Mercurial > repos > bgruening > sklearn_sample_generator

comparison main_macros.xml @ 0:dec5e182fd0c 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/tools/sklearn commit 0e582cf1f3134c777cce3aa57d71b80ed95e6ba9
author bgruening
date Fri, 16 Feb 2018 09:16:51 -0500
parents
children 70fbde68cc71
comparison
equal deleted inserted replaced
-1:000000000000 0:dec5e182fd0c
1 <macros>
2 <token name="@VERSION@">0.9</token>
3
4 <token name="@COLUMNS_FUNCTION@">
5 def columns(f,c):
6 data = pandas.read_csv(f, sep='\t', header=None, index_col=None, parse_dates=True, encoding=None, tupleize_cols=False)
7 cols = c.split (',')
8 cols = map(int, cols)
9 cols = list(map(lambda x: x - 1, cols))
10 y = data.iloc[:,cols].values
11 return y
12 </token>
13
14 <xml name="python_requirements">
15 <requirements>
16 <requirement type="package" version="2.7">python</requirement>
17 <requirement type="package" version="0.19.1">scikit-learn</requirement>
18 <requirement type="package" version="0.22.0">pandas</requirement>
19 <yield />
20 </requirements>
21 </xml>
22
23 <xml name="macro_stdio">
24 <stdio>
25 <exit_code range="1:" level="fatal" description="Error occurred. Please check Tool Standard Error"/>
26 </stdio>
27 </xml>
28
29
30 <!--Generic interface-->
31 <xml name="train_loadConditional" token_train="tabular" token_data="tabular" token_model="txt">
32 <conditional name="selected_tasks">
33 <param name="selected_task" type="select" label="Select a Classification Task">
34 <option value="train" selected="true">Train a model</option>
35 <option value="load">Load a model and predict</option>
36 </param>
37 <when value="load">
38 <param name="infile_model" type="data" format="@MODEL@" label="Models" help="Select a model file."/>
39 <param name="infile_data" type="data" format="@DATA@" label="Data (tabular)" help="Select the dataset you want to classify."/>
40 <conditional name="prediction_options">
41 <param name="prediction_option" type="select" label="Select the type of prediction">
42 <option value="predict">Predict class labels</option>
43 <option value="advanced">Include advanced options</option>
44 </param>
45 <when value="predict">
46 </when>
47 <when value="advanced">
48 </when>
49 </conditional>
50 </when>
51 <when value="train">
52 <param name="infile_train" type="data" format="@TRAIN@" label="Training samples (tabular)"/>
53 <conditional name="selected_algorithms">
54 <yield />
55 </conditional>
56 </when>
57 </conditional>
58 </xml>
59
60 <xml name="sl_Conditional" token_train="tabular" token_data="tabular" token_model="txt">
61 <conditional name="selected_tasks">
62 <param name="selected_task" type="select" label="Select a Classification Task">
63 <option value="train" selected="true">Train a model</option>
64 <option value="load">Load a model and predict</option>
65 </param>
66 <when value="load">
67 <param name="infile_model" type="data" format="@MODEL@" label="Models" help="Select a model file."/>
68 <param name="infile_data" type="data" format="@DATA@" label="Data (tabular)" help="Select the dataset you want to classify."/>
69 <conditional name="prediction_options">
70 <param name="prediction_option" type="select" label="Select the type of prediction">
71 <option value="predict">Predict class labels</option>
72 <option value="advanced">Include advanced options</option>
73 </param>
74 <when value="predict">
75 </when>
76 <when value="advanced">
77 </when>
78 </conditional>
79 </when>
80 <when value="train">
81 <conditional name="selected_algorithms">
82 <yield />
83 </conditional>
84 </when>
85 </conditional>
86 </xml>
87
88 <xml name="advanced_section">
89 <section name="options" title="Advanced Options" expanded="False">
90 <yield />
91 </section>
92 </xml>
93
94
95 <!--Generalized Linear Models-->
96 <xml name="loss" token_help=" " token_select="false">
97 <param argument="loss" type="select" label="Loss function" help="@HELP@">
98 <option value="squared_loss" selected="@SELECT@">squared loss</option>
99 <option value="huber">huber</option>
100 <option value="epsilon_insensitive">epsilon insensitive</option>
101 <option value="squared_epsilon_insensitive">squared epsilon insensitive</option>
102 <yield/>
103 </param>
104 </xml>
105
106 <xml name="penalty" token_help=" ">
107 <param argument="penalty" type="select" label="Penalty (regularization term)" help="@HELP@">
108 <option value="l2" selected="true">l2</option>
109 <option value="l1">l1</option>
110 <option value="elasticnet">elastic net</option>
111 <option value="none">none</option>
112 <yield/>
113 </param>
114 </xml>
115
116 <xml name="l1_ratio" token_default_value="0.15" token_help=" ">
117 <param argument="l1_ratio" type="float" value="@DEFAULT_VALUE@" label="Elastic Net mixing parameter" help="@HELP@"/>
118 </xml>
119
120 <xml name="epsilon" token_default_value="0.1" token_help="Used if loss is ‘huber’, ‘epsilon_insensitive’, or ‘squared_epsilon_insensitive’. ">
121 <param argument="epsilon" type="float" value="@DEFAULT_VALUE@" label="Epsilon (epsilon-sensitive loss functions only)" help="@HELP@"/>
122 </xml>
123
124 <xml name="learning_rate_s" token_help=" " token_selected1="false" token_selected2="false">
125 <param argument="learning_rate" type="select" optional="true" label="Learning rate schedule" help="@HELP@">
126 <option value="optimal" selected="@SELECTED1@">optimal</option>
127 <option value="constant">constant</option>
