comparison stacking_ensembles.xml @ 2:22560cf810b8 draft

planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/sklearn commit 60f0fbc0eafd7c11bc60fb6c77f2937782efd8a9-dirty

1:6717e5cc4d05

<tool id="sklearn_stacking_ensemble_models" name="Stacking Ensemble Models" version="0.1.0">
    <description>builds a strong model by stacking multiple algorithms</description>
    <macros>
        <import>main_macros.xml</import>
    </macros>
    <expand macro="python_requirements"/>
    <expand macro="macro_stdio"/>
    <version_command>echo "$version"</version_command>
    <command>
        <![CDATA[
        #for $i, $base in enumerate($base_est_builder)
        #if $i == 0
            #if $base.estimator_selector.selected_module == 'custom_estimator'

        #end for
        python '$__tool_directory__/stacking_ensembles.py'
            --inputs '$inputs'
            --outfile '$outfile'
            --bases "\$bases"
            #if $meta_estimator.estimator_selector.selected_module == 'custom_estimator'
            --meta '${meta_estimator.estimator_selector.c_estimator}'
            #end if
            #if $get_params
            --outfile_params '$outfile_params'
            #end if
        ]]>

        <inputs name="inputs" />
    </configfiles>
    <inputs>
        <conditional name="algo_selection">
            <param name="estimator_type" type="select" label="Choose the stacking ensemble type">
                <option value="StackingCVClassifier" selected="true">classification -- StackingCVClassifier</option>
                <option value="StackingClassifier">classification -- StackingClassifier</option>
                <option value="StackingCVRegressor">regression -- StackingCVRegressor</option>
                <option value="StackingRegressor">regression -- StackingRegressor</option>
            </param>
            <when value="StackingCVClassifier">
                <expand macro="stacking_ensemble_inputs">
                    <expand macro="cv_reduced"/>
                    <expand macro="shuffle" label="shuffle"/>
                    <expand macro="random_state" default_value="" help_text="Integer number. The seed of the pseudo random number generator to use when shuffling the data."/>
                    <param argument="use_probas" type="boolean" truevalue="booltrue" falsevalue="boolfalse" checked="false"/>
                </expand>
            </when>
            <when value="StackingClassifier">
                <expand macro="stacking_ensemble_inputs">
                    <param argument="use_probas" type="boolean" truevalue="booltrue" falsevalue="boolfalse" checked="false"/>
                    <param argument="average_probas" type="boolean" truevalue="booltrue" falsevalue="boolfalse" checked="false"/>
                </expand>
            </when>
            <when value="StackingCVRegressor">
                <expand macro="stacking_ensemble_inputs">
                    <expand macro="cv_reduced"/>
                    <!--TODO support group splitters. Hint: `groups` is a fit_param-->
                    <expand macro="shuffle" label="shuffle"/>
                    <expand macro="random_state" default_value="" help_text="Integer number. The seed of the pseudo random number generator to use when shuffling the data."/>
                    <param argument="refit" type="boolean" truevalue="booltrue" falsevalue="boolfalse" checked="true"/>
                </expand>
            </when>
            <when value="StackingRegressor">
                <expand macro="stacking_ensemble_inputs">
                    <param argument="refit" type="boolean" truevalue="booltrue" falsevalue="boolfalse" checked="true"/>
                </expand>
            </when>
        </conditional>
        <repeat name="base_est_builder" min="1" max="20" title="Base Estimator">
            <expand macro="stacking_base_estimator"/>
            <!--param name="base_estimator" type="data" format="zip,json" label="Select the dataset containing base estimator" help="One estimator at a time."/-->
        </repeat>
        <!--param name="meta_estimator" type="data" format="zip,json" label="Select the dataset containing the Meta estimator"/-->
        <section name="meta_estimator" title="Meta Estimator" expanded="true">
            <expand macro="stacking_base_estimator"/>
        </section>
        <param name="get_params" type="boolean" truevalue="booltrue" falsevalue="boolfalse" checked="true" label="Output parameters for searchCV?"
                help="Optional. Tunable parameters could be obtained through `estimator_attributes` tool."/>
    </inputs>
    <outputs>
        <data format="zip" name="outfile" label="${algo_selection.estimator_type} on ${on_string}"/>

        </data>
    </outputs>
    <tests>
        <test>
            <conditional name="algo_selection">
                <param name="estimator_type" value="StackingCVRegressor"/>
            </conditional>
            <repeat name="base_est_builder">
                <conditional name="estimator_selector">
                    <param name="selected_module" value="custom_estimator"/>
                    <param name="c_estimator" value="RandomForestRegressor01.zip" ftype="zip"/>

