Mercurial > repos > florianbegusch > qiime2_suite

diff qiime2/qiime_sample-classifier_regress-samples-ncv.xml @ 14:a0a8d77a991c draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
Uploaded
author florianbegusch
date Thu, 03 Sep 2020 09:51:29 +0000
parents f190567fe3f6
children
line wrap: on
line diff
--- a/qiime2/qiime_sample-classifier_regress-samples-ncv.xml	Thu Sep 03 09:46:00 2020 +0000
+++ b/qiime2/qiime_sample-classifier_regress-samples-ncv.xml	Thu Sep 03 09:51:29 2020 +0000
@@ -1,36 +1,60 @@
 <?xml version="1.0" ?>
-<tool id="qiime_sample-classifier_regress-samples-ncv" name="qiime sample-classifier regress-samples-ncv" version="2019.7">
-	<description> - Nested cross-validated supervised learning regressor.</description>
-	<requirements>
-		<requirement type="package" version="2019.7">qiime2</requirement>
-	</requirements>
-	<command><![CDATA[
+<tool id="qiime_sample-classifier_regress-samples-ncv" name="qiime sample-classifier regress-samples-ncv"
+      version="2020.8">
+  <description>Nested cross-validated supervised learning regressor.</description>
+  <requirements>
+    <requirement type="package" version="2020.8">qiime2</requirement>
+  </requirements>
+  <command><![CDATA[
 qiime sample-classifier regress-samples-ncv
 
 --i-table=$itable
---m-metadata-column="$mmetadatacolumn"
+# if $input_files_mmetadatafile:
+  # 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)
+# end if
 
-#if str($pcv):
- --p-cv=$pcv
+#if '__ob__' in str($mmetadatacolumn):
+  #set $mmetadatacolumn_temp = $mmetadatacolumn.replace('__ob__', '[')
+  #set $mmetadatacolumn = $mmetadatacolumn_temp
+#end if
+#if '__cb__' in str($mmetadatacolumn):
+  #set $mmetadatacolumn_temp = $mmetadatacolumn.replace('__cb__', ']')
+  #set $mmetadatacolumn = $mmetadatacolumn_temp
 #end if
-
-#if str($prandomstate):
- --p-random-state="$prandomstate"
+#if 'X' in str($mmetadatacolumn):
+  #set $mmetadatacolumn_temp = $mmetadatacolumn.replace('X', '\\')
+  #set $mmetadatacolumn = $mmetadatacolumn_temp
+#end if
+#if '__sq__' in str($mmetadatacolumn):
+  #set $mmetadatacolumn_temp = $mmetadatacolumn.replace('__sq__', "'")
+  #set $mmetadatacolumn = $mmetadatacolumn_temp
+#end if
+#if '__db__' in str($mmetadatacolumn):
+  #set $mmetadatacolumn_temp = $mmetadatacolumn.replace('__db__', '"')
+  #set $mmetadatacolumn = $mmetadatacolumn_temp
 #end if
 
-#set $pnjobs = '${GALAXY_SLOTS:-4}'
-
-#if str($pnjobs):
- --p-n-jobs="$pnjobs"
-#end if
+--m-metadata-column=$mmetadatacolumn
 
 
-#if str($pnestimators):
- --p-n-estimators=$pnestimators
+--p-cv=$pcv
+
+#if str($prandomstate):
+  --p-random-state=$prandomstate
 #end if
+--p-n-jobs=$pnjobs
+
+--p-n-estimators=$pnestimators
 
 #if str($pestimator) != 'None':
- --p-estimator=$pestimator
+--p-estimator=$pestimator
 #end if
 
 #if $pstratify:
@@ -42,64 +66,66 @@
 #end if
 
 #if str($pmissingsamples) != 'None':
- --p-missing-samples=$pmissingsamples
+--p-missing-samples=$pmissingsamples
 #end if
 
