Mercurial > repos > bgruening > sklearn_numeric_clustering

comparison numeric_clustering.xml @ 40:006e27f0a7ef 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 208a8d348e7c7a182cfbe1b6f17868146428a7e2"
author bgruening
date Tue, 13 Apr 2021 20:52:41 +0000
parents 80bb86a40de6
children 0e4066f5751d
comparison
equal deleted inserted replaced
39:14346b365787 40:006e27f0a7ef
1 <tool id="sklearn_numeric_clustering" name="Numeric Clustering" version="@VERSION@"> 1 <tool id="sklearn_numeric_clustering" name="Numeric Clustering" version="@VERSION@" profile="20.05">
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" />
7 <expand macro="macro_stdio"/> 7 <expand macro="macro_stdio" />
8 <version_command>echo "@VERSION@"</version_command> 8 <version_command>echo "@VERSION@"</version_command>
9 <command><![CDATA[ 9 <command><![CDATA[
10 python "$cluster_script" '$inputs' 10 python "$cluster_script" '$inputs'
11 ]]> 11 ]]>
12 </command> 12 </command>
13 <configfiles> 13 <configfiles>
14 <inputs name="inputs"/> 14 <inputs name="inputs" />
15 <configfile name="cluster_script"> 15 <configfile name="cluster_script">
16 <![CDATA[ 16 <![CDATA[
17 import sys 17 import sys
18 import json 18 import json
19 import numpy as np 19 import numpy as np
20 import sklearn.cluster 20 import sklearn.cluster
21 import pandas 21 import pandas
87 <param name="selected_input_type" type="select" label="Select the format of input data"> 87 <param name="selected_input_type" type="select" label="Select the format of input data">
88 <option value="tabular" selected="true">Tabular Format (tabular, txt)</option> 88 <option value="tabular" selected="true">Tabular Format (tabular, txt)</option>
89 <option value="sparse">Sparse Vector Representation (mtx)</option> 89 <option value="sparse">Sparse Vector Representation (mtx)</option>
90 </param> 90 </param>
91 <when value="sparse"> 91 <when value="sparse">
92 <param name="infile" type="data" format="txt" label="Sparse vector (scipy.sparse.csr_matrix) file:" help="The following clustering algorithms support sparse matrix operations: ''Birch'', ''DBSCAN'', ''KMeans'', ''Mini BatchK Means'', and ''Spectral Clustering''. If your data is in tabular format, please use other clustering algorithms."/> 92 <param name="infile" type="data" format="txt" label="Sparse vector (scipy.sparse.csr_matrix) file:" help="The following clustering algorithms support sparse matrix operations: ''Birch'', ''DBSCAN'', ''KMeans'', ''Mini BatchK Means'', and ''Spectral Clustering''. If your data is in tabular format, please use other clustering algorithms." />
93 <expand macro="clustering_algorithms_options"/> 93 <expand macro="clustering_algorithms_options" />
94 </when> 94 </when>
95 <when value="tabular"> 95 <when value="tabular">
96 <param name="infile" type="data" format="tabular" label="Data file with numeric values"/> 96 <param name="infile" type="data" format="tabular" label="Data file with numeric values" />
97 <param name="header" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolfalse" checked="True" label="Does the dataset contain header:" /> 97 <param name="header" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolfalse" checked="True" label="Does the dataset contain header:" />
98 <conditional name="column_selector_options"> 98 <conditional name="column_selector_options">
99 <expand macro="samples_column_selector_options" col_name="col" multiple="true" infile="infile"/> 99 <expand macro="samples_column_selector_options" col_name="col" multiple="true" infile="infile" />
100 </conditional> 100 </conditional>
101 <!--expand macro="clustering_algorithms_options"--> 101 <!--expand macro="clustering_algorithms_options"-->
102 <conditional name="algorithm_options"> 102 <conditional name="algorithm_options">
103 <param name="selected_algorithm" type="select" label="Clustering Algorithm"> 103 <param name="selected_algorithm" type="select" label="Clustering Algorithm">
104 <option value="AgglomerativeClustering">Hierarchical Agglomerative Clustering</option> 104 <option value="AgglomerativeClustering">Hierarchical Agglomerative Clustering</option>
