />
                <conditional name="column_selector_options_1">
                    <expand macro="samples_column_selector_options" multiple="true" column_option="selected_column_selector_option" col_name="col1" infile="infile"/>
                </conditional>
                <conditional name="pre_processors">
                    <expand macro="sparse_preprocessors_ext" />
                    <expand macro="sparse_preprocessor_options_ext" />
                </conditional>
            </when>
            <when value="sparse">
                <param name="infile" type="data" format="txt" label="Select a sparse representation you want to train your preprocessor on its data:"/>
                <conditional name="pre_processors">
                    <expand macro="sparse_preprocessors"/>
                    <expand macro="sparse_preprocessor_options"/>
                </conditional>
            </when>
        </conditional>
        <param name="save" type="boolean" truevalue="booltrue" falsevalue="boolflase" checked="false"
            label="Save the preprocessor"
            help="Saves the preprocessor after fitting to the data. The preprocessor can then be passed to other tools and used in later operations."/>
    </inputs>
    <outputs>
        <data format="tabular" name="outfile_transform" from_work_dir="./output"/>
        <data format="zip" name="outfile_fit">
            <filter>save</filter>
        </data>
    </outputs>
    <tests>
        <test>
            <param name="infile" value="train.tabular" ftype="tabular"/>
            <param name="selected_column_selector_option" value="all_columns"/>
            <param name="selected_input_type" value="tabular"/>
            <param name="selected_pre_processor" value="KernelCenterer"/>
            <param name="save" value="true"/>
            <output name="outfile_transform" file="prp_result01" ftype="tabular"/>
            <output name="outfile_fit" file="prp_model01" ftype="zip" compare="sim_size" delta="5"/>
        </test>
        <test>
            <param name="infile" value="train.tabular" ftype="tabular"/>
            <param name="selected_column_selector_option" value="all_columns"/>
            <param name="selected_input_type" value="tabular"/>
            <param name="selected_pre_processor" value="MinMaxScaler"/>
            <param name="save" value="true"/>
            <output name="outfile_transform" file="prp_result02" ftype="tabular"/>
            <output name="outfile_fit" file="prp_model02" ftype="zip" compare="sim_size" delta="5"/>
        </test>
        <test>
            <param name="infile" value="train.tabular" ftype="tabular"/>
            <param name="selected_column_selector_option" value="all_columns"/>
            <param name="selected_input_type" value="tabular"/>
            <param name="selected_pre_processor" value="PolynomialFeatures"/>
            <param name="save" value="true"/>
            <output name="outfile_transform" file="prp_result03" ftype="tabular"/>
            <output name="outfile_fit" file="prp_model03" ftype="zip" compare="sim_size" delta="5"/>
        </test>
        <test>
            <param name="infile" value="train.tabular" ftype="tabular"/>
            <param name="selected_column_selector_option" value="all_columns"/>
            <param name="selected_input_type" value="tabular"/>
            <param name="selected_pre_processor" value="RobustScaler"/>
            <param name="save" value="true"/>
            <output name="outfile_transform" file="prp_result04" ftype="tabular"/>
            <output name="outfile_fit" file="prp_model04" ftype="zip" compare="sim_size" delta="5"/>
        </test>
        <test>
            <param name="infile" value="csr_sparse2.mtx" ftype="txt"/>
            <param name="selected_input_type" value="sparse"/>
            <param name="selected_pre_processor" value="Binarizer"/>
            <param name="save" value="true"/>
            <output name="outfile_transform" file="prp_result05" ftype="tabular"/>
            <output name="outfile_fit" file="prp_model05" ftype="zip" compare="sim_size" delta="5"/>
        </test>
        <test>
            <param name="infile" value="train.tabular" ftype="tabular"/>
            <param name="selected_input_type" value="tabular"/>
            <param name="selected_column_selector_option" value="all_columns"/>
            <param name="selected_pre_processor" value="StandardScaler"/>
            <param name="save" value="true"/>
            <output name="outfile_transform" file="prp_result07" ftype="tabular"/>
            <output name="outfile_fit" file="prp_model07" ftype="zip" compare="sim_size" delta="5"/>
        </test>
        <test>
            <param name="infile" value="csr_sparse2.mtx" ftype="txt"/>
            <param name="selected_input_type" value="sparse"/>
            <param name="selected_pre_processor" value="MaxAbsScaler"/>
            <param name="save" value="true"/>
            <output name="outfile_transform" file="prp_result08" ftype="tabular"/>
            <output name="outfile_fit" file="prp_model08" ftype="zip" compare="sim_size" delta="5"/>
        </test>
        <test>
            <param name="infile" value="csr_sparse2.mtx" ftype="txt"/>
            <param name="selected_input_type" value="sparse"/>
            <param name="selected_pre_processor" value="Normalizer"/>
            <param name="save" value="true"/>
            <output name="outfile_transform" file="prp_result09" ftype="tabular"/>
            <output name="outfile_fit" file="prp_model09" ftype="zip" compare="sim_size" delta="5"/>
        </test>
        <test>
            <param name="infile" value="regression_X.tabular" ftype="tabular"/>
            <param name="header1" value="true"/>
            <param name="selected_column_selector_option" value="all_columns"/>
            <param name="selected_input_type" value="tabular"/>
            <param name="selected_pre_processor" value="MinMaxScaler"/>
            <param name="feature_range" value="(-1, 1)"/>
            <param name="save" value="false"/>
            <output name="outfile_transform" file="prp_result10" ftype="tabular"/>
        </test>
    </tests>
    <help>
        <![CDATA[
**What it does**

