comparison main_macros.xml @ 24:9bf11bbeccc3 draft

planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/sklearn commit c0a3a186966888e5787335a7628bf0a4382637e7

23:3cd0dbc038ec

<macros>
  <token name="@VERSION@">1.0</token>

  <xml name="python_requirements">
      <requirements>
          <requirement type="package" version="3.6">python</requirement>
          <requirement type="package" version="0.20.2">scikit-learn</requirement>
          <requirement type="package" version="0.23.4">pandas</requirement>
          <requirement type="package" version="0.80">xgboost</requirement>
          <requirement type="package" version="0.9.13">asteval</requirement>
          <yield />
      </requirements>
  </xml>

  <xml name="macro_stdio">
    <stdio>

      <option value="by_header_name">Select columns by column header name(s)</option>
      <option value="all_but_by_header_name">All columns BUT by column header name(s)</option>
      <option value="all_columns">All columns</option>
    </param>
    <when value="by_index_number">
      <param name="@COL_NAME@" multiple="@MULTIPLE@" type="data_column" data_ref="@INFILE@" label="Select target column(s):"/>
    </when>
    <when value="all_but_by_index_number">
      <param name="@COL_NAME@" multiple="@MULTIPLE@" type="data_column" data_ref="@INFILE@" label="Select target column(s):"/>
    </when>
    <when value="by_header_name">
      <param name="@COL_NAME@" type="text" value="" label="Type header name(s):" help="Comma-separated string. For example: target1,target2"/>
    </when>
    <when value="all_but_by_header_name">

      <param name="selected_input" type="select" label="Select input type:">
          <option value="tabular" selected="true">tabular data</option>
          <option value="sparse">sparse matrix</option>
      </param>
      <when value="tabular">
          <expand macro="samples_tabular" multiple1="true"/>
      </when>
      <when value="sparse">
          <expand macro="sparse_target"/>
      </when>
    </conditional>

    <option value="RepeatedStratifiedKFold">RepeatedStratifiedKFold</option>
    <option value="ShuffleSplit">ShuffleSplit</option>
    <option value="StratifiedShuffleSplit">StratifiedShuffleSplit</option>
    <option value="TimeSeriesSplit">TimeSeriesSplit</option>
    <option value="PredefinedSplit">PredefinedSplit</option>
    <yield/>
  </xml>

  <xml name="cv_splitter_options">
    <when value="default">

      <expand macro="cv_n_splits"/>
      <param argument="max_train_size" type="integer" value="" optional="true" label="Maximum size of the training set" help="Maximum size for a single training set." />
    </when>
    <when value="PredefinedSplit">
      <param argument="test_fold" type="text" value="" area="true" label="test_fold" help="List, e.g., [0, 1, -1, 1], represents two test sets, [X[0]] and [X[1], X[3]], X[2] is excluded from any test set due to '-1'."/>
    </when>
    <yield/>
  </xml>

  <xml name="cv">

  <xml name="cv_test_size" token_value="0.2">
    <param argument="test_size" type="float" value="@VALUE@" min="0.0" label="Portion or number of the test set" help="0.0-1.0, proportion of the dataset to include in the test split; >1, integer only, the absolute number of test samples "/>
  </xml>

  <xml name="cv_groups" >
    <param argument="groups" type="text" value="" area="true" label="Groups" help="Group lables in a list. e.g., [1, 1, 2, 2, 3, 3, 3]"/>
  </xml>

  <xml name="feature_selection_algorithms">
    <option value="SelectKBest" selected="true">SelectKBest - Select features according to the k highest scores</option>
    <option value="GenericUnivariateSelect">GenericUnivariateSelect - Univariate feature selector with configurable strategy</option>

    <option value="SelectFwe">SelectFwe - Filter: Select the p-values corresponding to Family-wise error rate</option>
    <option value="VarianceThreshold">VarianceThreshold - Feature selector that removes all low-variance features</option>
    <option value="SelectFromModel">SelectFromModel - Meta-transformer for selecting features based on importance weights</option>
    <option value="RFE">RFE - Feature ranking with recursive feature elimination</option>
    <option value="RFECV">RFECV - Feature ranking with recursive feature elimination and cross-validated selection of the best number of features</option>
  </xml>

