Mercurial > repos > iuc > deepmicro

comparison deepmicro.xml @ 2:2d20b3a1babd draft default tip

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
planemo upload for repository https://github.com/paulzierep/DeepMicro commit 574cb8c241e18a15f006bf307235c7dd23f07c69
author iuc
date Tue, 23 Jul 2024 15:56:32 +0000
parents c58c1a99578b
children
comparison
equal deleted inserted replaced
1:c58c1a99578b 2:2d20b3a1babd
16 #if $mode.mode_type == "only_encoding": 16 #if $mode.mode_type == "only_encoding":
17 17
18 #for $params in $mode.parameter_set: 18 #for $params in $mode.parameter_set:
19 19
20 #if $params.rl_type.rl_type_choice == "--pca" or $params.rl_type.rl_type_choice == "--rp": 20 #if $params.rl_type.rl_type_choice == "--pca" or $params.rl_type.rl_type_choice == "--rp":
21 DM.py -r 1 -cd features.csv '$params.rl_type.rl_type_choice' --save_rep --no_clf -t \${GALAXY_SLOTS:-8} && 21 DM.py -r 1
22 -cd features.csv
23 '$params.rl_type.rl_type_choice'
24 --save_rep
25 --no_clf
26 -t \${GALAXY_SLOTS:-8} &&
22 #else: 27 #else:
23 DM.py -r 1 -cd features.csv '$params.rl_type.rl_type_choice' -dm '$params.rl_type.dm' --save_rep --no_clf -t \${GALAXY_SLOTS:-8} && 28 DM.py -r 1
29 -cd features.csv
30 '$params.rl_type.rl_type_choice'
31 -dm '$params.rl_type.dm'
32 --save_rep
33 --no_clf
34 -t \${GALAXY_SLOTS:-8} &&
24 #end if 35 #end if
25 #end for 36 #end for
26 37
27 #else: 38 #else:
28 39
29 ln -s '$mode.class_labels' data/labels.csv && 40 ln -s '$mode.class_labels' data/labels.csv &&
30 41
31 #for $params in $mode.parameter_set: 42 #for $params in $mode.parameter_set:
32 43
44 ## general args
45 DM.py
46 -r '$mode.repeat'
47 -cd features.csv
48 -cl labels.csv
49 --save_rep
50 -m '$params.rl_type.classifier'
51 --scoring '$mode.scoring'
52 -f '$mode.folds'
53 -t \${GALAXY_SLOTS:-8}
54
33 ## only train classifier without encoding 55 ## only train classifier without encoding
34 #if $params.rl_type.rl_type_choice == "no_rl": 56 #if $params.rl_type.rl_type_choice == "no_rl":
35 DM.py -r 1 -cd features.csv -cl labels.csv --save_rep -m '$params.rl_type.classifier' -t \${GALAXY_SLOTS:-8} && 57 && echo "Only train Clf - no encoding!"
58 ## add rl type
36 #elif $params.rl_type.rl_type_choice == "--pca" or $params.rl_type.rl_type_choice == "--rp": 59 #elif $params.rl_type.rl_type_choice == "--pca" or $params.rl_type.rl_type_choice == "--rp":
37 DM.py -r 1 -cd features.csv -cl labels.csv '$params.rl_type.rl_type_choice' --save_rep -m '$params.rl_type.classifier' -t \${GALAXY_SLOTS:-8} && 60 '$params.rl_type.rl_type_choice'
61 ## add rl type and dm options
38 #else: 62 #else:
39 DM.py -r 1 -cd features.csv -cl labels.csv '$params.rl_type.rl_type_choice' -dm '$params.rl_type.dm' --save_rep -m '$params.rl_type.classifier' -t \${GALAXY_SLOTS:-8} && 63 '$params.rl_type.rl_type_choice'
64 -dm '$params.rl_type.dm'
40 #end if 65 #end if
66 &&
41 #end for 67 #end for
42 68
43 #end if 69 #end if
44 70
45 echo Done ! 71 echo Done !
