annotate 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
Ignore whitespace changes - Everywhere: Within whitespace: At end of lines:
rev   line source
20
d93d8888f0b0 Uploaded
florianbegusch
parents:
diff changeset
1 <?xml version="1.0" ?>
d93d8888f0b0 Uploaded
florianbegusch
parents:
diff changeset
2 <tool id="qiime_sample-classifier_fit-regressor" name="qiime sample-classifier fit-regressor"
d93d8888f0b0 Uploaded
florianbegusch
parents:
diff changeset
3 version="2020.8">
d93d8888f0b0 Uploaded
florianbegusch
parents:
diff changeset
4 <description>Fit a supervised learning regressor.</description>
d93d8888f0b0 Uploaded
florianbegusch
parents:
diff changeset
5 <requirements>
d93d8888f0b0 Uploaded
florianbegusch
parents:
diff changeset
6 <requirement type="package" version="2020.8">qiime2</requirement>
d93d8888f0b0 Uploaded
florianbegusch
parents:
diff changeset
7 </requirements>
d93d8888f0b0 Uploaded
florianbegusch
parents:
diff changeset
8 <command><![CDATA[
d93d8888f0b0 Uploaded
florianbegusch
parents:
diff changeset
9 qiime sample-classifier fit-regressor
d93d8888f0b0 Uploaded
florianbegusch
parents:
diff changeset
10
d93d8888f0b0 Uploaded
florianbegusch
parents:
diff changeset
11 --i-table=$itable
d93d8888f0b0 Uploaded
florianbegusch
parents:
diff changeset
12 # if $input_files_mmetadatafile:
d93d8888f0b0 Uploaded
florianbegusch
parents:
diff changeset
13 # def list_dict_to_string(list_dict):
d93d8888f0b0 Uploaded
florianbegusch
parents:
diff changeset
14 # set $file_list = list_dict[0]['additional_input'].__getattr__('file_name')
d93d8888f0b0 Uploaded
florianbegusch
parents:
diff changeset
15 # for d in list_dict[1:]:
d93d8888f0b0 Uploaded
florianbegusch
parents:
diff changeset
16 # set $file_list = $file_list + ' --m-metadata-file=' + d['additional_input'].__getattr__('file_name')
d93d8888f0b0 Uploaded
florianbegusch
parents:
diff changeset
17 # end for
d93d8888f0b0 Uploaded
florianbegusch
parents:
diff changeset
18 # return $file_list
d93d8888f0b0 Uploaded
florianbegusch
parents:
diff changeset
19 # end def
d93d8888f0b0 Uploaded
florianbegusch
parents:
diff changeset
20 --m-metadata-file=$list_dict_to_string($input_files_mmetadatafile)
d93d8888f0b0 Uploaded
florianbegusch
parents:
diff changeset
21 # end if
d93d8888f0b0 Uploaded
florianbegusch
parents:
diff changeset
22
d93d8888f0b0 Uploaded
florianbegusch
parents:
diff changeset
23 #if '__ob__' in str($mmetadatacolumn):
d93d8888f0b0 Uploaded
florianbegusch
parents:
diff changeset
24 #set $mmetadatacolumn_temp = $mmetadatacolumn.replace('__ob__', '[')
d93d8888f0b0 Uploaded
florianbegusch
parents:
diff changeset
25 #set $mmetadatacolumn = $mmetadatacolumn_temp
d93d8888f0b0 Uploaded
florianbegusch
parents:
diff changeset
26 #end if
d93d8888f0b0 Uploaded
florianbegusch
parents:
diff changeset
27 #if '__cb__' in str($mmetadatacolumn):
d93d8888f0b0 Uploaded
florianbegusch
parents:
diff changeset
28 #set $mmetadatacolumn_temp = $mmetadatacolumn.replace('__cb__', ']')
d93d8888f0b0 Uploaded
florianbegusch
parents:
diff changeset
29 #set $mmetadatacolumn = $mmetadatacolumn_temp
d93d8888f0b0 Uploaded
florianbegusch
parents:
diff changeset
30 #end if
d93d8888f0b0 Uploaded
florianbegusch
parents:
diff changeset
31 #if 'X' in str($mmetadatacolumn):
d93d8888f0b0 Uploaded
florianbegusch
parents:
diff changeset
32 #set $mmetadatacolumn_temp = $mmetadatacolumn.replace('X', '\\')
d93d8888f0b0 Uploaded
florianbegusch
parents:
diff changeset
33 #set $mmetadatacolumn = $mmetadatacolumn_temp
d93d8888f0b0 Uploaded
florianbegusch
parents:
diff changeset
34 #end if
d93d8888f0b0 Uploaded
florianbegusch
parents:
diff changeset
35 #if '__sq__' in str($mmetadatacolumn):