  <xml name="feature_selection_algorithm_details">
    <when value="GenericUnivariateSelect">
      <expand macro="feature_selection_score_function" />

        <param argument="alpha" type="float" value="" optional="True" label="Alpha" help="The highest uncorrected p-value for features to keep."/>
      </section>
    </when>
    <when value="VarianceThreshold">
      <section name="options" title="Options" expanded="False">
        <param argument="threshold" type="float" value="" optional="True" label="Threshold" help="Features with a training-set variance lower than this threshold will be removed."/>
      </section>
    </when>
  </xml>

  <xml name="feature_selection_SelectFromModel">

        <param argument="verbose" type="integer" value="0" label="verbose" help="Controls verbosity of output." />
      </section>
    </when>
  </xml>

  <xml name="feature_selection_RFECV">
    <when value="RFECV">
      <yield/>
      <section name="options" title="Advanced Options" expanded="False">
        <param argument="step" type="float" value="1" label="step" optional="true" help="Default = 1. " />
        <param argument="min_features_to_select" type="integer" value="1" optional="true" label="The minimum number of features to be selected"/>
        <expand macro="cv_reduced"/>
        <expand macro="scoring_selection"/>
        <param argument="verbose" type="integer" value="0" label="verbose" help="Controls verbosity of output." />
      </section>
    </when>
  </xml>

  <xml name="feature_selection_pipeline">
    <!--compare to `feature_selection_fs`, no fitted estimator for SelectFromModel and no customer estimator for RFE and RFECV-->
    <conditional name="fs_algorithm_selector">
      <param name="selected_algorithm" type="select" label="Select a feature selection algorithm">
        <expand macro="feature_selection_algorithms"/>
      </param>
      <expand macro="feature_selection_algorithm_details"/>
      <expand macro="feature_selection_SelectFromModel_no_prefitted"/>
      <expand macro="feature_selection_RFE">
        <expand macro="estimator_selector_all"/>
      </expand>  
      <expand macro="feature_selection_RFECV">
        <expand macro="estimator_selector_all"/>
      </expand>
    </conditional>
  </xml>

  <xml name="feature_selection_fs">
    <conditional name="fs_algorithm_selector">
      <param name="selected_algorithm" type="select" label="Select a feature selection algorithm">
        <expand macro="feature_selection_algorithms"/>
      </param>
      <expand macro="feature_selection_algorithm_details"/>
      <expand macro="feature_selection_SelectFromModel"/>
      <expand macro="feature_selection_RFE">
        <expand macro="estimator_selector_fs"/>
      </expand>  
      <expand macro="feature_selection_RFECV">
        <expand macro="estimator_selector_fs"/>
      </expand>
    </conditional>
  </xml>

    </param>
  </xml>

  <xml name="model_validation_common_options">
    <expand macro="cv"/>
    <expand macro="verbose"/>
    <yield/>
  </xml>

  <xml name="scoring_selection">
    <conditional name="scoring">

        <option value="neg_mean_absolute_error">Regression -- 'neg_mean_absolute_error'</option>
        <option value="neg_mean_squared_error">Regression -- 'neg_mean_squared_error'</option>
        <option value="neg_mean_squared_log_error">Regression -- 'neg_mean_squared_log_error'</option>
        <option value="neg_median_absolute_error">Regression -- 'neg_median_absolute_error'</option>
        <option value="r2">Regression -- 'r2'</option>
      </param>
      <when value="default"/>
      <when value="accuracy"><expand macro="secondary_scoring_selection_classification"/></when>
      <when value="balanced_accuracy"><expand macro="secondary_scoring_selection_classification"/></when>
      <when value="average_precision"><expand macro="secondary_scoring_selection_classification"/></when>