-
-
-#if $metadatafile:
- --m-metadata-file=$metadatafile
-#end if
-
-
-
 --o-predictions=opredictions
+
 --o-feature-importance=ofeatureimportance
+
+#if str($examples) != 'None':
+--examples=$examples
+#end if
+
 ;
-cp opredictions.qza $opredictions;
 cp ofeatureimportance.qza $ofeatureimportance
-	]]></command>
-	<inputs>
-		<param format="qza,no_unzip.zip" label="--i-table: ARTIFACT FeatureTable[Frequency] Feature table containing all features that should be used for target prediction.                  [required]" name="itable" optional="False" type="data"/>
-		<param label="--m-metadata-column: COLUMN  MetadataColumn[Numeric] Numeric metadata column to use as prediction target. [required]" name="mmetadatacolumn" optional="False" type="text"/>
-		<param label="--p-cv: INTEGER       Number of k-fold cross-validations to perform. Range(1, None)                                                [default: 5]" name="pcv" optional="True" type="integer" value="5" min="1"/>
-		<param label="--p-random-state: INTEGER Seed used by random number generator.        [optional]" name="prandomstate" optional="True" type="integer"/>
-		<param label="--p-n-estimators: INTEGER Range(1, None)     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" min="1"/>
-		<param label="--p-estimator: " name="pestimator" optional="True" type="select">
-			<option selected="True" value="None">Selection is Optional</option>
-			<option value="RandomForestRegressor">RandomForestRegressor</option>
-			<option value="ExtraTreesRegressor">ExtraTreesRegressor</option>
-			<option value="GradientBoostingRegressor">GradientBoostingRegressor</option>
-			<option value="AdaBoostRegressor">AdaBoostRegressor</option>
-			<option value="ElasticNet">ElasticNet</option>
-			<option value="Ridge">Ridge</option>
-			<option value="Lasso">Lasso</option>
-			<option value="KNeighborsRegressor">KNeighborsRegressor</option>
-			<option value="LinearSVR">LinearSVR</option>
-			<option value="SVR">SVR</option>
-		</param>
-		<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" selected="False" type="boolean"/>
-		<param label="--p-parameter-tuning: --p-no-parameter-tuning Automatically tune hyperparameters using random grid search.                                [default: False]" name="pparametertuning" selected="False" type="boolean"/>
-		<param label="--p-missing-samples: " name="pmissingsamples" optional="True" type="select">
-			<option selected="True" value="None">Selection is Optional</option>
-			<option value="error">error</option>
-			<option value="ignore">ignore</option>
-		</param>
 
-
-		<param label="--m-metadata-file METADATA" name="metadatafile" type="data" format="tabular,qza,no_unzip.zip" />
+  ]]></command>
+  <inputs>
+    <param format="qza,no_unzip.zip" label="--i-table: ARTIFACT 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="True" title="--m-metadata-file">
+      <param format="tabular,qza,no_unzip.zip" label="--m-metadata-file: METADATA" name="additional_input" optional="True" type="data" />
+    </repeat>
+    <param label="--m-metadata-column: COLUMN  MetadataColumn[Numeric] Numeric metadata column to use as prediction target. [required]" name="mmetadatacolumn" optional="False" type="text" />
+    <param label="--p-cv: INTEGER       Number of k-fold cross-validations to perform. Range(1, None)                                                [default: 5]" min="1" name="pcv" optional="True" type="integer" value="5" />
+    <param label="--p-random-state: INTEGER Seed used by random number generator.        [optional]" name="prandomstate" optional="False" type="text" />
+    <param label="--p-n-estimators: INTEGER Range(1, None)     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]" min="1" name="pnestimators" optional="True" type="integer" value="100" />
+    <param label="--p-estimator: " name="pestimator" optional="True" type="select">
+      <option selected="True" value="None">Selection is Optional</option>
+      <option value="RandomForestRegressor">RandomForestRegressor</option>
+      <option value="ExtraTreesRegressor">ExtraTreesRegressor</option>
+      <option value="GradientBoostingRegressor">GradientBoostingRegressor</option>
+      <option value="AdaBoostRegressor">AdaBoostRegressor</option>
+      <option value="ElasticNet">ElasticNet</option>
+      <option value="Ridge">Ridge</option>
+      <option value="Lasso">Lasso</option>
+      <option value="KNeighborsRegressor">KNeighborsRegressor</option>
+      <option value="LinearSVR">LinearSVR</option>
+      <option value="SVR">SVR</option>
+    </param>
+    <param label="--p-stratify: --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" selected="False" type="boolean" />
+    <param label="--p-parameter-tuning: --p-parameter-tuning: / --p-no-parameter-tuning Automatically tune hyperparameters using random grid search.                                [default: False]" name="pparametertuning" selected="False" type="boolean" />
+    <param label="--p-missing-samples: " name="pmissingsamples" optional="True" type="select">
+      <option selected="True" value="None">Selection is Optional</option>
+      <option value="error">error</option>
+      <option value="ignore">ignore</option>
+    </param>
+    <param label="--examples: Show usage examples and exit." name="examples" optional="False" type="data" />
+    
+  </inputs>
 
