|
0
|
1 <?xml version="1.0" ?>
|
|
|
2 <tool id="qiime_sample-classifier_classify-samples" name="qiime sample-classifier classify-samples" version="2018.4">
|
|
|
3 <description> - Supervised learning classifier.</description>
|
|
|
4 <requirements>
|
|
|
5 <requirement type="package" version="2018.4">qiime2</requirement>
|
|
|
6 </requirements>
|
|
|
7 <command>
|
|
|
8 <![CDATA[
|
|
|
9 qiime sample-classifier classify-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 #if $pstep:
|
|
|
21 --p-step=$pstep
|
|
|
22 #end if
|
|
|
23
|
|
|
24 #if $poptimizefeatureselection:
|
|
|
25 --p-optimize-feature-selection
|
|
|
26 #else
|
|
|
27 --p-no-optimize-feature-selection
|
|
|
28 #end if
|
|
|
29
|
|
|
30 #if $ptestsize:
|
|
|
31 --p-test-size=$ptestsize
|
|
|
32 #end if
|
|
|
33
|
|
|
34 #if str($cmdconfig) != 'None':
|
|
|
35 --cmd-config=$cmdconfig
|
|
|
36 #end if
|
|
|
37 --o-visualization=ovisualization
|
|
|
38 #if str($pestimator) != 'None':
|
|
|
39 --p-estimator=$pestimator
|
|
|
40 #end if
|
|
|
41
|
|
|
42 #if $pnestimators:
|
|
|
43 --p-n-estimators=$pnestimators
|
|
|
44 #end if
|
|
|
45
|
|
|
46 #set $pnjobs = '${GALAXY_SLOTS:-4}'
|
|
|
47
|
|
|
48 #if str($pnjobs):
|
|
|
49 --p-n-jobs="$pnjobs"
|
|
|
50 #end if
|
|
|
51
|
|
|
52
|
|
|
53 #if $pcv:
|
|
|
54 --p-cv=$pcv
|
|
|
55 #end if
|
|
|
56
|
|
|
57 #if str($ppalette) != 'None':
|
|
|
58 --p-palette=$ppalette
|
|
|
59 #end if
|
|
|
60
|
|
|
61 #if $pparametertuning:
|
|
|
62 --p-parameter-tuning
|
|
|
63 #else
|
|
|
64 --p-no-parameter-tuning
|
|
|
65 #end if
|
|
|
66
|
|
|
67 #if str($prandomstate):
|
|
|
68 --p-random-state="$prandomstate"
|
|
|
69 #end if
|
|
|
70 ;
|
|
|
71 qiime tools export ovisualization.qzv --output-dir out && mkdir -p '$ovisualization.files_path'
|
|
|
72 && cp -r out/* '$ovisualization.files_path'
|
|
|
73 && mv '$ovisualization.files_path/index.html' '$ovisualization'
|
|
|
74 ]]>
|
|
|
75 </command>
|
|
|
76 <inputs>
|
|
|
77 <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"/>
|
|
|
78
|
|
|
79 <repeat name="input_files_mmetadatafile" optional="False" title="--m-metadata-file">
|
|
|
80 <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" />
|
|
|
81 </repeat>
|
|
|
82 <param label="--m-metadata-column: MetadataColumn[Categorical] Column from metadata file or artifact viewable as metadata. Categorical metadata column to use as prediction target. [required]" name="mmetadatacolumn" optional="False" type="text"/>
|
|
|
83
|
|
|
84 <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"/>
|
|
|
85 <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"/>
|
|
|
86 <param label="--p-cv: Number of k-fold cross-validations to perform. [default: 5]" name="pcv" optional="True" type="integer" value="5"/>
|
|
|
87
|
|
|
88 <param label="--p-random-state: Seed used by random number generator. [optional]" name="prandomstate" optional="True" type="text"/>
|
|
|
89
|
|
|
90 <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"/>
|
|
|
91 <param label="--p-estimator: Estimator method to use for sample
|
|
|
92 prediction. [default:
|
|
|
93 RandomForestClassifier]" name="pestimator" optional="True" type="select">
|
|
|
94 <option selected="True" value="None">Selection is Optional</option>
|
|
|
95 <option value="LinearSVC">LinearSVC</option>
|
|
|
96 <option value="RandomForestClassifier">RandomForestClassifier</option>
|
|
|
97 <option value="SVC">SVC</option>
|
|
|
98 <option value="AdaBoostClassifier">AdaBoostClassifier</option>
|
|
|
99 <option value="GradientBoostingClassifier">GradientBoostingClassifier</option>
|
|
|
100 <option value="ExtraTreesClassifier">ExtraTreesClassifier</option>
|
|
|
101 <option value="KNeighborsClassifier">KNeighborsClassifier</option>
|
|
|
102 </param>
|
|
|
103
|
|
|
104 <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"/>
|
|
|
105
|
|
|
106 <param label="--p-parameter-tuning: --p-no-parameter-tuning Automatically tune hyperparameters using random grid search. [default: False]" name="pparametertuning" checked="False" type="boolean"/>
|
|
|
107
|
|
|
108 <param label="--p-palette: The color palette to use for plotting.
