comparison main_macros.xml @ 2:48ac998ec1b9 draft

planemo upload for repository https://github.com/bgruening/galaxytools/tools/sklearn commit 6c002ea2995c85f5f16adb2ef1c6be82dfbc5417

1:a43963a460fb

    <stdio>
        <exit_code range="1:" level="fatal" description="Error occurred. Please check Tool Standard Error" />
    </stdio>
  </xml>

  <xml name="train_loadConditional" token_train="tabular" token_data="tabular" token_model="txt">
    <conditional name="selected_tasks">
        <param name="selected_task" type="select" label="Select a Classification Task">
            <option value="load">Load a model and predict</option>
            <option value="train" selected="true">Train a model</option>
        </param>
        <when value="load">
            <param name="infile_model" type="data" format="@MODEL@" label="Models" help="Select a model file." />
            <param name="infile_data" type="data" format="@DATA@" label="Data (tabular)" help="Select the dataset you want to classify."/>
            <conditional name="prediction_options">

            </conditional>
        </when>
    </conditional>
  </xml>

  <xml name="advanced_section">
    <section name="options" title="Advanced Options" expanded="False">
      <yield />
    </section>
  </xml>

  <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="tol" token_default_value="0.0" token_help_text="Early stopping heuristics based on the relative center changes. Set to default (0.0) to disable this convergence detection.">
        <param argument="tol" type="float" optional="true" value="@DEFAULT_VALUE@" label="Tolerance" help="@HELP_TEXT@"/>
  </xml>

  <xml name="n_clusters" token_default_value="8">

    <param argument="degree" type="integer" optional="true" value="@DEFAULT_VALUE@" label="@LABEL@" help="@HELP_TEXT@"/>
  </xml>

  <xml name="coef0" token_default_value="1" token_label="Zero coefficient" token_help_text=" ">
    <param argument="coef0" type="integer" optional="true" value="@DEFAULT_VALUE@" label="@LABEL@" help="@HELP_TEXT@"/>
  </xml>    

  <xml name="multiple_input" token_name="input_files" token_max_num="10" token_format="txt" token_label="Sparse matrix file (.mtx, .txt)" token_help_text="Specify a sparse matrix file in .txt format.">
    <repeat name="@NAME@" min="1" max="@MAX_NUM@" title="Select input file(s):">
        <param name="input" type="data" format="@FORMAT@" label="@LABEL@" help="@HELP_TEXT@"/>
    </repeat>
  </xml>  

  <xml name="eden_citation">
    <citations>
        <citation type="bibtex">
            @misc{fabrizio_costa_2015_15094,
              author       = {Fabrizio Costa and
                              Björn Grüning and
                              gigolo},
              title        = {EDeN: EDeN - Graph Vectorizer},
              month        = feb,
              year         = 2015,
              doi          = {10.5281/zenodo.15094},
              url          = {http://dx.doi.org/10.5281/zenodo.15094}
                    }
                        }
        </citation>
    </citations>
  </xml>

  <xml name="sklearn_citation">
    <citations>
        <citation type="bibtex">
            @article{scikit-learn,
             title={Scikit-learn: Machine Learning in {P}ython},
             author={Pedregosa, F. and Varoquaux, G. and Gramfort, A. and Michel, V.
                     and Thirion, B. and Grisel, O. and Blondel, M. and Prettenhofer, P.
                     and Weiss, R. and Dubourg, V. and Vanderplas, J. and Passos, A. and
                     Cournapeau, D. and Brucher, M. and Perrot, M. and Duchesnay, E.},
             journal={Journal of Machine Learning Research},
             volume={12},
             pages={2825--2830},
             year={2011}
             url = {https://github.com/scikit-learn/scikit-learn}
            }
        </citation>
    </citations>
  </xml>

  <xml name="scipy_citation">
    <citations>
        <citation type="bibtex">
          @Misc{,
          author =    {Eric Jones and Travis Oliphant and Pearu Peterson and others},
          title =     {{SciPy}: Open source scientific tools for {Python}},
          year =      {2001--},
          url = "http://www.scipy.org/",
          note = {[Online; accessed 2016-04-09]}
        }
        </citation>
    </citations>
  </xml>