                <conditional name="estimator_selector">
                    <param name="selected_module" value="custom_estimator"/>
                    <param name="c_estimator" value="XGBRegressor01.zip" ftype="zip"/>
                </conditional>
            </repeat>
            <section name="meta_estimator">
                <conditional name="estimator_selector">
                    <param name="selected_module" value="custom_estimator"/>
                    <param name="c_estimator" value="LinearRegression01.zip" ftype="zip"/>
                </conditional>
            </section>
            <param name="get_params" value="false"/>
            <output name="outfile" file="StackingCVRegressor01.zip" compare="sim_size" delta="5"/>
        </test>
        <test>
            <conditional name="algo_selection">
                <param name="estimator_type" value="StackingCVRegressor"/>
            </conditional>
            <repeat name="base_est_builder">
                <conditional name="estimator_selector">
                    <param name="selected_module" value="custom_estimator"/>
                    <param name="c_estimator" value="RandomForestRegressor01.zip" ftype="zip"/>

                <conditional name="estimator_selector">
                    <param name="selected_module" value="xgboost"/>
                    <param name="selected_estimator" value="XGBRegressor"/>
                </conditional>
            </repeat>
            <section name="meta_estimator">
                <conditional name="estimator_selector">
                    <param name="selected_module" value="svm"/>
                    <param name="selected_estimator" value="SVR"/>
                </conditional>
            </section>
            <param name="get_params" value="false"/>
            <output name="outfile" file="StackingCVRegressor02.zip" compare="sim_size" delta="5"/>
        </test>
    </tests>
    <help>
        <![CDATA[
This tool wrapps Stacking Regression, also called Super Learning, in which different base algorithms train

2:22560cf810b8

<tool id="sklearn_stacking_ensemble_models" name="Stacking Ensemble Models" version="@ENSEMBLE_VERSION@">
    <description>builds a strong model by stacking multiple algorithms</description>
    <macros>
        <import>main_macros.xml</import>
    </macros>
    <expand macro="python_requirements"/>
    <expand macro="macro_stdio"/>
    <version_command>echo "$ENSEMBLE_VERSION"</version_command>
    <command>
        <![CDATA[
        #for $i, $base in enumerate($base_est_builder)
        #if $i == 0
            #if $base.estimator_selector.selected_module == 'custom_estimator'

        #end for
        python '$__tool_directory__/stacking_ensembles.py'
            --inputs '$inputs'
            --outfile '$outfile'
            --bases "\$bases"
            #if $algo_selection.estimator_type not in ('sklearn.ensemble_VotingClassifier', 'sklearn.ensemble_VotingRegressor')
            #if $algo_selection.meta_estimator.estimator_selector.selected_module == 'custom_estimator'
            --meta '${algo_selection.meta_estimator.estimator_selector.c_estimator}'
            #end if
            #end if
            #if $get_params
            --outfile_params '$outfile_params'
            #end if
        ]]>

        <inputs name="inputs" />
    </configfiles>
    <inputs>
        <conditional name="algo_selection">
            <param name="estimator_type" type="select" label="Choose the stacking ensemble type">
                <option value="sklearn.ensemble_VotingClassifier" selected="true">sklearn.ensemble -- VotingClassifier</option>
                <option value="sklearn.ensemble_VotingRegressor">sklearn.ensemble -- VotingRegressor</option>
                <option value="mlxtend.classifier_StackingCVClassifier">mlxtend.classifier -- StackingCVClassifier</option>
                <option value="mlxtend.classifier_StackingClassifier">mlxtend.classifier -- StackingClassifier</option>
                <option value="mlxtend.regressor_StackingCVRegressor">mlxtend.regressor -- StackingCVRegressor</option>
                <option value="mlxtend.regressor_StackingRegressor">mlxtend.regressor -- StackingRegressor</option>
            </param>
            <when value="sklearn.ensemble_VotingClassifier">
                <expand macro="stacking_voting_weights">
                    <param argument="voting" type="select" help="If ‘hard’, uses predicted class labels for majority rule voting. Else if ‘soft’, predicts the class label based on the argmax of the sums of the predicted probabilities, which is recommended for an ensemble of well-calibrated classifiers.">
                        <option value="hard" selected="true">hard</option>
                        <option value="soft">soft</option>
                    </param>
                    <param argument="flatten_transform" type="boolean" truevalue="booltrue" falsevalue="boolfalse" checked="true" help=""/>
                </expand>
            </when>
            <when value="sklearn.ensemble_VotingRegressor">
                <expand macro="stacking_voting_weights"/>
            </when>
            <when value="mlxtend.classifier_StackingCVClassifier">
                <expand macro="stacking_ensemble_inputs">
                    <expand macro="cv_reduced"/>
                    <expand macro="shuffle" label="shuffle"/>
                    <expand macro="random_state" default_value="" help_text="Integer number. The seed of the pseudo random number generator to use when shuffling the data."/>
                    <param argument="use_probas" type="boolean" truevalue="booltrue" falsevalue="boolfalse" checked="false"/>
                </expand>
                <section name="meta_estimator" title="Meta Estimator" expanded="true">
                    <expand macro="stacking_base_estimator"/>
                </section>
            </when>
            <when value="mlxtend.classifier_StackingClassifier">
                <expand macro="stacking_ensemble_inputs">
                    <param argument="use_probas" type="boolean" truevalue="booltrue" falsevalue="boolfalse" checked="false"/>
                    <param argument="average_probas" type="boolean" truevalue="booltrue" falsevalue="boolfalse" checked="false"/>
                </expand>
                <section name="meta_estimator" title="Meta Estimator" expanded="true">
                    <expand macro="stacking_base_estimator"/>
                </section>
            </when>
            <when value="mlxtend.regressor_StackingCVRegressor">
                <expand macro="stacking_ensemble_inputs">
                    <expand macro="cv_reduced"/>
                    <!--TODO support group splitters. Hint: `groups` is a fit_param-->
                    <expand macro="shuffle" label="shuffle"/>
                    <expand macro="random_state" default_value="" help_text="Integer number. The seed of the pseudo random number generator to use when shuffling the data."/>
                    <param argument="refit" type="boolean" truevalue="booltrue" falsevalue="boolfalse" checked="true"/>
                </expand>
                <section name="meta_estimator" title="Meta Estimator" expanded="true">
                    <expand macro="stacking_base_estimator"/>
                </section>
            </when>
            <when value="mlxtend.regressor_StackingRegressor">
                <expand macro="stacking_ensemble_inputs">
                    <param argument="refit" type="boolean" truevalue="booltrue" falsevalue="boolfalse" checked="true"/>
                </expand>
                <section name="meta_estimator" title="Meta Estimator" expanded="true">
                    <expand macro="stacking_base_estimator"/>
                </section>
            </when>
        </conditional>
        <repeat name="base_est_builder" min="1" max="20" title="Base Estimator">
            <expand macro="stacking_base_estimator"/>
            <!--param name="base_estimator" type="data" format="zip,json" label="Select the dataset containing base estimator" help="One estimator at a time."/-->
        </repeat>
        <!--param name="meta_estimator" type="data" format="zip,json" label="Select the dataset containing the Meta estimator"/-->
        <param name="get_params" type="boolean" truevalue="booltrue" falsevalue="boolfalse" checked="true" label="Output parameters for searchCV?"
                help="Optional. Tunable parameters could be obtained through `estimator_attributes` tool."/>
    </inputs>
    <outputs>
        <data format="zip" name="outfile" label="${algo_selection.estimator_type} on ${on_string}"/>