109 <option value="KMeans">KMeans</option> 109 <option value="KMeans">KMeans</option>
110 <option value="DBSCAN">DBSCAN</option> 110 <option value="DBSCAN">DBSCAN</option>
111 <option value="Birch">Birch</option> 111 <option value="Birch">Birch</option>
112 </param> 112 </param>
113 <when value="KMeans"> 113 <when value="KMeans">
114 <expand macro="kmeans_advanced_options"/> 114 <expand macro="kmeans_advanced_options" />
115 </when> 115 </when>
116 <when value="DBSCAN"> 116 <when value="DBSCAN">
117 <expand macro="dbscan_advanced_options"/> 117 <expand macro="dbscan_advanced_options" />
118 </when> 118 </when>
119 <when value="Birch"> 119 <when value="Birch">
120 <expand macro="birch_advanced_options"/> 120 <expand macro="birch_advanced_options" />
121 </when> 121 </when>
122 <when value="SpectralClustering"> 122 <when value="SpectralClustering">
123 <expand macro="spectral_clustering_advanced_options"/> 123 <expand macro="spectral_clustering_advanced_options" />
124 </when> 124 </when>
125 <when value="MiniBatchKMeans"> 125 <when value="MiniBatchKMeans">
126 <expand macro="minibatch_kmeans_advanced_options"/> 126 <expand macro="minibatch_kmeans_advanced_options" />
127 </when> 127 </when>
128 <when value="AffinityPropagation"> 128 <when value="AffinityPropagation">
129 <section name="options" title="Advanced Options" expanded="False"> 129 <section name="options" title="Advanced Options" expanded="False">
130 <param argument="damping" type="float" optional="true" value="0.5" label="Damping factor" help="Damping factor between 0.5 and 1."/> 130 <param argument="damping" type="float" optional="true" value="0.5" label="Damping factor" help="Damping factor between 0.5 and 1." />
131 <expand macro="max_iter" default_value="200"/> 131 <expand macro="max_iter" default_value="200" />
132 <param argument="convergence_iter" type="integer" optional="true" value="15" label="Number of iterations at each convergence step" help="Number of iterations with no change in the number of estimated clusters that stops the convergence."/> 132 <param argument="convergence_iter" type="integer" optional="true" value="15" label="Number of iterations at each convergence step" help="Number of iterations with no change in the number of estimated clusters that stops the convergence." />
133 <param argument="copy" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolflase" checked="true" label="Copy" help="If False, the affinity matrix is modified inplace by the algorithm, for memory efficiency."/> 133 <param argument="copy" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolflase" checked="true" label="Copy" help="If False, the affinity matrix is modified inplace by the algorithm, for memory efficiency." />
134 <!--param argument="preference"/--> 134 <!--param argument="preference"/-->
135 <param argument="affinity" type="select" label="Affinity" help="Affinity to use; euclidean uses the negative squared euclidean distance between points."> 135 <param argument="affinity" type="select" label="Affinity" help="Affinity to use; euclidean uses the negative squared euclidean distance between points.">
136 <option value="euclidean">Euclidean</option> 136 <option value="euclidean">Euclidean</option>
137 <option value="precomputed">precomputed</option> 137 <option value="precomputed">precomputed</option>
138 </param> 138 </param>
139 </section> 139 </section>
140 </when> 140 </when>
141 <when value="MeanShift"> 141 <when value="MeanShift">
142 <section name="options" title="Advanced Options" expanded="False"> 142 <section name="options" title="Advanced Options" expanded="False">
143 <param argument="bandwidth" type="float" optional="true" value="" label="Kernel bandwidth" help="Bandwidth used in the RBF kernel. If not given, it will be computed using a heuristic based on the median of all pairwise distances."/> 143 <param argument="bandwidth" type="float" optional="true" value="" label="Kernel bandwidth" help="Bandwidth used in the RBF kernel. If not given, it will be computed using a heuristic based on the median of all pairwise distances." />
