comparison main_macros.xml @ 15:8da7dc3f4e66 draft

planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/sklearn commit f54ff2ba2f8e7542d68966ce5a6b17d7f624ac48

14:830b48bb1617

  if inputs['selected_algorithm'] == 'SelectFromModel':
    if not options['threshold'] or options['threshold'] == 'None':
      options['threshold'] = None
      if 'extra_estimator' in inputs and inputs['extra_estimator']['has_estimator'] == 'no_load':
        fitted_estimator = pickle.load(open("inputs['extra_estimator']['fitted_estimator']", 'r'))
        new_selector = selector(fitted_estimator, prefit=True, **options)
      else:
        estimator=inputs["estimator"]
        if inputs["extra_estimator"]["has_estimator"]=='no':
          estimator=inputs["extra_estimator"]["new_estimator"]

      sep='\t',
      header=header,
      parse_dates=True
    )
  else:
    X = mmread(open(file1, 'r'))

  header = 'infer' if params["selected_tasks"]["selected_algorithms"]["input_options"]["header2"] else None
  column_option = params["selected_tasks"]["selected_algorithms"]["input_options"]["column_selector_options_2"]["selected_column_selector_option2"]
  if column_option in ["by_index_number", "all_but_by_index_number", "by_header_name", "all_but_by_header_name"]:
    c = params["selected_tasks"]["selected_algorithms"]["input_options"]["column_selector_options_2"]["col2"]

    <param argument="beta" type="float" value="1.0" label="The strength of recall versus precision in the F-score" help=" "/>
  </xml>


  <!--Data interface-->
  <xml name="tabular_input">
    <param name="infile" type="data" format="tabular" label="Data file with numeric values"/>
    <param name="start_column" type="data_column" data_ref="infile" optional="True" label="Select a subset of data. Start column:" />
    <param name="end_column" type="data_column" data_ref="infile" optional="True" label="End column:" />
  </xml>

  <xml name="sample_cols" token_label1="File containing true class labels:" token_label2="File containing predicted class labels:" token_multiple1="False" token_multiple2="False" token_format1="tabular" token_format2="tabular" token_help1="" token_help2="">
    <param name="infile1" type="data" format="@FORMAT1@" label="@LABEL1@" help="@HELP1@"/>
    <param name="col1" multiple="@MULTIPLE1@" type="data_column" data_ref="infile1" label="Select target column(s):"/>
    <param name="infile2" type="data" format="@FORMAT2@" label="@LABEL2@" help="@HELP2@"/>
    <param name="col2" multiple="@MULTIPLE2@" type="data_column" data_ref="infile2" label="Select target column(s):"/>
    <yield/>
  </xml>

  <xml name="samples_tabular" token_multiple1="false" token_multiple2="false">
    <param name="infile1" type="data" format="tabular" label="Training samples dataset:"/>
    <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">

    </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="by_header_name">
      <param name="@COL_NAME@" type="text" value="" label="Type header name(s):" help="String seperate by colon. For example: target1,target2"/>
    </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="all_but_by_header_name">
      <param name="@COL_NAME@" type="text" value="" label="Type header name(s):" help="String seperate by colon. For example: target1,target2"/>
    </when>
    <when value="all_columns">
    </when>
  </xml>

      <when value="sparse">
          <expand macro="sparse_target"/>
      </when>
    </conditional>
  </xml>

  <xml name="multitype_input" token_format="tabular" token_help="All datasets with tabular format are supporetd.">
    <param name="infile_transform" type="data" format="@FORMAT@" label="Select a dataset to transform:" help="@HELP@"/>
  </xml>


  <!--Advanced options-->
  <xml name="nn_advanced_options">
    <section name="options" title="Advanced Options" expanded="False">
      <yield/>

      <option value="Normalizer">Normalizer (Normalizes samples individually to unit norm)</option>
      <yield/>
    </param>
  </xml>

  <xml name="sparse_preprocessor_options">
    <when value="Binarizer">
        <expand macro="multitype_input" format="tabular,txt" help="Tabular and sparse datasets are supporetd."/>
        <section name="options" title="Advanced Options" expanded="False">
            <param argument="copy" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolfalse" checked="true"
                label="Use a copy of data for precomputing binarization" help=" "/>
            <param argument="threshold" type="float" optional="true" value="0.0"
                label="Threshold"
                help="Feature values below or equal to this are replaced by 0, above it by 1. Threshold may not be less than 0 for operations on sparse matrices. "/>
        </section>
    </when>
    <when value="Imputer">
      <expand macro="multitype_input" format="tabular,txt" help="Tabular and sparse datasets are supporetd."/>
      <section name="options" title="Advanced Options" expanded="False">
          <param argument="copy" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolfalse" checked="true"
            label="Use a copy of data for precomputing imputation" help=" "/>
          <param argument="strategy" type="select" optional="true" label="Imputation strategy" help=" ">
              <option value="mean" selected="true">Replace missing values using the mean along the axis</option>