      <when value="neg_mean_absolute_error"><expand macro="secondary_scoring_selection_regression"/></when>
      <when value="neg_mean_squared_error"><expand macro="secondary_scoring_selection_regression"/></when>
      <when value="neg_mean_squared_log_error"><expand macro="secondary_scoring_selection_regression"/></when>
      <when value="neg_median_absolute_error"><expand macro="secondary_scoring_selection_regression"/></when>
      <when value="r2"><expand macro="secondary_scoring_selection_regression"/></when>
    </conditional>
  </xml>

  <xml name="secondary_scoring_selection_classification">
    <param name="secondary_scoring" type="select" multiple="true" label="Additional scoring used in multi-metric mode:" help="If the same metric with the primary is chosen, the metric will be ignored.">

      <option value="neg_median_absolute_error">Regression -- 'neg_median_absolute_error'</option>
      <option value="r2">Regression -- 'r2'</option>
    </param>
  </xml>

  <xml name="pre_dispatch" token_type="hidden" token_default_value="all" token_help="Number of predispatched jobs for parallel execution">
    <param argument="pre_dispatch" type="@TYPE@" value="@DEFAULT_VALUE@" optional="true" label="pre_dispatch" help="@HELP@"/>
  </xml>

  <xml name="search_cv_estimator">
    <param name="infile_pipeline" type="data" format="zip" label="Choose the dataset containing pipeline object:"/>
    <section name="search_params_builder" title="Search parameters Builder" expanded="true">
      <repeat name="param_set" min="1" max="20" title="Parameter setting for search:">
        <conditional name="search_param_selector">
          <param name="selected_param_type" type="select" label="Choose the transformation the parameter belongs to">
            <option value="final_estimator_p" selected="true">Final estimator</option>
            <option value="prep_1_p">Pre-processing step #1</option>
            <option value="prep_2_p">Pre-processing step #2</option>
            <option value="prep_3_p">Pre-processing step #3</option>
            <option value="prep_4_p">Pre-processing step #4</option>
            <option value="prep_5_p">Pre-processing step #5</option>
          </param>
          <when value="final_estimator_p">
            <expand macro="search_param_input" />
          </when>
          <when value="prep_1_p">
            <expand macro="search_param_input" label="Pre_processing component #1  parameter:" help="One parameter per box. For example: with_centering: [True, False]."/>
          </when>
          <when value="prep_2_p">
            <expand macro="search_param_input" label="Pre_processing component #2 parameter:" help="One parameter per box. For example: k: [3, 5, 7, 9]. See bottom for more examples"/>
          </when>
          <when value="prep_3_p">
            <expand macro="search_param_input" label="Pre_processing component #3 parameter:" help="One parameter per box. For example: n_components: [1, 10, 100, 1000]. See bottom for more examples"/>
          </when>
          <when value="prep_4_p">
            <expand macro="search_param_input" label="Pre_processing component #4 parameter:" help="One parameter per box. For example: n_components: [1, 10, 100, 1000]. See bottom for more examples"/>
          </when>
          <when value="prep_5_p">
            <expand macro="search_param_input" label="Pre_processing component #5 parameter:" help="One parameter per box. For example: affinity: ['euclidean', 'l1', 'l2', 'manhattan']. See bottom for more examples"/>
          </when>
        </conditional>
      </repeat>
    </section>
  </xml>

  <xml name="search_param_input" token_label="Estimator parameter:" token_help="One parameter per box. For example: C: [1, 10, 100, 1000]. See bottom for more examples">
    <param name="search_p" type="text" value="" optional="true" label="@LABEL@" help="@HELP@">
      <sanitizer>
        <valid initial="default">
          <add value="&apos;"/>
          <add value="&quot;"/>
          <add value="["/>
          <add value="]"/>
        </valid>
      </sanitizer>
    </param>
  </xml>

