comparison lightgbm.xml @ 3:c3bafda50176 draft

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

2:c12485d058aa

<tool id="sklearn_lightgbm" name="LightGBM" version="@VERSION@">
    <description>- train and apply LightGBM models</description>
    <macros>
        <import>main_macros.xml</import>
    </macros>
    <expand macro="python_requirements">
          <requirement type="package" version="2.3.0">lightgbm</requirement>
    </expand>
    <expand macro="macro_stdio"/>
    <version_command>echo "@VERSION@"</version_command>
    <command><![CDATA[
    python '$lightgbm_script' '$inputs'
]]>
    </command>
    <configfiles>
        <inputs name="inputs"/>
        <configfile name="lightgbm_script">
<![CDATA[
import json
import lightgbm as lgb
import pandas
import sys

        <expand macro="sl_Conditional">
            <param name="selected_algorithm" type="select" label="Classification or regression?">
                <option value="LightGBMClassifier">Classification</option>
                <option value="LightGBMRegressor">Regression</option>
            </param>
            <when value="LightGBMClassifier" >
                <expand macro="sl_mixed_input"/>
                <section name="options" title="Advanced Options" expanded="False">
                    <param argument="objective" type="select" label="Loss function">
                        <option value="binary">Binary log loss classification</option>
                        <option value="multiclass">Multiclass - softmax objective function</option>
                        <option value="multiclassova">Multiclass - one-vs-all binary objective function</option>
                    </param>
                    <param name="num_class" label="Number of classes" type="integer" value="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="learning_rate" default_value='0.1'/>
                    <expand macro="max_leaf_nodes"/>
                    <expand macro="subsample"/>
                    <expand macro="verbose"/>
                    <expand macro="feature_fraction"/>
                    <expand macro="lambda_l1"/>
                    <expand macro="lambda_l2"/>
                    <expand macro="min_gain_to_split"/>
                    <expand macro="min_child_weight"/>
                    <expand macro="random_state"/>
                </section>
            </when>

            <when value="LightGBMRegressor">
                <expand macro="sl_mixed_input"/>
                <section name="options" title="Advanced Options" expanded="False">
                    <param argument="objective" type="select" label="Loss function">
                        <option value="l1">Absolute loss</option>
                        <option value="l2">Square loss</option>
                        <option value="rmse">Root square loss</option>
                        <option value="huber">Huber loss - combination of least squares regression and least absolute deviation</option>
                        <option value="quantile">Quantile - use alpha to specify the quantile</option>
                    </param>
                    <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="learning_rate" default_value='0.1'/>
                    <expand macro="max_leaf_nodes"/>
                    <expand macro="subsample"/>
                    <expand macro="verbose"/>
                    <expand macro="feature_fraction"/>
                    <expand macro="lambda_l1"/>
                    <expand macro="lambda_l2"/>
                    <expand macro="min_gain_to_split"/>
                    <expand macro="min_child_weight"/>
                    <expand macro="random_state"/>
                </section>
            </when>
        </expand>
    </inputs>

    <outputs>
      <data format="tabular" name="outfile_predict">
          <filter>selected_tasks['selected_task'] == 'load'</filter>
      </data>
      <data format="txt" name="outfile_fit" label="${tool.name}.${selected_tasks.selected_algorithms.selected_algorithm}">
          <filter>selected_tasks['selected_task'] == 'train'</filter>
      </data>
    </outputs>