        </data>
    </outputs>
    <tests>
        <test>
            <conditional name="algo_selection">
                <param name="estimator_type" value="sklearn.ensemble_VotingClassifier"/>
                <section name="options">
                    <param name="weights" value="[1, 2]"/>
                </section>
            </conditional>
            <repeat name="base_est_builder">
                <conditional name="estimator_selector">
                    <param name="selected_module" value="svm"/>
                    <param name="selected_estimator" value="SVC"/>
                </conditional>
            </repeat>
            <repeat name="base_est_builder">
                <conditional name="estimator_selector">
                    <param name="selected_module" value="xgboost"/>
                    <param name="selected_estimator" value="XGBClassifier"/>
                </conditional>
            </repeat>
            <param name="get_params" value="false"/>
            <output name="outfile" file="StackingVoting03.zip" compare="sim_size" delta="5"/>
        </test>
        <test>
            <conditional name="algo_selection">
                <param name="estimator_type" value="mlxtend.regressor_StackingCVRegressor"/>
                <section name="meta_estimator">
                    <conditional name="estimator_selector">
                        <param name="selected_module" value="custom_estimator"/>
                        <param name="c_estimator" value="LinearRegression01.zip" ftype="zip"/>
                    </conditional>
                </section>
            </conditional>
            <repeat name="base_est_builder">
                <conditional name="estimator_selector">
                    <param name="selected_module" value="custom_estimator"/>
                    <param name="c_estimator" value="RandomForestRegressor01.zip" ftype="zip"/>

                <conditional name="estimator_selector">
                    <param name="selected_module" value="custom_estimator"/>
                    <param name="c_estimator" value="XGBRegressor01.zip" ftype="zip"/>
                </conditional>
            </repeat>
            <param name="get_params" value="false"/>
            <output name="outfile" file="StackingCVRegressor01.zip" compare="sim_size" delta="5"/>
        </test>
        <test>
            <conditional name="algo_selection">
                <param name="estimator_type" value="mlxtend.regressor_StackingRegressor"/>
                <section name="meta_estimator">
                    <conditional name="estimator_selector">
                        <param name="selected_module" value="svm"/>
                        <param name="selected_estimator" value="SVR"/>
                    </conditional>
                </section>
            </conditional>
            <repeat name="base_est_builder">
                <conditional name="estimator_selector">
                    <param name="selected_module" value="custom_estimator"/>
                    <param name="c_estimator" value="RandomForestRegressor01.zip" ftype="zip"/>

                <conditional name="estimator_selector">
                    <param name="selected_module" value="xgboost"/>
                    <param name="selected_estimator" value="XGBRegressor"/>
                </conditional>
            </repeat>
            <param name="get_params" value="false"/>
            <output name="outfile" file="StackingRegressor02.zip" compare="sim_size" delta="5"/>
        </test>
    </tests>
    <help>
        <![CDATA[
This tool wrapps Stacking Regression, also called Super Learning, in which different base algorithms train