  <xml name="search_cv_options">
      <expand macro="scoring_selection"/>
      <expand macro="model_validation_common_options"/>
      <expand macro="pre_dispatch" value="2*n_jobs" help="Controls the number of jobs that get dispatched during parallel execution"/>
      <param argument="iid" type="boolean" truevalue="booltrue" falsevalue="boolfalse" checked="true" label="iid" help="If True, data is identically distributed across the folds"/>
      <param argument="refit" type="boolean" truevalue="booltrue" falsevalue="boolfalse" checked="true" label="refit" help="Refit an estimator using the best found parameters on the whole dataset."/>
      <param argument="error_score" type="boolean" truevalue="booltrue" falsevalue="boolfalse" checked="true" label="Raise fit error:" help="If false, the metric score is assigned to NaN if an error occurs in estimator fitting and FitFailedWarning is raised."/>
      <param argument="return_train_score" type="boolean" truevalue="booltrue" falsevalue="boolfalse" checked="false" label="return_train_score" help=""/>
  </xml>

  <xml name="estimator_selector_fs">
    <conditional name="estimator_selector">
      <param name="selected_module" type="select" label="Choose the module that contains target estimator:" >
        <expand macro="estimator_module_options">
            <option value="customer_estimator">Load a customer estimator</option>
        </expand>
      </param>
      <expand macro="estimator_suboptions">
        <when value="customer_estimator">
            <param name="c_estimator" type="data" format="zip" label="Choose the dataset containing the customer estimator or pipeline:"/>
        </when>
      </expand>
    </conditional>
  </xml>

        <option value="over_sampling.SVMSMOTE">over_sampling.SVMSMOTE</option>
        <option value="over_sampling.BorderlineSMOTE">over_sampling.BorderlineSMOTE</option>
        <option value="over_sampling.SMOTENC">over_sampling.SMOTENC</option>
        <option value="combine.SMOTEENN">combine.SMOTEENN</option>
        <option value="combine.SMOTETomek">combine.SMOTETomek</option>
      </param>
      <when value="under_sampling.ClusterCentroids">
        <expand macro="estimator_params_text"
              help="Default(=blank): sampling_strategy='auto', random_state=None, estimator=None, voting='auto'."/>
      </when>

      </when>
      <when value="combine.SMOTETomek">
        <expand macro="estimator_params_text"
              help="Default(=blank): sampling_strategy='auto', random_state=None, smote=None, tomek=None."/>
      </when>
    </conditional>
  </xml>

  <!-- Outputs -->

24:9bf11bbeccc3

<macros>
  <token name="@VERSION@">1.0.0.4</token>

  <xml name="python_requirements">
      <requirements>
          <requirement type="package" version="3.6">python</requirement>
          <requirement type="package" version="0.20.3">scikit-learn</requirement>
          <requirement type="package" version="0.24.2">pandas</requirement>
          <requirement type="package" version="0.80">xgboost</requirement>
          <requirement type="package" version="0.9.13">asteval</requirement>
          <requirement type="package" version="0.6">skrebate</requirement>
          <requirement type="package" version="0.4.2">imbalanced-learn</requirement>
          <requirement type="package" version="0.16.0">mlxtend</requirement>
          <yield/>
      </requirements>
  </xml>

  <xml name="macro_stdio">
    <stdio>

      <option value="by_header_name">Select columns by column header name(s)</option>
      <option value="all_but_by_header_name">All columns BUT by column header name(s)</option>
      <option value="all_columns">All columns</option>
    </param>
    <when value="by_index_number">
      <param name="@COL_NAME@" multiple="@MULTIPLE@" type="data_column" use_header_names="true" data_ref="@INFILE@" label="Select target column(s):"/>
    </when>
    <when value="all_but_by_index_number">
      <param name="@COL_NAME@" multiple="@MULTIPLE@" type="data_column" use_header_names="true" data_ref="@INFILE@" label="Select target column(s):"/>
    </when>
    <when value="by_header_name">
      <param name="@COL_NAME@" type="text" value="" label="Type header name(s):" help="Comma-separated string. For example: target1,target2"/>
    </when>
    <when value="all_but_by_header_name">