128 <option value="invscaling" selected="@SELECTED2@">inverse scaling</option>
129 <yield/>
130 </param>
131 </xml>
132
133 <xml name="eta0" token_default_value="0.0" token_help="Used with ‘constant’ or ‘invscaling’ schedules. ">
134 <param argument="eta0" type="float" value="@DEFAULT_VALUE@" label="Initial learning rate" help="@HELP@"/>
135 </xml>
136
137 <xml name="power_t" token_default_value="0.5" token_help=" ">
138 <param argument="power_t" type="float" value="@DEFAULT_VALUE@" label="Exponent for inverse scaling learning rate" help="@HELP@"/>
139 </xml>
140
141 <xml name="normalize" token_checked="false" token_help=" ">
142 <param argument="normalize" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolfalse" checked="@CHECKED@" label="Normalize samples before training" help=" "/>
143 </xml>
144
145 <xml name="copy_X" token_checked="true" token_help=" ">
146 <param argument="copy_X" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolfalse" checked="@CHECKED@" label="Use a copy of samples" help="If false, samples would be overwritten. "/>
147 </xml>
148
149 <xml name="ridge_params">
150 <expand macro="normalize"/>
151 <expand macro="alpha" default_value="1.0"/>
152 <expand macro="fit_intercept"/>
153 <expand macro="max_iter" default_value=""/>
154 <expand macro="tol" default_value="0.001" help_text="Precision of the solution. "/>
155 <!--class_weight-->
156 <expand macro="copy_X"/>
157 <param argument="solver" type="select" value="" label="Solver to use in the computational routines" help=" ">
158 <option value="auto" selected="true">auto</option>
159 <option value="svd">svd</option>
160 <option value="cholesky">cholesky</option>
161 <option value="lsqr">lsqr</option>
162 <option value="sparse_cg">sparse_cg</option>
163 <option value="sag">sag</option>
164 </param>
165 <expand macro="random_state"/>
166 </xml>
167
168 <!--Ensemble methods-->
169 <xml name="n_estimators" token_default_value="10" token_help=" ">
170 <param argument="n_estimators" type="integer" optional="true" value="@DEFAULT_VALUE@" label="Number of trees in the forest" help="@HELP@"/>
171 </xml>
172
173 <xml name="max_depth" token_default_value="" token_help=" ">
174 <param argument="max_depth" type="integer" optional="true" value="@DEFAULT_VALUE@" label="Maximum depth of the tree" help="@HELP@"/>
175 </xml>
176
177 <xml name="min_samples_split" token_default_value="2" token_help=" ">
178 <param argument="min_samples_split" type="integer" optional="true" value="@DEFAULT_VALUE@" label="Maximum depth of the tree" help="@HELP@"/>
179 </xml>
180
181 <xml name="min_samples_leaf" token_default_value="1" token_help=" ">
182 <param argument="min_samples_leaf" type="integer" optional="true" value="@DEFAULT_VALUE@" label="Minimum number of samples in newly created leaves" help="@HELP@"/>
183 </xml>
184
185 <xml name="min_weight_fraction_leaf" token_default_value="0.0" token_help=" ">
186 <param argument="min_weight_fraction_leaf" type="float" optional="true" value="@DEFAULT_VALUE@" label="Minimum weighted fraction of the input samples required to be at a leaf node" help="@HELP@"/>
187 </xml>
188
189 <xml name="max_leaf_nodes" token_default_value="" token_help=" ">
190 <param argument="max_leaf_nodes" type="integer" optional="true" value="@DEFAULT_VALUE@" label="Maximum number of leaf nodes in best-first method" help="@HELP@"/>
191 </xml>
192
193 <xml name="bootstrap" token_checked="true" token_help=" ">
194 <param argument="bootstrap" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolflase" checked="@CHECKED@" label="Use bootstrap samples for building trees." help="@HELP@"/>
195 </xml>
196
197 <xml name="criterion" token_help=" ">
198 <param argument="criterion" type="select" label="Function to measure the quality of a split" help=" ">
199 <option value="gini" selected="true">Gini impurity</option>
200 <option value="entropy">Information gain</option>
201 <yield/>
202 </param>
203 </xml>
204
205 <xml name="oob_score" token_checked="false" token_help=" ">
206 <param argument="oob_score" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolfalse" checked="@CHECKED@" label="Use out-of-bag samples to estimate the generalization error" help="@HELP@"/>
207 </xml>
208
209 <xml name="max_features" token_default_value="auto" token_help="This could be an integer, float, string, or None. For more information please refer to help. ">
210 <param argument="max_features" type="text" optional="true" value="@DEFAULT_VALUE@" label="Number of features for finding the best split" help="@HELP@"/>
211 </xml>
212
213 <xml name="learning_rate" token_default_value="1.0" token_help=" ">
214 <param argument="learning_rate" type="float" optional="true" value="@DEFAULT_VALUE@" label="Learning rate" help="@HELP@"/>
215 </xml>
216
217
218 <!--Parameters-->
219 <xml name="tol" token_default_value="0.0" token_help_text="Early stopping heuristics based on the relative center changes. Set to default (0.0) to disable this convergence detection.">
220 <param argument="tol" type="float" optional="true" value="@DEFAULT_VALUE@" label="Tolerance" help="@HELP_TEXT@"/>
221 </xml>
222
223 <xml name="n_clusters" token_default_value="8">
224 <param argument="n_clusters" type="integer" optional="true" value="@DEFAULT_VALUE@" label="Number of clusters" help=" "/>
225 </xml>
226
227 <xml name="fit_intercept" token_checked="true">
