Mercurial > repos > iuc > chopin2

comparison chopin2.xml @ 1:693bfd012601 draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/chopin2 commit a9f99c56d0ff858ca7b37ce00759f62401cbd806
author iuc
date Tue, 09 Apr 2024 11:23:55 +0000
parents d49893faf877
children
comparison
equal deleted inserted replaced
0:d49893faf877 1:693bfd012601
42 </command> 42 </command>
43 43
44 <inputs> 44 <inputs>
45 <param name="dataset" type="data" format="csv,tabular" 45 <param name="dataset" type="data" format="csv,tabular"
46 label="Select a dataset" 46 label="Select a dataset"
47 help="Input dataset with features on columns and observations on rows. The first column must contain the observation IDs, while the last column must contain classes. The header line is also required." /> 47 help="Input dataset with features on columns and observations on rows. The first column must contain the observation IDs, while the last column must contain classes. The header line is also required."/>
48 48
49 <param name="dimensionality" type="integer" value="10000" min="100" 49 <param name="dimensionality" type="integer" value="10000" min="100"
50 label="Vectors dimensionality" 50 label="Vectors dimensionality"
51 help="Size of hypervectors is usually 10,000 in vector-symbolic architectures. However, lower values could work 51 help="Size of hypervectors is usually 10,000 in vector-symbolic architectures. However, lower values could work
52 with small datasets in terms of number of features and observations. Please note that you may require 52 with small datasets in terms of number of features and observations. Please note that you may require
53 to increase this number in case of datasets with a huge number of features." /> 53 to increase this number in case of datasets with a huge number of features."/>
54 54
55 <param name="levels" type="integer" value="1000" min="2" 55 <param name="levels" type="integer" value="1000" min="2"
56 label="Levels" 56 label="Levels"
57 help="Number of level vectors. You may consider to look at the distribution of your data in order to choose 57 help="Number of level vectors. You may consider to look at the distribution of your data in order to choose
58 the most appropriate value." /> 58 the most appropriate value." />
59 59
60 <param name="retrain" type="integer" value="0" min="0" 60 <param name="retrain" type="integer" value="0" min="0"
61 label="Model retraining iterations" 61 label="Model retraining iterations"
62 help="Maximum number of retraining iterations. Class hypervectors are retrained to minimize errors caused by noise." /> 62 help="Maximum number of retraining iterations. Class hypervectors are retrained to minimize errors caused by noise."/>
63 63
64 <param name="folds" type="integer" value="2" min="2" 64 <param name="folds" type="integer" value="2" min="2"
65 label="Number of folds for cross-validation" 65 label="Number of folds for cross-validation"
66 help="This tool makes use of k-folds cross-validation to evaluate the accuracy of the hyperdimensional model. 66 help="This tool makes use of k-folds cross-validation to evaluate the accuracy of the hyperdimensional model.
67 Make sure to choose a good number of folds for validating the classification model. Please note that higher number 67 Make sure to choose a good number of folds for validating the classification model. Please note that higher number
68 of folds could significantly increase the running time." /> 68 of folds could significantly increase the running time."/>
69 69
70 <conditional name="feature_selection"> 70 <conditional name="feature_selection">
71 <param name="enable_fs" type="select" 71 <param name="enable_fs" type="select"
72 label="Enable feature selection" 72 label="Enable feature selection"
73 help="If selected, this will extract a set of features with the better discriminative power among classes. 73 help="If selected, this will extract a set of features with the better discriminative power among classes.
