view main_macros.xml @ 0:25b93d50158f draft

planemo upload for repository https://github.com/bgruening/galaxytools/tools/sklearn commit a6e80305ed0892c8163d690a2d376d6b454824de-dirty

<macros>
  <token name="@VERSION@">0.9</token>

  <xml name="python_requirements">
    <requirements>
        <requirement type="package" version="0.2.1b">eden</requirement>
        <yield />
    </requirements>
  </xml>

  <xml name="macro_stdio">
    <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">
                <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">
            <param name="infile_train" type="data" format="@TRAIN@" label="Training samples (tabular)" />
            <conditional name="selected_algorithms">
                <yield />
            </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="n_clusters" type="integer" optional="true" value="@DEFAULT_VALUE@" label="Number of clusters" help=" "/>
  </xml>

  <xml name="fit_intercept" token_checked="true">
    <param argument="fit_intercept" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolflase" checked="@CHECKED@" label="Estimate the intercept" help="If false, the data is assumed to be already centered."/>
  </xml>

  <xml name="n_iter" token_default_value="5" token_help_text="The number of passes over the training data (aka epochs). ">
    <param argument="n_iter" type="integer" optional="true" value="@DEFAULT_VALUE@" label="Number of iterations" help="@HELP_TEXT@"/>
  </xml>

  <xml name="shuffle" token_checked="true" token_help_text=" " token_label="Shuffle data after each iteration">
    <param argument="shuffle" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolflase" checked="@CHECKED@" label="@LABEL@" help="@HELP_TEXT@"/>
  </xml>

  <xml name="random_state" token_default_value="" token_help_text="Integer number. The seed of the pseudo random number generator to use when shuffling the data. A fixed seed allows reproducible results.">
    <param argument="random_state" type="integer" optional="true" value="@DEFAULT_VALUE@" label="Random seed number" help="@HELP_TEXT@"/>
  </xml>

  <xml name="warm_start" token_checked="true" token_help_text="When set to True, reuse the solution of the previous call to fit as initialization,otherwise, just erase the previous solution.">
    <param argument="warm_start" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolflase" checked="@CHECKED@" label="Perform warm start" help="@HELP_TEXT@"/>
  </xml>

  <xml name="C" token_default_value="1.0" token_help_text="Penalty parameter C of the error term.">
    <param argument="C" type="float" optional="true" value="@DEFAULT_VALUE@" label="Penalty parameter" help="@HELP_TEXT@"/>
  </xml>

  <!--xml name="class_weight" token_default_value="" token_help_text="">
    <param argument="class_weight" type="" optional="true" value="@DEFAULT_VALUE@" label="" help="@HELP_TEXT@"/>
  </xml-->

  <xml name="alpha" token_default_value="0.0001" token_help_text="Constant that multiplies the regularization term if regularization is used. ">
    <param argument="alpha" type="float" optional="true" value="@DEFAULT_VALUE@" label="Regularization coefficient" help="@HELP_TEXT@"/>
  </xml>

  <xml name="n_samples" token_default_value="100" token_help_text="The total number of points equally divided among clusters.">
    <param argument="n_samples" type="integer" optional="true" value="@DEFAULT_VALUE@" label="Number of samples" help="@HELP_TEXT@"/>
  </xml>

  <xml name="n_features" token_default_value="2" token_help_text="Number of different numerical properties produced for each sample.">
    <param argument="n_features" type="integer" optional="true" value="@DEFAULT_VALUE@" label="Number of features" help="@HELP_TEXT@"/>
  </xml>

  <xml name="noise" token_default_value="0.0" token_help_text="Floating point number. ">
    <param argument="noise" type="float" optional="true" value="@DEFAULT_VALUE@" label="Standard deviation of the Gaussian noise added to the data" help="@HELP_TEXT@"/>
  </xml>

  <xml name="C" token_default_value="1.0" token_help_text="Penalty parameter C of the error term. ">
      <param argument="C" type="float" optional="true" value="@DEFAULT_VALUE@" label="Penalty parameter" help="@HELP_TEXT@"/>
  </xml>

  <xml name="max_iter" token_default_value="300" token_label="Maximum number of iterations per single run" token_help_text=" ">
      <param argument="max_iter" type="integer" optional="true" value="@DEFAULT_VALUE@" label="@LABEL@" help="@HELP_TEXT@"/>
  </xml>

  <xml name="n_init" token_default_value="10" >
      <param argument="n_init" type="integer" optional="true" value="@DEFAULT_VALUE@" label="Number of runs with different centroid seeds" help=" "/>
  </xml>

  <xml name="init">
      <param argument="init" type="select" label="Centroid initialization method"  help="''k-means++'' selects initial cluster centers that speed up convergence. ''random'' chooses k observations (rows) at random from data as initial centroids.">
          <option value="k-means++">k-means++</option>
          <option value="random">random</option>
      </param>
  </xml>

