annotate qiime2/qiime_sample-classifier_regress-samples-ncv.xml @ 10:21c7954105a9 draft

Fix
author florianbegusch
date Sun, 25 Aug 2019 10:26:27 -0400
parents f190567fe3f6
children a0a8d77a991c
Ignore whitespace changes - Everywhere: Within whitespace: At end of lines:
rev   line source
0
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
1 <?xml version="1.0" ?>
9
f190567fe3f6 Uploaded
florianbegusch
parents: 6
diff changeset
2 <tool id="qiime_sample-classifier_regress-samples-ncv" name="qiime sample-classifier regress-samples-ncv" version="2019.7">
0
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
3 <description> - Nested cross-validated supervised learning regressor.</description>
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
4 <requirements>
9
f190567fe3f6 Uploaded
florianbegusch
parents: 6
diff changeset
5 <requirement type="package" version="2019.7">qiime2</requirement>
0
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
6 </requirements>
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
7 <command><![CDATA[
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
8 qiime sample-classifier regress-samples-ncv
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
9
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
10 --i-table=$itable
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
11 --m-metadata-column="$mmetadatacolumn"
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
12
6
florianbegusch
parents: 5
diff changeset
13 #if str($pcv):
0
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
14 --p-cv=$pcv
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
15 #end if
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
16
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
17 #if str($prandomstate):
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
18 --p-random-state="$prandomstate"
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
19 #end if
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
20
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
21 #set $pnjobs = '${GALAXY_SLOTS:-4}'
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
22
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
23 #if str($pnjobs):
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
24 --p-n-jobs="$pnjobs"
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
25 #end if
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
26
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
27
6
florianbegusch
parents: 5
diff changeset
28 #if str($pnestimators):
0
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
29 --p-n-estimators=$pnestimators
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
30 #end if
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
31
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
32 #if str($pestimator) != 'None':
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
33 --p-estimator=$pestimator
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
34 #end if
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
35
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
36 #if $pstratify:
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
37 --p-stratify
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
38 #end if
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
39
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
40 #if $pparametertuning:
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
41 --p-parameter-tuning
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
42 #end if
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
43
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
44 #if str($pmissingsamples) != 'None':
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
45 --p-missing-samples=$pmissingsamples
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
46 #end if
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
47
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
48
5
a025a4a89e07 Uploaded
florianbegusch
parents: 0
diff changeset
49
a025a4a89e07 Uploaded
florianbegusch
parents: 0
diff changeset
50 #if $metadatafile:
a025a4a89e07 Uploaded
florianbegusch
parents: 0
diff changeset
51 --m-metadata-file=$metadatafile
0
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
52 #end if
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
53
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
54
5
a025a4a89e07 Uploaded
florianbegusch
parents: 0
diff changeset
55
0
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
56 --o-predictions=opredictions
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
57 --o-feature-importance=ofeatureimportance
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
58 ;
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
59 cp opredictions.qza $opredictions;
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
60 cp ofeatureimportance.qza $ofeatureimportance
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
61 ]]></command>
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
62 <inputs>
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
63 <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"/>
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
64 <param label="--m-metadata-column: COLUMN MetadataColumn[Numeric] Numeric metadata column to use as prediction target. [required]" name="mmetadatacolumn" optional="False" type="text"/>
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
65 <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"/>
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
66 <param label="--p-random-state: INTEGER Seed used by random number generator. [optional]" name="prandomstate" optional="True" type="integer"/>
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
67 <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"/>
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
68 <param label="--p-estimator: " name="pestimator" optional="True" type="select">
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
69 <option selected="True" value="None">Selection is Optional</option>
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
70 <option value="RandomForestRegressor">RandomForestRegressor</option>
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
71 <option value="ExtraTreesRegressor">ExtraTreesRegressor</option>
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
72 <option value="GradientBoostingRegressor">GradientBoostingRegressor</option>
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
73 <option value="AdaBoostRegressor">AdaBoostRegressor</option>
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
74 <option value="ElasticNet">ElasticNet</option>
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
75 <option value="Ridge">Ridge</option>
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
76 <option value="Lasso">Lasso</option>
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
77 <option value="KNeighborsRegressor">KNeighborsRegressor</option>
