Mercurial > repos > florianbegusch > qiime2_suite
diff qiime2/qiime_sample-classifier_regress-samples.xml @ 14:a0a8d77a991c draft
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.xml Thu Sep 03 09:46:00 2020 +0000 +++ b/qiime2/qiime_sample-classifier_regress-samples.xml Thu Sep 03 09:51:29 2020 +0000 @@ -1,44 +1,64 @@ <?xml version="1.0" ?> -<tool id="qiime_sample-classifier_regress-samples" name="qiime sample-classifier regress-samples" version="2019.7"> - <description> - Train and test a 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" name="qiime sample-classifier regress-samples" + version="2020.8"> + <description>Train and test a cross-validated supervised learning regressor.</description> + <requirements> + <requirement type="package" version="2020.8">qiime2</requirement> + </requirements> + <command><![CDATA[ qiime sample-classifier regress-samples --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($input_files_mmetadatafile) +# end if -#if str($ptestsize): - --p-test-size=$ptestsize +#if '__ob__' in str($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 = $mmetadatacolumn_temp +#end if +#if 'X' in str($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 = $mmetadatacolumn_temp #end if -#if str($pstep): - --p-step=$pstep -#end if +--m-metadata-column=$mmetadatacolumn + -#if str($pcv): - --p-cv=$pcv -#end if +--p-test-size=$ptestsize + +--p-step=$pstep + +--p-cv=$pcv #if str($prandomstate): - --p-random-state="$prandomstate" + --p-random-state=$prandomstate #end if - -#set $pnjobs = '${GALAXY_SLOTS:-4}' +--p-n-jobs=$pnjobs -#if str($pnjobs): - --p-n-jobs="$pnjobs" -#end if - - -#if str($pnestimators): - --p-n-estimators=$pnestimators -#end if +--p-n-estimators=$pnestimators #if str($pestimator) != 'None': - --p-estimator=$pestimator +--p-estimator=$pestimator #end if #if $poptimizefeatureselection: @@ -54,78 +74,85 @@ #end if #if str($pmissingsamples) != 'None': - --p-missing-samples=$pmissingsamples -#end if - - - - -#if $metadatafile: - --m-metadata-file=$metadatafile +--p-missing-samples=$pmissingsamples #end if +--o-sample-estimator=osampleestimator - +--o-feature-importance=ofeatureimportance ---o-sample-estimator=osampleestimator ---o-feature-importance=ofeatureimportance --o-predictions=opredictions + --o-model-summary=omodelsummary + --o-accuracy-results=oaccuracyresults + +#if str($examples) != 'None': +--examples=$examples +#end if + ; -cp osampleestimator.qza $osampleestimator; -cp ofeatureimportance.qza $ofeatureimportance; -cp opredictions.qza $opredictions; -qiime tools export --input-path omodelsummary.qzv --output-path out && mkdir -p '$omodelsummary.files_path' +cp opredictions.qza $opredictions + +; +qiime tools export omodelsummary.qzv --output-path out +&& mkdir -p '$omodelsummary.files_path' && cp -r out/* '$omodelsummary.files_path' -&& mv '$omodelsummary.files_path/index.html' '$omodelsummary'; -qiime tools export --input-path oaccuracyresults.qzv --output-path out && mkdir -p '$oaccuracyresults.files_path' +&& mv '$omodelsummary.files_path/index.html' '$omodelsummary' + +; +qiime tools export oaccuracyresults.qzv --output-path out +&& mkdir -p '$oaccuracyresults.files_path' && cp -r out/* '$oaccuracyresults.files_path' && mv '$oaccuracyresults.files_path/index.html' '$oaccuracyresults' - ]]></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-test-size: PROPORTION Range(0.0, 1.0, inclusive_start=False) 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" min="0" max="1" /> - <param label="--p-step: PROPORTION Range(0.0, 1.0, inclusive_start=False) 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" min="0" max="1" /> - <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-optimize-feature-selection: --p-no-optimize-feature-selection Automatically optimize input feature selection using recursive feature elimination. [default: False]" name="poptimizefeatureselection" selected="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" 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 exclude_min="True" label="--p-test-size: PROPORTION Range(0.0, 1.0, inclusive_start=False) Fraction of input samples to exclude from training set and use for classifier testing. [default: 0.2]" max="1.0" min="0.0" name="ptestsize" optional="True" type="float" value="0.2" /> + <param exclude_min="True" label="--p-step: PROPORTION Range(0.0, 1.0, inclusive_start=False) If optimize-feature-selection is True, step is the percentage of features to remove at each iteration. [default: 0.05]" max="1.0" min="0.0" name="pstep" optional="True" type="float" value="0.05" /> + <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-optimize-feature-selection: --p-optimize-feature-selection: / --p-no-optimize-feature-selection Automatically optimize input feature selection using recursive feature elimination. [default: False]" name="poptimizefeatureselection" selected="False" type="boolean" /> + <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 ${on_string}: sampleestimator.qza" name="osampleestimator"/> - <data format="qza" label="${tool.name} on ${on_string}: featureimportance.qza" name="ofeatureimportance"/> - <data format="qza" label="${tool.name} on ${on_string}: predictions.qza" name="opredictions"/> - <data format="html" label="${tool.name} on ${on_string}: modelsummary.qzv" name="omodelsummary"/> - <data format="html" label="${tool.name} on ${on_string}: accuracyresults.qzv" name="oaccuracyresults"/> - </outputs> - <help><![CDATA[ + <outputs> + <data format="qza" label="${tool.name} on ${on_string}: sampleestimator.qza" name="osampleestimator" /> + <data format="qza" label="${tool.name} on ${on_string}: featureimportance.qza" name="ofeatureimportance" /> + <data format="qza" label="${tool.name} on ${on_string}: predictions.qza" name="opredictions" /> + <data format="html" label="${tool.name} on ${on_string}: modelsummary.html" name="omodelsummary" /> + <data format="html" label="${tool.name} on ${on_string}: accuracyresults.html" name="oaccuracyresults" /> + + </outputs> + + <help><![CDATA[ Train and test a cross-validated supervised learning regressor. ############################################################### @@ -155,6 +182,8 @@ 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 @@ -190,9 +219,9 @@ the trained estimator. accuracy_results : Visualization Accuracy results visualization. - ]]></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