  <xml name="nn_advanced_options">
    <section name="options" title="Advanced Options" expanded="False">
      <yield/>
      <param argument="weights" type="select" label="Weight function" help="Used in prediction.">
          <option value="uniform" selected="true" help="Uniform weights. All points in each neighborhood are weighted equally.">Uniform</option>

          <param argument="batch_size" type="integer" optional="true" value="500" label="Batch size" help="Number of rows to be processed in each batch run."/>
      </section>
    </when>
  </xml>

</macros>

2:48ac998ec1b9

    <stdio>
        <exit_code range="1:" level="fatal" description="Error occurred. Please check Tool Standard Error" />
    </stdio>
  </xml>


  <!--Generic interface-->
  <xml name="train_loadConditional" token_train="tabular" token_data="tabular" token_model="txt">
    <conditional name="selected_tasks">
        <param name="selected_task" type="select" label="Select a Classification Task">
            <option value="train" selected="true">Train a model</option>
            <option value="load">Load a model and predict</option>
        </param>
        <when value="load">
            <param name="infile_model" type="data" format="@MODEL@" label="Models" help="Select a model file." />
            <param name="infile_data" type="data" format="@DATA@" label="Data (tabular)" help="Select the dataset you want to classify."/>
            <conditional name="prediction_options">

            </conditional>
        </when>
    </conditional>
  </xml>

  <xml name="sl_Conditional" token_train="tabular" token_data="tabular" token_model="txt">
    <conditional name="selected_tasks">
        <param name="selected_task" type="select" label="Select a Classification Task">
            <option value="train" selected="true">Train a model</option>
            <option value="load">Load a model and predict</option>
        </param>
        <when value="load">
            <param name="infile_model" type="data" format="@MODEL@" label="Models" help="Select a model file." />
            <param name="infile_data" type="data" format="@DATA@" label="Data (tabular)" help="Select the dataset you want to classify."/>
            <conditional name="prediction_options">
                <param name="prediction_option" type="select" label="Select the type of prediction">
                    <option value="predict">Predict class labels</option>
                    <option value="advanced">Include advanced options</option>
                </param>
                <when value="predict">
                </when>
                <when value="advanced">
                </when>
            </conditional>
        </when>
        <when value="train">
            <conditional name="selected_algorithms">
                <yield />
            </conditional>
        </when>
    </conditional>
  </xml>

  <xml name="advanced_section">
    <section name="options" title="Advanced Options" expanded="False">
      <yield />
    </section>
  </xml>


  <!--Ensemble methods-->
  <xml name="n_estimators" token_default_value="10" token_help=" ">
    <param argument="n_estimators" type="integer" optional="true" value="@DEFAULT_VALUE@" label="Number of trees in the forest" help="@HELP@"/>
  </xml>

  <xml name="max_depth" token_default_value="" token_help=" ">
    <param argument="max_depth" type="integer" optional="true" value="@DEFAULT_VALUE@" label="Maximum depth of the tree" help="@HELP@"/>
  </xml>

  <xml name="min_samples_split" token_default_value="2" token_help=" ">
    <param argument="min_samples_split" type="integer" optional="true" value="@DEFAULT_VALUE@" label="Maximum depth of the tree" help="@HELP@"/>
  </xml>

  <xml name="min_samples_leaf" token_default_value="1" token_help=" ">
    <param argument="min_samples_leaf" type="integer" optional="true" value="@DEFAULT_VALUE@" label="Minimum number of samples in newly created leaves" help="@HELP@"/>
  </xml>
  
  <xml name="min_weight_fraction_leaf" token_default_value="0.0" token_help=" ">
    <param argument="min_weight_fraction_leaf" type="float" optional="true" value="@DEFAULT_VALUE@" label="Minimum weighted fraction of the input samples required to be at a leaf node" help="@HELP@"/>
  </xml>