d93d8888f0b0 Uploaded
florianbegusch
parents:
diff changeset
36 #set $mmetadatacolumn_temp = $mmetadatacolumn.replace('__sq__', "'")
d93d8888f0b0 Uploaded
florianbegusch
parents:
diff changeset
37 #set $mmetadatacolumn = $mmetadatacolumn_temp
d93d8888f0b0 Uploaded
florianbegusch
parents:
diff changeset
38 #end if
d93d8888f0b0 Uploaded
florianbegusch
parents:
diff changeset
39 #if '__db__' in str($mmetadatacolumn):
d93d8888f0b0 Uploaded
florianbegusch
parents:
diff changeset
40 #set $mmetadatacolumn_temp = $mmetadatacolumn.replace('__db__', '"')
d93d8888f0b0 Uploaded
florianbegusch
parents:
diff changeset
41 #set $mmetadatacolumn = $mmetadatacolumn_temp
d93d8888f0b0 Uploaded
florianbegusch
parents:
diff changeset
42 #end if
d93d8888f0b0 Uploaded
florianbegusch
parents:
diff changeset
43
d93d8888f0b0 Uploaded
florianbegusch
parents:
diff changeset
44 --m-metadata-column=$mmetadatacolumn
d93d8888f0b0 Uploaded
florianbegusch
parents:
diff changeset
45
d93d8888f0b0 Uploaded
florianbegusch
parents:
diff changeset
46
d93d8888f0b0 Uploaded
florianbegusch
parents:
diff changeset
47 --p-step=$pstep
d93d8888f0b0 Uploaded
florianbegusch
parents:
diff changeset
48
d93d8888f0b0 Uploaded
florianbegusch
parents:
diff changeset
49 --p-cv=$pcv
d93d8888f0b0 Uploaded
florianbegusch
parents:
diff changeset
50
d93d8888f0b0 Uploaded
florianbegusch
parents:
diff changeset
51 #if str($prandomstate):
d93d8888f0b0 Uploaded
florianbegusch
parents:
diff changeset
52 --p-random-state=$prandomstate
d93d8888f0b0 Uploaded
florianbegusch
parents:
diff changeset
53 #end if
d93d8888f0b0 Uploaded
florianbegusch
parents:
diff changeset
54 --p-n-jobs=$pnjobs
d93d8888f0b0 Uploaded
florianbegusch
parents:
diff changeset
55
d93d8888f0b0 Uploaded
florianbegusch
parents:
diff changeset
56 --p-n-estimators=$pnestimators
d93d8888f0b0 Uploaded
florianbegusch
parents:
diff changeset
57
d93d8888f0b0 Uploaded
florianbegusch
parents:
diff changeset
58 #if str($pestimator) != 'None':
d93d8888f0b0 Uploaded
florianbegusch
parents:
diff changeset
59 --p-estimator=$pestimator
d93d8888f0b0 Uploaded
florianbegusch
parents:
diff changeset
60 #end if
d93d8888f0b0 Uploaded
florianbegusch
parents:
diff changeset
61
d93d8888f0b0 Uploaded
florianbegusch
parents:
diff changeset
62 #if $poptimizefeatureselection:
d93d8888f0b0 Uploaded
florianbegusch
parents:
diff changeset
63 --p-optimize-feature-selection
d93d8888f0b0 Uploaded
florianbegusch
parents:
diff changeset
64 #end if
d93d8888f0b0 Uploaded
florianbegusch
parents:
diff changeset
65
d93d8888f0b0 Uploaded
florianbegusch
parents:
diff changeset
66 #if $pparametertuning:
d93d8888f0b0 Uploaded
florianbegusch
parents:
diff changeset
67 --p-parameter-tuning
d93d8888f0b0 Uploaded
florianbegusch
parents:
diff changeset
68 #end if
d93d8888f0b0 Uploaded
florianbegusch
parents:
diff changeset
69
d93d8888f0b0 Uploaded
florianbegusch
parents:
diff changeset
70 #if str($pmissingsamples) != 'None':
d93d8888f0b0 Uploaded
florianbegusch
parents:
diff changeset
71 --p-missing-samples=$pmissingsamples
d93d8888f0b0 Uploaded
florianbegusch
parents:
diff changeset
72 #end if
d93d8888f0b0 Uploaded
florianbegusch
parents:
diff changeset
73
d93d8888f0b0 Uploaded
florianbegusch
parents:
diff changeset
74 --o-sample-estimator=osampleestimator
d93d8888f0b0 Uploaded
florianbegusch
parents:
diff changeset
75
d93d8888f0b0 Uploaded
florianbegusch
parents:
diff changeset
76 --o-feature-importance=ofeatureimportance
d93d8888f0b0 Uploaded
florianbegusch
parents:
diff changeset
77
d93d8888f0b0 Uploaded
florianbegusch
parents:
diff changeset
78 #if str($examples) != 'None':
d93d8888f0b0 Uploaded
florianbegusch
parents:
diff changeset
