<?xml version="1.0" ?>
<tool id="qiime_sample-classifier_regress-samples" name="qiime sample-classifier regress-samples" version="2018.4">
	<description> - Supervised learning regressor.</description>
	<requirements>
		<requirement type="package" version="2018.4">qiime2</requirement>
	</requirements>
	<command>
	<![CDATA[
	qiime sample-classifier regress-samples --i-table=$itable

	#def list_dict_to_string(list_dict):
		#set $file_list = list_dict[0]['additional_input'].__getattr__('file_name')
		#for d in list_dict[1:]:
			#set $file_list = $file_list + ' --m-metadata-file=' + d['additional_input'].__getattr__('file_name')
		#end for
		#return $file_list
	#end def

	 --m-metadata-file=$list_dict_to_string($input_files_mmetadatafile) --m-metadata-column="$mmetadatacolumn"
	#set $pnjobs = '${GALAXY_SLOTS:-4}'

	#if str($pnjobs):
	 --p-n-jobs="$pnjobs"
	#end if


	#if $pstep:
	 --p-step=$pstep
	#end if

	#if $pstratify:
 	  --p-stratify
	#else
		--p-no-stratify
	#end if

	#if $poptimizefeatureselection:
	  --p-optimize-feature-selection
	#else
		--p-no-optimize-feature-selection
	#end if

	#if $ptestsize:
	 --p-test-size=$ptestsize
	#end if
	 --o-visualization=ovisualization
	#if str($pestimator) != 'None':
	 --p-estimator=$pestimator
	#end if

	#if $pnestimators:
	 --p-n-estimators=$pnestimators
	#end if

	#if str($cmdconfig) != 'None':
	 --cmd-config=$cmdconfig
	#end if

	#if $pcv:
	 --p-cv=$pcv
	#end if

	#if $pparametertuning:
	  --p-parameter-tuning
	#else
		--p-no-parameter-tuning
	#end if

	#if str($prandomstate):
	 --p-random-state="$prandomstate"
	#end if
	;
	qiime tools export ovisualization.qzv --output-dir out   && mkdir -p '$ovisualization.files_path'
	&& cp -r out/* '$ovisualization.files_path'
	&& mv '$ovisualization.files_path/index.html' '$ovisualization'
	]]>
	</command>
	<inputs>
		<param format="qza,no_unzip.zip" label="--i-table: FeatureTable[Frequency] Feature table containing all features that should be used for target prediction. [required]" name="itable" optional="False" type="data"/>
		<repeat name="input_files_mmetadatafile" optional="False" title="--m-metadata-file">
			<param label="--m-metadata-file: Metadata file or artifact viewable as metadata. This option may be supplied multiple times to merge metadata. [required]" name="additional_input" type="data" format="tabular,qza,no_unzip.zip" />
		</repeat>
		<param label="--m-metadata-column: MetadataColumn[Numeric] Column from metadata file or artifact viewable as metadata. Numeric metadata column to use as prediction target. [required]" name="mmetadatacolumn" optional="False" type="text"/>

		<param label="--p-test-size: Fraction of input samples to exclude from training set and use for classifier testing. [default: 0.2]" name="ptestsize" optional="True" type="float" value="0.2"/>

		<param label="--p-step: If optimize_feature_selection is True, step is the percentage of features to remove at each iteration.  [default: 0.05]" name="pstep" optional="True" type="float" value="0.05"/>

		<param label="--p-cv: Number of k-fold cross-validations to perform.  [default: 5]" name="pcv" optional="True" type="integer" value="5"/>

		<param label="--p-random-state: Seed used by random number generator. [optional]" name="prandomstate" optional="True" type="text"/>