228 <param argument="fit_intercept" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolfalse" checked="@CHECKED@" label="Estimate the intercept" help="If false, the data is assumed to be already centered."/>
229 </xml>
230
231 <xml name="n_iter" token_default_value="5" token_help_text="The number of passes over the training data (aka epochs). ">
232 <param argument="n_iter" type="integer" optional="true" value="@DEFAULT_VALUE@" label="Number of iterations" help="@HELP_TEXT@"/>
233 </xml>
234
235 <xml name="shuffle" token_checked="true" token_help_text=" " token_label="Shuffle data after each iteration">
236 <param argument="shuffle" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolfalse" checked="@CHECKED@" label="@LABEL@" help="@HELP_TEXT@"/>
237 </xml>
238
239 <xml name="random_state" token_default_value="" token_help_text="Integer number. The seed of the pseudo random number generator to use when shuffling the data. A fixed seed allows reproducible results.">
240 <param argument="random_state" type="integer" optional="true" value="@DEFAULT_VALUE@" label="Random seed number" help="@HELP_TEXT@"/>
241 </xml>
242
243 <xml name="warm_start" token_checked="true" token_help_text="When set to True, reuse the solution of the previous call to fit as initialization,otherwise, just erase the previous solution.">
244 <param argument="warm_start" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolfalse" checked="@CHECKED@" label="Perform warm start" help="@HELP_TEXT@"/>
245 </xml>
246
247 <xml name="C" token_default_value="1.0" token_help_text="Penalty parameter C of the error term.">
248 <param argument="C" type="float" optional="true" value="@DEFAULT_VALUE@" label="Penalty parameter" help="@HELP_TEXT@"/>
249 </xml>
250
251 <!--xml name="class_weight" token_default_value="" token_help_text="">
252 <param argument="class_weight" type="" optional="true" value="@DEFAULT_VALUE@" label="" help="@HELP_TEXT@"/>
253 </xml-->
254
255 <xml name="alpha" token_default_value="0.0001" token_help_text="Constant that multiplies the regularization term if regularization is used. ">
256 <param argument="alpha" type="float" optional="true" value="@DEFAULT_VALUE@" label="Regularization coefficient" help="@HELP_TEXT@"/>
257 </xml>
258
259 <xml name="n_samples" token_default_value="100" token_help_text="The total number of points equally divided among clusters.">
260 <param argument="n_samples" type="integer" optional="true" value="@DEFAULT_VALUE@" label="Number of samples" help="@HELP_TEXT@"/>
261 </xml>
262
263 <xml name="n_features" token_default_value="2" token_help_text="Number of different numerical properties produced for each sample.">
264 <param argument="n_features" type="integer" optional="true" value="@DEFAULT_VALUE@" label="Number of features" help="@HELP_TEXT@"/>
265 </xml>
266
267 <xml name="noise" token_default_value="0.0" token_help_text="Floating point number. ">
268 <param argument="noise" type="float" optional="true" value="@DEFAULT_VALUE@" label="Standard deviation of the Gaussian noise added to the data" help="@HELP_TEXT@"/>
269 </xml>
270
271 <xml name="C" token_default_value="1.0" token_help_text="Penalty parameter C of the error term. ">
272 <param argument="C" type="float" optional="true" value="@DEFAULT_VALUE@" label="Penalty parameter" help="@HELP_TEXT@"/>
273 </xml>
274
275 <xml name="max_iter" token_default_value="300" token_label="Maximum number of iterations per single run" token_help_text=" ">
276 <param argument="max_iter" type="integer" optional="true" value="@DEFAULT_VALUE@" label="@LABEL@" help="@HELP_TEXT@"/>
277 </xml>
278
279 <xml name="n_init" token_default_value="10" >
280 <param argument="n_init" type="integer" optional="true" value="@DEFAULT_VALUE@" label="Number of runs with different centroid seeds" help=" "/>
281 </xml>
282
283 <xml name="init">
284 <param argument="init" type="select" label="Centroid initialization method" help="''k-means++'' selects initial cluster centers that speed up convergence. ''random'' chooses k observations (rows) at random from data as initial centroids.">
285 <option value="k-means++">k-means++</option>
286 <option value="random">random</option>
287 </param>
288 </xml>
289
290 <xml name="gamma" token_default_value="1.0" token_label="Scaling parameter" token_help_text=" ">
291 <param argument="gamma" type="float" optional="true" value="@DEFAULT_VALUE@" label="@LABEL@" help="@HELP_TEXT@"/>
292 </xml>
293
294 <xml name="degree" token_default_value="3" token_label="Degree of the polynomial" token_help_text=" ">
295 <param argument="degree" type="integer" optional="true" value="@DEFAULT_VALUE@" label="@LABEL@" help="@HELP_TEXT@"/>
296 </xml>
297
298 <xml name="coef0" token_default_value="1" token_label="Zero coefficient" token_help_text=" ">
299 <param argument="coef0" type="integer" optional="true" value="@DEFAULT_VALUE@" label="@LABEL@" help="@HELP_TEXT@"/>
300 </xml>
301
302 <xml name="pos_label" token_default_value="">
303 <param argument="pos_label" type="integer" optional="true" value="@DEFAULT_VALUE@" label="Label of the positive class" help=" "/>
304 </xml>
305
306 <xml name="average">
307 <param argument="average" type="select" optional="true" label="Averaging type" help=" ">
308 <option value="micro">Calculate metrics globally by counting the total true positives, false negatives and false positives. (micro)</option>