74 The feature selection algorithm is defined as a backward variable selection method."> 74 The feature selection algorithm is defined as a backward variable selection method.">
75 <option value="false" selected="true">Disabled</option> 75 <option value="false" selected="true">Disabled</option>
76 <option value="true">Enabled</option> 76 <option value="true">Enabled</option>
77 </param> 77 </param>
78 78
79 <when value="false" /> 79 <when value="false"/>
80 80
81 <when value="true"> 81 <when value="true">
82 <param name="group_min" type="integer" value="1" min="1" 82 <param name="group_min" type="integer" value="1" min="1"
83 label="Minimum number of selected features" 83 label="Minimum number of selected features"
84 help="Tool will stop removing features if its number will reach this value." /> 84 help="Tool will stop removing features if its number will reach this value."/>
85 85
86 <param name="accuracy_threshold" type="float" value="60.0" min="0.0" max="100.0" 86 <param name="accuracy_threshold" type="float" value="60.0" min="0.0" max="100.0"
87 label="Accuracy threshold" 87 label="Accuracy threshold"
88 help="Stop the execution if the best accuracy reached for a group of features is lower than this value." /> 88 help="Stop the execution if the best accuracy reached for a group of features is lower than this value."/>
89 89
90 <param name="accuracy_uncertainty_perc" type="float" value="5.0" min="0.0" max="100.0" 90 <param name="accuracy_uncertainty_perc" type="float" value="5.0" min="0.0" max="100.0"
91 label="Accuracy uncertainty percentage" 91 label="Accuracy uncertainty percentage"
92 help="Consider non optimal solutions if model accuracy is greater than the best accuracy minus this percentage." /> 92 help="Consider non optimal solutions if model accuracy is greater than the best accuracy minus this percentage."/>
93 </when> 93 </when>
94 </conditional> 94 </conditional>
95 </inputs> 95 </inputs>
96 96
97 <outputs> 97 <outputs>
98 <data format="tabular" name="summary" label="${tool.name} on ${on_string}: Summary" from_work_dir="summary.txt"> 98 <data format="tabular" name="summary" label="${tool.name} on ${on_string}: Summary" from_work_dir="summary.txt">
99 <actions> 99 <actions>
100 <action name="column_names" type="metadata" default="Run ID,Group Size,Retraining,Accuracy,Excluded Feature" /> 100 <action name="column_names" type="metadata" default="Run ID,Group Size,Retraining,Accuracy,Excluded Feature"/>
101 <action name="column_types" type="metadata" default="str,int,int,float,str" /> 101 <action name="column_types" type="metadata" default="str,int,int,float,str"/>
102 <action name="comment_lines" type="metadata" default="7" /> 102 <action name="comment_lines" type="metadata" default="7"/>
103 </actions> 103 </actions>
104 </data> 104 </data>
105 105
106 <data format="tabular" name="selection" label="${tool.name} on ${on_string}: Selection" from_work_dir="selection.txt"> 106 <data format="tabular" name="selection" label="${tool.name} on ${on_string}: Selection" from_work_dir="selection.txt">
107 <filter>feature_selection["enable_fs"]</filter> 107 <filter>feature_selection["enable_fs"]</filter>
108 <actions> 108 <actions>
109 <action name="column_names" type="metadata" default="Selected Features:" /> 109 <action name="column_names" type="metadata" default="Selected Features:"/>
110 <action name="column_types" type="metadata" default="str" /> 110 <action name="column_types" type="metadata" default="str"/>
111 <action name="comment_lines" type="metadata" default="3" /> 111 <action name="comment_lines" type="metadata" default="3"/>
112 </actions> 112 </actions>
113 </data> 113 </data>
114 </outputs> 114 </outputs>
115 115
116 <tests> 116 <tests>
117 <test> 117 <test expect_num_outputs="2">
118 <param name="dataset" value="iris.csv" /> 118 <param name="dataset" value="iris.csv"/>
119 <param name="dimensionality" value="1000" /> 119 <param name="dimensionality" value="1000"/>
120 <param name="levels" value="100" /> 120 <param name="levels" value="100"/>
