comparison discriminant.xml @ 35:eeaf989f1024 draft

"planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/sklearn commit e2a5eade6d0e5ddf3a47630381a0ad90d80e8a04"

34:2d032cff49eb

<tool id="sklearn_discriminant_classifier" name="Discriminant Analysis" version="@VERSION@">
    <description></description>
    <macros>
        <import>main_macros.xml</import>
        <!--macro name="priors"-->
    </macros>
    <expand macro="python_requirements"/>
    <expand macro="macro_stdio"/>
    <version_command>echo "@VERSION@"</version_command>
    <command><![CDATA[
    python "$discriminant_script" '$inputs'
]]>
    </command>
    <configfiles>
        <inputs name="inputs"/>
        <configfile name="discriminant_script">
<![CDATA[
import json
import numpy as np
import pandas
import pickle
import sklearn.discriminant_analysis

            <param name="selected_algorithm" type="select" label="Classifier type">
                <option value="LinearDiscriminantAnalysis" selected="true">Linear Discriminant Classifier</option>
                <option value="QuadraticDiscriminantAnalysis">Quadratic Discriminant Classifier</option>
            </param>
            <when value="LinearDiscriminantAnalysis">
                <expand macro="sl_mixed_input"/>
                <section name="options" title="Advanced Options" expanded="False">
                    <param argument="solver" type="select" optional="true" label="Solver" help="">
                        <option value="svd" selected="true">Singular Value Decomposition</option>
                        <option value="lsqr">Least Squares Solution</option>
                        <option value="eigen">Eigenvalue Decomposition</option>
                    </param>
                    <!--param name="shrinkage"-->
                    <!--expand macro="priors"/-->
                    <param argument="n_components" type="integer" optional="true" value="" label="Number of components"
                        help="Number of components for dimensionality reduction. ( always less than  n_classes - 1 )"/>
                    <expand macro="tol" default_value="0.0001" help_text="Rank estimation threshold used in SVD solver."/>
                    <param argument="store_covariance" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolflase" checked="false"
                        label="Store covariance" help="Compute class covariance matrix."/>
                </section>
            </when>
            <when value="QuadraticDiscriminantAnalysis">
                <expand macro="sl_mixed_input"/>
                <section name="options" title="Advanced Options" expanded="False">
                    <!--expand macro="priors"/-->
                    <param argument="reg_param" type="float" optional="true" value="0.0" label="Regularization coefficient" help="Covariance estimate regularizer."/>
                    <expand macro="tol" default_value="0.00001" help_text="Rank estimation threshold used in SVD solver."/>
                    <param argument="store_covariance" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolflase" checked="false"
                        label="Store covariances" help="Compute class covariance matrixes."/>
                </section>
            </when>
        </expand>
    </inputs>
    <expand macro="output"/>
    <tests>
        <test>
            <param name="infile1" value="train.tabular" ftype="tabular"/>
            <param name="infile2" value="train.tabular" ftype="tabular"/>
            <param name="header1" value="True"/>
            <param name="header2" value="True"/>
            <param name="col1" value="1,2,3,4"/>
            <param name="col2" value="5"/>
            <param name="selected_task" value="train"/>
            <param name="selected_algorithm" value="LinearDiscriminantAnalysis"/>
            <param name="solver" value="svd" />
            <param name="store_covariance" value="True"/>
            <output name="outfile_fit" file="lda_model01" compare="sim_size" delta="1"/>
        </test>
        <test>
            <param name="infile1" value="train.tabular" ftype="tabular"/>
            <param name="infile2" value="train.tabular" ftype="tabular"/>
            <param name="header1" value="True"/>
            <param name="header2" value="True"/>
            <param name="col1" value="1,2,3,4"/>
            <param name="col2" value="5"/>
            <param name="selected_task" value="train"/>
            <param name="selected_algorithm" value="LinearDiscriminantAnalysis"/>
            <param name="solver" value="lsqr"/>
            <output name="outfile_fit" file="lda_model02" compare="sim_size" delta="1"/>
        </test>
        <test>
            <param name="infile1" value="train.tabular" ftype="tabular"/>
            <param name="infile2" value="train.tabular" ftype="tabular"/>
            <param name="header1" value="True"/>
            <param name="header2" value="True"/>
            <param name="col1" value="1,2,3,4"/>
            <param name="col2" value="5"/>
            <param name="selected_task" value="train"/>
            <param name="selected_algorithm" value="QuadraticDiscriminantAnalysis"/>
            <output name="outfile_fit" file="qda_model01" compare="sim_size" delta="1"/>
        </test>
        <test>
            <param name="infile_model" value="lda_model01" ftype="zip"/>
            <param name="infile_data" value="test.tabular" ftype="tabular"/>
            <param name="header" value="True"/>
            <param name="selected_task" value="load"/>
            <output name="outfile_predict" file="lda_prediction_result01.tabular"/>
        </test>
        <test>
            <param name="infile_model" value="lda_model02" ftype="zip"/>
            <param name="infile_data" value="test.tabular" ftype="tabular"/>
            <param name="header" value="True"/>
            <param name="selected_task" value="load"/>
            <output name="outfile_predict" file="lda_prediction_result02.tabular"/>
        </test>
        <test>
            <param name="infile_model" value="qda_model01" ftype="zip"/>
            <param name="infile_data" value="test.tabular" ftype="tabular"/>
            <param name="header" value="True"/>
            <param name="selected_task" value="load"/>
            <output name="outfile_predict" file="qda_prediction_result01.tabular"/>
        </test>
    </tests>
    <help><![CDATA[
***What it does***
Linear and Quadratic Discriminant Analysis are two classic classifiers with a linear and a quadratic decision surface respectively. These classifiers are fast and easy to interprete.

