Mercurial > repos > florianbegusch > qiime2_suite
comparison 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 |
comparison
equal
deleted
inserted
replaced
13:887cd4ad8e16 | 14:a0a8d77a991c |
---|---|
1 <?xml version="1.0" ?> | 1 <?xml version="1.0" ?> |
2 <tool id="qiime_sample-classifier_regress-samples" name="qiime sample-classifier regress-samples" version="2019.7"> | 2 <tool id="qiime_sample-classifier_regress-samples" name="qiime sample-classifier regress-samples" |
3 <description> - Train and test a cross-validated supervised learning regressor.</description> | 3 version="2020.8"> |
4 <requirements> | 4 <description>Train and test a cross-validated supervised learning regressor.</description> |
5 <requirement type="package" version="2019.7">qiime2</requirement> | 5 <requirements> |
6 </requirements> | 6 <requirement type="package" version="2020.8">qiime2</requirement> |
7 <command><![CDATA[ | 7 </requirements> |
8 <command><![CDATA[ | |
8 qiime sample-classifier regress-samples | 9 qiime sample-classifier regress-samples |
9 | 10 |
10 --i-table=$itable | 11 --i-table=$itable |
11 --m-metadata-column="$mmetadatacolumn" | 12 # if $input_files_mmetadatafile: |
12 | 13 # def list_dict_to_string(list_dict): |
13 #if str($ptestsize): | 14 # set $file_list = list_dict[0]['additional_input'].__getattr__('file_name') |
14 --p-test-size=$ptestsize | 15 # for d in list_dict[1:]: |
15 #end if | 16 # set $file_list = $file_list + ' --m-metadata-file=' + d['additional_input'].__getattr__('file_name') |
16 | 17 # end for |
17 #if str($pstep): | 18 # return $file_list |
18 --p-step=$pstep | 19 # end def |
19 #end if | 20 --m-metadata-file=$list_dict_to_string($input_files_mmetadatafile) |
20 | 21 # end if |
21 #if str($pcv): | 22 |
22 --p-cv=$pcv | 23 #if '__ob__' in str($mmetadatacolumn): |
23 #end if | 24 #set $mmetadatacolumn_temp = $mmetadatacolumn.replace('__ob__', '[') |
25 #set $mmetadatacolumn = $mmetadatacolumn_temp | |
26 #end if | |
27 #if '__cb__' in str($mmetadatacolumn): | |
28 #set $mmetadatacolumn_temp = $mmetadatacolumn.replace('__cb__', ']') | |
29 #set $mmetadatacolumn = $mmetadatacolumn_temp | |
30 #end if | |
31 #if 'X' in str($mmetadatacolumn): | |
32 #set $mmetadatacolumn_temp = $mmetadatacolumn.replace('X', '\\') | |
33 #set $mmetadatacolumn = $mmetadatacolumn_temp | |
34 #end if | |
35 #if '__sq__' in str($mmetadatacolumn): | |
36 #set $mmetadatacolumn_temp = $mmetadatacolumn.replace('__sq__', "'") | |
37 #set $mmetadatacolumn = $mmetadatacolumn_temp | |
38 #end if | |
39 #if '__db__' in str($mmetadatacolumn): | |
40 #set $mmetadatacolumn_temp = $mmetadatacolumn.replace('__db__', '"') | |
41 #set $mmetadatacolumn = $mmetadatacolumn_temp | |
42 #end if | |
43 | |
44 --m-metadata-column=$mmetadatacolumn | |
45 | |
46 | |
47 --p-test-size=$ptestsize | |
48 | |
49 --p-step=$pstep | |
50 | |
51 --p-cv=$pcv | |
24 | 52 |
25 #if str($prandomstate): | 53 #if str($prandomstate): |
26 --p-random-state="$prandomstate" | 54 --p-random-state=$prandomstate |
27 #end if | 55 #end if |
28 | 56 --p-n-jobs=$pnjobs |
29 #set $pnjobs = '${GALAXY_SLOTS:-4}' | 57 |
30 | 58 --p-n-estimators=$pnestimators |
31 #if str($pnjobs): | |
32 --p-n-jobs="$pnjobs" | |
33 #end if | |
34 | |
35 | |
36 #if str($pnestimators): | |
37 --p-n-estimators=$pnestimators | |
38 #end if | |
39 | 59 |
40 #if str($pestimator) != 'None': | 60 #if str($pestimator) != 'None': |
41 --p-estimator=$pestimator | 61 --p-estimator=$pestimator |
42 #end if | 62 #end if |
43 | 63 |
44 #if $poptimizefeatureselection: | 64 #if $poptimizefeatureselection: |
45 --p-optimize-feature-selection | 65 --p-optimize-feature-selection |
46 #end if | 66 #end if |
52 #if $pparametertuning: | 72 #if $pparametertuning: |
53 --p-parameter-tuning | 73 --p-parameter-tuning |
54 #end if | 74 #end if |
55 | 75 |
56 #if str($pmissingsamples) != 'None': | 76 #if str($pmissingsamples) != 'None': |
57 --p-missing-samples=$pmissingsamples | 77 --p-missing-samples=$pmissingsamples |
58 #end if | 78 #end if |
59 | |
60 | |
61 | |
62 | |
63 #if $metadatafile: | |
64 --m-metadata-file=$metadatafile | |
65 #end if | |
66 | |
67 | |
68 | |
69 | 79 |
70 --o-sample-estimator=osampleestimator | 80 --o-sample-estimator=osampleestimator |
81 | |
71 --o-feature-importance=ofeatureimportance | 82 --o-feature-importance=ofeatureimportance |
83 | |
72 --o-predictions=opredictions | 84 --o-predictions=opredictions |
85 | |
73 --o-model-summary=omodelsummary | 86 --o-model-summary=omodelsummary |
87 | |
74 --o-accuracy-results=oaccuracyresults | 88 --o-accuracy-results=oaccuracyresults |
89 | |
90 #if str($examples) != 'None': | |
91 --examples=$examples | |
92 #end if | |
93 | |
75 ; | 94 ; |