144 <!--param argument="seeds"/--> 144 <!--param argument="seeds"/-->
145 <param argument="bin_seeding" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolflase" checked="true" label="Discretize initial kernel locations" help="If true, initial kernel locations are the bins grid whose coarseness corresponds to the bandwidth, speeding up the algorithm."/> 145 <param argument="bin_seeding" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolflase" checked="true" label="Discretize initial kernel locations" help="If true, initial kernel locations are the bins grid whose coarseness corresponds to the bandwidth, speeding up the algorithm." />
146 <param argument="min_bin_freq" type="integer" optional="true" value="1" label="Minimum number of seeds per bin" help="To speed up the algorithm, accept only those bins with at least min_bin_freq points as seeds."/> 146 <param argument="min_bin_freq" type="integer" optional="true" value="1" label="Minimum number of seeds per bin" help="To speed up the algorithm, accept only those bins with at least min_bin_freq points as seeds." />
147 <param argument="cluster_all" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolflase" checked="true" label="Cluster all" help="If true, all points (including orphans) are clustered. If false, orphans are given cluster label -1."/> 147 <param argument="cluster_all" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolflase" checked="true" label="Cluster all" help="If true, all points (including orphans) are clustered. If false, orphans are given cluster label -1." />
148 </section> 148 </section>
149 </when> 149 </when>
150 <when value="AgglomerativeClustering"> 150 <when value="AgglomerativeClustering">
151 <section name="options" title="Advanced Options" expanded="False"> 151 <section name="options" title="Advanced Options" expanded="False">
152 <expand macro="n_clusters" default_value="2" /> 152 <expand macro="n_clusters" default_value="2" />
174 </conditional> 174 </conditional>
175 </when> 175 </when>
176 </conditional> 176 </conditional>
177 </inputs> 177 </inputs>
178 <outputs> 178 <outputs>
179 <data format="tabular" name="outfile"/> 179 <data format="tabular" name="outfile" />
180 </outputs> 180 </outputs>
181 <tests> 181 <tests>
182 <test> 182 <test>
183 <param name="infile" value="numeric_values.tabular" ftype="tabular"/> 183 <param name="infile" value="numeric_values.tabular" ftype="tabular" />
184 <param name="selected_input_type" value="tabular"/> 184 <param name="selected_input_type" value="tabular" />
185 <param name="selected_algorithm" value="KMeans"/> 185 <param name="selected_algorithm" value="KMeans" />
186 <param name="col" value="2,3,4" /> 186 <param name="col" value="2,3,4" />
187 <param name="n_clusters" value="4" /> 187 <param name="n_clusters" value="4" />
188 <param name="init" value="k-means++" /> 188 <param name="init" value="k-means++" />
189 <param name="random_state" value="100"/> 189 <param name="random_state" value="100" />
190 <output name="outfile" file="cluster_result01.txt"/> 190 <output name="outfile" file="cluster_result01.txt" />
191 </test> 191 </test>
192 <test> 192 <test>
193 <param name="infile" value="numeric_values.tabular" ftype="tabular"/> 193 <param name="infile" value="numeric_values.tabular" ftype="tabular" />
194 <param name="selected_algorithm" value="KMeans"/> 194 <param name="selected_algorithm" value="KMeans" />
195 <param name="selected_input_type" value="tabular"/> 195 <param name="selected_input_type" value="tabular" />
196 <param name="col" value="2,3,4" /> 196 <param name="col" value="2,3,4" />
197 <param name="n_clusters" value="4" /> 197 <param name="n_clusters" value="4" />
198 <param name="init" value="random" /> 198 <param name="init" value="random" />
199 <param name="random_state" value="100"/> 199 <param name="random_state" value="100" />
200 <output name="outfile" file="cluster_result02.txt"/> 200 <output name="outfile" file="cluster_result02.txt" />
201 </test> 201 </test>
202 <test> 202 <test>
