Mercurial > repos > bgruening > sklearn_numeric_clustering

comparison numeric_clustering.xml @ 40:06d772036a62 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 9981e25b00de29ed881b2229a173a8c812ded9bb
author bgruening
date Wed, 09 Aug 2023 13:11:48 +0000
parents 816b65d52c33
children
comparison
equal deleted inserted replaced
39:7dd3fb35904f 40:06d772036a62
1 <tool id="sklearn_numeric_clustering" name="Numeric Clustering" version="@VERSION@" profile="20.05"> 1 <tool id="sklearn_numeric_clustering" name="Numeric Clustering" version="@VERSION@" profile="@PROFILE@">
2 <description></description> 2 <description></description>
3 <macros> 3 <macros>
4 <import>main_macros.xml</import> 4 <import>main_macros.xml</import>
5 </macros> 5 </macros>
6 <expand macro="python_requirements" /> 6 <expand macro="python_requirements" />
40 40
41 cluster_object.set_params(**options) 41 cluster_object.set_params(**options)
42 if 'n_jobs' in cluster_object.get_params(): 42 if 'n_jobs' in cluster_object.get_params():
43 cluster_object.set_params( n_jobs=N_JOBS ) 43 cluster_object.set_params( n_jobs=N_JOBS )
44 44
45 header = None
45 #if $input_types.selected_input_type == "sparse": 46 #if $input_types.selected_input_type == "sparse":
46 data_matrix = mmread("$infile") 47 data_matrix = mmread("$infile")
47 #else: 48 #else:
48 data = pandas.read_csv("$infile", sep='\t', header=0, index_col=None, parse_dates=True, encoding=None) 49 data = pandas.read_csv("$infile", sep='\t', header=header, index_col=None, parse_dates=True, encoding=None)
50
49 header = 'infer' if params["input_types"]["header"] else None 51 header = 'infer' if params["input_types"]["header"] else None
50 column_option = params["input_types"]["column_selector_options"]["selected_column_selector_option"] 52 column_option = params["input_types"]["column_selector_options"]["selected_column_selector_option"]
51 if column_option in ["by_index_number", "all_but_by_index_number", "by_header_name", "all_but_by_header_name"]: 53 if column_option in ["by_index_number", "all_but_by_index_number", "by_header_name", "all_but_by_header_name"]:
52 c = params["input_types"]["column_selector_options"]["col"] 54 c = params["input_types"]["column_selector_options"]["col"]
53 else: 55 else:
181 <tests> 183 <tests>
182 <test> 184 <test>
183 <param name="infile" value="numeric_values.tabular" ftype="tabular" /> 185 <param name="infile" value="numeric_values.tabular" ftype="tabular" />
184 <param name="selected_input_type" value="tabular" /> 186 <param name="selected_input_type" value="tabular" />
185 <param name="selected_algorithm" value="KMeans" /> 187 <param name="selected_algorithm" value="KMeans" />
188 <param name="header" value="false" />
186 <param name="col" value="2,3,4" /> 189 <param name="col" value="2,3,4" />
187 <param name="n_clusters" value="4" /> 190 <param name="n_clusters" value="4" />
188 <param name="init" value="k-means++" /> 191 <param name="init" value="k-means++" />
189 <param name="random_state" value="100" /> 192 <param name="random_state" value="100" />
190 <output name="outfile" file="cluster_result01.txt" /> 193 <output name="outfile" file="cluster_result01.txt" />
191 </test> 194 </test>
192 <test> 195 <test>
193 <param name="infile" value="numeric_values.tabular" ftype="tabular" /> 196 <param name="infile" value="numeric_values.tabular" ftype="tabular" />
194 <param name="selected_algorithm" value="KMeans" /> 197 <param name="selected_algorithm" value="KMeans" />
195 <param name="selected_input_type" value="tabular" /> 198 <param name="selected_input_type" value="tabular" />
199 <param name="header" value="false" />
196 <param name="col" value="2,3,4" /> 200 <param name="col" value="2,3,4" />
197 <param name="n_clusters" value="4" /> 201 <param name="n_clusters" value="4" />
198 <param name="init" value="random" /> 202 <param name="init" value="random" />
199 <param name="random_state" value="100" /> 203 <param name="random_state" value="100" />
