Mercurial > repos > bgruening > sklearn_ensemble

comparison ensemble.xml @ 23:39ae276e75d9 draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/sklearn commit 57f4407e278a615f47a377a3328782b1d8e0b54d
author bgruening
date Sun, 30 Dec 2018 01:56:11 -0500
parents 2e69c6ca6e91
children e94395c672bd
comparison
equal deleted inserted replaced
22:2e69c6ca6e91 23:39ae276e75d9
98 <option value="GradientBoostingRegressor">Gradient Boosting Regressor</option> 98 <option value="GradientBoostingRegressor">Gradient Boosting Regressor</option>
99 </param> 99 </param>
100 <when value="RandomForestClassifier"> 100 <when value="RandomForestClassifier">
101 <expand macro="sl_mixed_input"/> 101 <expand macro="sl_mixed_input"/>
102 <section name="options" title="Advanced Options" expanded="False"> 102 <section name="options" title="Advanced Options" expanded="False">
103 <expand macro="n_estimators"/> 103 <expand macro="n_estimators" default_value="100"/>
104 <expand macro="criterion"/> 104 <expand macro="criterion"/>
105 <expand macro="max_features"/> 105 <expand macro="max_features"/>
106 <expand macro="max_depth"/> 106 <expand macro="max_depth"/>
107 <expand macro="min_samples_split"/> 107 <expand macro="min_samples_split"/>
108 <expand macro="min_samples_leaf"/> 108 <expand macro="min_samples_leaf"/>
156 </section> 156 </section>
157 </when> 157 </when>
158 <when value="RandomForestRegressor"> 158 <when value="RandomForestRegressor">
159 <expand macro="sl_mixed_input"/> 159 <expand macro="sl_mixed_input"/>
160 <section name="options" title="Advanced Options" expanded="False"> 160 <section name="options" title="Advanced Options" expanded="False">
161 <expand macro="n_estimators"/> 161 <expand macro="n_estimators" default_value="100"/>
162 <expand macro="criterion2"/> 162 <expand macro="criterion2"/>
163 <expand macro="max_features"/> 163 <expand macro="max_features"/>
164 <expand macro="max_depth"/> 164 <expand macro="max_depth"/>
165 <expand macro="min_samples_split"/> 165 <expand macro="min_samples_split"/>
166 <expand macro="min_samples_leaf"/> 166 <expand macro="min_samples_leaf"/>
230 <param name="col1" value="1,2,3,4"/> 230 <param name="col1" value="1,2,3,4"/>
231 <param name="col2" value="5"/> 231 <param name="col2" value="5"/>
232 <param name="selected_task" value="train"/> 232 <param name="selected_task" value="train"/>
233 <param name="selected_algorithm" value="RandomForestClassifier"/> 233 <param name="selected_algorithm" value="RandomForestClassifier"/>
234 <param name="random_state" value="10"/> 234 <param name="random_state" value="10"/>
235 <output name="outfile_fit" file="rfc_model01" compare="sim_size" delta="500"/> 235 <output name="outfile_fit" file="rfc_model01" compare="sim_size" delta="5"/>
236 </test> 236 </test>
237 <test> 237 <test>
238 <param name="infile_model" value="rfc_model01" ftype="zip"/> 238 <param name="infile_model" value="rfc_model01" ftype="zip"/>
239 <param name="infile_data" value="test.tabular" ftype="tabular"/> 239 <param name="infile_data" value="test.tabular" ftype="tabular"/>
240 <param name="selected_task" value="load"/> 240 <param name="selected_task" value="load"/>
241 <output name="outfile_predict" file="rfc_result01" compare="sim_size" delta="500"/> 241 <output name="outfile_predict" file="rfc_result01"/>
242 </test> 242 </test>
243 <test> 243 <test>
244 <param name="infile1" value="regression_train.tabular" ftype="tabular"/> 244 <param name="infile1" value="regression_train.tabular" ftype="tabular"/>
245 <param name="infile2" value="regression_train.tabular" ftype="tabular"/> 245 <param name="infile2" value="regression_train.tabular" ftype="tabular"/>
246 <param name="col1" value="1,2,3,4,5"/> 246 <param name="col1" value="1,2,3,4,5"/>
247 <param name="col2" value="6"/> 247 <param name="col2" value="6"/>
248 <param name="selected_task" value="train"/> 248 <param name="selected_task" value="train"/>
249 <param name="selected_algorithm" value="RandomForestRegressor"/> 249 <param name="selected_algorithm" value="RandomForestRegressor"/>
250 <param name="random_state" value="10"/> 250 <param name="random_state" value="10"/>