309 <option value="samples">Calculate metrics for each instance, and find their average. Only meaningful for multilabel. (samples)</option>
310 <option value="macro">Calculate metrics for each label, and find their unweighted mean. This does not take label imbalance into account. (macro)</option>
311 <option value="weighted">Calculate metrics for each label, and find their average, weighted by support (the number of true instances for each label). This alters ‘macro’ to account for label imbalance; it can result in an F-score that is not between precision and recall. (weighted)</option>
312 <option value="None">None</option>
313 <yield/>
314 </param>
315 </xml>
316
317 <xml name="beta">
318 <param argument="beta" type="float" value="1.0" label="The strength of recall versus precision in the F-score" help=" "/>
319 </xml>
320
321
322 <!--Data interface-->
323 <xml name="tabular_input">
324 <param name="infile" type="data" format="tabular" label="Data file with numeric values"/>
325 <param name="start_column" type="data_column" data_ref="infile" optional="True" label="Select a subset of data. Start column:" />
326 <param name="end_column" type="data_column" data_ref="infile" optional="True" label="End column:" />
327 </xml>
328
329 <xml name="sample_cols" token_label1="File containing true class labels:" token_label2="File containing predicted class labels:" token_multiple1="False" token_multiple2="False" token_format1="tabular" token_format2="tabular" token_help1="" token_help2="">
330 <param name="infile1" type="data" format="@FORMAT1@" label="@LABEL1@" help="@HELP1@"/>
331 <param name="col1" multiple="@MULTIPLE1@" type="data_column" data_ref="infile1" label="Select target column(s):"/>
332 <param name="infile2" type="data" format="@FORMAT2@" label="@LABEL2@" help="@HELP2@"/>
333 <param name="col2" multiple="@MULTIPLE2@" type="data_column" data_ref="infile2" label="Select target column(s):"/>
334 <yield/>
335 </xml>
336
337 <xml name="samples_tabular" token_multiple1="False" token_multiple2="False">
338 <param name="infile1" type="data" format="tabular" label="Training samples dataset:"/>
339 <param name="col1" multiple="@MULTIPLE1@" type="data_column" data_ref="infile1" label="Select target column(s):"/>
340 <param name="infile2" type="data" format="tabular" label="Dataset containing class labels:"/>
341 <param name="col2" multiple="@MULTIPLE2@" type="data_column" data_ref="infile2" label="Select target column(s):"/>
342 <yield/>
343 </xml>
344
345 <xml name="clf_inputs_extended" token_label1=" " token_label2=" " token_multiple="False">
346 <conditional name="true_columns">
347 <param name="selected_input1" type="select" label="Select the input type of true labels dataset:">
348 <option value="tabular" selected="true">Tabular</option>
349 <option value="sparse">Sparse</option>
350 </param>
351 <when value="tabular">
352 <param name="infile1" type="data" label="@LABEL1@"/>
353 <param name="col1" type="data_column" data_ref="infile1" label="Select the target column:"/>
354 </when>
355 <when value="sparse">
356 <param name="infile1" type="data" format="txt" label="@LABEL1@"/>
357 </when>
358 </conditional>
359 <conditional name="predicted_columns">
360 <param name="selected_input2" type="select" label="Select the input type of predicted labels dataset:">
361 <option value="tabular" selected="true">Tabular</option>
362 <option value="sparse">Sparse</option>
363 </param>
364 <when value="tabular">
365 <param name="infile2" type="data" label="@LABEL2@"/>
366 <param name="col2" multiple="@MULTIPLE@" type="data_column" data_ref="infile2" label="Select target column(s):"/>
367 </when>
368 <when value="sparse">
369 <param name="infile2" type="data" format="txt" label="@LABEL1@"/>
370 </when>
371 </conditional>
372 </xml>
373
374 <xml name="clf_inputs" token_label1="Dataset containing true labels (tabular):" token_label2="Dataset containing predicted values (tabular):" token_multiple1="False" token_multiple="False">
375 <param name="infile1" type="data" format="tabular" label="@LABEL1@"/>
376 <param name="col1" multiple="@MULTIPLE1@" type="data_column" data_ref="infile1" label="Select the target column:"/>
377 <param name="infile2" type="data" format="tabular" label="@LABEL2@"/>
378 <param name="col2" multiple="@MULTIPLE@" type="data_column" data_ref="infile2" label="Select target column(s):"/>
379 </xml>
380
381 <xml name="multiple_input" token_name="input_files" token_max_num="10" token_format="txt" token_label="Sparse matrix file (.mtx, .txt)" token_help_text="Specify a sparse matrix file in .txt format.">
382 <repeat name="@NAME@" min="1" max="@MAX_NUM@" title="Select input file(s):">
383 <param name="input" type="data" format="@FORMAT@" label="@LABEL@" help="@HELP_TEXT@"/>
384 </repeat>
385 </xml>
386
387 <xml name="sparse_target" token_label1="Select a sparse matrix:" token_label2="Select the tabular containing true labels:" token_multiple="False" token_format1="txt" token_format2="tabular" token_help1="" token_help2="">
388 <param name="infile1" type="data" format="@FORMAT1@" label="@LABEL1@" help="@HELP1@"/>
389 <param name="infile2" type="data" format="@FORMAT2@" label="@LABEL2@" help="@HELP2@"/>
390 <param name="col2" multiple="@MULTIPLE@" type="data_column" data_ref="infile2" label="Select target column(s):"/>
391 </xml>
392
393 <xml name="sl_mixed_input">
394 <conditional name="input_options">
