Mercurial > repos > florianbegusch > qiime2_all

comparison qiime_sample-classifier_regress-samples.xml @ 0:09b7bcb72fa7 draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
Uploaded
author florianbegusch
date Thu, 24 May 2018 02:11:44 -0400
parents
children
comparison
equal deleted inserted replaced
-1:000000000000 0:09b7bcb72fa7
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 </tool>