  <xml name="multiple_sparse">
    <repeat name="sparse_inputs" min="1" max="10" title="Inputs">
        <param name="input" type="data" format="txt" label="Sparse matrix file (.mtx, .txt)" help="Specify a sparse matrix file in .txt format."/>
    </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>
          <option value="distance" help="Weight points by the inverse of their distance.">Distance</option>
      </param>
      <param argument="algorithm" type="select" label="Neighbor selection algorithm" help=" ">
          <option value="auto" selected="true">Auto</option>
          <option value="ball_tree">BallTree</option>
          <option value="kd_tree">KDTree</option>
          <option value="brute">Brute-force</option>
      </param>
      <param argument="leaf_size" type="integer" value="30" label="Leaf size" help="Used with BallTree and KDTree. Affects the time and memory usage of the constructed tree."/>
      <!--param name="metric"-->
      <!--param name="p"-->
      <!--param name="metric_params"-->
    </section>
  </xml>

  <xml name="svc_advanced_options">
    <section name="options" title="Advanced Options" expanded="False">
        <yield/>
        <param argument="kernel" type="select" optional="true" label="Kernel type" help="Kernel type to be used in the algorithm. If none is given, ‘rbf’ will be used.">
            <option value="rbf" selected="true">rbf</option>
            <option value="linear">linear</option>
            <option value="poly">poly</option>
            <option value="sigmoid">sigmoid</option>
            <option value="precomputed">precomputed</option>
        </param>
        <param argument="degree" type="integer" optional="true" value="3" label="Degree of the polynomial (polynomial kernel only)" help="Ignored by other kernels. dafault : 3 "/>
        <!--TODO: param argument="gamma" float, optional (default=’auto’) -->
        <param argument="coef0" type="float" optional="true" value="0.0" label="Zero coefficient (polynomial and sigmoid kernels only)" help="Independent term in kernel function. dafault: 0.0 "/>
        <param argument="shrinking" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolflase" checked="true" label="Use the shrinking heuristic" help=" "/>
        <param argument="probability" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolflase" checked="false" label="Enable probability estimates. " help="This must be enabled prior to calling fit, and will slow down that method."/>
        <!-- param argument="cache_size"-->
        <!--expand macro="class_weight"/-->
        <expand macro="tol" default_value="0.001" help_text="Tolerance for stopping criterion. "/> 
        <expand macro="max_iter" default_value="-1" label="Solver maximum number of iterations" help_text="Hard limit on iterations within solver, or -1 for no limit."/>
        <!--param argument="decision_function_shape"-->
        <expand macro="random_state" help_text="Integer number. The seed of the pseudo random number generator to use when shuffling the data for probability estimation. A fixed seed allows reproducible results."/>
    </section>
  </xml>

  <xml name="spectral_clustering_advanced_options">
    <section name="options" title="Advanced Options" expanded="False">
        <expand macro="n_clusters"/>
        <param argument="eigen_solver" type="select" value="" label="Eigen solver" help="The eigenvalue decomposition strategy to use.">
            <option value="arpack" selected="true">arpack</option>
            <option value="lobpcg">lobpcg</option>
            <option value="amg">amg</option>
            <!--None-->
        </param>
        <expand macro="random_state"/>
        <expand macro="n_init"/>
        <param argument="gamma" type="float" optional="true" value="1.0" label="Kernel scaling factor" help="Scaling factor of RBF, polynomial, exponential chi^2 and sigmoid affinity kernel. Ignored for affinity=''nearest_neighbors''."/>
        <param argument="affinity" type="select" label="Affinity" help="Affinity kernel to use. ">
            <option value="rbf" selected="true">RBF</option>
            <option value="precomputed">precomputed</option>
            <option value="nearest_neighbors">Nearset neighbors</option>
        </param>
        <param argument="n_neighbors" type="integer" optional="true" value="10" label="Number of neighbors" help="Number of neighbors to use when constructing the affinity matrix using the nearest neighbors method. Ignored for affinity=''rbf''"/>
        <!--param argument="eigen_tol"-->
        <param argument="assign_labels" type="select" label="Assign labels" help="The strategy to use to assign labels in the embedding space.">
            <option value="kmeans" selected="true">kmeans</option>
            <option value="discretize">discretize</option>
        </param>
        <param argument="degree" type="integer" optional="true" value="3" label="Degree of the polynomial (polynomial kernel only)" help="Ignored by other kernels. dafault : 3 "/>
        <param argument="coef0" type="integer" optional="true" value="1" label="Zero coefficient (polynomial and sigmoid kernels only)" help="Ignored by other kernels. dafault : 1 "/>
        <!--param argument="kernel_params"-->
    </section>
  </xml>

