|
0
|
1 <?xml version="1.0" ?>
|
|
|
2 <tool id="qiime_sample-classifier_regress-samples" name="qiime sample-classifier regress-samples" version="2018.4">
|
|
|
3 <description> - Supervised learning regressor.</description>
|
|
|
4 <requirements>
|
|
|
5 <requirement type="package" version="2018.4">qiime2</requirement>
|
|
|
6 </requirements>
|
|
|
7 <command>
|
|
|
8 <![CDATA[
|
|
|
9 qiime sample-classifier regress-samples --i-table=$itable
|
|
|
10
|
|
|
11 #def list_dict_to_string(list_dict):
|
|
|
12 #set $file_list = list_dict[0]['additional_input'].__getattr__('file_name')
|
|
|
13 #for d in list_dict[1:]:
|
|
|
14 #set $file_list = $file_list + ' --m-metadata-file=' + d['additional_input'].__getattr__('file_name')
|
|
|
15 #end for
|
|
|
16 #return $file_list
|
|
|
17 #end def
|
|
|
18
|
|
|
19 --m-metadata-file=$list_dict_to_string($input_files_mmetadatafile) --m-metadata-column="$mmetadatacolumn"
|
|
|
20 #set $pnjobs = '${GALAXY_SLOTS:-4}'
|
|
|
21
|
|
|
22 #if str($pnjobs):
|
|
|
23 --p-n-jobs="$pnjobs"
|
|
|
24 #end if
|
|
|
25
|
|
|
26
|
|
|
27 #if $pstep:
|
|
|
28 --p-step=$pstep
|
|
|
29 #end if
|
|
|
30
|
|
|
31 #if $pstratify:
|
|
|
32 --p-stratify
|
|
|
33 #else
|
|
|
34 --p-no-stratify
|
|
|
35 #end if
|
|
|
36
|
|
|
37 #if $poptimizefeatureselection:
|
|
|
38 --p-optimize-feature-selection
|
|
|
39 #else
|
|
|
40 --p-no-optimize-feature-selection
|
|
|
41 #end if
|
|
|
42
|
|
|
43 #if $ptestsize:
|
|
|
44 --p-test-size=$ptestsize
|
|
|
45 #end if
|
|
|
46 --o-visualization=ovisualization
|
|
|
47 #if str($pestimator) != 'None':
|
|
|
48 --p-estimator=$pestimator
|
|
|
49 #end if
|
|
|
50
|
|
|
51 #if $pnestimators:
|
|
|
52 --p-n-estimators=$pnestimators
|
|
|
53 #end if
|
|
|
54
|
|
|
55 #if str($cmdconfig) != 'None':
|
|
|
56 --cmd-config=$cmdconfig
|
|
|
57 #end if
|
|
|
58
|
|
|
59 #if $pcv:
|
|
|
60 --p-cv=$pcv
|
|
|
61 #end if
|
|
|
62
|
|
|
63 #if $pparametertuning:
|
|
|
64 --p-parameter-tuning
|
|
|
65 #else
|
|
|
66 --p-no-parameter-tuning
|
|
|
67 #end if
|
|
|
68
|
|
|
69 #if str($prandomstate):
|
|
|
70 --p-random-state="$prandomstate"
|
|
|
71 #end if
|
|
|
72 ;
|
|
|
73 qiime tools export ovisualization.qzv --output-dir out && mkdir -p '$ovisualization.files_path'
|
|
|
74 && cp -r out/* '$ovisualization.files_path'
|
|
|
75 && mv '$ovisualization.files_path/index.html' '$ovisualization'
|
|
|
76 ]]>
|
|
|
77 </command>
|
|
|
78 <inputs>
|
|
|
79 <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"/>
|
|
|
80 <repeat name="input_files_mmetadatafile" optional="False" title="--m-metadata-file">
|
|
|
81 <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" />
|
|
|
82 </repeat>
|
|
|
83 <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"/>
|
|
|
84
|
|
|
85 <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"/>
|
|
|
86
|
|
|
87 <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"/>
|
|
|
88
|
|
|
89 <param label="--p-cv: Number of k-fold cross-validations to perform. [default: 5]" name="pcv" optional="True" type="integer" value="5"/>
|
|
|
90
|
|
|
91 <param label="--p-random-state: Seed used by random number generator. [optional]" name="prandomstate" optional="True" type="text"/>
|
|
|
92
|
|
|
93 <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"/>
|
|
|
94 <param label="--p-estimator: Estimator method to use for sample
|
|
|
95 prediction. [default:
|
|
|
96 RandomForestRegressor]" name="pestimator" optional="True" type="select">
|
|
|
97 <option selected="True" value="None">Selection is Optional</option>
|
|
|
98 <option value="Ridge">Ridge</option>
|
|
|
99 <option value="RandomForestRegressor">RandomForestRegressor</option>
|
|
|
100 <option value="GradientBoostingRegressor">GradientBoostingRegressor</option>
|
|
|
101 <option value="AdaBoostRegressor">AdaBoostRegressor</option>
|
|
|
102 <option value="LinearSVR">LinearSVR</option>
|
|
|
103 <option value="ExtraTreesRegressor">ExtraTreesRegressor</option>
|
|
|