79 --examples=$examples
d93d8888f0b0 Uploaded
florianbegusch
parents:
diff changeset
80 #end if
d93d8888f0b0 Uploaded
florianbegusch
parents:
diff changeset
81
d93d8888f0b0 Uploaded
florianbegusch
parents:
diff changeset
82 ;
d93d8888f0b0 Uploaded
florianbegusch
parents:
diff changeset
83 cp ofeatureimportance.qza $ofeatureimportance
d93d8888f0b0 Uploaded
florianbegusch
parents:
diff changeset
84
d93d8888f0b0 Uploaded
florianbegusch
parents:
diff changeset
85 ]]></command>
d93d8888f0b0 Uploaded
florianbegusch
parents:
diff changeset
86 <inputs>
d93d8888f0b0 Uploaded
florianbegusch
parents:
diff changeset
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" />
d93d8888f0b0 Uploaded
florianbegusch
parents:
diff changeset
88 <repeat name="input_files_mmetadatafile" optional="True" title="--m-metadata-file">
d93d8888f0b0 Uploaded
florianbegusch
parents:
diff changeset
89 <param format="tabular,qza,no_unzip.zip" label="--m-metadata-file: METADATA" name="additional_input" optional="True" type="data" />
d93d8888f0b0 Uploaded
florianbegusch
parents:
diff changeset
90 </repeat>
d93d8888f0b0 Uploaded
florianbegusch
parents:
diff changeset
91 <param label="--m-metadata-column: COLUMN MetadataColumn[Numeric] Numeric metadata column to use as prediction target. [required]" name="mmetadatacolumn" optional="False" type="text" />
d93d8888f0b0 Uploaded
florianbegusch
parents:
diff changeset
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" />
d93d8888f0b0 Uploaded
florianbegusch
parents:
diff changeset
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" />
d93d8888f0b0 Uploaded
florianbegusch
parents:
diff changeset
94 <param label="--p-random-state: INTEGER Seed used by random number generator. [optional]" name="prandomstate" optional="False" type="text" />
d93d8888f0b0 Uploaded
florianbegusch
parents:
diff changeset
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" />
d93d8888f0b0 Uploaded
florianbegusch
parents:
diff changeset
96 <param label="--p-estimator: " name="pestimator" optional="True" type="select">
d93d8888f0b0 Uploaded
florianbegusch
parents:
diff changeset
97 <option selected="True" value="None">Selection is Optional</option>
d93d8888f0b0 Uploaded
florianbegusch
parents:
diff changeset
98 <option value="RandomForestRegressor">RandomForestRegressor</option>
d93d8888f0b0 Uploaded
florianbegusch
parents:
diff changeset
99 <option value="ExtraTreesRegressor">ExtraTreesRegressor</option>
d93d8888f0b0 Uploaded
florianbegusch
parents:
diff changeset
100 <option value="GradientBoostingRegressor">GradientBoostingRegressor</option>
d93d8888f0b0 Uploaded
florianbegusch
parents:
diff changeset
101 <option value="AdaBoostRegressor">AdaBoostRegressor</option>
d93d8888f0b0 Uploaded
florianbegusch
parents:
diff changeset
102 <option value="ElasticNet">ElasticNet</option>
d93d8888f0b0 Uploaded
florianbegusch
parents:
diff changeset
103 <option value="Ridge">Ridge</option>
d93d8888f0b0 Uploaded
florianbegusch
parents:
diff changeset
104 <option value="Lasso">Lasso</option>
d93d8888f0b0 Uploaded
florianbegusch
parents:
diff changeset
105 <option value="KNeighborsRegressor">KNeighborsRegressor</option>
d93d8888f0b0 Uploaded
florianbegusch
parents:
diff changeset
106 <option value="LinearSVR">LinearSVR</option>
d93d8888f0b0 Uploaded
florianbegusch
parents:
diff changeset
107 <option value="SVR">SVR</option>
d93d8888f0b0 Uploaded
florianbegusch
parents:
diff changeset
108 </param>
d93d8888f0b0 Uploaded
florianbegusch
parents:
diff changeset
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" />
d93d8888f0b0 Uploaded
florianbegusch
parents:
diff changeset
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" />