251 <output name="outfile_fit" file="rfr_model01" compare="sim_size" delta="500"/> 251 <output name="outfile_fit" file="rfr_model01" compare="sim_size" delta="5"/>
252 </test> 252 </test>
253 <test> 253 <test>
254 <param name="infile_model" value="rfr_model01" ftype="zip"/> 254 <param name="infile_model" value="rfr_model01" ftype="zip"/>
255 <param name="infile_data" value="regression_test.tabular" ftype="tabular"/> 255 <param name="infile_data" value="regression_test.tabular" ftype="tabular"/>
256 <param name="selected_task" value="load"/> 256 <param name="selected_task" value="load"/>
257 <output name="outfile_predict" file="rfr_result01" compare="sim_size" delta="500"/> 257 <output name="outfile_predict" file="rfr_result01"/>
258 </test> 258 </test>
259 <test> 259 <test>
260 <param name="infile1" value="regression_X.tabular" ftype="tabular"/> 260 <param name="infile1" value="regression_X.tabular" ftype="tabular"/>
261 <param name="infile2" value="regression_y.tabular" ftype="tabular"/> 261 <param name="infile2" value="regression_y.tabular" ftype="tabular"/>
262 <param name="header1" value="True"/> 262 <param name="header1" value="True"/>
266 <param name="selected_task" value="train"/> 266 <param name="selected_task" value="train"/>
267 <param name="selected_algorithm" value="GradientBoostingRegressor"/> 267 <param name="selected_algorithm" value="GradientBoostingRegressor"/>
268 <param name="max_features" value="number_input"/> 268 <param name="max_features" value="number_input"/>
269 <param name="num_max_features" value="0.5"/> 269 <param name="num_max_features" value="0.5"/>
270 <param name="random_state" value="42"/> 270 <param name="random_state" value="42"/>
271 <output name="outfile_fit" file="gbr_model01" compare="sim_size" delta="500"/> 271 <output name="outfile_fit" file="gbr_model01" compare="sim_size" delta="5"/>
272 </test> 272 </test>
273 <test> 273 <test>
274 <param name="infile_model" value="gbr_model01" ftype="zip"/> 274 <param name="infile_model" value="gbr_model01" ftype="zip"/>
275 <param name="infile_data" value="regression_test_X.tabular" ftype="tabular"/> 275 <param name="infile_data" value="regression_test_X.tabular" ftype="tabular"/>
276 <param name="selected_task" value="load"/> 276 <param name="selected_task" value="load"/>
277 <param name="header" value="True"/> 277 <param name="header" value="True"/>
278 <output name="outfile_predict" file="gbr_prediction_result01.tabular" compare="sim_size" delta="500"/> 278 <output name="outfile_predict" file="gbr_prediction_result01.tabular"/>
279 </test> 279 </test>
280 <test> 280 <test>
281 <param name="infile1" value="train.tabular" ftype="tabular"/> 281 <param name="infile1" value="train.tabular" ftype="tabular"/>
282 <param name="infile2" value="train.tabular" ftype="tabular"/> 282 <param name="infile2" value="train.tabular" ftype="tabular"/>
283 <param name="col1" value="1,2,3,4"/> 283 <param name="col1" value="1,2,3,4"/>
284 <param name="col2" value="5"/> 284 <param name="col2" value="5"/>
285 <param name="selected_task" value="train"/> 285 <param name="selected_task" value="train"/>
286 <param name="selected_algorithm" value="GradientBoostingClassifier"/> 286 <param name="selected_algorithm" value="GradientBoostingClassifier"/>
287 <output name="outfile_fit" file="gbc_model01" compare="sim_size" delta="500"/> 287 <output name="outfile_fit" file="gbc_model01" compare="sim_size" delta="5"/>
288 </test> 288 </test>
289 <test> 289 <test>
290 <param name="infile_model" value="gbc_model01" ftype="zip"/> 290 <param name="infile_model" value="gbc_model01" ftype="zip"/>
291 <param name="infile_data" value="test.tabular" ftype="tabular"/> 291 <param name="infile_data" value="test.tabular" ftype="tabular"/>
292 <param name="selected_task" value="load"/> 292 <param name="selected_task" value="load"/>
293 <output name="outfile_predict" file="gbc_result01" compare="sim_size" delta="500"/> 293 <output name="outfile_predict" file="gbc_result01"/>
294 </test> 294 </test>
295 <test> 295 <test>
296 <param name="infile1" value="train.tabular" ftype="tabular"/> 296 <param name="infile1" value="train.tabular" ftype="tabular"/>