76 cp osampleestimator.qza $osampleestimator; | 95 cp opredictions.qza $opredictions |
77 cp ofeatureimportance.qza $ofeatureimportance; | 96 |
78 cp opredictions.qza $opredictions; | 97 ; |
79 qiime tools export --input-path omodelsummary.qzv --output-path out && mkdir -p '$omodelsummary.files_path' | 98 qiime tools export omodelsummary.qzv --output-path out |
99 && mkdir -p '$omodelsummary.files_path' | |
80 && cp -r out/* '$omodelsummary.files_path' | 100 && cp -r out/* '$omodelsummary.files_path' |
81 && mv '$omodelsummary.files_path/index.html' '$omodelsummary'; | 101 && mv '$omodelsummary.files_path/index.html' '$omodelsummary' |
82 qiime tools export --input-path oaccuracyresults.qzv --output-path out && mkdir -p '$oaccuracyresults.files_path' | 102 |
103 ; | |
104 qiime tools export oaccuracyresults.qzv --output-path out | |
105 && mkdir -p '$oaccuracyresults.files_path' | |
83 && cp -r out/* '$oaccuracyresults.files_path' | 106 && cp -r out/* '$oaccuracyresults.files_path' |
84 && mv '$oaccuracyresults.files_path/index.html' '$oaccuracyresults' | 107 && mv '$oaccuracyresults.files_path/index.html' '$oaccuracyresults' |
85 ]]></command> | 108 |
86 <inputs> | 109 ]]></command> |
87 <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"/> | 110 <inputs> |
88 <param label="--m-metadata-column: COLUMN MetadataColumn[Numeric] Numeric metadata column to use as prediction target. [required]" name="mmetadatacolumn" optional="False" type="text"/> | 111 <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" /> |
89 <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" /> | 112 <repeat name="input_files_mmetadatafile" optional="True" title="--m-metadata-file"> |
90 <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" /> | 113 <param format="tabular,qza,no_unzip.zip" label="--m-metadata-file: METADATA" name="additional_input" optional="True" type="data" /> |
91 <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"/> | 114 </repeat> |
92 <param label="--p-random-state: INTEGER Seed used by random number generator. [optional]" name="prandomstate" optional="True" type="integer"/> | 115 <param label="--m-metadata-column: COLUMN MetadataColumn[Numeric] Numeric metadata column to use as prediction target. [required]" name="mmetadatacolumn" optional="False" type="text" /> |
93 <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"/> | 116 <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" /> |
94 <param label="--p-estimator: " name="pestimator" optional="True" type="select"> | 117 <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" /> |
95 <option selected="True" value="None">Selection is Optional</option> | 118 <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" /> |
96 <option value="RandomForestRegressor">RandomForestRegressor</option> | 119 <param label="--p-random-state: INTEGER Seed used by random number generator. [optional]" name="prandomstate" optional="False" type="text" /> |
97 <option value="ExtraTreesRegressor">ExtraTreesRegressor</option> | 120 <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" /> |
98 <option value="GradientBoostingRegressor">GradientBoostingRegressor</option> | 121 <param label="--p-estimator: " name="pestimator" optional="True" type="select"> |
99 <option value="AdaBoostRegressor">AdaBoostRegressor</option> | 122 <option selected="True" value="None">Selection is Optional</option> |
100 <option value="ElasticNet">ElasticNet</option> | 123 <option value="RandomForestRegressor">RandomForestRegressor</option> |
101 <option value="Ridge">Ridge</option> | 124 <option value="ExtraTreesRegressor">ExtraTreesRegressor</option> |
102 <option value="Lasso">Lasso</option> | 125 <option value="GradientBoostingRegressor">GradientBoostingRegressor</option> |
103 <option value="KNeighborsRegressor">KNeighborsRegressor</option> | 126 <option value="AdaBoostRegressor">AdaBoostRegressor</option> |
104 <option value="LinearSVR">LinearSVR</option> | 127 <option value="ElasticNet">ElasticNet</option> |
105 <option value="SVR">SVR</option> | 128 <option value="Ridge">Ridge</option> |
106 </param> | 129 <option value="Lasso">Lasso</option> |
107 <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"/> | 130 <option value="KNeighborsRegressor">KNeighborsRegressor</option> |
108 <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"/> | 131 <option value="LinearSVR">LinearSVR</option> |
109 <param label="--p-parameter-tuning: --p-no-parameter-tuning Automatically tune hyperparameters using random grid search. [default: False]" name="pparametertuning" selected="False" type="boolean"/> | 132 <option value="SVR">SVR</option> |
110 <param label="--p-missing-samples: " name="pmissingsamples" optional="True" type="select"> | 133 </param> |