For information about preprocessing classes and parameter settings please refer to `Scikit-learn preprocessing`_.

.. _`Scikit-learn preprocessing`: http://scikit-learn.org/stable/modules/preprocessing.html
        ]]>
    </help>
    <expand macro="sklearn_citation"/>
</tool>

36:ff2a7f89069e

<tool id="sklearn_data_preprocess" name="Preprocess" version="@VERSION@" profile="20.05">
    <description>raw feature vectors into standardized datasets</description>
    <macros>
        <import>main_macros.xml</import>
    </macros>
    <expand macro="python_requirements" />
    <expand macro="macro_stdio" />
    <version_command>echo "@VERSION@"</version_command>
    <command>
        <![CDATA[
        python "$pre_processor_script" '$inputs'
        ]]>

            </param>
            <when value="tabular">
                <param name="infile" type="data" format="tabular" label="Select a tabular file you want to train your preprocessor on its data:" />
                <param name="header1" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolfalse" checked="false" label="Does the dataset contain header:" />
                <conditional name="column_selector_options_1">
                    <expand macro="samples_column_selector_options" multiple="true" column_option="selected_column_selector_option" col_name="col1" infile="infile" />
                </conditional>
                <conditional name="pre_processors">
                    <expand macro="sparse_preprocessors_ext" />
                    <expand macro="sparse_preprocessor_options_ext" />
                </conditional>
            </when>
            <when value="sparse">
                <param name="infile" type="data" format="txt" label="Select a sparse representation you want to train your preprocessor on its data:" />
                <conditional name="pre_processors">
                    <expand macro="sparse_preprocessors" />
                    <expand macro="sparse_preprocessor_options" />
                </conditional>
            </when>
        </conditional>
        <param name="save" type="boolean" truevalue="booltrue" falsevalue="boolflase" checked="false" label="Save the preprocessor" help="Saves the preprocessor after fitting to the data. The preprocessor can then be passed to other tools and used in later operations." />
    </inputs>
    <outputs>
        <data format="tabular" name="outfile_transform" from_work_dir="./output" />
        <data format="zip" name="outfile_fit">
            <filter>save</filter>
        </data>
    </outputs>
    <tests>
        <test>
            <param name="infile" value="train.tabular" ftype="tabular" />
            <param name="selected_column_selector_option" value="all_columns" />
            <param name="selected_input_type" value="tabular" />
            <param name="selected_pre_processor" value="KernelCenterer" />
            <param name="save" value="true" />
            <output name="outfile_transform" file="prp_result01" ftype="tabular" />
            <output name="outfile_fit" file="prp_model01" ftype="zip" compare="sim_size" delta="5" />
        </test>
        <test>
            <param name="infile" value="train.tabular" ftype="tabular" />
            <param name="selected_column_selector_option" value="all_columns" />
            <param name="selected_input_type" value="tabular" />
            <param name="selected_pre_processor" value="MinMaxScaler" />
            <param name="save" value="true" />
            <output name="outfile_transform" file="prp_result02" ftype="tabular" />
            <output name="outfile_fit" file="prp_model02" ftype="zip" compare="sim_size" delta="5" />
        </test>
        <test>
            <param name="infile" value="train.tabular" ftype="tabular" />
            <param name="selected_column_selector_option" value="all_columns" />
