comparison ensemble.xml @ 35:19d6c2745d34 draft

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

34:841a6cc5fc58

<tool id="sklearn_ensemble" name="Ensemble methods" version="@VERSION@">
    <description>for classification and regression</description>
    <macros>
        <import>main_macros.xml</import>
    </macros>
    <expand macro="python_requirements"/>
    <expand macro="macro_stdio"/>
    <version_command>echo "@VERSION@"</version_command>
    <command><![CDATA[
    python "$ensemble_script" '$inputs'
]]>
    </command>
    <configfiles>
        <inputs name="inputs"/>
        <configfile name="ensemble_script">
<![CDATA[
import json
import numpy as np
import pandas
import pickle
import sys

                <option value="RandomForestRegressor">Random forest regressor</option>
                <option value="AdaBoostRegressor">Ada boost regressor</option>
                <option value="GradientBoostingRegressor">Gradient Boosting Regressor</option>
            </param>
            <when value="RandomForestClassifier">
                <expand macro="sl_mixed_input"/>
                <section name="options" title="Advanced Options" expanded="False">
                    <expand macro="n_estimators" default_value="100"/>
                    <expand macro="criterion"/>
                    <expand macro="max_features"/>
                    <expand macro="max_depth"/>
                    <expand macro="min_samples_split"/>
                    <expand macro="min_samples_leaf"/>
                    <expand macro="min_weight_fraction_leaf"/>
                    <expand macro="max_leaf_nodes"/>
                    <expand macro="bootstrap"/>
                    <expand macro="warm_start" checked="false"/>
                    <expand macro="random_state"/>
                    <expand macro="oob_score"/>
                    <!--class_weight=None-->
                </section>
            </when>
            <when value="AdaBoostClassifier">
                <expand macro="sl_mixed_input"/>
                <section name="options" title="Advanced Options" expanded="False">
                    <!--base_estimator=None-->
                    <expand macro="n_estimators" default_value="50"/>
                    <expand macro="learning_rate"/>
                    <param argument="algorithm" type="select" label="Boosting algorithm"  help=" ">
                        <option value="SAMME.R" selected="true">SAMME.R</option>
                        <option value="SAMME">SAMME</option>
                    </param>
                    <expand macro="random_state"/>
                </section>
            </when>
            <when value="GradientBoostingClassifier">
                <expand macro="sl_mixed_input"/>
                <section name="options" title="Advanced Options" expanded="False">
                    <!--base_estimator=None-->
                    <param argument="loss" type="select" label="Loss function">
                        <option value="deviance" selected="true">deviance - logistic regression with probabilistic outputs</option>
                        <option value="exponential">exponential - gradient boosting recovers the AdaBoost algorithm</option>
                    </param>
                    <expand macro="learning_rate" default_value='0.1'/>
                    <expand macro="n_estimators" default_value="100" help="The number of boosting stages to perform"/>
                    <expand macro="max_depth" default_value="3" help="maximum depth of the individual regression estimators"/>
                    <expand macro="criterion2">
                        <option value="friedman_mse" selected="true">friedman_mse - mean squared error with improvement score by Friedman</option>
                    </expand>
                    <expand macro="min_samples_split" type="float"/>
                    <expand macro="min_samples_leaf" type="float" label="The minimum number of samples required to be at a leaf node"/>
                    <expand macro="min_weight_fraction_leaf"/>
                    <expand macro="subsample"/>
                    <expand macro="max_features"/>
                    <expand macro="max_leaf_nodes"/>
                    <expand macro="min_impurity_decrease"/>
                    <expand macro="verbose"/>
                    <expand macro="warm_start" checked="false"/>
                    <expand macro="random_state"/>
                    <expand macro="presort"/>
                </section>
            </when>
            <when value="RandomForestRegressor">
                <expand macro="sl_mixed_input"/>
                <section name="options" title="Advanced Options" expanded="False">
                    <expand macro="n_estimators" default_value="100"/>
                    <expand macro="criterion2"/>