              <option value="1">Impute along rows</option>
          </param-->
      </section>
    </when>
    <when value="StandardScaler">
      <expand macro="multitype_input"/>
      <section name="options" title="Advanced Options" expanded="False">
        <param argument="copy" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolfalse" checked="true"
            label="Use a copy of data for performing inplace scaling" help=" "/>
        <param argument="with_mean" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolfalse" checked="true"
            label="Center the data before scaling" help=" "/>
        <param argument="with_std" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolfalse" checked="true"
            label="Scale the data to unit variance (or unit standard deviation)" help=" "/>
      </section>
    </when>
    <when value="MaxAbsScaler">
      <expand macro="multitype_input" format="tabular,txt" help="Tabular and sparse datasets are supporetd."/>
      <section name="options" title="Advanced Options" expanded="False">
        <param argument="copy" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolfalse" checked="true"
            label="Use a copy of data for precomputing scaling" help=" "/>
      </section>
    </when>
    <when value="Normalizer">
      <expand macro="multitype_input" format="tabular,txt" help="Tabular and sparse datasets are supporetd."/>
      <section name="options" title="Advanced Options" expanded="False">
        <param argument="norm" type="select" optional="true" label="The norm to use to normalize non zero samples" help=" ">
          <option value="l1" selected="true">l1</option>
          <option value="l2">l2</option>
          <option value="max">max</option>

            label="Use a copy of data for precomputing row normalization" help=" "/>
      </section>
    </when>
    <yield/>
  </xml>
  <xml name="estimator_input_no_fit">
    <expand macro="feature_selection_estimator" />
    <conditional name="extra_estimator">
      <expand macro="feature_selection_extra_estimator" />
      <expand macro="feature_selection_estimator_choices" />
    </conditional>
  </xml>
  <xml name="feature_selection_all">
    <conditional name="feature_selection_algorithms">
      <param name="selected_algorithm" type="select" label="Select a feature selection algorithm">
        <option value="SelectFromModel" selected="true">SelectFromModel - Meta-transformer for selecting features based on importance weights</option>
        <option value="GenericUnivariateSelect" selected="true">GenericUnivariateSelect - Univariate feature selector with configurable strategy</option>

      </when>
      <when value="mutual_info_regression">
      </when-->
    </conditional>
  </xml>
  <xml name="feature_selection_score_function">
    <param argument="score_func" type="select" label="Select a score function">
      <option value="chi2">chi2 - Compute chi-squared stats between each non-negative feature and class</option>
      <option value="f_classif">f_classif - Compute the ANOVA F-value for the provided sample</option>
      <option value="f_regression">f_regression - Univariate linear regression tests</option>
      <option value="mutual_info_classif">mutual_info_classif - Estimate mutual information for a discrete target variable</option>
      <option value="mutual_info_regression">mutual_info_regression - Estimate mutual information for a continuous target variable</option>
    </param>
  </xml>
  <xml name="feature_selection_estimator">
    <param argument="estimator" type="select" label="Select an estimator" help="The base estimator from which the transformer is built.">
      <option value="svm.SVR(kernel=&quot;linear&quot;)">svm.SVR(kernel=&quot;linear&quot;)</option>
      <option value="svm.SVC(kernel=&quot;linear&quot;)">svm.SVC(kernel=&quot;linear&quot;)</option>
      <option value="svm.LinearSVC(penalty=&quot;l1&quot;, dual=False, tol=1e-3)">svm.LinearSVC(penalty=&quot;l1&quot;, dual=False, tol=1e-3)</option>
      <option value="linear_model.LassoCV()">linear_model.LassoCV()</option>
      <option value="ensemble.RandomForestRegressor(n_estimators = 1000, random_state = 42)">ensemble.RandomForestRegressor(n_estimators = 1000, random_state = 42)</option>
    </param>
  </xml>
  <xml name="feature_selection_extra_estimator">   
      <param name="has_estimator" type="select" label="Does your estimator on the list above?">
        <option value="yes">Yes, my estimator is on the list</option>
        <option value="no">No, I need make a new estimator</option>
        <yield/>
      </param>
  </xml>
  <xml name="feature_selection_estimator_choices">
    <when value="yes">
    </when>
    <when value="no">
      <param name="new_estimator" type="text" value="" label="Make a new estimator" />
    </when>
    <yield/>
  </xml>
  <xml name="feature_selection_methods">
    <conditional name="select_methods">
      <param name="selected_method" type="select" label="Select an operation">
          <option value="fit_transform">fit_transform - Fit to data, then transform it</option>
          <option value="get_support">get_support - Get a mask, or integer index, of the features selected</option>

