Mercurial > repos > florianbegusch > qiime2_suite

comparison qiime2/qiime_sample-classifier_classify-samples.xml @ 14:a0a8d77a991c draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
Uploaded
author florianbegusch
date Thu, 03 Sep 2020 09:51:29 +0000
parents f190567fe3f6
children
comparison
equal deleted inserted replaced
13:887cd4ad8e16 14:a0a8d77a991c
1 <?xml version="1.0" ?> 1 <?xml version="1.0" ?>
2 <tool id="qiime_sample-classifier_classify-samples" name="qiime sample-classifier classify-samples" version="2019.7"> 2 <tool id="qiime_sample-classifier_classify-samples" name="qiime sample-classifier classify-samples"
3 <description> - Train and test a cross-validated supervised learning classifier.</description> 3 version="2020.8">
4 <requirements> 4 <description>Train and test a cross-validated supervised learning classifier.</description>
5 <requirement type="package" version="2019.7">qiime2</requirement> 5 <requirements>
6 </requirements> 6 <requirement type="package" version="2020.8">qiime2</requirement>
7 <command><![CDATA[ 7 </requirements>
8 <command><![CDATA[
8 qiime sample-classifier classify-samples 9 qiime sample-classifier classify-samples
9 10
10 --i-table=$itable 11 --i-table=$itable
11 --m-metadata-column="$mmetadatacolumn" 12 # if $input_files_mmetadatafile:
12 13 # def list_dict_to_string(list_dict):
13 #if str($ptestsize): 14 # set $file_list = list_dict[0]['additional_input'].__getattr__('file_name')
14 --p-test-size=$ptestsize 15 # for d in list_dict[1:]:
15 #end if 16 # set $file_list = $file_list + ' --m-metadata-file=' + d['additional_input'].__getattr__('file_name')
16 17 # end for
17 #if str($pstep): 18 # return $file_list
18 --p-step=$pstep 19 # end def
19 #end if 20 --m-metadata-file=$list_dict_to_string($input_files_mmetadatafile)
20 21 # end if
21 #if str($pcv): 22
22 --p-cv=$pcv 23 #if '__ob__' in str($mmetadatacolumn):
23 #end if 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-test-size=$ptestsize
48
49 --p-step=$pstep
50
51 --p-cv=$pcv
24 52
25 #if str($prandomstate): 53 #if str($prandomstate):
26 --p-random-state="$prandomstate" 54 --p-random-state=$prandomstate
27 #end if 55 #end if
28 56 --p-n-jobs=$pnjobs
29 #set $pnjobs = '${GALAXY_SLOTS:-4}' 57
30 58 --p-n-estimators=$pnestimators
31 #if str($pnjobs):
32 --p-n-jobs="$pnjobs"
33 #end if
34
35
36 #if $pnestimators:
37 --p-n-estimators=$pnestimators
38 #end if
39 59
40 #if str($pestimator) != 'None': 60 #if str($pestimator) != 'None':
41 --p-estimator=$pestimator 61 --p-estimator=$pestimator
42 #end if 62 #end if
43 63
44 #if $poptimizefeatureselection: 64 #if $poptimizefeatureselection:
45 --p-optimize-feature-selection 65 --p-optimize-feature-selection
46 #end if 66 #end if
48 #if $pparametertuning: 68 #if $pparametertuning:
49 --p-parameter-tuning 69 --p-parameter-tuning
50 #end if 70 #end if
51 71
52 #if str($ppalette) != 'None': 72 #if str($ppalette) != 'None':
53 --p-palette=$ppalette 73 --p-palette=$ppalette
54 #end if 74 #end if
55 75
56 #if str($pmissingsamples) != 'None': 76 #if str($pmissingsamples) != 'None':
57 --p-missing-samples=$pmissingsamples 77 --p-missing-samples=$pmissingsamples
58 #end if 78 #end if
59 79
60 80 --o-sample-estimator=osampleestimator
61 #if $metadatafile: 81
62 --m-metadata-file=$metadatafile 82 --o-feature-importance=ofeatureimportance
63 #end if 83
64 84 --o-predictions=opredictions
65 85
86 --o-model-summary=omodelsummary
87
88 --o-accuracy-results=oaccuracyresults
66 89
67 --o-probabilities=oprobabilities 90 --o-probabilities=oprobabilities
68 --o-sample-estimator=osampleestimator 91
69 --o-feature-importance=ofeatureimportance 92 --o-heatmap=oheatmap
70 --o-predictions=opredictions 93
71 --o-model-summary=omodelsummary 94 #if str($examples) != 'None':