395 <param name="selected_input" type="select" label="Select input type:">
396 <option value="tabular" selected="true">tabular data</option>
397 <option value="sparse">sparse matrix</option>
398 </param>
399 <when value="tabular">
400 <expand macro="samples_tabular" multiple1="true"/>
401 </when>
402 <when value="sparse">
403 <expand macro="sparse_target"/>
404 </when>
405 </conditional>
406 </xml>
407
408 <xml name="multitype_input" token_format="tabular" token_help="All datasets with tabular format are supporetd.">
409 <param name="infile_transform" type="data" format="@FORMAT@" label="Select a dataset to transform:" help="@HELP@"/>
410 </xml>
411
412
413 <!--Advanced options-->
414 <xml name="nn_advanced_options">
415 <section name="options" title="Advanced Options" expanded="False">
416 <yield/>
417 <param argument="weights" type="select" label="Weight function" help="Used in prediction.">
418 <option value="uniform" selected="true">Uniform weights. All points in each neighborhood are weighted equally. (Uniform)</option>
419 <option value="distance">Weight points by the inverse of their distance. (Distance)</option>
420 </param>
421 <param argument="algorithm" type="select" label="Neighbor selection algorithm" help=" ">
422 <option value="auto" selected="true">Auto</option>
423 <option value="ball_tree">BallTree</option>
424 <option value="kd_tree">KDTree</option>
425 <option value="brute">Brute-force</option>
426 </param>
427 <param argument="leaf_size" type="integer" value="30" label="Leaf size" help="Used with BallTree and KDTree. Affects the time and memory usage of the constructed tree."/>
428 <!--param name="metric"-->
429 <!--param name="p"-->
430 <!--param name="metric_params"-->
431 </section>
432 </xml>
433
434 <xml name="svc_advanced_options">
435 <section name="options" title="Advanced Options" expanded="False">
436 <yield/>
437 <param argument="kernel" type="select" optional="true" label="Kernel type" help="Kernel type to be used in the algorithm. If none is given, ‘rbf’ will be used.">
438 <option value="rbf" selected="true">rbf</option>
439 <option value="linear">linear</option>
440 <option value="poly">poly</option>
441 <option value="sigmoid">sigmoid</option>
442 <option value="precomputed">precomputed</option>
443 </param>
444 <param argument="degree" type="integer" optional="true" value="3" label="Degree of the polynomial (polynomial kernel only)" help="Ignored by other kernels. dafault : 3 "/>
445 <!--TODO: param argument="gamma" float, optional (default=’auto’) -->
446 <param argument="coef0" type="float" optional="true" value="0.0" label="Zero coefficient (polynomial and sigmoid kernels only)"
447 help="Independent term in kernel function. dafault: 0.0 "/>
448 <param argument="shrinking" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolfalse" checked="true"
449 label="Use the shrinking heuristic" help=" "/>
450 <param argument="probability" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolfalse" checked="false"
451 label="Enable probability estimates. " help="This must be enabled prior to calling fit, and will slow down that method."/>
452 <!-- param argument="cache_size"-->
453 <!--expand macro="class_weight"/-->
454 <expand macro="tol" default_value="0.001" help_text="Tolerance for stopping criterion. "/>
455 <expand macro="max_iter" default_value="-1" label="Solver maximum number of iterations" help_text="Hard limit on iterations within solver, or -1 for no limit."/>
456 <!--param argument="decision_function_shape"-->
457 <expand macro="random_state" help_text="Integer number. The seed of the pseudo random number generator to use when shuffling the data for probability estimation. A fixed seed allows reproducible results."/>
458 </section>
459 </xml>
460
461 <xml name="spectral_clustering_advanced_options">
462 <section name="options" title="Advanced Options" expanded="False">
463 <expand macro="n_clusters"/>
464 <param argument="eigen_solver" type="select" value="" label="Eigen solver" help="The eigenvalue decomposition strategy to use.">
465 <option value="arpack" selected="true">arpack</option>
466 <option value="lobpcg">lobpcg</option>
467 <option value="amg">amg</option>
468 <!--None-->
469 </param>
470 <expand macro="random_state"/>
471 <expand macro="n_init"/>
472 <param argument="gamma" type="float" optional="true" value="1.0" label="Kernel scaling factor" help="Scaling factor of RBF, polynomial, exponential chi^2 and sigmoid affinity kernel. Ignored for affinity=''nearest_neighbors''."/>
473 <param argument="affinity" type="select" label="Affinity" help="Affinity kernel to use. ">
474 <option value="rbf" selected="true">RBF</option>
475 <option value="precomputed">precomputed</option>
476 <option value="nearest_neighbors">Nearset neighbors</option>
477 </param>
478 <param argument="n_neighbors" type="integer" optional="true" value="10" label="Number of neighbors" help="Number of neighbors to use when constructing the affinity matrix using the nearest neighbors method. Ignored for affinity=''rbf''"/>
479 <!--param argument="eigen_tol"-->
480 <param argument="assign_labels" type="select" label="Assign labels" help="The strategy to use to assign labels in the embedding space.">
481 <option value="kmeans" selected="true">kmeans</option>
482 <option value="discretize">discretize</option>
483 </param>