121 <param name="retrain" value="10" /> 121 <param name="retrain" value="10"/>
122 <param name="folds" value="5" /> 122 <param name="folds" value="5"/>
123 123
124 <output name="summary" ftype="tabular" value="summary.txt"> 124 <output name="summary" ftype="tabular" value="summary_1.txt">
125 <assert_contents> 125 <assert_contents>
126 <has_text_matching expression="# Run ID\tGroup Size\tRetraining\tAccuracy"/> 126 <has_text_matching expression="# Run ID\tGroup Size\tRetraining\tAccuracy"/>
127 <has_text text="8f0e142ff27db7f8d2cc66cfcc05e27c" /> 127 <has_text text="8f0e142ff27db7f8d2cc66cfcc05e27c"/>
128 </assert_contents> 128 </assert_contents>
129 </output> 129 </output>
130 </test> 130 </test>
131 131
132 <test> 132 <test expect_num_outputs="2">
133 <param name="dataset" value="iris.tabular" /> 133 <param name="dataset" value="iris.tabular"/>
134 <param name="dimensionality" value="1000" /> 134 <param name="dimensionality" value="1000"/>
135 <param name="levels" value="100" /> 135 <param name="levels" value="100"/>
136 <param name="retrain" value="10" /> 136 <param name="retrain" value="10"/>
137 <param name="folds" value="5" /> 137 <param name="folds" value="5"/>
138 138
139 <output name="summary" ftype="tabular" value="summary.txt"> 139 <output name="summary" ftype="tabular" value="summary_2.txt">
140 <assert_contents> 140 <assert_contents>
141 <has_text_matching expression="# Run ID\tGroup Size\tRetraining\tAccuracy"/> 141 <has_text_matching expression="# Run ID\tGroup Size\tRetraining\tAccuracy"/>
142 <has_text text="8f0e142ff27db7f8d2cc66cfcc05e27c" /> 142 <has_text text="8f0e142ff27db7f8d2cc66cfcc05e27c"/>
143 </assert_contents> 143 </assert_contents>
144 </output> 144 </output>
145 </test> 145 </test>
146 146
147 <test> 147 <test expect_num_outputs="2">
148 <param name="dataset" value="iris.csv" /> 148 <param name="dataset" value="iris.csv"/>
149 <param name="dimensionality" value="1000" /> 149 <param name="dimensionality" value="1000"/>
150 <param name="levels" value="100" /> 150 <param name="levels" value="100"/>
151 <param name="retrain" value="10" /> 151 <param name="retrain" value="10"/>
152 <param name="folds" value="5" /> 152 <param name="folds" value="5"/>
153 153
154 <conditional name="feature_selection"> 154 <conditional name="feature_selection">
155 <param name="enable_fs" value="true" /> 155 <param name="enable_fs" value="true"/>
156 <param name="group_min" value="1" /> 156 <param name="group_min" value="1"/>
157 <param name="accuracy_threshold" value="60.0" /> 157 <param name="accuracy_threshold" value="60.0"/>
158 <param name="accuracy_uncertainty_perc" value="5.0" /> 158 <param name="accuracy_uncertainty_perc" value="5.0"/>
159 </conditional> 159 </conditional>
160 160
161 <output name="summary" ftype="tabular" value="summary.txt"> 161 <output name="summary" ftype="tabular" value="summary_3.txt">
162 <assert_contents> 162 <assert_contents>
163 <has_text_matching expression="# Run ID\tGroup Size\tRetraining\tAccuracy" /> 163 <has_text_matching expression="# Run ID\tGroup Size\tRetraining\tAccuracy"/>
164 <has_text text="8f0e142ff27db7f8d2cc66cfcc05e27c" /> 164 <has_text text="8f0e142ff27db7f8d2cc66cfcc05e27c"/>
165 </assert_contents> 165 </assert_contents>
166 </output> 166 </output>
167 167
168 <output name="selection" ftype="tabular" value="selection.txt"> 168 <output name="selection" ftype="tabular" value="selection.txt">
169 <assert_contents> 169 <assert_contents>
170 <has_text text="# Selected Features:" /> 170 <has_text text="# Selected Features:"/>
171 <has_text text="PetalLengthCm" /> 171 <has_text text="PetalLengthCm"/>
172 <has_text text="PetalWidthCm" /> 172 <has_text text="PetalWidthCm"/>
173 <has_text text="SepalLengthCm" /> 173 <has_text text="SepalLengthCm"/>
174 <has_text text="SepalWidthCm" /> 174 <has_text text="SepalWidthCm"/>
175 </assert_contents> 175 </assert_contents>
176 </output> 176 </output>
177 </test> 177 </test>
178 </tests> 178 </tests>
179 179