      <param name="selected_input" type="select" label="Select input type:">
          <option value="tabular" selected="true">tabular data</option>
          <option value="sparse">sparse matrix</option>
      </param>
      <when value="tabular">
          <expand macro="samples_tabular" multiple1="true" multiple2="false"/>
      </when>
      <when value="sparse">
          <expand macro="sparse_target"/>
      </when>
    </conditional>

    <option value="RepeatedStratifiedKFold">RepeatedStratifiedKFold</option>
    <option value="ShuffleSplit">ShuffleSplit</option>
    <option value="StratifiedShuffleSplit">StratifiedShuffleSplit</option>
    <option value="TimeSeriesSplit">TimeSeriesSplit</option>
    <option value="PredefinedSplit">PredefinedSplit</option>
    <option value="OrderedKFold">OrderedKFold</option>
    <option value="RepeatedOrderedKFold">RepeatedOrderedKFold</option>
    <yield/>
  </xml>

  <xml name="cv_splitter_options">
    <when value="default">

      <expand macro="cv_n_splits"/>
      <param argument="max_train_size" type="integer" value="" optional="true" label="Maximum size of the training set" help="Maximum size for a single training set." />
    </when>
    <when value="PredefinedSplit">
      <param argument="test_fold" type="text" value="" area="true" label="test_fold" help="List, e.g., [0, 1, -1, 1], represents two test sets, [X[0]] and [X[1], X[3]], X[2] is excluded from any test set due to '-1'."/>
    </when>
    <when value="OrderedKFold">
      <expand macro="cv_n_splits"/>
      <expand macro="cv_shuffle"/>
      <expand macro="random_state"/>
    </when>
    <when value="RepeatedOrderedKFold">
      <expand macro="cv_n_splits"/>
      <param argument="n_repeats" type="integer" value="5"/>
      <expand macro="random_state"/>
    </when>
    <yield/>
  </xml>

  <xml name="cv">

  <xml name="cv_test_size" token_value="0.2">
    <param argument="test_size" type="float" value="@VALUE@" min="0.0" label="Portion or number of the test set" help="0.0-1.0, proportion of the dataset to include in the test split; >1, integer only, the absolute number of test samples "/>
  </xml>

  <xml name="cv_groups" >
    <section name="groups_selector" title="Groups column selector" expanded="true">
      <param name="infile_g" type="data" format="tabular" label="Choose dataset containing groups info:"/>
      <param name="header_g" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolfalse" checked="False" label="Does the dataset contain header:" />
      <conditional name="column_selector_options_g">
        <expand macro="samples_column_selector_options" column_option="selected_column_selector_option_g" col_name="col_g" multiple="False" infile="infile_g"/>
      </conditional>
    </section>
  </xml>

  <xml name="feature_selection_algorithms">
    <option value="SelectKBest" selected="true">SelectKBest - Select features according to the k highest scores</option>
    <option value="GenericUnivariateSelect">GenericUnivariateSelect - Univariate feature selector with configurable strategy</option>

    <option value="SelectFwe">SelectFwe - Filter: Select the p-values corresponding to Family-wise error rate</option>
    <option value="VarianceThreshold">VarianceThreshold - Feature selector that removes all low-variance features</option>
    <option value="SelectFromModel">SelectFromModel - Meta-transformer for selecting features based on importance weights</option>
    <option value="RFE">RFE - Feature ranking with recursive feature elimination</option>
    <option value="RFECV">RFECV - Feature ranking with recursive feature elimination and cross-validated selection of the best number of features</option>
    <yield/>
  </xml>

  <xml name="feature_selection_algorithm_details">
    <when value="GenericUnivariateSelect">
      <expand macro="feature_selection_score_function" />

        <param argument="alpha" type="float" value="" optional="True" label="Alpha" help="The highest uncorrected p-value for features to keep."/>
      </section>
    </when>
    <when value="VarianceThreshold">
      <section name="options" title="Options" expanded="False">
        <param argument="threshold" type="float" value="0.0" optional="True" label="Threshold" help="Features with a training-set variance lower than this threshold will be removed."/>
      </section>
    </when>
  </xml>