  <xml name="max_leaf_nodes" token_default_value="" token_help=" ">
    <param argument="max_leaf_nodes" type="integer" optional="true" value="@DEFAULT_VALUE@" label="Maximum number of leaf nodes in best-first method" help="@HELP@"/>
  </xml>  

  <xml name="bootstrap" token_checked="true" token_help=" ">
    <param argument="bootstrap" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolflase" checked="@CHECKED@" label="Use bootstrap samples for building trees." help="@HELP@"/>
  </xml>  

  <xml name="criterion" token_help=" ">
    <param argument="criterion" type="select" label="Function to measure the quality of a split"  help=" ">
        <option value="gini" selected="true">Gini impurity</option>
        <option value="entropy">Information gain</option>
        <yield/>
    </param>
  </xml>

  <xml name="oob_score" token_checked="flase" token_help=" ">
    <param argument="oob_score" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolflase" checked="@CHECKED@" label="Use out-of-bag samples to estimate the generalization error" help="@HELP@"/>
  </xml>

  <xml name="max_features" token_default_value="auto" token_help="This could be an integer, float, string, or None. For more information please refer to help. ">
    <param argument="max_features" type="text" optional="true" value="@DEFAULT_VALUE@" label="Number of features for finding the best split" help="@HELP@"/>
  </xml>   

  <xml name="learning_rate" token_default_value="1.0" token_help=" ">
    <param argument="learning_rate" type="float" optional="true" value="@DEFAULT_VALUE@" label="Learning rate" help="@HELP@"/>
  </xml>


  <!--Parameters-->
  <xml name="tol" token_default_value="0.0" token_help_text="Early stopping heuristics based on the relative center changes. Set to default (0.0) to disable this convergence detection.">
        <param argument="tol" type="float" optional="true" value="@DEFAULT_VALUE@" label="Tolerance" help="@HELP_TEXT@"/>
  </xml>

  <xml name="n_clusters" token_default_value="8">

    <param argument="degree" type="integer" optional="true" value="@DEFAULT_VALUE@" label="@LABEL@" help="@HELP_TEXT@"/>
  </xml>

  <xml name="coef0" token_default_value="1" token_label="Zero coefficient" token_help_text=" ">
    <param argument="coef0" type="integer" optional="true" value="@DEFAULT_VALUE@" label="@LABEL@" help="@HELP_TEXT@"/>
  </xml>

  <xml name="pos_label" token_default_value="">
    <param argument="pos_label" type="integer" optional="true" value="@DEFAULT_VALUE@" label="Label of the positive class" help=" "/>
  </xml>

  <xml name="average">
    <param argument="average" type="select" optional="True" label="Averaging type" help=" ">
      <option value="binary" selected="true" help="Only report results for the class specified by pos_label. Applicable only on binary classification.">binary</option>
      <option value="micro" help="Calculate metrics globally by counting the total true positives, false negatives and false positives.">micro</option>
      <option value="samples" help="Calculate metrics for each instance, and find their average (only meaningful for multilabel).">samples</option>
      <!--option value="macro" help=""></option-->
      <!--option value="weighted" help=""></option-->
    </param>
  </xml>

  <xml name="beta">
    <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="multiple_input" token_name="input_files" token_max_num="10" token_format="txt" token_label="Sparse matrix file (.mtx, .txt)" token_help_text="Specify a sparse matrix file in .txt format.">
    <repeat name="@NAME@" min="1" max="@MAX_NUM@" title="Select input file(s):">
        <param name="input" type="data" format="@FORMAT@" label="@LABEL@" help="@HELP_TEXT@"/>
    </repeat>
  </xml> 

  <xml name="sparse_target" token_label1="Select a sparse matrix:" token_label2="Select the tabular containing true labels:" token_multiple="False" token_format1="txt" token_format2="tabular" token_help1="" token_help2="">
    <param name="infile1" type="data" format="@FORMAT1@" label="@LABEL1@" help="@HELP1@"/>
    <param name="infile2" type="data" format="@FORMAT2@" label="@LABEL2@" help="@HELP2@"/>
    <param name="col2" multiple="@MULTIPLE@" type="data_column" data_ref="infile2" label="Select target column(s):"/>
  </xml>