57 <repeat name="parameter_set" title="Parameter Set"> 83 <repeat name="parameter_set" title="Parameter Set">
58 <conditional name="rl_type"> 84 <conditional name="rl_type">
59 <param name="rl_type_choice" type="select" label="Representation learning type" help="The type of representation learning" > 85 <param name="rl_type_choice" type="select" label="Representation learning type" help="The type of representation learning" >
60 <option value="--pca">PCA</option> 86 <option value="--pca">PCA</option>
61 <option value="--rp">Random Projection</option> 87 <option value="--rp">Random Projection</option>
62 <option value="--ae">Autoencoder or Deep Autoencoder</option> 88 <option value="--ae">Shallow Autoencoder or Deep Autoencoder (SAE, DAE)</option>
63 <option value="--vae">Variational Autoencoder</option> 89 <option value="--vae">Variational Autoencoder (VAE)</option>
64 <option value="--cae">Convolutional Autoencoder</option> 90 <option value="--cae">Convolutional Autoencoder (CAE)</option>
65 </param> 91 </param>
66 <when value="--pca"/> 92 <when value="--pca"/>
67 <when value="--rp"/> 93 <when value="--rp"/>
68 <when value="--ae"> 94 <when value="--ae">
69 <expand macro="dm" /> 95 <expand macro="dm" />
77 </conditional> 103 </conditional>
78 </repeat> 104 </repeat>
79 </when> 105 </when>
80 <when value="e_and_c"> 106 <when value="e_and_c">
81 <param argument="--class_labels" type="data" format="tabular" label="Class labels" help="Dataset containing the class labels corresponding to the features"/> 107 <param argument="--class_labels" type="data" format="tabular" label="Class labels" help="Dataset containing the class labels corresponding to the features"/>
108 <param name="scoring" type="select" label="Scoring function for the classifiere" help="The classifiere will be optimized for this scoring function." >
109 <option value="roc_auc">ROC AUC</option>
110 <option value="accuracy">Accuracy</option>
111 <option value="f1">F1 Score</option>
112 <option value="recall">Recall</option>
113 <option value="precision">Precision</option>
114 </param>
115 <param name="folds" type="integer" value="5" label="Cross-validation folds" min="2" max="10" help="The number of folds for cross-validation in the tranining set"/>
116 <param name="repeat" type="integer" value="1" label="Repeat the experiment with different seed" min="1" max="5" help="Repeat the experiment with different seeds. Leads to a different train / test split each time."/>
82 <repeat name="parameter_set" title="Parameter Set"> 117 <repeat name="parameter_set" title="Parameter Set">
83 <conditional name="rl_type"> 118 <conditional name="rl_type">
84 <param name="rl_type_choice" type="select" label="Representation learning type" help="The type of representation learning. `Train on input` trains the classifier on the input features without representation learning" > 119 <param name="rl_type_choice" type="select" label="Representation learning type" help="The type of representation learning. `Train on input` trains the classifier on the input features without representation learning" >
85 <option value="--pca">PCA</option> 120 <option value="--pca">PCA</option>
86 <option value="--rp">Random Projection</option> 121 <option value="--rp">Random Projection</option>
87 <option value="--ae">Autoencoder or Deep Autoencoder</option> 122 <option value="--ae">Shallow Autoencoder or Deep Autoencoder (SAE, DAE)</option>
88 <option value="--vae">Variational Autoencoder</option> 123 <option value="--vae">Variational Autoencoder (VAE)</option>
89 <option value="--cae">Convolutional Autoencoder</option> 124 <option value="--cae">Convolutional Autoencoder (CAE)</option>
90 <option value="no_rl">Train on input</option> 125 <option value="no_rl">Train on input</option>
91 </param> 126 </param>
92 <when value="no_rl"> 127 <when value="no_rl">
93 <expand macro="clfs" /> 128 <expand macro="clfs" />
94 </when> 129 </when>
124 <!-- the encoded features generated by the tool are only for the training set, this is not very useful, therefore omitting 159 <!-- the encoded features generated by the tool are only for the training set, this is not very useful, therefore omitting
125 todo change tool do export features complete dataset also when classification is performed --> 160 todo change tool do export features complete dataset also when classification is performed -->
126 <filter>mode["mode_type"] == "only_encoding"</filter> 161 <filter>mode["mode_type"] == "only_encoding"</filter>
127 <discover_datasets directory="results" pattern="(?P&lt;designation&gt;.*)_rep\.csv" format="tabular" visible="false" /> 162 <discover_datasets directory="results" pattern="(?P&lt;designation&gt;.*)_rep\.csv" format="tabular" visible="false" />
128 </collection> 163 </collection>
164 <collection name="model" type="list" label="Keras Models">
165 <!-- the encoded features generated by the tool are only for the training set, this is not very useful, therefore omitting