72 --o-accuracy-results=oaccuracyresults 95 --examples=$examples
96 #end if
97
73 ; 98 ;
74 cp oprobabilities.qza $oprobabilities; 99 cp oprobabilities.qza $oprobabilities
75 cp osampleestimator.qza $osampleestimator; 100
76 cp ofeatureimportance.qza $ofeatureimportance; 101 ;
77 cp opredictions.qza $opredictions; 102 qiime tools export oheatmap.qzv --output-path out
78 qiime tools export --input-path omodelsummary.qzv --output-path out && mkdir -p '$omodelsummary.files_path' 103 && mkdir -p '$oheatmap.files_path'
79 && cp -r out/* '$omodelsummary.files_path' 104 && cp -r out/* '$oheatmap.files_path'
80 && mv '$omodelsummary.files_path/index.html' '$omodelsummary'; 105 && mv '$oheatmap.files_path/index.html' '$oheatmap'
81 qiime tools export --input-path oaccuracyresults.qzv --output-path out && mkdir -p '$oaccuracyresults.files_path' 106
82 && cp -r out/* '$oaccuracyresults.files_path' 107 ]]></command>
83 && mv '$oaccuracyresults.files_path/index.html' '$oaccuracyresults' 108 <inputs>
84 ]]></command> 109 <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" />
85 <inputs> 110 <repeat name="input_files_mmetadatafile" optional="True" title="--m-metadata-file">
86 <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"/> 111 <param format="tabular,qza,no_unzip.zip" label="--m-metadata-file: METADATA" name="additional_input" optional="True" type="data" />
87 <param label="--m-metadata-column: COLUMN MetadataColumn[Categorical] Categorical metadata column to use as prediction target. [required]" name="mmetadatacolumn" optional="False" type="text"/> 112 </repeat>
88 <param label="--p-test-size: PROPORTION Range(0.0, 1.0, inclusive_start=False) 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" min="0" max="1" exclusive_start="True"/> 113 <param label="--m-metadata-column: COLUMN MetadataColumn[Categorical] Categorical metadata column to use as prediction target. [required]" name="mmetadatacolumn" optional="False" type="text" />
89 <param 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]" name="pstep" optional="True" type="float" value="0.05" min="0" max="1" exclusive_start="True"/> 114 <param exclude_min="True" label="--p-test-size: PROPORTION Range(0.0, 1.0, inclusive_start=False) Fraction of input samples to exclude from training set and use for classifier testing. [default: 0.2]" max="1.0" min="0.0" name="ptestsize" optional="True" type="float" value="0.2" />
90 <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"/> 115 <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" />
91 <param label="--p-random-state: INTEGER Seed used by random number generator. [optional]" name="prandomstate" optional="True" type="integer"/> 116 <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" />
92 <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"/> 117 <param label="--p-random-state: INTEGER Seed used by random number generator. [optional]" name="prandomstate" optional="False" type="text" />
93 <param label="--p-estimator: " name="pestimator" optional="True" type="select"> 118 <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" />
94 <option selected="True" value="None">Selection is Optional</option> 119 <param label="--p-estimator: " name="pestimator" optional="True" type="select">
95 <option value="RandomForestClassifier">RandomForestClassifier</option> 120 <option selected="True" value="None">Selection is Optional</option>
96 <option value="ExtraTreesClassifier">ExtraTreesClassifier</option> 121 <option value="RandomForestClassifier">RandomForestClassifier</option>
97 <option value="GradientBoostingClassifier">GradientBoostingClassifier</option> 122 <option value="ExtraTreesClassifier">ExtraTreesClassifier</option>