200 <output name="outfile" file="cluster_result02.txt" /> 204 <output name="outfile" file="cluster_result02.txt" />
201 </test> 205 </test>
202 <test> 206 <test>
203 <param name="infile" value="numeric_values.tabular" ftype="tabular" /> 207 <param name="infile" value="numeric_values.tabular" ftype="tabular" />
204 <param name="selected_algorithm" value="DBSCAN" /> 208 <param name="selected_algorithm" value="DBSCAN" />
205 <param name="selected_input_type" value="tabular" /> 209 <param name="selected_input_type" value="tabular" />
210 <param name="header" value="false" />
206 <param name="col" value="2,3,4" /> 211 <param name="col" value="2,3,4" />
207 <param name="algorithm" value="kd_tree" /> 212 <param name="algorithm" value="kd_tree" />
208 <param name="leaf_size" value="10" /> 213 <param name="leaf_size" value="10" />
209 <param name="eps" value="1.0" /> 214 <param name="eps" value="1.0" />
210 <output name="outfile" file="cluster_result03.txt" /> 215 <output name="outfile" file="cluster_result03.txt" />
211 </test> 216 </test>
212 <test> 217 <test>
213 <param name="infile" value="numeric_values.tabular" ftype="tabular" /> 218 <param name="infile" value="numeric_values.tabular" ftype="tabular" />
214 <param name="selected_algorithm" value="Birch" /> 219 <param name="selected_algorithm" value="Birch" />
215 <param name="selected_input_type" value="tabular" /> 220 <param name="selected_input_type" value="tabular" />
221 <param name="header" value="false" />
216 <param name="col" value="2,3,4" /> 222 <param name="col" value="2,3,4" />
217 <param name="n_clusters" value="4" /> 223 <param name="n_clusters" value="4" />
218 <param name="threshold" value="0.008" /> 224 <param name="threshold" value="0.008" />
219 <output name="outfile" file="cluster_result04.txt" /> 225 <output name="outfile" file="cluster_result04.txt" />
220 </test> 226 </test>
221 <test> 227 <test>
222 <param name="infile" value="numeric_values.tabular" ftype="tabular" /> 228 <param name="infile" value="numeric_values.tabular" ftype="tabular" />
223 <param name="selected_algorithm" value="Birch" /> 229 <param name="selected_algorithm" value="Birch" />
224 <param name="selected_input_type" value="tabular" /> 230 <param name="selected_input_type" value="tabular" />
231 <param name="header" value="false" />
225 <param name="col" value="2,3,4" /> 232 <param name="col" value="2,3,4" />
226 <param name="branching_factor" value="20" /> 233 <param name="branching_factor" value="20" />
227 <output name="outfile" file="cluster_result05.txt" /> 234 <output name="outfile" file="cluster_result05.txt" />
228 </test> 235 </test>
229 <test> 236 <test>
230 <param name="infile" value="numeric_values.tabular" ftype="tabular" /> 237 <param name="infile" value="numeric_values.tabular" ftype="tabular" />
231 <param name="selected_algorithm" value="AffinityPropagation" /> 238 <param name="selected_algorithm" value="AffinityPropagation" />
232 <param name="selected_input_type" value="tabular" /> 239 <param name="selected_input_type" value="tabular" />
240 <param name="header" value="false" />
233 <param name="col" value="2,3,4" /> 241 <param name="col" value="2,3,4" />
234 <param name="affinity" value="euclidean" /> 242 <param name="affinity" value="euclidean" />
235 <param name="copy" value="false" /> 243 <param name="copy" value="false" />
236 <output name="outfile" file="cluster_result06.txt" /> 244 <output name="outfile" file="cluster_result06.txt" />
237 </test> 245 </test>
238 <test> 246 <test>
239 <param name="infile" value="numeric_values.tabular" ftype="tabular" /> 247 <param name="infile" value="numeric_values.tabular" ftype="tabular" />
240 <param name="selected_algorithm" value="AffinityPropagation" /> 248 <param name="selected_algorithm" value="AffinityPropagation" />
241 <param name="selected_input_type" value="tabular" /> 249 <param name="selected_input_type" value="tabular" />
250 <param name="header" value="false" />
242 <param name="col" value="2,3,4" /> 251 <param name="col" value="2,3,4" />
243 <param name="damping" value="0.8" /> 252 <param name="damping" value="0.8" />