297 <param name="infile2" value="train.tabular" ftype="tabular"/> 297 <param name="infile2" value="train.tabular" ftype="tabular"/>
298 <param name="col1" value="1,2,3,4"/> 298 <param name="col1" value="1,2,3,4"/>
299 <param name="col2" value="5"/> 299 <param name="col2" value="5"/>
300 <param name="selected_task" value="train"/> 300 <param name="selected_task" value="train"/>
301 <param name="selected_algorithm" value="AdaBoostClassifier"/> 301 <param name="selected_algorithm" value="AdaBoostClassifier"/>
302 <param name="random_state" value="10"/> 302 <param name="random_state" value="10"/>
303 <output name="outfile_fit" file="abc_model01" compare="sim_size" delta="500"/> 303 <output name="outfile_fit" file="abc_model01" compare="sim_size" delta="5"/>
304 </test> 304 </test>
305 <test> 305 <test>
306 <param name="infile_model" value="abc_model01" ftype="zip"/> 306 <param name="infile_model" value="abc_model01" ftype="zip"/>
307 <param name="infile_data" value="test.tabular" ftype="tabular"/> 307 <param name="infile_data" value="test.tabular" ftype="tabular"/>
308 <param name="selected_task" value="load"/> 308 <param name="selected_task" value="load"/>
309 <output name="outfile_predict" file="abc_result01" compare="sim_size" delta="500"/> 309 <output name="outfile_predict" file="abc_result01"/>
310 </test> 310 </test>
311 <test> 311 <test>
312 <param name="infile1" value="regression_train.tabular" ftype="tabular"/> 312 <param name="infile1" value="regression_train.tabular" ftype="tabular"/>
313 <param name="infile2" value="regression_train.tabular" ftype="tabular"/> 313 <param name="infile2" value="regression_train.tabular" ftype="tabular"/>
314 <param name="col1" value="1,2,3,4,5"/> 314 <param name="col1" value="1,2,3,4,5"/>
315 <param name="col2" value="6"/> 315 <param name="col2" value="6"/>
316 <param name="selected_task" value="train"/> 316 <param name="selected_task" value="train"/>
317 <param name="selected_algorithm" value="AdaBoostRegressor"/> 317 <param name="selected_algorithm" value="AdaBoostRegressor"/>
318 <param name="random_state" value="10"/> 318 <param name="random_state" value="10"/>
319 <output name="outfile_fit" file="abr_model01" compare="sim_size" delta="500"/> 319 <output name="outfile_fit" file="abr_model01" compare="sim_size" delta="5"/>
320 </test> 320 </test>
321 <test> 321 <test>
322 <param name="infile_model" value="abr_model01" ftype="zip"/> 322 <param name="infile_model" value="abr_model01" ftype="zip"/>
323 <param name="infile_data" value="regression_test.tabular" ftype="tabular"/> 323 <param name="infile_data" value="regression_test.tabular" ftype="tabular"/>
324 <param name="selected_task" value="load"/> 324 <param name="selected_task" value="load"/>
325 <output name="outfile_predict" file="abr_result01" compare="sim_size" delta="500"/> 325 <output name="outfile_predict" file="abr_result01"/>
326 </test> 326 </test>
327 </tests> 327 </tests>
328 <help><![CDATA[ 328 <help><![CDATA[
329 ***What it does*** 329 ***What it does***
330 The goal of ensemble methods is to combine the predictions of several base estimators built with a given learning algorithm in order to improve generalizability / robustness over a single estimator. This tool offers two sets of ensemble algorithms for classification and regression: random forests and ADA boosting which are based on sklearn.ensemble library from Scikit-learn. Here you can find out about the input, output and methods presented in the tools. For information about ensemble methods and parameters settings please refer to `Scikit-learn ensemble`_. 330 The goal of ensemble methods is to combine the predictions of several base estimators built with a given learning algorithm in order to improve generalizability / robustness over a single estimator. This tool offers two sets of ensemble algorithms for classification and regression: random forests and ADA boosting which are based on sklearn.ensemble library from Scikit-learn. Here you can find out about the input, output and methods presented in the tools. For information about ensemble methods and parameters settings please refer to `Scikit-learn ensemble`_.