98 <option value="AdaBoostClassifier">AdaBoostClassifier</option> 123 <option value="GradientBoostingClassifier">GradientBoostingClassifier</option>
99 <option value="KNeighborsClassifier">KNeighborsClassifier</option> 124 <option value="AdaBoostClassifier">AdaBoostClassifier</option>
100 <option value="LinearSVC">LinearSVC</option> 125 <option value="KNeighborsClassifier">KNeighborsClassifier</option>
101 <option value="SVC">SVC</option> 126 <option value="LinearSVC">LinearSVC</option>
102 </param> 127 <option value="SVC">SVC</option>
103 <param label="--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"/> 128 </param>
104 <param label="--p-parameter-tuning: --p-no-parameter-tuning Automatically tune hyperparameters using random grid search. [default: False]" name="pparametertuning" selected="False" type="boolean"/> 129 <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" />
105 <param label="--p-palette: " name="ppalette" optional="True" type="select"> 130 <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" />
106 <option selected="True" value="None">Selection is Optional</option> 131 <param label="--p-palette: " name="ppalette" optional="True" type="select">
107 <option value="YellowOrangeBrown">YellowOrangeBrown</option> 132 <option selected="True" value="None">Selection is Optional</option>
108 <option value="YellowOrangeRed">YellowOrangeRed</option> 133 <option value="YellowOrangeBrown">YellowOrangeBrown</option>
109 <option value="OrangeRed">OrangeRed</option> 134 <option value="YellowOrangeRed">YellowOrangeRed</option>
110 <option value="PurpleRed">PurpleRed</option> 135 <option value="OrangeRed">OrangeRed</option>
111 <option value="RedPurple">RedPurple</option> 136 <option value="PurpleRed">PurpleRed</option>
112 <option value="BluePurple">BluePurple</option> 137 <option value="RedPurple">RedPurple</option>
113 <option value="GreenBlue">GreenBlue</option> 138 <option value="BluePurple">BluePurple</option>
114 <option value="PurpleBlue">PurpleBlue</option> 139 <option value="GreenBlue">GreenBlue</option>
115 <option value="YellowGreen">YellowGreen</option> 140 <option value="PurpleBlue">PurpleBlue</option>
116 <option value="summer">summer</option> 141 <option value="YellowGreen">YellowGreen</option>
117 <option value="copper">copper</option> 142 <option value="summer">summer</option>
118 <option value="viridis">viridis</option> 143 <option value="copper">copper</option>
119 <option value="plasma">plasma</option> 144 <option value="viridis">viridis</option>
120 <option value="inferno">inferno</option> 145 <option value="cividis">cividis</option>
121 <option value="magma">magma</option> 146 <option value="plasma">plasma</option>
122 <option value="sirocco">sirocco</option> 147 <option value="inferno">inferno</option>
123 <option value="drifting">drifting</option> 148 <option value="magma">magma</option>
124 <option value="melancholy">melancholy</option> 149 <option value="sirocco">sirocco</option>
125 <option value="enigma">enigma</option> 150 <option value="drifting">drifting</option>
126 <option value="eros">eros</option> 151 <option value="melancholy">melancholy</option>
127 <option value="spectre">spectre</option> 152 <option value="enigma">enigma</option>
128 <option value="ambition">ambition</option> 153 <option value="eros">eros</option>
129 <option value="mysteriousstains">mysteriousstains</option> 154 <option value="spectre">spectre</option>
130 <option value="daydream">daydream</option> 155 <option value="ambition">ambition</option>
131 <option value="solano">solano</option> 156 <option value="mysteriousstains">mysteriousstains</option>
132 <option value="navarro">navarro</option> 157 <option value="daydream">daydream</option>