166 todo change tool do export features complete dataset also when classification is performed -->
167 <filter>mode["mode_type"] == "only_encoding"</filter>
168 <discover_datasets directory="." pattern="(?P&lt;designation&gt;.*).h5" format="data" visible="false" />
169 </collection>
129 </outputs> 170 </outputs>
130 <tests> 171 <tests>
131 172
132 <!-- only encoding --> 173 <!-- only encoding -->
133 <!-- test one parameter sets --> 174 <!-- test one parameter sets -->
134 175
135 <test expect_num_outputs="1"> 176 <test expect_num_outputs="2">
136 <param name="mode_type" value="only_encoding" /> 177 <param name="mode_type" value="only_encoding" />
137 <param name="features" value="UserDataExample.csv" /> 178 <param name="features" value="UserDataExample.csv" />
138 <param name="rl_type_choice" value="--ae" /> 179 <param name="rl_type_choice" value="--ae" />
139 <param name="dm" value="40" /> 180 <param name="dm" value="40" />
140 <output_collection name="encoded_features" type="list"> 181 <output_collection name="encoded_features" type="list">
146 </assert_contents> 187 </assert_contents>
147 </element> 188 </element>
148 </output_collection> 189 </output_collection>
149 </test> 190 </test>
150 191
151 <test expect_num_outputs="1"> 192 <test expect_num_outputs="2">
152 <param name="mode_type" value="only_encoding" /> 193 <param name="mode_type" value="only_encoding" />
153 <param name="features" value="UserDataExample.csv" /> 194 <param name="features" value="UserDataExample.csv" />
154 <param name="rl_type_choice" value="--pca" /> 195 <param name="rl_type_choice" value="--pca" />
155 <output_collection name="encoded_features" type="list"> 196 <output_collection name="encoded_features" type="list">
156 <element name="PCA_features" ftype="tabular" > 197 <element name="PCA_features" ftype="tabular" >
160 </assert_contents> 201 </assert_contents>
161 </element> 202 </element>
162 </output_collection> 203 </output_collection>
163 </test> 204 </test>
164 205
206 <!-- only encoding -->
207
208 <test expect_num_outputs="2">
209 <param name="mode_type" value="only_encoding" />
210 <param name="features" value="UserDataExample.csv" />
211 <param name="rl_type_choice" value="--ae" />
212 <param name="dm" value="40" />
213
214 <output_collection name="encoded_features" type="list">
215 <!-- output is non determinisitc -->
216 <element name="AE[40]_features" ftype="tabular" >
217 <assert_contents>
218 <has_n_lines n="20"/>
219 <!-- <has_n_columns n="40" sep="," /> -->
220 </assert_contents>
221 </element>
222 </output_collection>
223 </test>
224
165 <!-- test multiple parameter sets --> 225 <!-- test multiple parameter sets -->
166 <test expect_num_outputs="1"> 226 <test expect_num_outputs="2">
167 <param name="features" value="UserDataExample.csv" /> 227 <param name="features" value="UserDataExample.csv" />
168 <conditional name="mode"> 228 <conditional name="mode">
169 <param name="mode_type" value="only_encoding" /> 229 <param name="mode_type" value="only_encoding" />
170 230
171 <repeat name="parameter_set"> 231 <repeat name="parameter_set">
200 260
201 </test> 261 </test>
202 262
203 <!-- encoding and clf --> 263 <!-- encoding and clf -->
204 <!-- test one parameter set --> 264 <!-- test one parameter set -->
205 265 <!-- test additional parameters scoring / folds and repeat -->
206 <test expect_num_outputs="1"> 266 <test expect_num_outputs="1">
207 <param name="features" value="UserDataExample.csv" /> 267 <param name="features" value="UserDataExample.csv" />
208 <param name="mode_type" value="e_and_c" /> 268 <param name="mode_type" value="e_and_c" />
209 <param name="class_labels" value="UserLabelExample.csv" /> 269 <param name="class_labels" value="UserLabelExample.csv" />
210 <param name="rl_type_choice" value="--vae" /> 270 <param name="rl_type_choice" value="--vae" />
211 <param name="dm" value="40" /> 271 <param name="dm" value="40" />
272 <param name="scoring" value="roc_auc" />
273 <param name="folds" value="2" />
274 <param name="repeat" value="2" />
212 <param name="classifier" value="rf" /> 275 <param name="classifier" value="rf" />
213 <output ftype="tabular" name="results" > 276 <output ftype="tabular" name="results" >
214 <assert_contents> 277 <assert_contents>
215 <has_text text="VAE[40]_rf" /> 278 <has_text text="VAE[40]_rf" />
216 </assert_contents> 279 </assert_contents>
217 </output> 280 </output>
218 281
219 </test> 282 </test>
220 283
284
285 <!-- no rl -->
221 <test expect_num_outputs="1"> 286 <test expect_num_outputs="1">
222 <param name="features" value="UserDataExample.csv" /> 287 <param name="features" value="UserDataExample.csv" />
223 <param name="mode_type" value="e_and_c" /> 288 <param name="mode_type" value="e_and_c" />
224 <param name="class_labels" value="UserLabelExample.csv" /> 289 <param name="class_labels" value="UserLabelExample.csv" />
225 <param name="rl_type_choice" value="no_rl" /> 290 <param name="rl_type_choice" value="no_rl" />