  <xml name="feature_selection_SelectFromModel">

        <param argument="verbose" type="integer" value="0" label="verbose" help="Controls verbosity of output." />
      </section>
    </when>
  </xml>

  <xml name="feature_selection_RFECV_fs">
    <when value="RFECV">
      <yield/>
      <section name="options" title="Advanced Options" expanded="False">
        <param argument="step" type="float" value="1" label="step" optional="true" help="Default = 1. " />
        <param argument="min_features_to_select" type="integer" value="1" optional="true" label="The minimum number of features to be selected"/>
        <expand macro="cv"/>
        <expand macro="scoring_selection"/>
        <param argument="verbose" type="integer" value="0" label="verbose" help="Controls verbosity of output." />
      </section>
    </when>
  </xml>

  <xml name="feature_selection_RFECV_pipeline">
    <when value="RFECV">
      <yield/>
      <section name="options" title="Advanced Options" expanded="False">
        <param argument="step" type="float" value="1" label="step" optional="true" help="Default = 1. " />
        <param argument="min_features_to_select" type="integer" value="1" optional="true" label="The minimum number of features to be selected"/>
        <expand macro="cv_reduced"/>
        <!-- TODO: group splitter support-->
        <expand macro="scoring_selection"/>
        <param argument="verbose" type="integer" value="0" label="verbose" help="Controls verbosity of output." />
      </section>
    </when>
  </xml>

  <xml name="feature_selection_DyRFECV_fs">
    <when value="DyRFECV">
      <yield/>
      <section name="options" title="Advanced Options" expanded="False">
        <param argument="step" type="text" size="30" value="1" label="step" optional="true" help="Default = 1. Support float, int and list." >
          <sanitizer>
            <valid initial="default">
              <add value="["/>
              <add value="]"/>
            </valid>
          </sanitizer>
        </param>
        <param argument="min_features_to_select" type="integer" value="1" optional="true" label="The minimum number of features to be selected"/>
        <expand macro="cv"/>
        <expand macro="scoring_selection"/>
        <param argument="verbose" type="integer" value="0" label="verbose" help="Controls verbosity of output." />
      </section>
    </when>
  </xml>

  <xml name="feature_selection_pipeline">
    <!--compare to `feature_selection_fs`, no fitted estimator for SelectFromModel and no custom estimator for RFE and RFECV-->
    <conditional name="fs_algorithm_selector">
      <param name="selected_algorithm" type="select" label="Select a feature selection algorithm">
        <expand macro="feature_selection_algorithms"/>
      </param>
      <expand macro="feature_selection_algorithm_details"/>
      <expand macro="feature_selection_SelectFromModel_no_prefitted"/>
      <expand macro="feature_selection_RFE">
        <expand macro="estimator_selector_all"/>
      </expand>  
      <expand macro="feature_selection_RFECV_pipeline">
        <expand macro="estimator_selector_all"/>
      </expand>
      <!-- TODO: add DyRFECV to pipeline-->
    </conditional>
  </xml>

  <xml name="feature_selection_fs">
    <conditional name="fs_algorithm_selector">
      <param name="selected_algorithm" type="select" label="Select a feature selection algorithm">
        <expand macro="feature_selection_algorithms">
          <option value="DyRFECV">DyRFECV - Extended RFECV with changeable steps</option>
        </expand>
      </param>
      <expand macro="feature_selection_algorithm_details"/>
      <expand macro="feature_selection_SelectFromModel"/>
      <expand macro="feature_selection_RFE">
        <expand macro="estimator_selector_fs"/>
      </expand>  
      <expand macro="feature_selection_RFECV_fs">
        <expand macro="estimator_selector_fs"/>
      </expand>
      <expand macro="feature_selection_DyRFECV_fs">
        <expand macro="estimator_selector_fs"/>
      </expand>
    </conditional>
  </xml>

    </param>
  </xml>

  <xml name="model_validation_common_options">
    <expand macro="cv"/>
    <!-- expand macro="verbose"/> -->
    <yield/>
  </xml>