133 <option value="dandelions">dandelions</option> 158 <option value="solano">solano</option>
134 <option value="deepblue">deepblue</option> 159 <option value="navarro">navarro</option>
135 <option value="verve">verve</option> 160 <option value="dandelions">dandelions</option>
136 <option value="greyscale">greyscale</option> 161 <option value="deepblue">deepblue</option>
137 </param> 162 <option value="verve">verve</option>
138 <param label="--p-missing-samples: " name="pmissingsamples" optional="True" type="select"> 163 <option value="greyscale">greyscale</option>
139 <option selected="True" value="None">Selection is Optional</option> 164 </param>
140 <option value="error">error</option> 165 <param label="--p-missing-samples: " name="pmissingsamples" optional="True" type="select">
141 <option value="ignore">ignore</option> 166 <option selected="True" value="None">Selection is Optional</option>
142 </param> 167 <option value="error">error</option>
143 168 <option value="ignore">ignore</option>
144 <param label="--m-metadata-file METADATA" name="metadatafile" type="data" format="tabular,qza,no_unzip.zip" /> 169 </param>
145 170 <param label="--examples: Show usage examples and exit." name="examples" optional="False" type="data" />
146 </inputs> 171
147 <outputs> 172 </inputs>
148 <data format="qza" label="${tool.name} on ${on_string}: probabilities.qza" name="oprobabilities"/> 173
149 <data format="qza" label="${tool.name} on ${on_string}: sampleestimator.qza" name="osampleestimator"/> 174 <outputs>
150 <data format="qza" label="${tool.name} on ${on_string}: featureimportance.qza" name="ofeatureimportance"/> 175 <data format="qza" label="${tool.name} on ${on_string}: sampleestimator.qza" name="osampleestimator" />
151 <data format="qza" label="${tool.name} on ${on_string}: predictions.qza" name="opredictions"/> 176 <data format="qza" label="${tool.name} on ${on_string}: featureimportance.qza" name="ofeatureimportance" />
152 <data format="html" label="${tool.name} on ${on_string}: modelsummary.qzv" name="omodelsummary"/> 177 <data format="qza" label="${tool.name} on ${on_string}: predictions.qza" name="opredictions" />
153 <data format="html" label="${tool.name} on ${on_string}: accuracyresults.qzv" name="oaccuracyresults"/> 178 <data format="html" label="${tool.name} on ${on_string}: modelsummary.html" name="omodelsummary" />
154 </outputs> 179 <data format="html" label="${tool.name} on ${on_string}: accuracyresults.html" name="oaccuracyresults" />
155 <help><![CDATA[ 180 <data format="qza" label="${tool.name} on ${on_string}: probabilities.qza" name="oprobabilities" />
181 <data format="html" label="${tool.name} on ${on_string}: heatmap.html" name="oheatmap" />
182
183 </outputs>
184
185 <help><![CDATA[
156 Train and test a cross-validated supervised learning classifier. 186 Train and test a cross-validated supervised learning classifier.
157 ################################################################ 187 ###############################################################
158 188
159 Predicts a categorical sample metadata column using a supervised learning 189 Predicts a categorical sample metadata column using a supervised learning
160 classifier. Splits input data into training and test sets. The training set 190 classifier. Splits input data into training and test sets. The training set
161 is used to train and test the estimator using a stratified k-fold cross- 191 is used to train and test the estimator using a stratified k-fold cross-
162 validation scheme. This includes optional steps for automated feature 192 validation scheme. This includes optional steps for automated feature
180 features to remove at each iteration. 210 features to remove at each iteration.