d93d8888f0b0 Uploaded
florianbegusch
parents:
diff changeset
111 <param label="--p-missing-samples: " name="pmissingsamples" optional="True" type="select">
d93d8888f0b0 Uploaded
florianbegusch
parents:
diff changeset
112 <option selected="True" value="None">Selection is Optional</option>
d93d8888f0b0 Uploaded
florianbegusch
parents:
diff changeset
113 <option value="error">error</option>
d93d8888f0b0 Uploaded
florianbegusch
parents:
diff changeset
114 <option value="ignore">ignore</option>
d93d8888f0b0 Uploaded
florianbegusch
parents:
diff changeset
115 </param>
d93d8888f0b0 Uploaded
florianbegusch
parents:
diff changeset
116 <param label="--examples: Show usage examples and exit." name="examples" optional="False" type="data" />
d93d8888f0b0 Uploaded
florianbegusch
parents:
diff changeset
117
d93d8888f0b0 Uploaded
florianbegusch
parents:
diff changeset
118 </inputs>
d93d8888f0b0 Uploaded
florianbegusch
parents:
diff changeset
119
d93d8888f0b0 Uploaded
florianbegusch
parents:
diff changeset
120 <outputs>
d93d8888f0b0 Uploaded
florianbegusch
parents:
diff changeset
121 <data format="qza" label="${tool.name} on ${on_string}: sampleestimator.qza" name="osampleestimator" />
d93d8888f0b0 Uploaded
florianbegusch
parents:
diff changeset
122 <data format="qza" label="${tool.name} on ${on_string}: featureimportance.qza" name="ofeatureimportance" />
d93d8888f0b0 Uploaded
florianbegusch
parents:
diff changeset
123
d93d8888f0b0 Uploaded
florianbegusch
parents:
diff changeset
124 </outputs>
d93d8888f0b0 Uploaded
florianbegusch
parents:
diff changeset
125
d93d8888f0b0 Uploaded
florianbegusch
parents:
diff changeset
126 <help><![CDATA[
d93d8888f0b0 Uploaded
florianbegusch
parents:
diff changeset
127 Fit a supervised learning regressor.
d93d8888f0b0 Uploaded
florianbegusch
parents:
diff changeset
128 ###############################################################
d93d8888f0b0 Uploaded
florianbegusch
parents:
diff changeset
129
d93d8888f0b0 Uploaded
florianbegusch
parents:
diff changeset
130 Fit a supervised learning regressor. Outputs the fit estimator (for
d93d8888f0b0 Uploaded
florianbegusch
parents:
diff changeset
131 prediction of test samples and/or unknown samples) and the relative
d93d8888f0b0 Uploaded
florianbegusch
parents:
diff changeset
132 importance of each feature for model accuracy. Optionally use k-fold cross-
d93d8888f0b0 Uploaded
florianbegusch
parents:
diff changeset
133 validation for automatic recursive feature elimination and hyperparameter
d93d8888f0b0 Uploaded
florianbegusch
parents:
diff changeset
134 tuning.
d93d8888f0b0 Uploaded
florianbegusch
parents:
diff changeset
135
d93d8888f0b0 Uploaded
florianbegusch
parents:
diff changeset
136 Parameters
d93d8888f0b0 Uploaded
florianbegusch
parents:
diff changeset
137 ----------
d93d8888f0b0 Uploaded
florianbegusch
parents:
diff changeset
138 table : FeatureTable[Frequency]
d93d8888f0b0 Uploaded
florianbegusch
parents:
diff changeset
139 Feature table containing all features that should be used for target
d93d8888f0b0 Uploaded
florianbegusch
parents:
diff changeset
140 prediction.
d93d8888f0b0 Uploaded
florianbegusch
parents:
diff changeset
141 metadata : MetadataColumn[Numeric]
d93d8888f0b0 Uploaded
florianbegusch
parents:
diff changeset
142 Numeric metadata column to use as prediction target.
d93d8888f0b0 Uploaded
florianbegusch
parents:
diff changeset
143 step : Float % Range(0.0, 1.0, inclusive_start=False), optional
d93d8888f0b0 Uploaded
florianbegusch
parents:
diff changeset
144 If optimize_feature_selection is True, step is the percentage of
d93d8888f0b0 Uploaded
florianbegusch
parents:
diff changeset
145 features to remove at each iteration.