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
78 <option value="LinearSVR">LinearSVR</option>
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
79 <option value="SVR">SVR</option>
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
80 </param>
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
81 <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"/>
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
82 <param label="--p-parameter-tuning: --p-no-parameter-tuning Automatically tune hyperparameters using random grid search. [default: False]" name="pparametertuning" selected="False" type="boolean"/>
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
83 <param label="--p-missing-samples: " name="pmissingsamples" optional="True" type="select">
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
84 <option selected="True" value="None">Selection is Optional</option>
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
85 <option value="error">error</option>
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
86 <option value="ignore">ignore</option>
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
87 </param>
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
88
5
a025a4a89e07 Uploaded
florianbegusch
parents: 0
diff changeset
89
a025a4a89e07 Uploaded
florianbegusch
parents: 0
diff changeset
90 <param label="--m-metadata-file METADATA" name="metadatafile" type="data" format="tabular,qza,no_unzip.zip" />
a025a4a89e07 Uploaded
florianbegusch
parents: 0
diff changeset
91
0
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
92 </inputs>
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
93 <outputs>
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
94 <data format="qza" label="${tool.name} on ${on_string}: predictions.qza" name="opredictions"/>
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
95 <data format="qza" label="${tool.name} on ${on_string}: featureimportance.qza" name="ofeatureimportance"/>
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
96 </outputs>
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
97 <help><![CDATA[
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
98 Nested cross-validated supervised learning classifier.
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
99 ######################################################
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
100
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
101 Predicts a categorical sample metadata column using a supervised learning
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
102 classifier. Uses nested stratified k-fold cross validation for automated
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
103 hyperparameter optimization and sample prediction. Outputs predicted values
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
104 for each input sample, and relative importance of each feature for model
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
105 accuracy.
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
106
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
107 Parameters
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
108 ----------
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
109 table : FeatureTable[Frequency]
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
110 Feature table containing all features that should be used for target
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
111 prediction.
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
112 metadata : MetadataColumn[Categorical]
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
113 Categorical metadata column to use as prediction target.
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
114 cv : Int % Range(1, None), optional
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
115 Number of k-fold cross-validations to perform.
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
116 random_state : Int, optional
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
117 Seed used by random number generator.
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
118 n_estimators : Int % Range(1, None), optional
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
119 Number of trees to grow for estimation. More trees will improve
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
120 predictive accuracy up to a threshold level, but will also increase
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
121 time and memory requirements. This parameter only affects ensemble
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
122 estimators, such as Random Forest, AdaBoost, ExtraTrees, and
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
123 GradientBoosting.
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
124 estimator : Str % Choices('RandomForestClassifier', 'ExtraTreesClassifier', 'GradientBoostingClassifier', 'AdaBoostClassifier', 'KNeighborsClassifier', 'LinearSVC', 'SVC'), optional
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
125 Estimator method to use for sample prediction.
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
126 parameter_tuning : Bool, optional
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
127 Automatically tune hyperparameters using random grid search.
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
128 missing_samples : Str % Choices('error', 'ignore'), optional
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
129 How to handle missing samples in metadata. "error" will fail if missing
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
130 samples are detected. "ignore" will cause the feature table and
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
131 metadata to be filtered, so that only samples found in both files are
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
132 retained.
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
133
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
134 Returns
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
135 -------
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
136 predictions : SampleData[ClassifierPredictions]
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
137 Predicted target values for each input sample.
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
138 feature_importance : FeatureData[Importance]
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
139 Importance of each input feature to model accuracy.
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
140 ]]></help>
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
141 <macros>
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
142 <import>qiime_citation.xml</import>
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
143 </macros>
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
144 <expand macro="qiime_citation"/>
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
145 </tool>