484 <param argument="degree" type="integer" optional="true" value="3"
485 label="Degree of the polynomial (polynomial kernel only)" help="Ignored by other kernels. dafault : 3 "/>
486 <param argument="coef0" type="integer" optional="true" value="1"
487 label="Zero coefficient (polynomial and sigmoid kernels only)" help="Ignored by other kernels. dafault : 1 "/>
488 <!--param argument="kernel_params"-->
489 </section>
490 </xml>
491
492 <xml name="minibatch_kmeans_advanced_options">
493 <section name="options" title="Advanced Options" expanded="False">
494 <expand macro="n_clusters"/>
495 <expand macro="init"/>
496 <expand macro="n_init" default_value="3"/>
497 <expand macro="max_iter" default_value="100"/>
498 <expand macro="tol" help_text="Early stopping heuristics based on normalized center change. To disable set to 0.0 ."/>
499 <expand macro="random_state"/>
500 <param argument="batch_size" type="integer" optional="true" value="100" label="Batch size" help="Size of the mini batches."/>
501 <!--param argument="compute_labels"-->
502 <param argument="max_no_improvement" type="integer" optional="true" value="10" label="Maximum number of improvement attempts" help="
503 Convergence detection based on inertia (the consecutive number of mini batches that doe not yield an improvement on the smoothed inertia).
504 To disable, set max_no_improvement to None. "/>
505 <param argument="init_size" type="integer" optional="true" value="" label="Number of random initialization samples" help="Number of samples to randomly sample for speeding up the initialization . ( default: 3 * batch_size )"/>
506 <param argument="reassignment_ratio" type="float" optional="true" value="0.01" label="Re-assignment ratio" help="Controls the fraction of the maximum number of counts for a center to be reassigned. Higher values yield better clustering results."/>
507 </section>
508 </xml>
509
510 <xml name="kmeans_advanced_options">
511 <section name="options" title="Advanced Options" expanded="False">
512 <expand macro="n_clusters"/>
513 <expand macro="init"/>
514 <expand macro="n_init"/>
515 <expand macro="max_iter"/>
516 <expand macro="tol" default_value="0.0001" help_text="Relative tolerance with regards to inertia to declare convergence."/>
517 <!--param argument="precompute_distances"/-->
518 <expand macro="random_state"/>
519 <param argument="copy_x" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolfalse" checked="true" label="Use a copy of data for precomputing distances" help="Mofifying the original data introduces small numerical differences caused by subtracting and then adding the data mean."/>
520 </section>
521 </xml>
522
523 <xml name="birch_advanced_options">
524 <section name="options" title="Advanced Options" expanded="False">
525 <param argument="threshold" type="float" optional="true" value="0.5" label="Subcluster radius threshold" help="The radius of the subcluster obtained by merging a new sample; the closest subcluster should be less than the threshold to avoid a new subcluster."/>
526 <param argument="branching_factor" type="integer" optional="true" value="50" label="Maximum number of subclusters per branch" help="Maximum number of CF subclusters in each node."/>
527 <expand macro="n_clusters" default_value="3"/>
528 <!--param argument="compute_labels"/-->
529 </section>
530 </xml>
531
532 <xml name="dbscan_advanced_options">
533 <section name="options" title="Advanced Options" expanded="False">
534 <param argument="eps" type="float" optional="true" value="0.5" label="Maximum neighborhood distance" help="The maximum distance between two samples for them to be considered as in the same neighborhood."/>
535 <param argument="min_samples" type="integer" optional="true" value="5" label="Minimal core point density" help="The number of samples (or total weight) in a neighborhood for a point (including the point itself) to be considered as a core point."/>
536 <param argument="metric" type="text" optional="true" value="euclidean" label="Metric" help="The metric to use when calculating distance between instances in a feature array."/>
537 <param argument="algorithm" type="select" label="Pointwise distance computation algorithm" help="The algorithm to be used by the NearestNeighbors module to compute pointwise distances and find nearest neighbors.">
538 <option value="auto" selected="true">auto</option>
539 <option value="ball_tree">ball_tree</option>
540 <option value="kd_tree">kd_tree</option>
541 <option value="brute">brute</option>
542 </param>
543 <param argument="leaf_size" type="integer" optional="true" value="30" label="Leaf size" help="Leaf size passed to BallTree or cKDTree. Memory and time efficieny factor in tree constrution and querying."/>
544 </section>
545 </xml>
546
547 <xml name="clustering_algorithms_options">
548 <conditional name="algorithm_options">
549 <param name="selected_algorithm" type="select" label="Clustering Algorithm">
550 <option value="KMeans" selected="true">KMeans</option>
551 <option value="SpectralClustering">Spectral Clustering</option>
552 <option value="MiniBatchKMeans">Mini Batch KMeans</option>
553 <option value="DBSCAN">DBSCAN</option>
554 <option value="Birch">Birch</option>
555 </param>
556 <when value="KMeans">
557 <expand macro="kmeans_advanced_options"/>
558 </when>
559 <when value="DBSCAN">
560 <expand macro="dbscan_advanced_options"/>
561 </when>
562 <when value="Birch">