                    <expand macro="max_features"/>
                    <expand macro="max_depth"/>
                    <expand macro="min_samples_split"/>
                    <expand macro="min_samples_leaf"/>
                    <expand macro="min_weight_fraction_leaf"/>
                    <expand macro="max_leaf_nodes"/>
                    <expand macro="min_impurity_decrease"/>
                    <expand macro="bootstrap"/>
                    <expand macro="oob_score"/>
                    <expand macro="random_state"/>
                    <expand macro="verbose"/>
                    <expand macro="warm_start" checked="false"/>
                </section>
            </when>
            <when value="AdaBoostRegressor">
                <expand macro="sl_mixed_input"/>
                <section name="options" title="Advanced Options" expanded="False">
                    <!--base_estimator=None-->
                    <expand macro="n_estimators" default_value="50"/>
                    <expand macro="learning_rate"/>
                    <param argument="loss" type="select" label="Loss function"  optional="true" help="Used when updating the weights after each boosting iteration. ">
                        <option value="linear" selected="true">linear</option>
                        <option value="square">square</option>
                        <option value="exponential">exponential</option>
                    </param>
                    <expand macro="random_state"/>
                </section>
            </when>
            <when value="GradientBoostingRegressor">
                <expand macro="sl_mixed_input"/>
                <section name="options" title="Advanced Options" expanded="False">
                    <param argument="loss" type="select" label="Loss function">
                        <option value="ls" selected="true">ls - least squares regression</option>
                        <option value="lad">lad - least absolute deviation</option>
                        <option value="huber">huber - combination of least squares regression and least absolute deviation</option>
                        <option value="quantile">quantile - use alpha to specify the quantile</option>
                    </param>
                    <expand macro="learning_rate" default_value="0.1"/>
                    <expand macro="n_estimators" default_value="100" help="The number of boosting stages to perform"/>
                    <expand macro="max_depth" default_value="3" help="maximum depth of the individual regression estimators"/>
                    <expand macro="criterion2">
                        <option value="friedman_mse" selected="true">friedman_mse - mean squared error with improvement score by Friedman</option>
                    </expand>
                    <expand macro="min_samples_split" type="float"/>
                    <expand macro="min_samples_leaf" type="float" label="The minimum number of samples required to be at a leaf node"/>
                    <expand macro="min_weight_fraction_leaf"/>
                    <expand macro="subsample"/>
                    <expand macro="max_features"/>
                    <expand macro="max_leaf_nodes"/>
                    <expand macro="min_impurity_decrease"/>
                    <param argument="alpha" type="float" value="0.9" label="alpha" help="The alpha-quantile of the huber loss function and the quantile loss function" />
                    <!--base_estimator=None-->
                    <expand macro="verbose"/>
                    <expand macro="warm_start" checked="false"/>
                    <expand macro="random_state"/>
                    <expand macro="presort"/>
                </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="col1" value="1,2,3,4"/>
            <param name="col2" value="5"/>
            <param name="selected_task" value="train"/>
            <param name="selected_algorithm" value="RandomForestClassifier"/>
            <param name="random_state" value="10"/>
            <output name="outfile_fit" file="rfc_model01" compare="sim_size" delta="5"/>
        </test>
        <test>
            <param name="infile_model" value="rfc_model01" ftype="zip"/>
            <param name="infile_data" value="test.tabular" ftype="tabular"/>
            <param name="selected_task" value="load"/>
            <output name="outfile_predict" file="rfc_result01"/>
        </test>
        <test>
            <param name="infile1" value="regression_train.tabular" ftype="tabular"/>
            <param name="infile2" value="regression_train.tabular" ftype="tabular"/>
            <param name="col1" value="1,2,3,4,5"/>
            <param name="col2" value="6"/>
            <param name="selected_task" value="train"/>
            <param name="selected_algorithm" value="RandomForestRegressor"/>