15:8da7dc3f4e66

  if inputs['selected_algorithm'] == 'SelectFromModel':
    if not options['threshold'] or options['threshold'] == 'None':
      options['threshold'] = None
      if 'extra_estimator' in inputs and inputs['extra_estimator']['has_estimator'] == 'no_load':
        with open("inputs['extra_estimator']['fitted_estimator']", 'rb') as model_handler:
          fitted_estimator = pickle.load(model_handler)
        new_selector = selector(fitted_estimator, prefit=True, **options)
      else:
        estimator=inputs["estimator"]
        if inputs["extra_estimator"]["has_estimator"]=='no':
          estimator=inputs["extra_estimator"]["new_estimator"]

      sep='\t',
      header=header,
      parse_dates=True
    )
  else:
    X = mmread(file1)

  header = 'infer' if params["selected_tasks"]["selected_algorithms"]["input_options"]["header2"] else None
  column_option = params["selected_tasks"]["selected_algorithms"]["input_options"]["column_selector_options_2"]["selected_column_selector_option2"]
  if column_option in ["by_index_number", "all_but_by_index_number", "by_header_name", "all_but_by_header_name"]:
    c = params["selected_tasks"]["selected_algorithms"]["input_options"]["column_selector_options_2"]["col2"]

    <param argument="beta" type="float" value="1.0" label="The strength of recall versus precision in the F-score" help=" "/>
  </xml>


  <!--Data interface-->

  <xml name="samples_tabular" token_multiple1="false" token_multiple2="false">
    <param name="infile1" type="data" format="tabular" label="Training samples dataset:"/>
    <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">

    </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="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_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_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_columns">
    </when>
  </xml>

      <when value="sparse">
          <expand macro="sparse_target"/>
      </when>
    </conditional>
  </xml>

  <!--Advanced options-->
  <xml name="nn_advanced_options">
    <section name="options" title="Advanced Options" expanded="False">
      <yield/>

      <option value="Normalizer">Normalizer (Normalizes samples individually to unit norm)</option>
      <yield/>
    </param>
  </xml>

  <xml name="sparse_preprocessors_ext">
    <expand macro="sparse_preprocessors">
      <option value="KernelCenterer">Kernel Centerer (Centers a kernel matrix)</option>
      <option value="MinMaxScaler">Minmax Scaler (Scales features to a range)</option>
      <option value="PolynomialFeatures">Polynomial Features (Generates polynomial and interaction features)</option>
      <option value="RobustScaler">Robust Scaler (Scales features using outlier-invariance statistics)</option>
    </expand>
  </xml>

  <xml name="sparse_preprocessor_options">
    <when value="Binarizer">
        <section name="options" title="Advanced Options" expanded="False">
            <param argument="copy" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolfalse" checked="true"
                label="Use a copy of data for precomputing binarization" help=" "/>
            <param argument="threshold" type="float" optional="true" value="0.0"
                label="Threshold"
                help="Feature values below or equal to this are replaced by 0, above it by 1. Threshold may not be less than 0 for operations on sparse matrices. "/>
        </section>
    </when>
    <when value="Imputer">
      <section name="options" title="Advanced Options" expanded="False">
          <param argument="copy" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolfalse" checked="true"
            label="Use a copy of data for precomputing imputation" help=" "/>
          <param argument="strategy" type="select" optional="true" label="Imputation strategy" help=" ">
              <option value="mean" selected="true">Replace missing values using the mean along the axis</option>

              <option value="1">Impute along rows</option>
          </param-->
      </section>
    </when>
    <when value="StandardScaler">
      <section name="options" title="Advanced Options" expanded="False">
        <param argument="copy" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolfalse" checked="true"
            label="Use a copy of data for performing inplace scaling" help=" "/>
        <param argument="with_mean" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolfalse" checked="true"
            label="Center the data before scaling" help=" "/>
        <param argument="with_std" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolfalse" checked="true"
            label="Scale the data to unit variance (or unit standard deviation)" help=" "/>
      </section>
    </when>
    <when value="MaxAbsScaler">
      <section name="options" title="Advanced Options" expanded="False">
        <param argument="copy" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolfalse" checked="true"
            label="Use a copy of data for precomputing scaling" help=" "/>
      </section>
    </when>
    <when value="Normalizer">
      <section name="options" title="Advanced Options" expanded="False">
        <param argument="norm" type="select" optional="true" label="The norm to use to normalize non zero samples" help=" ">
          <option value="l1" selected="true">l1</option>
          <option value="l2">l2</option>
          <option value="max">max</option>

            label="Use a copy of data for precomputing row normalization" help=" "/>
      </section>
    </when>
    <yield/>
  </xml>