203 <param name="infile" value="numeric_values.tabular" ftype="tabular"/> 203 <param name="infile" value="numeric_values.tabular" ftype="tabular" />
204 <param name="selected_algorithm" value="DBSCAN"/> 204 <param name="selected_algorithm" value="DBSCAN" />
205 <param name="selected_input_type" value="tabular"/> 205 <param name="selected_input_type" value="tabular" />
206 <param name="col" value="2,3,4" /> 206 <param name="col" value="2,3,4" />
207 <param name="algorithm" value="kd_tree"/> 207 <param name="algorithm" value="kd_tree" />
208 <param name="leaf_size" value="10"/> 208 <param name="leaf_size" value="10" />
209 <param name="eps" value="1.0"/> 209 <param name="eps" value="1.0" />
210 <output name="outfile" file="cluster_result03.txt"/> 210 <output name="outfile" file="cluster_result03.txt" />
211 </test> 211 </test>
212 <test> 212 <test>
213 <param name="infile" value="numeric_values.tabular" ftype="tabular"/> 213 <param name="infile" value="numeric_values.tabular" ftype="tabular" />
214 <param name="selected_algorithm" value="Birch"/> 214 <param name="selected_algorithm" value="Birch" />
215 <param name="selected_input_type" value="tabular"/> 215 <param name="selected_input_type" value="tabular" />
216 <param name="col" value="2,3,4" /> 216 <param name="col" value="2,3,4" />
217 <param name="n_clusters" value="4"/> 217 <param name="n_clusters" value="4" />
218 <param name="threshold" value="0.008"/> 218 <param name="threshold" value="0.008" />
219 <output name="outfile" file="cluster_result04.txt"/> 219 <output name="outfile" file="cluster_result04.txt" />
220 </test> 220 </test>
221 <test> 221 <test>
222 <param name="infile" value="numeric_values.tabular" ftype="tabular"/> 222 <param name="infile" value="numeric_values.tabular" ftype="tabular" />
223 <param name="selected_algorithm" value="Birch"/> 223 <param name="selected_algorithm" value="Birch" />
224 <param name="selected_input_type" value="tabular"/> 224 <param name="selected_input_type" value="tabular" />
225 <param name="col" value="2,3,4" /> 225 <param name="col" value="2,3,4" />
226 <param name="branching_factor" value="20"/> 226 <param name="branching_factor" value="20" />
227 <output name="outfile" file="cluster_result05.txt"/> 227 <output name="outfile" file="cluster_result05.txt" />
228 </test> 228 </test>
229 <test> 229 <test>
230 <param name="infile" value="numeric_values.tabular" ftype="tabular"/> 230 <param name="infile" value="numeric_values.tabular" ftype="tabular" />
231 <param name="selected_algorithm" value="AffinityPropagation"/> 231 <param name="selected_algorithm" value="AffinityPropagation" />
232 <param name="selected_input_type" value="tabular"/> 232 <param name="selected_input_type" value="tabular" />
233 <param name="col" value="2,3,4" /> 233 <param name="col" value="2,3,4" />
234 <param name="affinity" value="euclidean"/> 234 <param name="affinity" value="euclidean" />
235 <param name="copy" value="false"/> 235 <param name="copy" value="false" />
236 <output name="outfile" file="cluster_result06.txt"/> 236 <output name="outfile" file="cluster_result06.txt" />
237 </test> 237 </test>
238 <test> 238 <test>
239 <param name="infile" value="numeric_values.tabular" ftype="tabular"/> 239 <param name="infile" value="numeric_values.tabular" ftype="tabular" />
240 <param name="selected_algorithm" value="AffinityPropagation"/> 240 <param name="selected_algorithm" value="AffinityPropagation" />
241 <param name="selected_input_type" value="tabular"/> 241 <param name="selected_input_type" value="tabular" />
242 <param name="col" value="2,3,4" /> 242 <param name="col" value="2,3,4" />
243 <param name="damping" value="0.8"/> 243 <param name="damping" value="0.8" />
244 <output name="outfile" file="cluster_result07.txt"/> 244 <output name="outfile" file="cluster_result07.txt" />
245 </test> 245 </test>
246 <test> 246 <test>
247 <param name="infile" value="numeric_values.tabular" ftype="tabular"/> 247 <param name="infile" value="numeric_values.tabular" ftype="tabular" />
248 <param name="selected_algorithm" value="MeanShift"/> 248 <param name="selected_algorithm" value="MeanShift" />