    <tests>
        <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="LightGBMRegressor"/>
            <param name="objective" value="l2"/>
            <param name="n_estimators" value="10000"/>
            <param name="learning_rate" value="0.02"/>
            <param name="max_leaf_nodes" value="32"/>
            <param name="feature_fraction" value="0.9"/>
            <param name="subsample" value="0.9"/>
            <param name="max_depth" value="8"/>
            <param name="lambda_l1" value="0.04"/>
            <param name="lambda_l2" value="0.07"/>
            <param name="min_gain_to_split" value="0.02"/>
            <param name="min_child_weight" value="39.0"/>
            <param name="verbose" value="-1"/>
            <param name="random_state" value="1"/>
            <output name="outfile_fit" file="lgb_regr_model.txt" compare="sim_size" delta="5"/>
        </test>
        <test>
            <param name="infile_model" value="lgb_regr_model.txt" ftype="txt"/>
            <param name="infile_data" value="regression_X.tabular" ftype="tabular"/>
            <param name="selected_task" value="load"/>
            <param name="header" value="True"/>
            <output name="outfile_predict" file="lgb_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="LightGBMClassifier"/>
            <param name="objective" value="binary"/>
            <param name="n_estimators" value="10000"/>
            <param name="learning_rate" value="0.02"/>
            <param name="max_leaf_nodes" value="32"/>
            <param name="feature_fraction" value="0.9"/>
            <param name="subsample" value="0.9"/>
            <param name="max_depth" value="8"/>
            <param name="lambda_l1" value="0.04"/>
            <param name="lambda_l2" value="0.07"/>
            <param name="min_gain_to_split" value="0.02"/>
            <param name="min_child_weight" value="39.0"/>
            <param name="verbose" value="-1"/>
            <param name="random_state" value="1"/>
            <output name="outfile_fit" file="lgb_class_model.txt" compare="sim_size" delta="5"/>
        </test>

    </tests>
    <help><![CDATA[
**What it does**

 **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 (i.e. tabular input plus an additional column containing predicted values) is then returned as a tabular file. The prediction output format should look like the training dataset.

    ]]></help>
    <expand macro="sklearn_citation">
        <citation type="bibtex">
@incollection{NIPS2017_6907,
title = {LightGBM: A Highly Efficient Gradient Boosting Decision Tree},
author = {Ke, Guolin and Meng, Qi and Finley, Thomas and Wang, Taifeng and Chen, Wei and Ma, Weidong and Ye, Qiwei and Liu, Tie-Yan},

3:c3bafda50176

<tool id="sklearn_lightgbm" name="LightGBM" version="@VERSION@" profile="20.05">
    <description>- train and apply LightGBM models</description>
    <macros>
        <import>main_macros.xml</import>
    </macros>
    <expand macro="python_requirements">
        <requirement type="package" version="2.3.0">lightgbm</requirement>
    </expand>
    <expand macro="macro_stdio" />
    <version_command>echo "@VERSION@"</version_command>
    <command><![CDATA[
    python '$lightgbm_script' '$inputs'
]]>
    </command>
    <configfiles>
        <inputs name="inputs" />
        <configfile name="lightgbm_script">
            <![CDATA[
import json
import lightgbm as lgb
import pandas
import sys

        <expand macro="sl_Conditional">
            <param name="selected_algorithm" type="select" label="Classification or regression?">
                <option value="LightGBMClassifier">Classification</option>
                <option value="LightGBMRegressor">Regression</option>
            </param>
            <when value="LightGBMClassifier">
                <expand macro="sl_mixed_input" />
                <section name="options" title="Advanced Options" expanded="False">
                    <param argument="objective" type="select" label="Loss function">
                        <option value="binary">Binary log loss classification</option>
                        <option value="multiclass">Multiclass - softmax objective function</option>
                        <option value="multiclassova">Multiclass - one-vs-all binary objective function</option>
                    </param>
                    <param name="num_class" label="Number of classes" type="integer" value="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="learning_rate" default_value='0.1' />
                    <expand macro="max_leaf_nodes" />
                    <expand macro="subsample" />
                    <expand macro="verbose" />
                    <expand macro="feature_fraction" />
                    <expand macro="lambda_l1" />
                    <expand macro="lambda_l2" />
                    <expand macro="min_gain_to_split" />
                    <expand macro="min_child_weight" />
                    <expand macro="random_state" />
                </section>
            </when>