  <xml name="minibatch_kmeans_advanced_options">
    <section name="options" title="Advanced Options" expanded="False">
        <expand macro="n_clusters"/>
        <expand macro="init"/>
        <expand macro="n_init" default_value="3"/>
        <expand macro="max_iter" default_value="100"/>
        <expand macro="tol" help_text="Early stopping heuristics based on normalized center change. To disable set to 0.0 ."/> 
        <expand macro="random_state"/>
        <param argument="batch_size" type="integer" optional="true" value="100" label="Batch size" help="Size of the mini batches."/>
        <!--param argument="compute_labels"-->
        <param argument="max_no_improvement" type="integer" optional="true" value="10" label="Maximum number of improvement attempts" help="
        Convergence detection based on inertia (the consecutive number of mini batches that doe not yield an improvement on the smoothed inertia).
        To disable, set max_no_improvement to None. "/>
        <param argument="init_size" type="integer" optional="true" value="" label="Number of random initialization samples" help="Number of samples to randomly sample for speeding up the initialization . ( default: 3 * batch_size )"/>
        <param argument="reassignment_ratio" type="float" optional="true" value="0.01" label="Re-assignment ratio" help="Controls the fraction of the maximum number of counts for a center to be reassigned. Higher values yield better clustering results."/>
    </section>
  </xml>

  <xml name="kmeans_advanced_options">
    <section name="options" title="Advanced Options" expanded="False">
      <expand macro="n_clusters"/>
      <expand macro="init"/>
      <expand macro="n_init"/>
      <expand macro="max_iter"/>
      <expand macro="tol" default_value="0.0001" help_text="Relative tolerance with regards to inertia to declare convergence."/>
      <!--param argument="precompute_distances"/-->
      <expand macro="random_state"/>
      <param argument="copy_x" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolflase" checked="true" label="Use a copy of data for precomputing distances" help="Mofifying the original data introduces small numerical differences caused by subtracting and then adding the data mean."/>
    </section>
  </xml>

  <xml name="birch_advanced_options">
    <section name="options" title="Advanced Options" expanded="False">
      <param argument="threshold" type="float" optional="true" value="0.5" label="Subcluster radius threshold" help="The radius of the subcluster obtained by merging a new sample; the closest subcluster should be less than the threshold to avoid a new subcluster."/>
      <param argument="branching_factor" type="integer" optional="true" value="50" label="Maximum number of subclusters per branch" help="Maximum number of CF subclusters in each node."/>
      <expand macro="n_clusters" default_value="3"/>
      <!--param argument="compute_labels"/-->
    </section>
  </xml>

  <xml name="dbscan_advanced_options">
    <section name="options" title="Advanced Options" expanded="False">
      <param argument="eps" type="float" optional="true" value="0.5" label="Maximum neighborhood distance" help="The maximum distance between two samples for them to be considered as in the same neighborhood."/>
      <param argument="min_samples" type="integer" optional="true" value="5" label="Minimal core point density" help="The number of samples (or total weight) in a neighborhood for a point (including the point itself) to be considered as a core point."/>
      <param argument="metric" type="text" optional="true" value="euclidean" label="Metric" help="The metric to use when calculating distance between instances in a feature array."/>
      <param argument="algorithm" type="select" label="Pointwise distance computation algorithm" help="The algorithm to be used by the NearestNeighbors module to compute pointwise distances and find nearest neighbors.">
          <option value="auto" selected="true">auto</option>
          <option value="ball_tree">ball_tree</option>
          <option value="kd_tree">kd_tree</option>
          <option value="brute">brute</option>
      </param>
      <param argument="leaf_size" type="integer" optional="true" value="30" label="Leaf size" help="Leaf size passed to BallTree or cKDTree. Memory and time efficieny factor in tree constrution and querying."/>
    </section>
  </xml>

  <xml name="clustering_algorithms_options">
    <conditional name="algorithm_options">
      <param name="selected_algorithm" type="select" label="Clustering Algorithm">
          <option value="KMeans" selected="true">KMeans</option>
          <option value="SpectralClustering">Spectral Clustering</option>
          <option value="MiniBatchKMeans">Mini Batch KMeans</option>
          <option value="DBSCAN">DBSCAN</option>
          <option value="Birch">Birch</option>
      </param>
      <when value="KMeans">
          <expand macro="kmeans_advanced_options"/>
      </when>
      <when value="DBSCAN">
          <expand macro="dbscan_advanced_options"/>
      </when>
      <when value="Birch">
          <expand macro="birch_advanced_options"/>
      </when>
      <when value="SpectralClustering">
          <expand macro="spectral_clustering_advanced_options"/>
      </when>
      <when value="MiniBatchKMeans">
          <expand macro="minibatch_kmeans_advanced_options"/>
      </when>
    </conditional>
  </xml>
</macros>