249 <param name="selected_input_type" value="tabular"/> 249 <param name="selected_input_type" value="tabular" />
250 <param name="col" value="2,3,4" /> 250 <param name="col" value="2,3,4" />
251 <param name="min_bin_freq" value="3"/> 251 <param name="min_bin_freq" value="3" />
252 <output name="outfile" file="cluster_result08.txt"/> 252 <output name="outfile" file="cluster_result08.txt" />
253 </test> 253 </test>
254 <test> 254 <test>
255 <param name="infile" value="numeric_values.tabular" ftype="tabular"/> 255 <param name="infile" value="numeric_values.tabular" ftype="tabular" />
256 <param name="selected_algorithm" value="MeanShift"/> 256 <param name="selected_algorithm" value="MeanShift" />
257 <param name="selected_input_type" value="tabular"/> 257 <param name="selected_input_type" value="tabular" />
258 <param name="col" value="2,3,4" /> 258 <param name="col" value="2,3,4" />
259 <param name="cluster_all" value="False"/> 259 <param name="cluster_all" value="False" />
260 <output name="outfile" file="cluster_result09.txt"/> 260 <output name="outfile" file="cluster_result09.txt" />
261 </test> 261 </test>
262 <test> 262 <test>
263 <param name="infile" value="numeric_values.tabular" ftype="tabular"/> 263 <param name="infile" value="numeric_values.tabular" ftype="tabular" />
264 <param name="selected_algorithm" value="AgglomerativeClustering"/> 264 <param name="selected_algorithm" value="AgglomerativeClustering" />
265 <param name="selected_input_type" value="tabular"/> 265 <param name="selected_input_type" value="tabular" />
266 <param name="col" value="2,3,4" /> 266 <param name="col" value="2,3,4" />
267 <param name="affinity" value="euclidean"/> 267 <param name="affinity" value="euclidean" />
268 <param name="linkage" value="average"/> 268 <param name="linkage" value="average" />
269 <param name="n_clusters" value="4"/> 269 <param name="n_clusters" value="4" />
270 <output name="outfile" file="cluster_result10.txt"/> 270 <output name="outfile" file="cluster_result10.txt" />
271 </test> 271 </test>
272 <test> 272 <test>
273 <param name="infile" value="numeric_values.tabular" ftype="tabular"/> 273 <param name="infile" value="numeric_values.tabular" ftype="tabular" />
274 <param name="selected_algorithm" value="AgglomerativeClustering"/> 274 <param name="selected_algorithm" value="AgglomerativeClustering" />
275 <param name="selected_input_type" value="tabular"/> 275 <param name="selected_input_type" value="tabular" />
276 <param name="col" value="2,3,4" /> 276 <param name="col" value="2,3,4" />
277 <param name="linkage" value="complete"/> 277 <param name="linkage" value="complete" />
278 <param name="n_clusters" value="4"/> 278 <param name="n_clusters" value="4" />
279 <output name="outfile" file="cluster_result11.txt"/> 279 <output name="outfile" file="cluster_result11.txt" />
280 </test> 280 </test>
281 <test> 281 <test>
282 <param name="infile" value="numeric_values.tabular" ftype="tabular"/> 282 <param name="infile" value="numeric_values.tabular" ftype="tabular" />
283 <param name="selected_algorithm" value="SpectralClustering"/> 283 <param name="selected_algorithm" value="SpectralClustering" />
284 <param name="selected_input_type" value="tabular"/> 284 <param name="selected_input_type" value="tabular" />
285 <param name="col" value="2,3,4" /> 285 <param name="col" value="2,3,4" />
286 <param name="eigen_solver" value="arpack"/> 286 <param name="eigen_solver" value="arpack" />
287 <param name="n_neighbors" value="12"/> 287 <param name="n_neighbors" value="12" />
288 <param name="n_clusters" value="4"/> 288 <param name="n_clusters" value="4" />
289 <param name="assign_labels" value="discretize"/> 289 <param name="assign_labels" value="discretize" />
290 <param name="random_state" value="100"/> 290 <param name="random_state" value="100" />
291 <output name="outfile" file="cluster_result12.txt" compare="sim_size" /> 291 <output name="outfile" file="cluster_result12.txt" compare="sim_size" />
292 </test> 292 </test>
293 <test> 293 <test>