d93d8888f0b0 Uploaded
florianbegusch
parents:
diff changeset
146 cv : Int % Range(1, None), optional
d93d8888f0b0 Uploaded
florianbegusch
parents:
diff changeset
147 Number of k-fold cross-validations to perform.
d93d8888f0b0 Uploaded
florianbegusch
parents:
diff changeset
148 random_state : Int, optional
d93d8888f0b0 Uploaded
florianbegusch
parents:
diff changeset
149 Seed used by random number generator.
d93d8888f0b0 Uploaded
florianbegusch
parents:
diff changeset
150 n_jobs : Int, optional
d93d8888f0b0 Uploaded
florianbegusch
parents:
diff changeset
151 Number of jobs to run in parallel.
d93d8888f0b0 Uploaded
florianbegusch
parents:
diff changeset
152 n_estimators : Int % Range(1, None), optional
d93d8888f0b0 Uploaded
florianbegusch
parents:
diff changeset
153 Number of trees to grow for estimation. More trees will improve
d93d8888f0b0 Uploaded
florianbegusch
parents:
diff changeset
154 predictive accuracy up to a threshold level, but will also increase
d93d8888f0b0 Uploaded
florianbegusch
parents:
diff changeset
155 time and memory requirements. This parameter only affects ensemble
d93d8888f0b0 Uploaded
florianbegusch
parents:
diff changeset
156 estimators, such as Random Forest, AdaBoost, ExtraTrees, and
d93d8888f0b0 Uploaded
florianbegusch
parents:
diff changeset
157 GradientBoosting.
d93d8888f0b0 Uploaded
florianbegusch
parents:
diff changeset
158 estimator : Str % Choices('RandomForestRegressor', 'ExtraTreesRegressor', 'GradientBoostingRegressor', 'AdaBoostRegressor', 'ElasticNet', 'Ridge', 'Lasso', 'KNeighborsRegressor', 'LinearSVR', 'SVR'), optional
d93d8888f0b0 Uploaded
florianbegusch
parents:
diff changeset
159 Estimator method to use for sample prediction.
d93d8888f0b0 Uploaded
florianbegusch
parents:
diff changeset
160 optimize_feature_selection : Bool, optional
d93d8888f0b0 Uploaded
florianbegusch
parents:
diff changeset
161 Automatically optimize input feature selection using recursive feature
d93d8888f0b0 Uploaded
florianbegusch
parents:
diff changeset
162 elimination.
d93d8888f0b0 Uploaded
florianbegusch
parents:
diff changeset
163 parameter_tuning : Bool, optional
d93d8888f0b0 Uploaded
florianbegusch
parents:
diff changeset
164 Automatically tune hyperparameters using random grid search.
d93d8888f0b0 Uploaded
florianbegusch
parents:
diff changeset
165 missing_samples : Str % Choices('error', 'ignore'), optional
d93d8888f0b0 Uploaded
florianbegusch
parents:
diff changeset
166 How to handle missing samples in metadata. "error" will fail if missing
d93d8888f0b0 Uploaded
florianbegusch
parents:
diff changeset
167 samples are detected. "ignore" will cause the feature table and
d93d8888f0b0 Uploaded
florianbegusch
parents:
diff changeset
168 metadata to be filtered, so that only samples found in both files are
d93d8888f0b0 Uploaded
florianbegusch
parents:
diff changeset
169 retained.
d93d8888f0b0 Uploaded
florianbegusch
parents:
diff changeset
170
d93d8888f0b0 Uploaded
florianbegusch
parents:
diff changeset
171 Returns
d93d8888f0b0 Uploaded
florianbegusch
parents:
diff changeset
172 -------
d93d8888f0b0 Uploaded
florianbegusch
parents:
diff changeset
173 sample_estimator : SampleEstimator[Regressor]
d93d8888f0b0 Uploaded
florianbegusch
parents:
diff changeset
174 feature_importance : FeatureData[Importance]
d93d8888f0b0 Uploaded
florianbegusch
parents:
diff changeset
175 Importance of each input feature to model accuracy.
d93d8888f0b0 Uploaded
florianbegusch
parents:
diff changeset
176 ]]></help>
d93d8888f0b0 Uploaded
florianbegusch
parents:
diff changeset
177 <macros>
d93d8888f0b0 Uploaded
florianbegusch
parents:
diff changeset
178 <import>qiime_citation.xml</import>
d93d8888f0b0 Uploaded
florianbegusch
parents:
diff changeset
179 </macros>
d93d8888f0b0 Uploaded
florianbegusch
parents:
diff changeset
180 <expand macro="qiime_citation"/>
d93d8888f0b0 Uploaded
florianbegusch
parents:
diff changeset
181 </tool>