104 <option value="KNeighborsRegressor">KNeighborsRegressor</option>
|
|
|
105 <option value="SVR">SVR</option>
|
|
|
106 <option value="ElasticNet">ElasticNet</option>
|
|
|
107 <option value="Lasso">Lasso</option>
|
|
|
108 </param>
|
|
|
109
|
|
|
110 <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"/>
|
|
|
111
|
|
|
112 <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"/>
|
|
|
113
|
|
|
114 <param label="--p-parameter-tuning: --p-no-parameter-tuning Automatically tune hyperparameters using random grid search. [default: False]" name="pparametertuning" checked="False" type="boolean"/>
|
|
|
115
|
|
|
116 <param label="--cmd-config: Use config file for command options" name="cmdconfig" optional="True" type="data"/>
|
|
|
117 </inputs>
|
|
|
118 <outputs>
|
|
|
119 <data format="html" label="${tool.name} on ${on_string}: visualization.qzv" name="ovisualization"/>
|
|
|
120 </outputs>
|
|
|
121 <help>
|
|
|
122 <![CDATA[
|
|
|
123 Supervised learning regressor.
|
|
|
124 -------------------------------
|
|
|
125
|
|
|
126 Predicts a continuous sample metadata column using a supervised learning
|
|
|
127 regressor. Splits input data into training and test sets. The training set
|
|
|
128 is used to train and test the estimator using a stratified k-fold cross-
|
|
|
129 validation scheme. This includes optional steps for automated feature
|
|
|
130 extraction and hyperparameter optimization. The test set validates
|
|
|
131 classification accuracy of the optimized estimator. Outputs classification
|
|
|
132 results for test set. For more details on the learning algorithm, see
|
|
|
133 http://scikit-learn.org/stable/supervised_learning.html
|
|
|
134
|
|
|
135 Parameters
|
|
|
136 ----------
|
|
|
137 table : FeatureTable[Frequency]
|
|
|
138 Feature table containing all features that should be used for target
|
|
|
139 prediction.
|
|
|
140 metadata : MetadataColumn[Numeric]
|
|
|
141 Numeric metadata column to use as prediction target.
|
|
|
142 test_size : Float % Range(0.0, 1.0, inclusive_start=False), optional
|
|
|
143 Fraction of input samples to exclude from training set and use for
|
|
|
144 classifier testing.
|
|
|
145 step : Float % Range(0.0, 1.0, inclusive_start=False), optional
|
|
|
146 If optimize_feature_selection is True, step is the percentage of
|
|
|
147 features to remove at each iteration.
|
|
|
148 cv : Int % Range(1, None), optional
|
|
|
149 Number of k-fold cross-validations to perform.
|
|
|
150 random_state : Int, optional
|
|
|
151 Seed used by random number generator.
|
|
|
152 n_estimators : Int % Range(1, None), optional
|
|
|
153 Number of trees to grow for estimation. More trees will improve
|
|
|
154 predictive accuracy up to a threshold level, but will also increase
|
|
|
155 time and memory requirements. This parameter only affects ensemble
|
|
|
156 estimators, such as Random Forest, AdaBoost, ExtraTrees, and
|
|
|
157 GradientBoosting.
|
|
|
158 estimator : Str % Choices({'AdaBoostRegressor', 'ElasticNet', 'ExtraTreesRegressor', 'GradientBoostingRegressor', 'KNeighborsRegressor', 'Lasso', 'LinearSVR', 'RandomForestRegressor', 'Ridge', 'SVR'}), optional
|
|
|
159 Estimator method to use for sample prediction.
|
|
|
160 optimize_feature_selection : Bool, optional
|
|
|
161 Automatically optimize input feature selection using recursive feature
|
|
|
162 elimination.
|
|
|
163 stratify : Bool, optional
|
|
|
164 Evenly stratify training and test data among metadata categories. If
|
|
|
165 True, all values in column must match at least two samples.
|
|
|
166 parameter_tuning : Bool, optional
|
|
|
167 Automatically tune hyperparameters using random grid search.
|
|
|
168
|
|
|
169 Returns
|
|
|
170 -------
|
|
|
171 visualization : Visualization
|
|
|
172 \
|
|
|
173 ]]>
|
|
|
174 </help>
|
|
|
175 <macros>
|
|
|
176 <import>qiime_citation.xml</import>
|
|
|
177 </macros>
|
|
|
178 <expand macro="qiime_citation" />
|
|
|
179 </tool>
|