294 <param name="infile" value="numeric_values.tabular" ftype="tabular"/> 294 <param name="infile" value="numeric_values.tabular" ftype="tabular" />
295 <param name="selected_algorithm" value="SpectralClustering"/> 295 <param name="selected_algorithm" value="SpectralClustering" />
296 <param name="selected_input_type" value="tabular"/> 296 <param name="selected_input_type" value="tabular" />
297 <param name="col" value="2,3,4" /> 297 <param name="col" value="2,3,4" />
298 <param name="assign_labels" value="discretize"/> 298 <param name="assign_labels" value="discretize" />
299 <param name="random_state" value="100"/> 299 <param name="random_state" value="100" />
300 <param name="degree" value="2"/> 300 <param name="degree" value="2" />
301 <output name="outfile" file="cluster_result13.txt" compare="sim_size" /> 301 <output name="outfile" file="cluster_result13.txt" compare="sim_size" />
302 </test> 302 </test>
303 <test> 303 <test>
304 <param name="infile" value="numeric_values.tabular" ftype="tabular"/> 304 <param name="infile" value="numeric_values.tabular" ftype="tabular" />
305 <param name="selected_algorithm" value="MiniBatchKMeans"/> 305 <param name="selected_algorithm" value="MiniBatchKMeans" />
306 <param name="selected_input_type" value="tabular"/> 306 <param name="selected_input_type" value="tabular" />
307 <param name="col" value="2,3,4" /> 307 <param name="col" value="2,3,4" />
308 <param name="tol" value="0.5"/> 308 <param name="tol" value="0.5" />
309 <param name="random_state" value="100"/> 309 <param name="random_state" value="100" />
310 <output name="outfile" file="cluster_result14.txt"/> 310 <output name="outfile" file="cluster_result14.txt" />
311 </test> 311 </test>
312 <test> 312 <test>
313 <param name="infile" value="numeric_values.tabular" ftype="tabular"/> 313 <param name="infile" value="numeric_values.tabular" ftype="tabular" />
314 <param name="selected_algorithm" value="MiniBatchKMeans"/> 314 <param name="selected_algorithm" value="MiniBatchKMeans" />
315 <param name="selected_input_type" value="tabular"/> 315 <param name="selected_input_type" value="tabular" />
316 <param name="n_init" value="5"/> 316 <param name="n_init" value="5" />
317 <param name="col" value="2,3,4" /> 317 <param name="col" value="2,3,4" />
318 <param name="batch_size" value="10"/> 318 <param name="batch_size" value="10" />
319 <param name="n_clusters" value="4"/> 319 <param name="n_clusters" value="4" />
320 <param name="random_state" value="100"/> 320 <param name="random_state" value="100" />
321 <param name="reassignment_ratio" value="1.0"/> 321 <param name="reassignment_ratio" value="1.0" />
322 <output name="outfile" file="cluster_result15.txt"/> 322 <output name="outfile" file="cluster_result15.txt" />
323 </test> 323 </test>
324 <test> 324 <test>
325 <param name="infile" value="numeric_values.tabular" ftype="tabular"/> 325 <param name="infile" value="numeric_values.tabular" ftype="tabular" />
326 <param name="selected_algorithm" value="KMeans"/> 326 <param name="selected_algorithm" value="KMeans" />
327 <param name="selected_input_type" value="tabular"/> 327 <param name="selected_input_type" value="tabular" />
328 <param name="col" value="1" /> 328 <param name="col" value="1" />
329 <param name="n_clusters" value="4" /> 329 <param name="n_clusters" value="4" />
330 <param name="random_state" value="100"/> 330 <param name="random_state" value="100" />
331 <output name="outfile" file="cluster_result16.txt"/> 331 <output name="outfile" file="cluster_result16.txt" />
332 </test> 332 </test>
333 <test> 333 <test>
334 <param name="infile" value="sparse.mtx" ftype="txt"/> 334 <param name="infile" value="sparse.mtx" ftype="txt" />
335 <param name="selected_input_type" value="sparse"/> 335 <param name="selected_input_type" value="sparse" />
336 <param name="selected_algorithm" value="KMeans"/> 336 <param name="selected_algorithm" value="KMeans" />
337 <param name="n_clusters" value="2" /> 337 <param name="n_clusters" value="2" />
338 <param name="init" value="k-means++" /> 338 <param name="init" value="k-means++" />