            <param name="random_state" value="10"/>
            <output name="outfile_fit" file="rfr_model01" compare="sim_size" delta="5"/>
        </test>
        <test>
            <param name="infile_model" value="rfr_model01" ftype="zip"/>
            <param name="infile_data" value="regression_test.tabular" ftype="tabular"/>
            <param name="selected_task" value="load"/>
            <output name="outfile_predict" file="rfr_result01"/>
        </test>
        <test>
            <param name="infile1" value="regression_X.tabular" ftype="tabular"/>
            <param name="infile2" value="regression_y.tabular" ftype="tabular"/>
            <param name="header1" value="True"/>
            <param name="selected_column_selector_option" value="all_columns"/>
            <param name="header2" value="True"/>
            <param name="col2" value="1"/>
            <param name="selected_task" value="train"/>
            <param name="selected_algorithm" value="GradientBoostingRegressor"/>
            <param name="max_features" value="number_input"/>
            <param name="num_max_features" value="0.5"/>
            <param name="random_state" value="42"/>
            <output name="outfile_fit" file="gbr_model01" compare="sim_size" delta="5"/>
        </test>
        <test>
            <param name="infile_model" value="gbr_model01" ftype="zip"/>
            <param name="infile_data" value="regression_test_X.tabular" ftype="tabular"/>
            <param name="selected_task" value="load"/>
            <param name="header" value="True"/>
            <output name="outfile_predict" file="gbr_prediction_result01.tabular"/>
        </test>
        <test>
            <param name="infile1" value="train.tabular" ftype="tabular"/>
            <param name="infile2" value="train.tabular" ftype="tabular"/>
            <param name="col1" value="1,2,3,4"/>
            <param name="col2" value="5"/>
            <param name="selected_task" value="train"/>
            <param name="selected_algorithm" value="GradientBoostingClassifier"/>
            <output name="outfile_fit" file="gbc_model01" compare="sim_size" delta="5"/>
        </test>
        <test>
            <param name="infile_model" value="gbc_model01" ftype="zip"/>
            <param name="infile_data" value="test.tabular" ftype="tabular"/>
            <param name="selected_task" value="load"/>
            <output name="outfile_predict" file="gbc_result01"/>
        </test>
        <test>
            <param name="infile1" value="train.tabular" ftype="tabular"/>
            <param name="infile2" value="train.tabular" ftype="tabular"/>
            <param name="col1" value="1,2,3,4"/>
            <param name="col2" value="5"/>
            <param name="selected_task" value="train"/>
            <param name="selected_algorithm" value="AdaBoostClassifier"/>
            <param name="random_state" value="10"/>
            <output name="outfile_fit" file="abc_model01" compare="sim_size" delta="5"/>
        </test>
        <test>
            <param name="infile_model" value="abc_model01" ftype="zip"/>
            <param name="infile_data" value="test.tabular" ftype="tabular"/>
            <param name="selected_task" value="load"/>
            <output name="outfile_predict" file="abc_result01"/>
        </test>
        <test>
            <param name="infile1" value="regression_train.tabular" ftype="tabular"/>
            <param name="infile2" value="regression_train.tabular" ftype="tabular"/>
            <param name="col1" value="1,2,3,4,5"/>
            <param name="col2" value="6"/>
            <param name="selected_task" value="train"/>
            <param name="selected_algorithm" value="AdaBoostRegressor"/>
            <param name="random_state" value="10"/>
            <output name="outfile_fit" file="abr_model01" compare="sim_size" delta="5"/>
        </test>
        <test>
            <param name="infile_model" value="abr_model01" ftype="zip"/>
            <param name="infile_data" value="regression_test.tabular" ftype="tabular"/>
            <param name="selected_task" value="load"/>
            <output name="outfile_predict" file="abr_result01"/>
        </test>
    </tests>
    <help><![CDATA[
***What it does***
The goal of ensemble methods is to combine the predictions of several base estimators built with a given learning algorithm in order to improve generalizability / robustness over a single estimator. This tool offers two sets of ensemble algorithms for classification and regression: random forests and ADA boosting which are based on sklearn.ensemble library from Scikit-learn. Here you can find out about the input, output and methods presented in the tools. For information about ensemble methods and parameters settings please refer to `Scikit-learn ensemble`_.