  <xml name="scoring_selection">
    <conditional name="scoring">

        <option value="neg_mean_absolute_error">Regression -- 'neg_mean_absolute_error'</option>
        <option value="neg_mean_squared_error">Regression -- 'neg_mean_squared_error'</option>
        <option value="neg_mean_squared_log_error">Regression -- 'neg_mean_squared_log_error'</option>
        <option value="neg_median_absolute_error">Regression -- 'neg_median_absolute_error'</option>
        <option value="r2">Regression -- 'r2'</option>
        <option value="binarize_auc_scorer">anomaly detection -- binarize_auc_scorer</option>
        <option value="binarize_average_precision_scorer">anomaly detection -- binarize_average_precision_scorer</option>
      </param>
      <when value="default"/>
      <when value="accuracy"><expand macro="secondary_scoring_selection_classification"/></when>
      <when value="balanced_accuracy"><expand macro="secondary_scoring_selection_classification"/></when>
      <when value="average_precision"><expand macro="secondary_scoring_selection_classification"/></when>

      <when value="neg_mean_absolute_error"><expand macro="secondary_scoring_selection_regression"/></when>
      <when value="neg_mean_squared_error"><expand macro="secondary_scoring_selection_regression"/></when>
      <when value="neg_mean_squared_log_error"><expand macro="secondary_scoring_selection_regression"/></when>
      <when value="neg_median_absolute_error"><expand macro="secondary_scoring_selection_regression"/></when>
      <when value="r2"><expand macro="secondary_scoring_selection_regression"/></when>
      <when value="binarize_auc_scorer"><expand macro="secondary_scoring_selection_anormaly"/></when>
      <when value="binarize_average_precision_scorer"><expand macro="secondary_scoring_selection_anormaly"/></when>
    </conditional>
  </xml>

  <xml name="secondary_scoring_selection_classification">
    <param name="secondary_scoring" type="select" multiple="true" label="Additional scoring used in multi-metric mode:" help="If the same metric with the primary is chosen, the metric will be ignored.">

      <option value="neg_median_absolute_error">Regression -- 'neg_median_absolute_error'</option>
      <option value="r2">Regression -- 'r2'</option>
    </param>
  </xml>

  <xml name="secondary_scoring_selection_anormaly">
    <param name="secondary_scoring" type="select" multiple="true" label="Additional scoring used in multi-metric mode:" help="If the same metric with the primary is chosen, the metric will be ignored.">
      <option value="binarize_auc_scorer">anomaly detection -- binarize_auc_scorer</option>
      <option value="binarize_average_precision_scorer">anomaly detection -- binarize_average_precision_scorer</option>
    </param>
  </xml>

  <xml name="pre_dispatch" token_type="hidden" token_default_value="all" token_help="Number of predispatched jobs for parallel execution">
    <param argument="pre_dispatch" type="@TYPE@" value="@DEFAULT_VALUE@" optional="true" label="pre_dispatch" help="@HELP@"/>
  </xml>

  <xml name="search_cv_estimator">
    <param name="infile_estimator" type="data" format="zip" label="Choose the dataset containing pipeline/estimator object"/>
    <section name="search_params_builder" title="Search parameters Builder" expanded="true">
      <param name="infile_params" type="data" format="tabular" label="Choose the dataset containing parameter names"/>
      <repeat name="param_set" min="1" max="30" title="Parameter settings for search:">
          <param name="sp_name" type="select" label="Choose a parameter name (with current value)">
            <options from_dataset="infile_params" startswith="@">
              <column name="name" index="2"/>
              <column name="value" index="1"/>
              <filter type="unique_value" name="unique_param" column="1"/>
              <filter type="sort_by" name="sorted_param" column="2"/>
            </options>
          </param>
          <param name="sp_list" type="text" value="" optional="true" label="Search list" help="list or array-like, for example: [1, 10, 100, 1000], [True, False] and ['auto', 'sqrt', None]. See `help` section for more examples">
            <sanitizer>
              <valid initial="default">
                <add value="&apos;"/>
                <add value="&quot;"/>
                <add value="["/>
                <add value="]"/>
              </valid>
            </sanitizer>
          </param>
      </repeat>
    </section>
  </xml>