339 <param name="random_state" value="100"/> 339 <param name="random_state" value="100" />
340 <output name="outfile" file="cluster_result17.txt"/> 340 <output name="outfile" file="cluster_result17.txt" />
341 </test> 341 </test>
342 <test> 342 <test>
343 <param name="infile" value="sparse.mtx" ftype="txt"/> 343 <param name="infile" value="sparse.mtx" ftype="txt" />
344 <param name="selected_algorithm" value="DBSCAN"/> 344 <param name="selected_algorithm" value="DBSCAN" />
345 <param name="selected_input_type" value="sparse"/> 345 <param name="selected_input_type" value="sparse" />
346 <param name="algorithm" value="kd_tree"/> 346 <param name="algorithm" value="kd_tree" />
347 <param name="leaf_size" value="10"/> 347 <param name="leaf_size" value="10" />
348 <param name="eps" value="1.0"/> 348 <param name="eps" value="1.0" />
349 <output name="outfile" file="cluster_result18.txt"/> 349 <output name="outfile" file="cluster_result18.txt" />
350 </test> 350 </test>
351 <test> 351 <test>
352 <param name="infile" value="sparse.mtx" ftype="txt"/> 352 <param name="infile" value="sparse.mtx" ftype="txt" />
353 <param name="selected_algorithm" value="Birch"/> 353 <param name="selected_algorithm" value="Birch" />
354 <param name="selected_input_type" value="sparse"/> 354 <param name="selected_input_type" value="sparse" />
355 <param name="n_clusters" value="2"/> 355 <param name="n_clusters" value="2" />
356 <param name="threshold" value="0.008"/> 356 <param name="threshold" value="0.008" />
357 <output name="outfile" file="cluster_result19.txt"/> 357 <output name="outfile" file="cluster_result19.txt" />
358 </test> 358 </test>
359 <test> 359 <test>
360 <param name="infile" value="sparse.mtx" ftype="txt"/> 360 <param name="infile" value="sparse.mtx" ftype="txt" />
361 <param name="selected_algorithm" value="MiniBatchKMeans"/> 361 <param name="selected_algorithm" value="MiniBatchKMeans" />
362 <param name="selected_input_type" value="sparse"/> 362 <param name="selected_input_type" value="sparse" />
363 <param name="n_init" value="5"/> 363 <param name="n_init" value="5" />
364 <param name="batch_size" value="10"/> 364 <param name="batch_size" value="10" />
365 <param name="n_clusters" value="2"/> 365 <param name="n_clusters" value="2" />
366 <param name="random_state" value="100"/> 366 <param name="random_state" value="100" />
367 <param name="reassignment_ratio" value="1.0"/> 367 <param name="reassignment_ratio" value="1.0" />
368 <output name="outfile" file="cluster_result20.txt"/> 368 <output name="outfile" file="cluster_result20.txt" />
369 </test> 369 </test>
370 <test> 370 <test>
371 <param name="infile" value="sparse.mtx" ftype="txt"/> 371 <param name="infile" value="sparse.mtx" ftype="txt" />
372 <param name="selected_algorithm" value="SpectralClustering"/> 372 <param name="selected_algorithm" value="SpectralClustering" />
373 <param name="selected_input_type" value="sparse"/> 373 <param name="selected_input_type" value="sparse" />
374 <param name="assign_labels" value="discretize"/> 374 <param name="assign_labels" value="discretize" />
375 <param name="n_clusters" value="2"/> 375 <param name="n_clusters" value="2" />
376 <param name="random_state" value="100"/> 376 <param name="random_state" value="100" />
377 <param name="degree" value="2"/> 377 <param name="degree" value="2" />
378 <output name="outfile" file="cluster_result21.txt"/> 378 <output name="outfile" file="cluster_result21.txt" />
379 </test> 379 </test>
380 </tests> 380 </tests>
381 <help><![CDATA[ 381 <help><![CDATA[
382 **What it does** 382 **What it does**
383 This tool offers different clustering algorithms which are provided by 383 This tool offers different clustering algorithms which are provided by
384 scikit-learn to find similarities among samples and cluster the samples based on these similarities. 384 scikit-learn to find similarities among samples and cluster the samples based on these similarities.
385 ]]></help> 385 ]]> </help>
386 <expand macro="sklearn_citation"/> 386 <expand macro="sklearn_citation" />
387 </tool> 387 </tool>