244 <output name="outfile" file="cluster_result07.txt" /> 253 <output name="outfile" file="cluster_result07.txt" />
245 </test> 254 </test>
246 <test> 255 <test>
247 <param name="infile" value="numeric_values.tabular" ftype="tabular" /> 256 <param name="infile" value="numeric_values.tabular" ftype="tabular" />
248 <param name="selected_algorithm" value="MeanShift" /> 257 <param name="selected_algorithm" value="MeanShift" />
249 <param name="selected_input_type" value="tabular" /> 258 <param name="selected_input_type" value="tabular" />
259 <param name="header" value="false" />
250 <param name="col" value="2,3,4" /> 260 <param name="col" value="2,3,4" />
251 <param name="min_bin_freq" value="3" /> 261 <param name="min_bin_freq" value="3" />
252 <output name="outfile" file="cluster_result08.txt" /> 262 <output name="outfile" file="cluster_result08.txt" />
253 </test> 263 </test>
254 <test> 264 <test>
255 <param name="infile" value="numeric_values.tabular" ftype="tabular" /> 265 <param name="infile" value="numeric_values.tabular" ftype="tabular" />
256 <param name="selected_algorithm" value="MeanShift" /> 266 <param name="selected_algorithm" value="MeanShift" />
257 <param name="selected_input_type" value="tabular" /> 267 <param name="selected_input_type" value="tabular" />
268 <param name="header" value="false" />
258 <param name="col" value="2,3,4" /> 269 <param name="col" value="2,3,4" />
259 <param name="cluster_all" value="False" /> 270 <param name="cluster_all" value="False" />
260 <output name="outfile" file="cluster_result09.txt" /> 271 <output name="outfile" file="cluster_result09.txt" />
261 </test> 272 </test>
262 <test> 273 <test>
263 <param name="infile" value="numeric_values.tabular" ftype="tabular" /> 274 <param name="infile" value="numeric_values.tabular" ftype="tabular" />
264 <param name="selected_algorithm" value="AgglomerativeClustering" /> 275 <param name="selected_algorithm" value="AgglomerativeClustering" />
265 <param name="selected_input_type" value="tabular" /> 276 <param name="selected_input_type" value="tabular" />
277 <param name="header" value="false" />
266 <param name="col" value="2,3,4" /> 278 <param name="col" value="2,3,4" />
267 <param name="affinity" value="euclidean" /> 279 <param name="affinity" value="euclidean" />
268 <param name="linkage" value="average" /> 280 <param name="linkage" value="average" />
269 <param name="n_clusters" value="4" /> 281 <param name="n_clusters" value="4" />
270 <output name="outfile" file="cluster_result10.txt" /> 282 <output name="outfile" file="cluster_result10.txt" />
271 </test> 283 </test>
272 <test> 284 <test>
273 <param name="infile" value="numeric_values.tabular" ftype="tabular" /> 285 <param name="infile" value="numeric_values.tabular" ftype="tabular" />
274 <param name="selected_algorithm" value="AgglomerativeClustering" /> 286 <param name="selected_algorithm" value="AgglomerativeClustering" />
275 <param name="selected_input_type" value="tabular" /> 287 <param name="selected_input_type" value="tabular" />
288 <param name="header" value="false" />
276 <param name="col" value="2,3,4" /> 289 <param name="col" value="2,3,4" />
277 <param name="linkage" value="complete" /> 290 <param name="linkage" value="complete" />
278 <param name="n_clusters" value="4" /> 291 <param name="n_clusters" value="4" />
279 <output name="outfile" file="cluster_result11.txt" /> 292 <output name="outfile" file="cluster_result11.txt" />
280 </test> 293 </test>
281 <test> 294 <test>
282 <param name="infile" value="numeric_values.tabular" ftype="tabular" /> 295 <param name="infile" value="numeric_values.tabular" ftype="tabular" />
283 <param name="selected_algorithm" value="SpectralClustering" /> 296 <param name="selected_algorithm" value="SpectralClustering" />
284 <param name="selected_input_type" value="tabular" /> 297 <param name="selected_input_type" value="tabular" />
285 <param name="col" value="2,3,4" /> 298 <param name="col" value="2,3,4" />
299 <param name="header" value="false" />