 **3 - Prediction output**
 The tool predicts the class labels for new samples and adds them as the last column to the prediction dataset. The new dataset then is output as a tabular file. The prediction output format should look like the training dataset.

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

35:19d6c2745d34

<tool id="sklearn_ensemble" name="Ensemble methods" version="@VERSION@" profile="20.05">
    <description>for classification and regression</description>
    <macros>
        <import>main_macros.xml</import>
    </macros>
    <expand macro="python_requirements" />
    <expand macro="macro_stdio" />
    <version_command>echo "@VERSION@"</version_command>
    <command><![CDATA[
    python "$ensemble_script" '$inputs'
]]>
    </command>
    <configfiles>
        <inputs name="inputs" />
        <configfile name="ensemble_script">
            <![CDATA[
import json
import numpy as np
import pandas
import pickle
import sys

                <option value="RandomForestRegressor">Random forest regressor</option>
                <option value="AdaBoostRegressor">Ada boost regressor</option>
                <option value="GradientBoostingRegressor">Gradient Boosting Regressor</option>
            </param>
            <when value="RandomForestClassifier">
                <expand macro="sl_mixed_input" />
                <section name="options" title="Advanced Options" expanded="False">
                    <expand macro="n_estimators" default_value="100" />
                    <expand macro="criterion" />
                    <expand macro="max_features" />
                    <expand macro="max_depth" />
                    <expand macro="min_samples_split" />
                    <expand macro="min_samples_leaf" />
                    <expand macro="min_weight_fraction_leaf" />
                    <expand macro="max_leaf_nodes" />
                    <expand macro="bootstrap" />
                    <expand macro="warm_start" checked="false" />
                    <expand macro="random_state" />
                    <expand macro="oob_score" />
                    <!--class_weight=None-->
                </section>
            </when>
            <when value="AdaBoostClassifier">
                <expand macro="sl_mixed_input" />
                <section name="options" title="Advanced Options" expanded="False">
                    <!--base_estimator=None-->
                    <expand macro="n_estimators" default_value="50" />
                    <expand macro="learning_rate" />
                    <param argument="algorithm" type="select" label="Boosting algorithm" help=" ">
                        <option value="SAMME.R" selected="true">SAMME.R</option>
                        <option value="SAMME">SAMME</option>
                    </param>
                    <expand macro="random_state" />
                </section>
            </when>
            <when value="GradientBoostingClassifier">
                <expand macro="sl_mixed_input" />
                <section name="options" title="Advanced Options" expanded="False">
                    <!--base_estimator=None-->
                    <param argument="loss" type="select" label="Loss function">
                        <option value="deviance" selected="true">deviance - logistic regression with probabilistic outputs</option>
                        <option value="exponential">exponential - gradient boosting recovers the AdaBoost algorithm</option>
                    </param>
                    <expand macro="learning_rate" default_value='0.1' />
                    <expand macro="n_estimators" default_value="100" help="The number of boosting stages to perform" />
                    <expand macro="max_depth" default_value="3" help="maximum depth of the individual regression estimators" />
                    <expand macro="criterion2">
                        <option value="friedman_mse" selected="true">friedman_mse - mean squared error with improvement score by Friedman</option>
                    </expand>
                    <expand macro="min_samples_split" type="float" />
                    <expand macro="min_samples_leaf" type="float" label="The minimum number of samples required to be at a leaf node" />
                    <expand macro="min_weight_fraction_leaf" />
                    <expand macro="subsample" />
                    <expand macro="max_features" />
                    <expand macro="max_leaf_nodes" />
                    <expand macro="min_impurity_decrease" />
                    <expand macro="verbose" />
                    <expand macro="warm_start" checked="false" />
                    <expand macro="random_state" />
                    <expand macro="presort" />
                </section>
            </when>
            <when value="RandomForestRegressor">
                <expand macro="sl_mixed_input" />
                <section name="options" title="Advanced Options" expanded="False">
                    <expand macro="n_estimators" default_value="100" />