-	</inputs>
-	<outputs>
-		<data format="qza" label="${tool.name} on ${on_string}: predictions.qza" name="opredictions"/>
-		<data format="qza" label="${tool.name} on ${on_string}: featureimportance.qza" name="ofeatureimportance"/>
-	</outputs>
-	<help><![CDATA[
-Nested cross-validated supervised learning classifier.
-######################################################
+  <outputs>
+    <data format="qza" label="${tool.name} on ${on_string}: predictions.qza" name="opredictions" />
+    <data format="qza" label="${tool.name} on ${on_string}: featureimportance.qza" name="ofeatureimportance" />
+    
+  </outputs>
 
-Predicts a categorical sample metadata column using a supervised learning
-classifier. Uses nested stratified k-fold cross validation for automated
+  <help><![CDATA[
+Nested cross-validated supervised learning regressor.
+###############################################################
+
+Predicts a continuous sample metadata column using a supervised learning
+regressor. Uses nested stratified k-fold cross validation for automated
 hyperparameter optimization and sample prediction. Outputs predicted values
 for each input sample, and relative importance of each feature for model
 accuracy.
@@ -109,20 +135,25 @@
 table : FeatureTable[Frequency]
     Feature table containing all features that should be used for target
     prediction.
-metadata : MetadataColumn[Categorical]
-    Categorical metadata column to use as prediction target.
+metadata : MetadataColumn[Numeric]
+    Numeric metadata column to use as prediction target.
 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_jobs : Int, optional
+    Number of jobs to run in parallel.
 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('RandomForestClassifier', 'ExtraTreesClassifier', 'GradientBoostingClassifier', 'AdaBoostClassifier', 'KNeighborsClassifier', 'LinearSVC', 'SVC'), optional
+estimator : Str % Choices('RandomForestRegressor', 'ExtraTreesRegressor', 'GradientBoostingRegressor', 'AdaBoostRegressor', 'ElasticNet', 'Ridge', 'Lasso', 'KNeighborsRegressor', 'LinearSVR', 'SVR'), optional
     Estimator method to use for sample prediction.
+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.
 missing_samples : Str % Choices('error', 'ignore'), optional
@@ -133,13 +164,13 @@
 
 Returns
 -------
-predictions : SampleData[ClassifierPredictions]
+predictions : SampleData[RegressorPredictions]
     Predicted target values for each input sample.
 feature_importance : FeatureData[Importance]
     Importance of each input feature to model accuracy.
-	]]></help>
-<macros>
+  ]]></help>
+  <macros>
     <import>qiime_citation.xml</import>
-</macros>
-<expand macro="qiime_citation"/>
-</tool>
+  </macros>
+  <expand macro="qiime_citation"/>
+</tool>
\ No newline at end of file