            <param name="selected_input_type" value="tabular" />
            <param name="selected_pre_processor" value="PolynomialFeatures" />
            <param name="save" value="true" />
            <output name="outfile_transform" file="prp_result03" ftype="tabular" />
            <output name="outfile_fit" file="prp_model03" ftype="zip" compare="sim_size" delta="5" />
        </test>
        <test>
            <param name="infile" value="train.tabular" ftype="tabular" />
            <param name="selected_column_selector_option" value="all_columns" />
            <param name="selected_input_type" value="tabular" />
            <param name="selected_pre_processor" value="RobustScaler" />
            <param name="save" value="true" />
            <output name="outfile_transform" file="prp_result04" ftype="tabular" />
            <output name="outfile_fit" file="prp_model04" ftype="zip" compare="sim_size" delta="5" />
        </test>
        <test>
            <param name="infile" value="csr_sparse2.mtx" ftype="txt" />
            <param name="selected_input_type" value="sparse" />
            <param name="selected_pre_processor" value="Binarizer" />
            <param name="save" value="true" />
            <output name="outfile_transform" file="prp_result05" ftype="tabular" />
            <output name="outfile_fit" file="prp_model05" ftype="zip" compare="sim_size" delta="5" />
        </test>
        <test>
            <param name="infile" value="train.tabular" ftype="tabular" />
            <param name="selected_input_type" value="tabular" />
            <param name="selected_column_selector_option" value="all_columns" />
            <param name="selected_pre_processor" value="StandardScaler" />
            <param name="save" value="true" />
            <output name="outfile_transform" file="prp_result07" ftype="tabular" />
            <output name="outfile_fit" file="prp_model07" ftype="zip" compare="sim_size" delta="5" />
        </test>
        <test>
            <param name="infile" value="csr_sparse2.mtx" ftype="txt" />
            <param name="selected_input_type" value="sparse" />
            <param name="selected_pre_processor" value="MaxAbsScaler" />
            <param name="save" value="true" />
            <output name="outfile_transform" file="prp_result08" ftype="tabular" />
            <output name="outfile_fit" file="prp_model08" ftype="zip" compare="sim_size" delta="5" />
        </test>
        <test>
            <param name="infile" value="csr_sparse2.mtx" ftype="txt" />
            <param name="selected_input_type" value="sparse" />
            <param name="selected_pre_processor" value="Normalizer" />
            <param name="save" value="true" />
            <output name="outfile_transform" file="prp_result09" ftype="tabular" />
            <output name="outfile_fit" file="prp_model09" ftype="zip" compare="sim_size" delta="5" />
        </test>
        <test>
            <param name="infile" value="regression_X.tabular" ftype="tabular" />
            <param name="header1" value="true" />
            <param name="selected_column_selector_option" value="all_columns" />
            <param name="selected_input_type" value="tabular" />
            <param name="selected_pre_processor" value="MinMaxScaler" />
            <param name="feature_range" value="(-1, 1)" />
            <param name="save" value="false" />
            <output name="outfile_transform" file="prp_result10" ftype="tabular" />
        </test>
    </tests>
    <help>
        <![CDATA[
**What it does**

For information about preprocessing classes and parameter settings please refer to `Scikit-learn preprocessing`_.

.. _`Scikit-learn preprocessing`: http://scikit-learn.org/stable/modules/preprocessing.html
        ]]>
    </help>
    <expand macro="sklearn_citation" />
</tool>