286 <param name="eigen_solver" value="arpack" /> 300 <param name="eigen_solver" value="arpack" />
287 <param name="n_neighbors" value="12" /> 301 <param name="n_neighbors" value="12" />
288 <param name="n_clusters" value="4" /> 302 <param name="n_clusters" value="4" />
289 <param name="assign_labels" value="discretize" /> 303 <param name="assign_labels" value="discretize" />
290 <param name="random_state" value="100" /> 304 <param name="random_state" value="100" />
293 <test> 307 <test>
294 <param name="infile" value="numeric_values.tabular" ftype="tabular" /> 308 <param name="infile" value="numeric_values.tabular" ftype="tabular" />
295 <param name="selected_algorithm" value="SpectralClustering" /> 309 <param name="selected_algorithm" value="SpectralClustering" />
296 <param name="selected_input_type" value="tabular" /> 310 <param name="selected_input_type" value="tabular" />
297 <param name="col" value="2,3,4" /> 311 <param name="col" value="2,3,4" />
312 <param name="header" value="false" />
298 <param name="assign_labels" value="discretize" /> 313 <param name="assign_labels" value="discretize" />
299 <param name="random_state" value="100" /> 314 <param name="random_state" value="100" />
300 <param name="degree" value="2" /> 315 <param name="degree" value="2" />
301 <output name="outfile" file="cluster_result13.txt" compare="sim_size" /> 316 <output name="outfile" file="cluster_result13.txt" compare="sim_size" />
302 </test> 317 </test>
303 <test> 318 <test>
304 <param name="infile" value="numeric_values.tabular" ftype="tabular" /> 319 <param name="infile" value="numeric_values.tabular" ftype="tabular" />
305 <param name="selected_algorithm" value="MiniBatchKMeans" /> 320 <param name="selected_algorithm" value="MiniBatchKMeans" />
306 <param name="selected_input_type" value="tabular" /> 321 <param name="selected_input_type" value="tabular" />
322 <param name="header" value="false" />
307 <param name="col" value="2,3,4" /> 323 <param name="col" value="2,3,4" />
308 <param name="tol" value="0.5" /> 324 <param name="tol" value="0.5" />
309 <param name="random_state" value="100" /> 325 <param name="random_state" value="100" />
310 <output name="outfile" file="cluster_result14.txt" /> 326 <output name="outfile" file="cluster_result14.txt" />
311 </test> 327 </test>
312 <test> 328 <test>
313 <param name="infile" value="numeric_values.tabular" ftype="tabular" /> 329 <param name="infile" value="numeric_values.tabular" ftype="tabular" />
314 <param name="selected_algorithm" value="MiniBatchKMeans" /> 330 <param name="selected_algorithm" value="MiniBatchKMeans" />
315 <param name="selected_input_type" value="tabular" /> 331 <param name="selected_input_type" value="tabular" />
332 <param name="header" value="false" />
316 <param name="n_init" value="5" /> 333 <param name="n_init" value="5" />
317 <param name="col" value="2,3,4" /> 334 <param name="col" value="2,3,4" />
318 <param name="batch_size" value="10" /> 335 <param name="batch_size" value="10" />
319 <param name="n_clusters" value="4" /> 336 <param name="n_clusters" value="4" />
320 <param name="random_state" value="100" /> 337 <param name="random_state" value="100" />
323 </test> 340 </test>
324 <test> 341 <test>
325 <param name="infile" value="numeric_values.tabular" ftype="tabular" /> 342 <param name="infile" value="numeric_values.tabular" ftype="tabular" />
326 <param name="selected_algorithm" value="KMeans" /> 343 <param name="selected_algorithm" value="KMeans" />
327 <param name="selected_input_type" value="tabular" /> 344 <param name="selected_input_type" value="tabular" />
345 <param name="header" value="false" />
328 <param name="col" value="1" /> 346 <param name="col" value="1" />
329 <param name="n_clusters" value="4" /> 347 <param name="n_clusters" value="4" />
330 <param name="random_state" value="100" /> 348 <param name="random_state" value="100" />
331 <output name="outfile" file="cluster_result16.txt" /> 349 <output name="outfile" file="cluster_result16.txt" />
332 </test> 350 </test>