  <xml name="sl_mixed_input">
    <conditional name="input_options">
      <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="sample_cols" multiple1="true"/>
      </when>
      <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/>
      <param argument="weights" type="select" label="Weight function" help="Used in prediction.">
          <option value="uniform" selected="true" help="Uniform weights. All points in each neighborhood are weighted equally.">Uniform</option>

          <param argument="batch_size" type="integer" optional="true" value="500" label="Batch size" help="Number of rows to be processed in each batch run."/>
      </section>
    </when>
  </xml>

  <xml name="sparse_preprocessors">
    <param name="selected_pre_processor" type="select" label="Select a preprocessor:">
      <option value="StandardScaler" selected="true">Standardize features by removing the mean and scaling to unit variance</option>
      <option value="Binarizer">Binarize data</option>
      <option value="Imputer">Complete missing values</option>
      <option value="MaxAbsScaler">Scale features by their maximum absolute value</option>
      <option value="Normalizer">Normalize samples individually to unit norm</option>
      <yield/>
    </param>
  </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="boolflase" 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="boolflase" 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="median">Replace missing values using the median along the axis</option>
                <option value="most_frequent">Replace missing using the most frequent value along the axis</option>
            </param>
            <param argument="missing_values" type="text" optional="true" value="NaN" label="Placeholder for missing values" help="For missing values encoded as numpy.nan, use the string value “NaN”"/>
            <param argument="axis" type="select" optional="true" label="The axis along which to impute" help=" ">
                <option value="0" selected="true">Impute along columns</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="boolflase" checked="true" label="Use a copy of data for performing inplace scaling" help=" "/>
            <param argument="with_mean" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolflase" checked="true" label="Center the data before scaling" help=" "/>
            <param argument="with_std" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolflase" 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="boolflase" 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>
                <param argument="copy" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolflase" checked="true" label="Use a copy of data for precomputing row normalization" help=" "/>
            </param>
        </section>
    </when>
    <yield/>
  </xml>


  <!--Citations-->
  <xml name="eden_citation">
    <citations>
        <citation type="bibtex">
            @misc{fabrizio_costa_2015_15094,
              author       = {Fabrizio Costa and
                              Björn Grüning and
                              gigolo},
              title        = {EDeN: EDeN - Graph Vectorizer},
              month        = feb,
              year         = 2015,
              doi          = {10.5281/zenodo.15094},
              url          = {http://dx.doi.org/10.5281/zenodo.15094}
                    }
                        }
        </citation>
    </citations>
  </xml>

  <xml name="sklearn_citation">
    <citations>
        <citation type="bibtex">
            @article{scikit-learn,
             title={Scikit-learn: Machine Learning in {P}ython},
             author={Pedregosa, F. and Varoquaux, G. and Gramfort, A. and Michel, V.
                     and Thirion, B. and Grisel, O. and Blondel, M. and Prettenhofer, P.
                     and Weiss, R. and Dubourg, V. and Vanderplas, J. and Passos, A. and
                     Cournapeau, D. and Brucher, M. and Perrot, M. and Duchesnay, E.},
             journal={Journal of Machine Learning Research},
             volume={12},
             pages={2825--2830},
             year={2011}
             url = {https://github.com/scikit-learn/scikit-learn}
            }
        </citation>
    </citations>
  </xml>

  <xml name="scipy_citation">
    <citations>
        <citation type="bibtex">
          @Misc{,
          author =    {Eric Jones and Travis Oliphant and Pearu Peterson and others},
          title =     {{SciPy}: Open source scientific tools for {Python}},
          year =      {2001--},
          url = "http://www.scipy.org/",
          note = {[Online; accessed 2016-04-09]}
        }
        </citation>
    </citations>
  </xml>

</macros>