		<param label="--p-n-estimators: Number of trees to grow for estimation. More trees will improve predictive accuracy up to a threshold level, but will also increase time and memory requirements. This parameter only affects ensemble estimators, such as Random Forest, AdaBoost, ExtraTrees, and GradientBoosting.  [default: 100]" name="pnestimators" optional="True" type="integer" value="100"/>
		<param label="--p-estimator: Estimator method to use for sample
                                  prediction.  [default:
                                  RandomForestRegressor]" name="pestimator" optional="True" type="select">
			<option selected="True" value="None">Selection is Optional</option>
			<option value="Ridge">Ridge</option>
			<option value="RandomForestRegressor">RandomForestRegressor</option>
			<option value="GradientBoostingRegressor">GradientBoostingRegressor</option>
			<option value="AdaBoostRegressor">AdaBoostRegressor</option>
			<option value="LinearSVR">LinearSVR</option>
			<option value="ExtraTreesRegressor">ExtraTreesRegressor</option>
			<option value="KNeighborsRegressor">KNeighborsRegressor</option>
			<option value="SVR">SVR</option>
			<option value="ElasticNet">ElasticNet</option>
			<option value="Lasso">Lasso</option>
		</param>

		<param label="--p-optimize-feature-selection: --p-no-optimize-feature-selection Automatically optimize input feature selection using recursive feature elimination.  [default: False]" name="poptimizefeatureselection" checked="False" type="boolean"/>

		<param label="--p-stratify: --p-no-stratify  Evenly stratify training and test data among metadata categories. If True, all values in column must match at least two samples. [default: False]" name="pstratify" checked="False" type="boolean"/>

		<param label="--p-parameter-tuning: --p-no-parameter-tuning Automatically tune hyperparameters using random grid search.  [default: False]" name="pparametertuning" checked="False" type="boolean"/>

		<param label="--cmd-config: Use config file for command options" name="cmdconfig" optional="True" type="data"/>
	</inputs>
	<outputs>
		<data format="html" label="${tool.name} on ${on_string}: visualization.qzv" name="ovisualization"/>
	</outputs>
	<help>
		<![CDATA[
Supervised learning regressor.
-------------------------------

Predicts a continuous sample metadata column using a supervised learning
regressor. Splits input data into training and test sets. The training set
is used to train and test the estimator using a stratified k-fold cross-
validation scheme. This includes optional steps for automated feature
extraction and hyperparameter optimization. The test set validates
classification accuracy of the optimized estimator. Outputs classification
results for test set. For more details on the learning  algorithm, see
http://scikit-learn.org/stable/supervised_learning.html

Parameters
----------
table : FeatureTable[Frequency]
    Feature table containing all features that should be used for target
    prediction.
metadata : MetadataColumn[Numeric]
    Numeric metadata column to use as prediction target.
test_size : Float % Range(0.0, 1.0, inclusive_start=False), optional
    Fraction of input samples to exclude from training set and use for
    classifier testing.
step : Float % Range(0.0, 1.0, inclusive_start=False), optional
    If optimize_feature_selection is True, step is the percentage of
    features to remove at each iteration.
cv : Int % Range(1, None), optional
    Number of k-fold cross-validations to perform.
random_state : Int, optional
    Seed used by random number generator.
n_estimators : Int % Range(1, None), optional
    Number of trees to grow for estimation. More trees will improve
    predictive accuracy up to a threshold level, but will also increase
    time and memory requirements. This parameter only affects ensemble
    estimators, such as Random Forest, AdaBoost, ExtraTrees, and
    GradientBoosting.
estimator : Str % Choices({'AdaBoostRegressor', 'ElasticNet', 'ExtraTreesRegressor', 'GradientBoostingRegressor', 'KNeighborsRegressor', 'Lasso', 'LinearSVR', 'RandomForestRegressor', 'Ridge', 'SVR'}), optional
    Estimator method to use for sample prediction.
optimize_feature_selection : Bool, optional
    Automatically optimize input feature selection using recursive feature
    elimination.
stratify : Bool, optional
    Evenly stratify training and test data among metadata categories. If
    True, all values in column must match at least two samples.
parameter_tuning : Bool, optional
    Automatically tune hyperparameters using random grid search.

Returns
-------
visualization : Visualization
		\
		]]>
	</help>
</tool>