563 <expand macro="birch_advanced_options"/>
564 </when>
565 <when value="SpectralClustering">
566 <expand macro="spectral_clustering_advanced_options"/>
567 </when>
568 <when value="MiniBatchKMeans">
569 <expand macro="minibatch_kmeans_advanced_options"/>
570 </when>
571 </conditional>
572 </xml>
573
574 <xml name="distance_metrics">
575 <param argument="metric" type="select" label="Distance metric" help=" ">
576 <option value="euclidean" selected="true">euclidean</option>
577 <option value="cityblock">cityblock</option>
578 <option value="cosine">cosine</option>
579 <option value="l1">l1</option>
580 <option value="l2">l2</option>
581 <option value="manhattan">manhattan</option>
582 <yield/>
583 </param>
584 </xml>
585
586 <xml name="distance_nonsparse_metrics">
587 <option value="braycurtis">braycurtis</option>
588 <option value="canberra">canberra</option>
589 <option value="chebyshev">chebyshev</option>
590 <option value="correlation">correlation</option>
591 <option value="dice">dice</option>
592 <option value="hamming">hamming</option>
593 <option value="jaccard">jaccard</option>
594 <option value="kulsinski">kulsinski</option>
595 <option value="mahalanobis">mahalanobis</option>
596 <option value="matching">matching</option>
597 <option value="minkowski">minkowski</option>
598 <option value="rogerstanimoto">rogerstanimoto</option>
599 <option value="russellrao">russellrao</option>
600 <option value="seuclidean">seuclidean</option>
601 <option value="sokalmichener">sokalmichener</option>
602 <option value="sokalsneath">sokalsneath</option>
603 <option value="sqeuclidean">sqeuclidean</option>
604 <option value="yule">yule</option>
605 </xml>
606
607 <xml name="pairwise_kernel_metrics">
608 <param argument="metric" type="select" label="Pirwise Kernel metric" help=" ">
609 <option value="rbf" selected="true">rbf</option>
610 <option value="sigmoid">sigmoid</option>
611 <option value="polynomial">polynomial</option>
612 <option value="linear" selected="true">linear</option>
613 <option value="chi2">chi2</option>
614 <option value="additive_chi2">additive_chi2</option>
615 </param>
616 </xml>
617
618 <xml name="sparse_pairwise_metric_functions">
619 <param name="selected_metric_function" type="select" label="Select the pairwise metric you want to compute:">
620 <option value="euclidean_distances" selected="true">Euclidean distance matrix</option>
621 <option value="pairwise_distances">Distance matrix</option>
622 <option value="pairwise_distances_argmin">Minimum distances between one point and a set of points</option>
623 <yield/>
624 </param>
625 </xml>
626
627 <xml name="pairwise_metric_functions">
628 <option value="additive_chi2_kernel" >Additive chi-squared kernel</option>
629 <option value="chi2_kernel">Exponential chi-squared kernel</option>
630 <option value="linear_kernel">Linear kernel</option>
631 <option value="manhattan_distances">L1 distances</option>
632 <option value="pairwise_kernels">Kernel</option>
633 <option value="polynomial_kernel">Polynomial kernel</option>
634 <option value="rbf_kernel">Gaussian (rbf) kernel</option>
635 <option value="laplacian_kernel">Laplacian kernel</option>
636 </xml>
637
638 <xml name="sparse_pairwise_condition">
639 <when value="pairwise_distances">
640 <section name="options" title="Advanced Options" expanded="False">
641 <expand macro="distance_metrics">
642 <yield/>
643 </expand>
644 </section>
645 </when>
646 <when value="euclidean_distances">
647 <section name="options" title="Advanced Options" expanded="False">
648 <param argument="squared" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolfalse" checked="false"
649 label="Return squared Euclidean distances" help=" "/>
650 </section>
651 </when>
652 </xml>
653
654 <xml name="argmin_distance_condition">
655 <when value="pairwise_distances_argmin">
656 <section name="options" title="Advanced Options" expanded="False">
657 <param argument="axis" type="integer" optional="true" value="1" label="Axis" help="Axis along which the argmin and distances are to be computed."/>
658 <expand macro="distance_metrics">
659 <yield/>
660 </expand>
661 <param argument="batch_size" type="integer" optional="true" value="500" label="Batch size" help="Number of rows to be processed in each batch run."/>
662 </section>
663 </when>
664 </xml>
665
666 <xml name="sparse_preprocessors">
667 <param name="selected_pre_processor" type="select" label="Select a preprocessor:">
668 <option value="StandardScaler" selected="true">Standard Scaler (Standardizes features by removing the mean and scaling to unit variance)</option>
669 <option value="Binarizer">Binarizer (Binarizes data)</option>
670 <option value="Imputer">Imputer (Completes missing values)</option>
671 <option value="MaxAbsScaler">Max Abs Scaler (Scales features by their maximum absolute value)</option>
672 <option value="Normalizer">Normalizer (Normalizes samples individually to unit norm)</option>
673 <yield/>
674 </param>
675 </xml>
676
677 <xml name="sparse_preprocessor_options">
678 <when value="Binarizer">
679 <expand macro="multitype_input" format="tabular,txt" help="Tabular and sparse datasets are supporetd."/>
680 <section name="options" title="Advanced Options" expanded="False">
681 <param argument="copy" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolfalse" checked="true"
682 label="Use a copy of data for precomputing binarization" help=" "/>