            <when value="LightGBMRegressor">
                <expand macro="sl_mixed_input" />
                <section name="options" title="Advanced Options" expanded="False">
                    <param argument="objective" type="select" label="Loss function">
                        <option value="l1">Absolute loss</option>
                        <option value="l2">Square loss</option>
                        <option value="rmse">Root square loss</option>
                        <option value="huber">Huber loss - combination of least squares regression and least absolute deviation</option>
                        <option value="quantile">Quantile - use alpha to specify the quantile</option>
                    </param>
                    <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="learning_rate" default_value='0.1' />
                    <expand macro="max_leaf_nodes" />
                    <expand macro="subsample" />
                    <expand macro="verbose" />
                    <expand macro="feature_fraction" />
                    <expand macro="lambda_l1" />
                    <expand macro="lambda_l2" />
                    <expand macro="min_gain_to_split" />
                    <expand macro="min_child_weight" />
                    <expand macro="random_state" />
                </section>
            </when>
        </expand>
    </inputs>

    <outputs>
        <data format="tabular" name="outfile_predict">
            <filter>selected_tasks['selected_task'] == 'load'</filter>
        </data>
        <data format="txt" name="outfile_fit" label="${tool.name}.${selected_tasks.selected_algorithms.selected_algorithm}">
            <filter>selected_tasks['selected_task'] == 'train'</filter>
        </data>
    </outputs>

    <tests>
        <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="LightGBMRegressor" />
            <param name="objective" value="l2" />
            <param name="n_estimators" value="10000" />
            <param name="learning_rate" value="0.02" />
            <param name="max_leaf_nodes" value="32" />
            <param name="feature_fraction" value="0.9" />
            <param name="subsample" value="0.9" />
            <param name="max_depth" value="8" />
            <param name="lambda_l1" value="0.04" />
            <param name="lambda_l2" value="0.07" />
            <param name="min_gain_to_split" value="0.02" />
            <param name="min_child_weight" value="39.0" />
            <param name="verbose" value="-1" />
            <param name="random_state" value="1" />
            <output name="outfile_fit" file="lgb_regr_model.txt" compare="sim_size" delta="5" />
        </test>
        <!-- See 'Fix get_scoring method #1103'
        <test>
            <param name="infile_model" value="lgb_regr_model.txt" ftype="txt" />
            <param name="infile_data" value="regression_X.tabular" ftype="tabular" />
            <param name="selected_task" value="load" />
            <param name="header" value="True" />
            <output name="outfile_predict" file="lgb_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="LightGBMClassifier" />
            <param name="objective" value="binary" />
            <param name="n_estimators" value="10000" />
            <param name="learning_rate" value="0.02" />
            <param name="max_leaf_nodes" value="32" />
            <param name="feature_fraction" value="0.9" />
            <param name="subsample" value="0.9" />
            <param name="max_depth" value="8" />
            <param name="lambda_l1" value="0.04" />
            <param name="lambda_l2" value="0.07" />
            <param name="min_gain_to_split" value="0.02" />
            <param name="min_child_weight" value="39.0" />
            <param name="verbose" value="-1" />
            <param name="random_state" value="1" />
            <output name="outfile_fit" file="lgb_class_model.txt" compare="sim_size" delta="5" />
        </test>

    </tests>
    <help><![CDATA[
**What it does**

 **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 (i.e. tabular input plus an additional column containing predicted values) is then returned as a tabular file. The prediction output format should look like the training dataset.

    ]]>    </help>
    <expand macro="sklearn_citation">
        <citation type="bibtex">
@incollection{NIPS2017_6907,
title = {LightGBM: A Highly Efficient Gradient Boosting Decision Tree},
author = {Ke, Guolin and Meng, Qi and Finley, Thomas and Wang, Taifeng and Chen, Wei and Ma, Weidong and Ye, Qiwei and Liu, Tie-Yan},