                    <expand macro="criterion2" />
                    <expand macro="max_features" />
                    <expand macro="max_depth" />
                    <expand macro="min_samples_split" />
                    <expand macro="min_samples_leaf" />
                    <expand macro="min_weight_fraction_leaf" />
                    <expand macro="max_leaf_nodes" />
                    <expand macro="min_impurity_decrease" />
                    <expand macro="bootstrap" />
                    <expand macro="oob_score" />
                    <expand macro="random_state" />
                    <expand macro="verbose" />
                    <expand macro="warm_start" checked="false" />
                </section>
            </when>
            <when value="AdaBoostRegressor">
                <expand macro="sl_mixed_input" />
                <section name="options" title="Advanced Options" expanded="False">
                    <!--base_estimator=None-->
                    <expand macro="n_estimators" default_value="50" />
                    <expand macro="learning_rate" />
                    <param argument="loss" type="select" label="Loss function" optional="true" help="Used when updating the weights after each boosting iteration. ">
                        <option value="linear" selected="true">linear</option>
                        <option value="square">square</option>
                        <option value="exponential">exponential</option>
                    </param>
                    <expand macro="random_state" />
                </section>
            </when>
            <when value="GradientBoostingRegressor">
                <expand macro="sl_mixed_input" />
                <section name="options" title="Advanced Options" expanded="False">
                    <param argument="loss" type="select" label="Loss function">
                        <option value="ls" selected="true">ls - least squares regression</option>
                        <option value="lad">lad - least absolute deviation</option>
                        <option value="huber">huber - combination of least squares regression and least absolute deviation</option>
                        <option value="quantile">quantile - use alpha to specify the quantile</option>
                    </param>
                    <expand macro="learning_rate" default_value="0.1" />
                    <expand macro="n_estimators" default_value="100" help="The number of boosting stages to perform" />
                    <expand macro="max_depth" default_value="3" help="maximum depth of the individual regression estimators" />
                    <expand macro="criterion2">
                        <option value="friedman_mse" selected="true">friedman_mse - mean squared error with improvement score by Friedman</option>
                    </expand>
                    <expand macro="min_samples_split" type="float" />
                    <expand macro="min_samples_leaf" type="float" label="The minimum number of samples required to be at a leaf node" />
                    <expand macro="min_weight_fraction_leaf" />
                    <expand macro="subsample" />
                    <expand macro="max_features" />
                    <expand macro="max_leaf_nodes" />
                    <expand macro="min_impurity_decrease" />
                    <param argument="alpha" type="float" value="0.9" label="alpha" help="The alpha-quantile of the huber loss function and the quantile loss function" />
                    <!--base_estimator=None-->
                    <expand macro="verbose" />
                    <expand macro="warm_start" checked="false" />
                    <expand macro="random_state" />
                    <expand macro="presort" />
                </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="col1" value="1,2,3,4" />
            <param name="col2" value="5" />
            <param name="selected_task" value="train" />
            <param name="selected_algorithm" value="RandomForestClassifier" />
            <param name="random_state" value="10" />
            <output name="outfile_fit" file="rfc_model01" compare="sim_size" delta="5" />
        </test>
        <test>
            <param name="infile_model" value="rfc_model01" ftype="zip" />
            <param name="infile_data" value="test.tabular" ftype="tabular" />
            <param name="selected_task" value="load" />
            <output name="outfile_predict" file="rfc_result01" />
        </test>
        <test>
            <param name="infile1" value="regression_train.tabular" ftype="tabular" />
            <param name="infile2" value="regression_train.tabular" ftype="tabular" />
            <param name="col1" value="1,2,3,4,5" />
            <param name="col2" value="6" />
            <param name="selected_task" value="train" />
            <param name="selected_algorithm" value="RandomForestRegressor" />
            <param name="random_state" value="10" />
            <output name="outfile_fit" file="rfr_model01" compare="sim_size" delta="5" />