  <xml name="sparse_preprocessor_options_ext">
    <expand macro="sparse_preprocessor_options">
      <when value="KernelCenterer">
        <section name="options" title="Advanced Options" expanded="False">
        </section>
      </when>
      <when value="MinMaxScaler">
          <section name="options" title="Advanced Options" expanded="False">
              <!--feature_range-->
              <param argument="copy" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolflase" checked="true"
                  label="Use a copy of data for precomputing normalization" help=" "/>
          </section>
      </when>
      <when value="PolynomialFeatures">
          <section name="options" title="Advanced Options" expanded="False">
              <param argument="degree" type="integer" optional="true" value="2" label="The degree of the polynomial features " help=""/>
              <param argument="interaction_only" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolflase" checked="false" label="Produce interaction features only" help="(Features that are products of at most degree distinct input features) "/>
              <param argument="include_bias" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolflase" checked="true" label="Include a bias column" help="Feature in which all polynomial powers are zero "/>
          </section>
      </when>
      <when value="RobustScaler">
          <section name="options" title="Advanced Options" expanded="False">
              <!--=True, =True, copy=True-->
              <param argument="with_centering" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolflase" checked="true"
                  label="Center the data before scaling" help=" "/>
              <param argument="with_scaling" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolflase" checked="true"
                  label="Scale the data to interquartile range" help=" "/>
              <param argument="copy" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolflase" checked="true"
                  label="Use a copy of data for inplace scaling" help=" "/>
          </section>
      </when>
    </expand>
  </xml>

  <xml name="estimator_input_no_fit">
    <expand macro="feature_selection_estimator" />
    <conditional name="extra_estimator">
      <expand macro="feature_selection_extra_estimator" />
      <expand macro="feature_selection_estimator_choices" />
    </conditional>
  </xml>

  <xml name="feature_selection_all">
    <conditional name="feature_selection_algorithms">
      <param name="selected_algorithm" type="select" label="Select a feature selection algorithm">
        <option value="SelectFromModel" selected="true">SelectFromModel - Meta-transformer for selecting features based on importance weights</option>
        <option value="GenericUnivariateSelect" selected="true">GenericUnivariateSelect - Univariate feature selector with configurable strategy</option>

      </when>
      <when value="mutual_info_regression">
      </when-->
    </conditional>
  </xml>

  <xml name="feature_selection_score_function">
    <param argument="score_func" type="select" label="Select a score function">
      <option value="chi2">chi2 - Compute chi-squared stats between each non-negative feature and class</option>
      <option value="f_classif">f_classif - Compute the ANOVA F-value for the provided sample</option>
      <option value="f_regression">f_regression - Univariate linear regression tests</option>
      <option value="mutual_info_classif">mutual_info_classif - Estimate mutual information for a discrete target variable</option>
      <option value="mutual_info_regression">mutual_info_regression - Estimate mutual information for a continuous target variable</option>
    </param>
  </xml>

  <xml name="feature_selection_estimator">
    <param argument="estimator" type="select" label="Select an estimator" help="The base estimator from which the transformer is built.">
      <option value="svm.SVR(kernel=&quot;linear&quot;)">svm.SVR(kernel=&quot;linear&quot;)</option>
      <option value="svm.SVC(kernel=&quot;linear&quot;)">svm.SVC(kernel=&quot;linear&quot;)</option>
      <option value="svm.LinearSVC(penalty=&quot;l1&quot;, dual=False, tol=1e-3)">svm.LinearSVC(penalty=&quot;l1&quot;, dual=False, tol=1e-3)</option>
      <option value="linear_model.LassoCV()">linear_model.LassoCV()</option>
      <option value="ensemble.RandomForestRegressor(n_estimators = 1000, random_state = 42)">ensemble.RandomForestRegressor(n_estimators = 1000, random_state = 42)</option>
    </param>
  </xml>

  <xml name="feature_selection_extra_estimator">   
      <param name="has_estimator" type="select" label="Does your estimator on the list above?">
        <option value="yes">Yes, my estimator is on the list</option>
        <option value="no">No, I need make a new estimator</option>
        <yield/>
      </param>
  </xml>

  <xml name="feature_selection_estimator_choices">
    <when value="yes">
    </when>
    <when value="no">
      <param name="new_estimator" type="text" value="" label="Make a new estimator" />
    </when>
    <yield/>
  </xml>

  <xml name="feature_selection_methods">
    <conditional name="select_methods">
      <param name="selected_method" type="select" label="Select an operation">
          <option value="fit_transform">fit_transform - Fit to data, then transform it</option>
          <option value="get_support">get_support - Get a mask, or integer index, of the features selected</option>