181 cv : Int % Range(1, None), optional 211 cv : Int % Range(1, None), optional
182 Number of k-fold cross-validations to perform. 212 Number of k-fold cross-validations to perform.
183 random_state : Int, optional 213 random_state : Int, optional
184 Seed used by random number generator. 214 Seed used by random number generator.
215 n_jobs : Int, optional
216 Number of jobs to run in parallel.
185 n_estimators : Int % Range(1, None), optional 217 n_estimators : Int % Range(1, None), optional
186 Number of trees to grow for estimation. More trees will improve 218 Number of trees to grow for estimation. More trees will improve
187 predictive accuracy up to a threshold level, but will also increase 219 predictive accuracy up to a threshold level, but will also increase
188 time and memory requirements. This parameter only affects ensemble 220 time and memory requirements. This parameter only affects ensemble
189 estimators, such as Random Forest, AdaBoost, ExtraTrees, and 221 estimators, such as Random Forest, AdaBoost, ExtraTrees, and
193 optimize_feature_selection : Bool, optional 225 optimize_feature_selection : Bool, optional
194 Automatically optimize input feature selection using recursive feature 226 Automatically optimize input feature selection using recursive feature
195 elimination. 227 elimination.
196 parameter_tuning : Bool, optional 228 parameter_tuning : Bool, optional
197 Automatically tune hyperparameters using random grid search. 229 Automatically tune hyperparameters using random grid search.
198 palette : Str % Choices('YellowOrangeBrown', 'YellowOrangeRed', 'OrangeRed', 'PurpleRed', 'RedPurple', 'BluePurple', 'GreenBlue', 'PurpleBlue', 'YellowGreen', 'summer', 'copper', 'viridis', 'plasma', 'inferno', 'magma', 'sirocco', 'drifting', 'melancholy', 'enigma', 'eros', 'spectre', 'ambition', 'mysteriousstains', 'daydream', 'solano', 'navarro', 'dandelions', 'deepblue', 'verve', 'greyscale'), optional 230 palette : Str % Choices('YellowOrangeBrown', 'YellowOrangeRed', 'OrangeRed', 'PurpleRed', 'RedPurple', 'BluePurple', 'GreenBlue', 'PurpleBlue', 'YellowGreen', 'summer', 'copper', 'viridis', 'cividis', 'plasma', 'inferno', 'magma', 'sirocco', 'drifting', 'melancholy', 'enigma', 'eros', 'spectre', 'ambition', 'mysteriousstains', 'daydream', 'solano', 'navarro', 'dandelions', 'deepblue', 'verve', 'greyscale'), optional
199 The color palette to use for plotting. 231 The color palette to use for plotting.
200 missing_samples : Str % Choices('error', 'ignore'), optional 232 missing_samples : Str % Choices('error', 'ignore'), optional
201 How to handle missing samples in metadata. "error" will fail if missing 233 How to handle missing samples in metadata. "error" will fail if missing
202 samples are detected. "ignore" will cause the feature table and 234 samples are detected. "ignore" will cause the feature table and
203 metadata to be filtered, so that only samples found in both files are 235 metadata to be filtered, so that only samples found in both files are
216 the trained estimator. 248 the trained estimator.
217 accuracy_results : Visualization 249 accuracy_results : Visualization
218 Accuracy results visualization. 250 Accuracy results visualization.
219 probabilities : SampleData[Probabilities] 251 probabilities : SampleData[Probabilities]
220 Predicted class probabilities for each input sample. 252 Predicted class probabilities for each input sample.
221 ]]></help> 253 heatmap : Visualization
222 <macros> 254 A heatmap of the top 50 most important features from the table.
255 ]]></help>
256 <macros>
223 <import>qiime_citation.xml</import> 257 <import>qiime_citation.xml</import>
224 </macros> 258 </macros>
225 <expand macro="qiime_citation"/> 259 <expand macro="qiime_citation"/>
226 </tool> 260 </tool>