|
|
|
109 [default: sirocco]" name="ppalette" optional="True" type="select">
|
|
|
110 <option selected="True" value="None">Selection is Optional</option>
|
|
|
111 <option value="plasma">plasma</option>
|
|
|
112 <option value="inferno">inferno</option>
|
|
|
113 <option value="BluePurple">BluePurple</option>
|
|
|
114 <option value="summer">summer</option>
|
|
|
115 <option value="magma">magma</option>
|
|
|
116 <option value="drifting">drifting</option>
|
|
|
117 <option value="sirocco">sirocco</option>
|
|
|
118 <option value="enigma">enigma</option>
|
|
|
119 <option value="YellowOrangeRed">YellowOrangeRed</option>
|
|
|
120 <option value="GreenBlue">GreenBlue</option>
|
|
|
121 <option value="deepblue">deepblue</option>
|
|
|
122 <option value="ambition">ambition</option>
|
|
|
123 <option value="melancholy">melancholy</option>
|
|
|
124 <option value="PurpleRed">PurpleRed</option>
|
|
|
125 <option value="greyscale">greyscale</option>
|
|
|
126 <option value="dandelions">dandelions</option>
|
|
|
127 <option value="YellowOrangeBrown">YellowOrangeBrown</option>
|
|
|
128 <option value="verve">verve</option>
|
|
|
129 <option value="viridis">viridis</option>
|
|
|
130 <option value="OrangeRed">OrangeRed</option>
|
|
|
131 <option value="mysteriousstains">mysteriousstains</option>
|
|
|
132 <option value="spectre">spectre</option>
|
|
|
133 <option value="solano">solano</option>
|
|
|
134 <option value="daydream">daydream</option>
|
|
|
135 <option value="eros">eros</option>
|
|
|
136 <option value="RedPurple">RedPurple</option>
|
|
|
137 <option value="PurpleBlue">PurpleBlue</option>
|
|
|
138 <option value="YellowGreen">YellowGreen</option>
|
|
|
139 <option value="copper">copper</option>
|
|
|
140 <option value="navarro">navarro</option>
|
|
|
141 </param>
|
|
|
142
|
|
|
143 <param label="--cmd-config: Use config file for command options" name="cmdconfig" optional="True" type="data"/>
|
|
|
144 </inputs>
|
|
|
145 <outputs>
|
|
|
146 <data format="html" label="${tool.name} on ${on_string}: visualization.qzv" name="ovisualization"/>
|
|
|
147 </outputs>
|
|
|
148 <help>
|
|
|
149 <![CDATA[
|
|
|
150 Supervised learning classifier.
|
|
|
151 --------------------------------
|
|
|
152
|
|
|
153 Predicts a categorical sample metadata column using a supervised learning
|
|
|
154 classifier. Splits input data into training and test sets. The training set
|
|
|
155 is used to train and test the estimator using a stratified k-fold cross-
|
|
|
156 validation scheme. This includes optional steps for automated feature
|
|
|
157 extraction and hyperparameter optimization. The test set validates
|
|
|
158 classification accuracy of the optimized estimator. Outputs classification
|
|
|
159 results for test set. For more details on the learning algorithm, see
|
|
|
160 http://scikit-learn.org/stable/supervised_learning.html
|
|
|
161
|
|
|
162 Parameters
|
|
|
163 ----------
|
|
|
164 table : FeatureTable[Frequency]
|
|
|
165 Feature table containing all features that should be used for target
|
|
|
166 prediction.
|
|
|
167 metadata : MetadataColumn[Categorical]
|
|
|
168 Categorical metadata column to use as prediction target.
|
|
|
169 test_size : Float % Range(0.0, 1.0, inclusive_start=False), optional
|
|
|
170 Fraction of input samples to exclude from training set and use for
|
|
|
171 classifier testing.
|
|
|
172 step : Float % Range(0.0, 1.0, inclusive_start=False), optional
|
|
|
173 If optimize_feature_selection is True, step is the percentage of
|
|
|
174 features to remove at each iteration.
|
|
|
175 cv : Int % Range(1, None), optional
|
|
|
176 Number of k-fold cross-validations to perform.
|
|
|
177 random_state : Int, optional
|
|
|
178 Seed used by random number generator.
|
|
|
179 n_estimators : Int % Range(1, None), optional
|
|
|
180 Number of trees to grow for estimation. More trees will improve
|
|
|
181 predictive accuracy up to a threshold level, but will also increase
|
|
|
182 time and memory requirements. This parameter only affects ensemble
|
|
|
183 estimators, such as Random Forest, AdaBoost, ExtraTrees, and
|
|
|
184 GradientBoosting.
|
|
|
185 estimator : Str % Choices({'AdaBoostClassifier', 'ExtraTreesClassifier', 'GradientBoostingClassifier', 'KNeighborsClassifier', 'LinearSVC', 'RandomForestClassifier', 'SVC'}), optional
|
|
|
186 Estimator method to use for sample prediction.
|
|
|
187 optimize_feature_selection : Bool, optional
|
|
|
188 Automatically optimize input feature selection using recursive feature
|
|
|
189 elimination.
|
|
|
190 parameter_tuning : Bool, optional
|
|
|
191 Automatically tune hyperparameters using random grid search.
|
|
|
192 palette : Str % Choices({'BluePurple', 'GreenBlue', 'OrangeRed', 'PurpleBlue', 'PurpleRed', 'RedPurple', 'YellowGreen', 'YellowOrangeBrown', 'YellowOrangeRed', 'ambition', 'copper', 'dandelions', 'daydream', 'deepblue', 'drifting', 'enigma', 'eros', 'greyscale', 'inferno', 'magma', 'melancholy', 'mysteriousstains', 'navarro', 'plasma', 'sirocco', 'solano', 'spectre', 'summer', 'verve', 'viridis'}), optional
|
|
|
193 The color palette to use for plotting.
|
|
|
194
|
|
|
195 Returns
|
|
|
196 -------
|
|
|
197 visualization : Visualization
|
|
|
198 \
|
|
|
199 ]]>
|
|
|
200 </help>
|
|
|
201 <macros>
|
|
|
202 <import>qiime_citation.xml</import>
|
|
|
203 </macros>
|
|
|
204 <expand macro="qiime_citation" />
|
|
|
205 </tool>
|