  <xml name="search_cv_options">
      <expand macro="scoring_selection"/>
      <expand macro="model_validation_common_options"/>
      <!--expand macro="pre_dispatch" default_value="2*n_jobs" help="Controls the number of jobs that get dispatched during parallel execution"/-->
      <param argument="iid" type="boolean" truevalue="booltrue" falsevalue="boolfalse" checked="true" label="iid" help="If True, data is identically distributed across the folds"/>
      <param argument="refit" type="boolean" truevalue="booltrue" falsevalue="boolfalse" checked="true" label="refit" help="Refit an estimator using the best found parameters on the whole dataset."/>
      <param argument="error_score" type="boolean" truevalue="booltrue" falsevalue="boolfalse" checked="true" label="Raise fit error:" help="If false, the metric score is assigned to NaN if an error occurs in estimator fitting and FitFailedWarning is raised."/>
      <param argument="return_train_score" type="boolean" truevalue="booltrue" falsevalue="boolfalse" checked="false" label="return_train_score" help=""/>
  </xml>

  <xml name="estimator_selector_fs">
    <conditional name="estimator_selector">
      <param name="selected_module" type="select" label="Choose the module that contains target estimator:" >
        <expand macro="estimator_module_options">
            <option value="custom_estimator">Load a custom estimator</option>
        </expand>
      </param>
      <expand macro="estimator_suboptions">
        <when value="custom_estimator">
            <param name="c_estimator" type="data" format="zip" label="Choose the dataset containing the custom estimator or pipeline:"/>
        </when>
      </expand>
    </conditional>
  </xml>

        <option value="over_sampling.SVMSMOTE">over_sampling.SVMSMOTE</option>
        <option value="over_sampling.BorderlineSMOTE">over_sampling.BorderlineSMOTE</option>
        <option value="over_sampling.SMOTENC">over_sampling.SMOTENC</option>
        <option value="combine.SMOTEENN">combine.SMOTEENN</option>
        <option value="combine.SMOTETomek">combine.SMOTETomek</option>
        <option value="Z_RandomOverSampler">Z_RandomOverSampler - for regression</option>
      </param>
      <when value="under_sampling.ClusterCentroids">
        <expand macro="estimator_params_text"
              help="Default(=blank): sampling_strategy='auto', random_state=None, estimator=None, voting='auto'."/>
      </when>

      </when>
      <when value="combine.SMOTETomek">
        <expand macro="estimator_params_text"
              help="Default(=blank): sampling_strategy='auto', random_state=None, smote=None, tomek=None."/>
      </when>
      <when value="Z_RandomOverSampler">
        <expand macro="estimator_params_text"
              help="Default(=blank): sampling_strategy='auto', random_state=None, negative_thres=0, positive_thres=-1."/>
      </when>
    </conditional>
  </xml>

  <xml name="stacking_ensemble_inputs">
    <section name="options" title="Advanced Options" expanded="false">
        <yield/>
        <param argument="use_features_in_secondary" type="boolean" truevalue="booltrue" falsevalue="boolfalse" checked="false"/>
        <param argument="store_train_meta_features" type="boolean" truevalue="booltrue" falsevalue="boolfalse" checked="false"/>
    </section>
  </xml>

  <xml name="stacking_base_estimator">
    <conditional name="estimator_selector">
        <param name="selected_module" type="select" label="Choose the module that contains target estimator:" >
            <expand macro="estimator_module_options">
                <option value="custom_estimator">Load a custom estimator</option>
            </expand>
        </param>
        <expand macro="estimator_suboptions">
            <when value="custom_estimator">
                <param name="c_estimator" type="data" format="zip" label="Choose the dataset containing the custom estimator or pipeline"/>
            </when>
        </expand>
    </conditional>
  </xml>

  <!-- Outputs -->