683 <param argument="threshold" type="float" optional="true" value="0.0"
684 label="Threshold"
685 help="Feature values below or equal to this are replaced by 0, above it by 1. Threshold may not be less than 0 for operations on sparse matrices. "/>
686 </section>
687 </when>
688 <when value="Imputer">
689 <expand macro="multitype_input" format="tabular,txt" help="Tabular and sparse datasets are supporetd."/>
690 <section name="options" title="Advanced Options" expanded="False">
691 <param argument="copy" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolfalse" checked="true"
692 label="Use a copy of data for precomputing imputation" help=" "/>
693 <param argument="strategy" type="select" optional="true" label="Imputation strategy" help=" ">
694 <option value="mean" selected="true">Replace missing values using the mean along the axis</option>
695 <option value="median">Replace missing values using the median along the axis</option>
696 <option value="most_frequent">Replace missing using the most frequent value along the axis</option>
697 </param>
698 <param argument="missing_values" type="text" optional="true" value="NaN"
699 label="Placeholder for missing values" help="For missing values encoded as numpy.nan, use the string value “NaN”"/>
700 <param argument="axis" type="boolean" optional="true" truevalue="1" falsevalue="0"
701 label="Impute along axis = 1" help="If fasle, axis = 0 is selected for imputation. "/>
702 <!--param argument="axis" type="select" optional="true" label="The axis along which to impute" help=" ">
703 <option value="0" selected="true">Impute along columns</option>
704 <option value="1">Impute along rows</option>
705 </param-->
706 </section>
707 </when>
708 <when value="StandardScaler">
709 <expand macro="multitype_input"/>
710 <section name="options" title="Advanced Options" expanded="False">
711 <param argument="copy" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolfalse" checked="true"
712 label="Use a copy of data for performing inplace scaling" help=" "/>
713 <param argument="with_mean" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolfalse" checked="true"
714 label="Center the data before scaling" help=" "/>
715 <param argument="with_std" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolfalse" checked="true"
716 label="Scale the data to unit variance (or unit standard deviation)" help=" "/>
717 </section>
718 </when>
719 <when value="MaxAbsScaler">
720 <expand macro="multitype_input" format="tabular,txt" help="Tabular and sparse datasets are supporetd."/>
721 <section name="options" title="Advanced Options" expanded="False">
722 <param argument="copy" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolfalse" checked="true"
723 label="Use a copy of data for precomputing scaling" help=" "/>
724 </section>
725 </when>
726 <when value="Normalizer">
727 <expand macro="multitype_input" format="tabular,txt" help="Tabular and sparse datasets are supporetd."/>
728 <section name="options" title="Advanced Options" expanded="False">
729 <param argument="norm" type="select" optional="true" label="The norm to use to normalize non zero samples" help=" ">
730 <option value="l1" selected="true">l1</option>
731 <option value="l2">l2</option>
732 <option value="max">max</option>
733 </param>
734 <param argument="copy" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolfalse" checked="true"
735 label="Use a copy of data for precomputing row normalization" help=" "/>
736 </section>
737 </when>
738 <yield/>
739 </xml>
740
741 <!-- Outputs -->
742
743 <xml name="output">
744 <outputs>
745 <data format="tabular" name="outfile_predict">
746 <filter>selected_tasks['selected_task'] == 'load'</filter>
747 </data>
748 <data format="zip" name="outfile_fit">
749 <filter>selected_tasks['selected_task'] == 'train'</filter>
750 </data>
751 </outputs>
752 </xml>
753
754
755 <!--Citations-->
756 <xml name="eden_citation">
757 <citations>
758 <citation type="bibtex">
759 @misc{fabrizio_costa_2015_15094,
760 author = {Fabrizio Costa and
761 Björn Grüning and
762 gigolo},
763 title = {EDeN: EDeN - Graph Vectorizer},
764 month = feb,
765 year = 2015,
766 doi = {10.5281/zenodo.15094},
767 url = {http://dx.doi.org/10.5281/zenodo.15094}
768 }
769 }
770 </citation>
771 </citations>
772 </xml>
773
774 <xml name="sklearn_citation">
775 <citations>
776 <citation type="bibtex">
777 @article{scikit-learn,
778 title={Scikit-learn: Machine Learning in {P}ython},
779 author={Pedregosa, F. and Varoquaux, G. and Gramfort, A. and Michel, V.
780 and Thirion, B. and Grisel, O. and Blondel, M. and Prettenhofer, P.
781 and Weiss, R. and Dubourg, V. and Vanderplas, J. and Passos, A. and
782 Cournapeau, D. and Brucher, M. and Perrot, M. and Duchesnay, E.},
783 journal={Journal of Machine Learning Research},
784 volume={12},
785 pages={2825--2830},
786 year={2011}
787 url = {https://github.com/scikit-learn/scikit-learn}
788 }
789 </citation>
790 </citations>
791 </xml>
792
793 <xml name="scipy_citation">
794 <citations>
795 <citation type="bibtex">
796 @Misc{,
797 author = {Eric Jones and Travis Oliphant and Pearu Peterson and others},
798 title = {{SciPy}: Open source scientific tools for {Python}},
799 year = {2001--},
800 url = "http://www.scipy.org/",
801 note = {[Online; accessed 2016-04-09]}
802 }
803 </citation>
804 </citations>
805 </xml>
806
807 </macros>