111 <option selected="True" value="None">Selection is Optional</option> | 134 <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" /> |
112 <option value="error">error</option> | 135 <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" /> |
113 <option value="ignore">ignore</option> | 136 <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" /> |
114 </param> | 137 <param label="--p-missing-samples: " name="pmissingsamples" optional="True" type="select"> |
115 | 138 <option selected="True" value="None">Selection is Optional</option> |
116 | 139 <option value="error">error</option> |
117 <param label="--m-metadata-file METADATA" name="metadatafile" type="data" format="tabular,qza,no_unzip.zip" /> | 140 <option value="ignore">ignore</option> |
118 | 141 </param> |
119 | 142 <param label="--examples: Show usage examples and exit." name="examples" optional="False" type="data" /> |
120 </inputs> | 143 |
121 <outputs> | 144 </inputs> |
122 <data format="qza" label="${tool.name} on ${on_string}: sampleestimator.qza" name="osampleestimator"/> | 145 |
123 <data format="qza" label="${tool.name} on ${on_string}: featureimportance.qza" name="ofeatureimportance"/> | 146 <outputs> |
124 <data format="qza" label="${tool.name} on ${on_string}: predictions.qza" name="opredictions"/> | 147 <data format="qza" label="${tool.name} on ${on_string}: sampleestimator.qza" name="osampleestimator" /> |
125 <data format="html" label="${tool.name} on ${on_string}: modelsummary.qzv" name="omodelsummary"/> | 148 <data format="qza" label="${tool.name} on ${on_string}: featureimportance.qza" name="ofeatureimportance" /> |
126 <data format="html" label="${tool.name} on ${on_string}: accuracyresults.qzv" name="oaccuracyresults"/> | 149 <data format="qza" label="${tool.name} on ${on_string}: predictions.qza" name="opredictions" /> |
127 </outputs> | 150 <data format="html" label="${tool.name} on ${on_string}: modelsummary.html" name="omodelsummary" /> |
128 <help><![CDATA[ | 151 <data format="html" label="${tool.name} on ${on_string}: accuracyresults.html" name="oaccuracyresults" /> |
152 | |
153 </outputs> | |
154 | |
155 <help><![CDATA[ | |
129 Train and test a cross-validated supervised learning regressor. | 156 Train and test a cross-validated supervised learning regressor. |
130 ############################################################### | 157 ############################################################### |
131 | 158 |
132 Predicts a continuous sample metadata column using a supervised learning | 159 Predicts a continuous sample metadata column using a supervised learning |
133 regressor. Splits input data into training and test sets. The training set | 160 regressor. Splits input data into training and test sets. The training set |
153 features to remove at each iteration. | 180 features to remove at each iteration. |
154 cv : Int % Range(1, None), optional | 181 cv : Int % Range(1, None), optional |
155 Number of k-fold cross-validations to perform. | 182 Number of k-fold cross-validations to perform. |
156 random_state : Int, optional | 183 random_state : Int, optional |
157 Seed used by random number generator. | 184 Seed used by random number generator. |
185 n_jobs : Int, optional | |
186 Number of jobs to run in parallel. | |
158 n_estimators : Int % Range(1, None), optional | 187 n_estimators : Int % Range(1, None), optional |
159 Number of trees to grow for estimation. More trees will improve | 188 Number of trees to grow for estimation. More trees will improve |
160 predictive accuracy up to a threshold level, but will also increase | 189 predictive accuracy up to a threshold level, but will also increase |
161 time and memory requirements. This parameter only affects ensemble | 190 time and memory requirements. This parameter only affects ensemble |
162 estimators, such as Random Forest, AdaBoost, ExtraTrees, and | 191 estimators, such as Random Forest, AdaBoost, ExtraTrees, and |
188 model_summary : Visualization | 217 model_summary : Visualization |
189 Summarized parameter and (if enabled) feature selection information for | 218 Summarized parameter and (if enabled) feature selection information for |
190 the trained estimator. | 219 the trained estimator. |
191 accuracy_results : Visualization | 220 accuracy_results : Visualization |
192 Accuracy results visualization. | 221 Accuracy results visualization. |
193 ]]></help> | 222 ]]></help> |
194 <macros> | 223 <macros> |
195 <import>qiime_citation.xml</import> | 224 <import>qiime_citation.xml</import> |
196 </macros> | 225 </macros> |
197 <expand macro="qiime_citation"/> | 226 <expand macro="qiime_citation"/> |
198 </tool> | 227 </tool> |