Discriminant Analysis is based on sklearn.discriminant_analysis library from Scikit-learn.
For more information please refer to `Scikit-learn site`_.

.. _`Scikit-learn site`: http://scikit-learn.org/stable/modules/lda_qda.html

    ]]></help>
    <expand macro="sklearn_citation"/>
</tool>

35:eeaf989f1024

<tool id="sklearn_discriminant_classifier" name="Discriminant Analysis" version="@VERSION@" profile="20.05">
    <description></description>
    <macros>
        <import>main_macros.xml</import>
        <!--macro name="priors"-->
    </macros>
    <expand macro="python_requirements" />
    <expand macro="macro_stdio" />
    <version_command>echo "@VERSION@"</version_command>
    <command><![CDATA[
    python "$discriminant_script" '$inputs'
]]>
    </command>
    <configfiles>
        <inputs name="inputs" />
        <configfile name="discriminant_script">
            <![CDATA[
import json
import numpy as np
import pandas
import pickle
import sklearn.discriminant_analysis

            <param name="selected_algorithm" type="select" label="Classifier type">
                <option value="LinearDiscriminantAnalysis" selected="true">Linear Discriminant Classifier</option>
                <option value="QuadraticDiscriminantAnalysis">Quadratic Discriminant Classifier</option>
            </param>
            <when value="LinearDiscriminantAnalysis">
                <expand macro="sl_mixed_input" />
                <section name="options" title="Advanced Options" expanded="False">
                    <param argument="solver" type="select" optional="true" label="Solver" help="">
                        <option value="svd" selected="true">Singular Value Decomposition</option>
                        <option value="lsqr">Least Squares Solution</option>
                        <option value="eigen">Eigenvalue Decomposition</option>
                    </param>
                    <!--param name="shrinkage"-->
                    <!--expand macro="priors"/-->
                    <param argument="n_components" type="integer" optional="true" value="" label="Number of components" help="Number of components for dimensionality reduction. ( always less than  n_classes - 1 )" />
                    <expand macro="tol" default_value="0.0001" help_text="Rank estimation threshold used in SVD solver." />
                    <param argument="store_covariance" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolflase" checked="false" label="Store covariance" help="Compute class covariance matrix." />
                </section>
            </when>
            <when value="QuadraticDiscriminantAnalysis">
                <expand macro="sl_mixed_input" />
                <section name="options" title="Advanced Options" expanded="False">
                    <!--expand macro="priors"/-->
                    <param argument="reg_param" type="float" optional="true" value="0.0" label="Regularization coefficient" help="Covariance estimate regularizer." />
                    <expand macro="tol" default_value="0.00001" help_text="Rank estimation threshold used in SVD solver." />
                    <param argument="store_covariance" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolflase" checked="false" label="Store covariances" help="Compute class covariance matrixes." />
                </section>
            </when>
        </expand>
    </inputs>
    <expand macro="output" />
    <tests>
        <test>
            <param name="infile1" value="train.tabular" ftype="tabular" />
