comparison qiime2-2020.8/qiime_sample-classifier_fit-regressor.xml @ 20:d93d8888f0b0 draft

Uploaded
author florianbegusch
date Fri, 04 Sep 2020 12:44:24 +0000
parents
children
comparison
equal deleted inserted replaced
19:6c48f8d82424 20:d93d8888f0b0
1 <?xml version="1.0" ?>
2 <tool id="qiime_sample-classifier_fit-regressor" name="qiime sample-classifier fit-regressor"
3 version="2020.8">
4 <description>Fit a supervised learning regressor.</description>
5 <requirements>
6 <requirement type="package" version="2020.8">qiime2</requirement>
7 </requirements>
8 <command><![CDATA[
9 qiime sample-classifier fit-regressor
10
11 --i-table=$itable
12 # if $input_files_mmetadatafile:
13 # def list_dict_to_string(list_dict):
14 # set $file_list = list_dict[0]['additional_input'].__getattr__('file_name')
15 # for d in list_dict[1:]:
16 # set $file_list = $file_list + ' --m-metadata-file=' + d['additional_input'].__getattr__('file_name')
17 # end for
18 # return $file_list
19 # end def
20 --m-metadata-file=$list_dict_to_string($input_files_mmetadatafile)
21 # end if
22
23 #if '__ob__' in str($mmetadatacolumn):
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-step=$pstep
48
49 --p-cv=$pcv
50
51 #if str($prandomstate):
52 --p-random-state=$prandomstate
53 #end if
54 --p-n-jobs=$pnjobs
55
56 --p-n-estimators=$pnestimators
57
58 #if str($pestimator) != 'None':
59 --p-estimator=$pestimator
60 #end if
61
62 #if $poptimizefeatureselection:
63 --p-optimize-feature-selection
64 #end if
65
66 #if $pparametertuning:
67 --p-parameter-tuning
68 #end if
69
70 #if str($pmissingsamples) != 'None':
71 --p-missing-samples=$pmissingsamples
72 #end if
73
74 --o-sample-estimator=osampleestimator
75
76 --o-feature-importance=ofeatureimportance
77
78 #if str($examples) != 'None':
79 --examples=$examples
80 #end if
81
82 ;
83 cp ofeatureimportance.qza $ofeatureimportance
84
85 ]]></command>
86 <inputs>
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" />
88 <repeat name="input_files_mmetadatafile" optional="True" title="--m-metadata-file">
89 <param format="tabular,qza,no_unzip.zip" label="--m-metadata-file: METADATA" name="additional_input" optional="True" type="data" />
90 </repeat>
91 <param label="--m-metadata-column: COLUMN MetadataColumn[Numeric] Numeric metadata column to use as prediction target. [required]" name="mmetadatacolumn" optional="False" type="text" />
92 <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" />
93 <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" />
94 <param label="--p-random-state: INTEGER Seed used by random number generator. [optional]" name="prandomstate" optional="False" type="text" />
95 <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" />
96 <param label="--p-estimator: " name="pestimator" optional="True" type="select">
97 <option selected="True" value="None">Selection is Optional</option>
98 <option value="RandomForestRegressor">RandomForestRegressor</option>
99 <option value="ExtraTreesRegressor">ExtraTreesRegressor</option>
100 <option value="GradientBoostingRegressor">GradientBoostingRegressor</option>
101 <option value="AdaBoostRegressor">AdaBoostRegressor</option>
102 <option value="ElasticNet">ElasticNet</option>
103 <option value="Ridge">Ridge</option>
104 <option value="Lasso">Lasso</option>
105 <option value="KNeighborsRegressor">KNeighborsRegressor</option>
106 <option value="LinearSVR">LinearSVR</option>
107 <option value="SVR">SVR</option>
108 </param>
109 <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" />
110 <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" />
111 <param label="--p-missing-samples: " name="pmissingsamples" optional="True" type="select">
112 <option selected="True" value="None">Selection is Optional</option>
113 <option value="error">error</option>
114 <option value="ignore">ignore</option>
115 </param>
116 <param label="--examples: Show usage examples and exit." name="examples" optional="False" type="data" />
117
118 </inputs>
119
120 <outputs>
121 <data format="qza" label="${tool.name} on ${on_string}: sampleestimator.qza" name="osampleestimator" />
122 <data format="qza" label="${tool.name} on ${on_string}: featureimportance.qza" name="ofeatureimportance" />
123
124 </outputs>
125
126 <help><![CDATA[
127 Fit a supervised learning regressor.
128 ###############################################################
129
130 Fit a supervised learning regressor. Outputs the fit estimator (for
131 prediction of test samples and/or unknown samples) and the relative
132 importance of each feature for model accuracy. Optionally use k-fold cross-
133 validation for automatic recursive feature elimination and hyperparameter
134 tuning.
135
136 Parameters
137 ----------
138 table : FeatureTable[Frequency]
139 Feature table containing all features that should be used for target
140 prediction.
141 metadata : MetadataColumn[Numeric]
142 Numeric metadata column to use as prediction target.
143 step : Float % Range(0.0, 1.0, inclusive_start=False), optional
144 If optimize_feature_selection is True, step is the percentage of
145 features to remove at each iteration.
146 cv : Int % Range(1, None), optional
147 Number of k-fold cross-validations to perform.
148 random_state : Int, optional
149 Seed used by random number generator.
150 n_jobs : Int, optional
151 Number of jobs to run in parallel.
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('RandomForestRegressor', 'ExtraTreesRegressor', 'GradientBoostingRegressor', 'AdaBoostRegressor', 'ElasticNet', 'Ridge', 'Lasso', 'KNeighborsRegressor', 'LinearSVR', '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 parameter_tuning : Bool, optional
164 Automatically tune hyperparameters using random grid search.
165 missing_samples : Str % Choices('error', 'ignore'), optional
166 How to handle missing samples in metadata. "error" will fail if missing
167 samples are detected. "ignore" will cause the feature table and
168 metadata to be filtered, so that only samples found in both files are
169 retained.
170
171 Returns
172 -------
173 sample_estimator : SampleEstimator[Regressor]
174 feature_importance : FeatureData[Importance]
175 Importance of each input feature to model accuracy.
176 ]]></help>
177 <macros>
178 <import>qiime_citation.xml</import>
179 </macros>
180 <expand macro="qiime_citation"/>
181 </tool>