        </test>
        <test>
            <param name="infile_model" value="rfr_model01" ftype="zip" />
            <param name="infile_data" value="regression_test.tabular" ftype="tabular" />
            <param name="selected_task" value="load" />
            <output name="outfile_predict" file="rfr_result01" />
        </test>
        <test>
            <param name="infile1" value="regression_X.tabular" ftype="tabular" />
            <param name="infile2" value="regression_y.tabular" ftype="tabular" />
            <param name="header1" value="True" />
            <param name="selected_column_selector_option" value="all_columns" />
            <param name="header2" value="True" />
            <param name="col2" value="1" />
            <param name="selected_task" value="train" />
            <param name="selected_algorithm" value="GradientBoostingRegressor" />
            <param name="max_features" value="number_input" />
            <param name="num_max_features" value="0.5" />
            <param name="random_state" value="42" />
            <output name="outfile_fit" file="gbr_model01" compare="sim_size" delta="5" />
        </test>
        <test>
            <param name="infile_model" value="gbr_model01" ftype="zip" />
            <param name="infile_data" value="regression_test_X.tabular" ftype="tabular" />
            <param name="selected_task" value="load" />
            <param name="header" value="True" />
            <output name="outfile_predict" file="gbr_prediction_result01.tabular" />
        </test>
        <test>
            <param name="infile1" value="train.tabular" ftype="tabular" />
            <param name="infile2" value="train.tabular" ftype="tabular" />
            <param name="col1" value="1,2,3,4" />
            <param name="col2" value="5" />
            <param name="selected_task" value="train" />
            <param name="selected_algorithm" value="GradientBoostingClassifier" />
            <output name="outfile_fit" file="gbc_model01" compare="sim_size" delta="5" />
        </test>
        <test>
            <param name="infile_model" value="gbc_model01" ftype="zip" />
            <param name="infile_data" value="test.tabular" ftype="tabular" />
            <param name="selected_task" value="load" />
            <output name="outfile_predict" file="gbc_result01" />
        </test>
        <test>
            <param name="infile1" value="train.tabular" ftype="tabular" />
            <param name="infile2" value="train.tabular" ftype="tabular" />
            <param name="col1" value="1,2,3,4" />
            <param name="col2" value="5" />
            <param name="selected_task" value="train" />
            <param name="selected_algorithm" value="AdaBoostClassifier" />
            <param name="random_state" value="10" />
            <output name="outfile_fit" file="abc_model01" compare="sim_size" delta="5" />
        </test>
        <test>
            <param name="infile_model" value="abc_model01" ftype="zip" />
            <param name="infile_data" value="test.tabular" ftype="tabular" />
            <param name="selected_task" value="load" />
            <output name="outfile_predict" file="abc_result01" />
        </test>
        <test>
            <param name="infile1" value="regression_train.tabular" ftype="tabular" />
            <param name="infile2" value="regression_train.tabular" ftype="tabular" />
            <param name="col1" value="1,2,3,4,5" />
            <param name="col2" value="6" />
            <param name="selected_task" value="train" />
            <param name="selected_algorithm" value="AdaBoostRegressor" />
            <param name="random_state" value="10" />
            <output name="outfile_fit" file="abr_model01" compare="sim_size" delta="5" />
        </test>
        <test>
            <param name="infile_model" value="abr_model01" ftype="zip" />
            <param name="infile_data" value="regression_test.tabular" ftype="tabular" />
            <param name="selected_task" value="load" />
            <output name="outfile_predict" file="abr_result01" />
        </test>
    </tests>
    <help><![CDATA[
***What it does***
The goal of ensemble methods is to combine the predictions of several base estimators built with a given learning algorithm in order to improve generalizability / robustness over a single estimator. This tool offers two sets of ensemble algorithms for classification and regression: random forests and ADA boosting which are based on sklearn.ensemble library from Scikit-learn. Here you can find out about the input, output and methods presented in the tools. For information about ensemble methods and parameters settings please refer to `Scikit-learn ensemble`_.

 **3 - Prediction output**
 The tool predicts the class labels for new samples and adds them as the last column to the prediction dataset. The new dataset then is output as a tabular file. The prediction output format should look like the training dataset.

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