            <param name="infile2" value="train.tabular" ftype="tabular" />
            <param name="header1" value="True" />
            <param name="header2" value="True" />
            <param name="col1" value="1,2,3,4" />
            <param name="col2" value="5" />
            <param name="selected_task" value="train" />
            <param name="selected_algorithm" value="LinearDiscriminantAnalysis" />
            <param name="solver" value="svd" />
            <param name="store_covariance" value="True" />
            <output name="outfile_fit" file="lda_model01" compare="sim_size" delta="1" />
        </test>
        <test>
            <param name="infile1" value="train.tabular" ftype="tabular" />
            <param name="infile2" value="train.tabular" ftype="tabular" />
            <param name="header1" value="True" />
            <param name="header2" value="True" />
            <param name="col1" value="1,2,3,4" />
            <param name="col2" value="5" />
            <param name="selected_task" value="train" />
            <param name="selected_algorithm" value="LinearDiscriminantAnalysis" />
            <param name="solver" value="lsqr" />
            <output name="outfile_fit" file="lda_model02" compare="sim_size" delta="1" />
        </test>
        <test>
            <param name="infile1" value="train.tabular" ftype="tabular" />
            <param name="infile2" value="train.tabular" ftype="tabular" />
            <param name="header1" value="True" />
            <param name="header2" value="True" />
            <param name="col1" value="1,2,3,4" />
            <param name="col2" value="5" />
            <param name="selected_task" value="train" />
            <param name="selected_algorithm" value="QuadraticDiscriminantAnalysis" />
            <output name="outfile_fit" file="qda_model01" compare="sim_size" delta="1" />
        </test>
        <test>
            <param name="infile_model" value="lda_model01" ftype="zip" />
            <param name="infile_data" value="test.tabular" ftype="tabular" />
            <param name="header" value="True" />
            <param name="selected_task" value="load" />
            <output name="outfile_predict" file="lda_prediction_result01.tabular" />
        </test>
        <test>
            <param name="infile_model" value="lda_model02" ftype="zip" />
            <param name="infile_data" value="test.tabular" ftype="tabular" />
            <param name="header" value="True" />
            <param name="selected_task" value="load" />
            <output name="outfile_predict" file="lda_prediction_result02.tabular" />
        </test>
        <test>
            <param name="infile_model" value="qda_model01" ftype="zip" />
            <param name="infile_data" value="test.tabular" ftype="tabular" />
            <param name="header" value="True" />
            <param name="selected_task" value="load" />
            <output name="outfile_predict" file="qda_prediction_result01.tabular" />
        </test>
    </tests>
    <help><![CDATA[
***What it does***
Linear and Quadratic Discriminant Analysis are two classic classifiers with a linear and a quadratic decision surface respectively. These classifiers are fast and easy to interprete.

Discriminant Analysis is based on sklearn.discriminant_analysis library from Scikit-learn.
For more information please refer to `Scikit-learn site`_.

.. _`Scikit-learn site`: http://scikit-learn.org/stable/modules/lda_qda.html

    ]]>    </help>
    <expand macro="sklearn_citation" />
</tool>