comparison main_macros.xml @ 0:b7d0fc23bfe4 draft

planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/sklearn commit 8cbb681224f23fa95783514f949c97d6c2c60966
author bgruening
date Sat, 04 Aug 2018 12:49:47 -0400
parents
children 23fb598a09d7
comparison
equal deleted inserted replaced
-1:000000000000 0:b7d0fc23bfe4
1 <macros>
2 <token name="@VERSION@">0.9</token>
3
4 <token name="@COLUMNS_FUNCTION@">
5 def read_columns(f, c=None, c_option='by_index_number', return_df=False, **args):
6 data = pandas.read_csv(f, **args)
7 if c_option == 'by_index_number':
8 cols = list(map(lambda x: x - 1, c))
9 data = data.iloc[:,cols]
10 if c_option == 'all_but_by_index_number':
11 cols = list(map(lambda x: x - 1, c))
12 data.drop(data.columns[cols], axis=1, inplace=True)
13 if c_option == 'by_header_name':
14 cols = [e.strip() for e in c.split(',')]
15 data = data[cols]
16 if c_option == 'all_but_by_header_name':
17 cols = [e.strip() for e in c.split(',')]
18 data.drop(cols, axis=1, inplace=True)
19 y = data.values
20 if return_df:
21 return y, data
22 else:
23 return y
24 return y
25 </token>
26
27 ## generate an instance for one of sklearn.feature_selection classes
28 <token name="@FEATURE_SELECTOR_FUNCTION@">
29 def feature_selector(inputs):
30 selector = inputs["selected_algorithm"]
31 selector = getattr(sklearn.feature_selection, selector)
32 options = inputs["options"]
33
34 if inputs['selected_algorithm'] == 'SelectFromModel':
35 if not options['threshold'] or options['threshold'] == 'None':
36 options['threshold'] = None
37 if inputs['model_inputter']['input_mode'] == 'prefitted':
38 model_file = inputs['model_inputter']['fitted_estimator']
39 with open(model_file, 'rb') as model_handler:
40 fitted_estimator = pickle.load(model_handler)
41 new_selector = selector(fitted_estimator, prefit=True, **options)
42 else:
43 estimator_json = inputs['model_inputter']["estimator_selector"]
44 estimator = get_estimator(estimator_json)
45 new_selector = selector(estimator, **options)
46
47 elif inputs['selected_algorithm'] in ['RFE', 'RFECV']:
48 if 'scoring' in options and (not options['scoring'] or options['scoring'] == 'None'):
49 options['scoring'] = None
50 estimator=get_estimator(inputs["estimator_selector"])
51 new_selector = selector(estimator, **options)
52
53 elif inputs['selected_algorithm'] == "VarianceThreshold":
54 new_selector = selector(**options)
55
56 else:
57 score_func = inputs["score_func"]
58 score_func = getattr(sklearn.feature_selection, score_func)
59 new_selector = selector(score_func, **options)
60
61 return new_selector
62 </token>
63
64 <token name="@GET_X_y_FUNCTION@">
65 def get_X_y(params, file1, file2):
66 input_type = params["selected_tasks"]["selected_algorithms"]["input_options"]["selected_input"]
67 if input_type=="tabular":
68 header = 'infer' if params["selected_tasks"]["selected_algorithms"]["input_options"]["header1"] else None
69 column_option = params["selected_tasks"]["selected_algorithms"]["input_options"]["column_selector_options_1"]["selected_column_selector_option"]
70 if column_option in ["by_index_number", "all_but_by_index_number", "by_header_name", "all_but_by_header_name"]:
71 c = params["selected_tasks"]["selected_algorithms"]["input_options"]["column_selector_options_1"]["col1"]
72 else:
73 c = None
74 X = read_columns(
75 file1,
76 c = c,
77 c_option = column_option,
78 sep='\t',
79 header=header,
80 parse_dates=True
81 )
82 else:
83 X = mmread(file1)
84
85 header = 'infer' if params["selected_tasks"]["selected_algorithms"]["input_options"]["header2"] else None
86 column_option = params["selected_tasks"]["selected_algorithms"]["input_options"]["column_selector_options_2"]["selected_column_selector_option2"]
87 if column_option in ["by_index_number", "all_but_by_index_number", "by_header_name", "all_but_by_header_name"]:
88 c = params["selected_tasks"]["selected_algorithms"]["input_options"]["column_selector_options_2"]["col2"]
89 else:
90 c = None
91 y = read_columns(
92 file2,
93 c = c,
94 c_option = column_option,
95 sep='\t',
96 header=header,
97 parse_dates=True
98 )
99 y=y.ravel()
100 return X, y
101 </token>
102
103 <token name="@GET_SEARCH_PARAMS_FUNCTION@">
104 def get_search_params(params_builder):
105 search_params = {}
106
107 def safe_eval(literal):
108
109 FROM_SCIPY_STATS = [ 'bernoulli', 'binom', 'boltzmann', 'dlaplace', 'geom', 'hypergeom',
110 'logser', 'nbinom', 'planck', 'poisson', 'randint', 'skellam', 'zipf' ]
111
112 FROM_NUMPY_RANDOM = [ 'beta', 'binomial', 'bytes', 'chisquare', 'choice', 'dirichlet', 'division',
113 'exponential', 'f', 'gamma', 'geometric', 'gumbel', 'hypergeometric',
114 'laplace', 'logistic', 'lognormal', 'logseries', 'mtrand', 'multinomial',
115 'multivariate_normal', 'negative_binomial', 'noncentral_chisquare', 'noncentral_f',
116 'normal', 'pareto', 'permutation', 'poisson', 'power', 'rand', 'randint',
117 'randn', 'random', 'random_integers', 'random_sample', 'ranf', 'rayleigh',
118 'sample', 'seed', 'set_state', 'shuffle', 'standard_cauchy', 'standard_exponential',
119 'standard_gamma', 'standard_normal', 'standard_t', 'triangular', 'uniform',
120 'vonmises', 'wald', 'weibull', 'zipf' ]
121
122 # File opening and other unneeded functions could be dropped
123 UNWANTED = ['open', 'type', 'dir', 'id', 'str', 'repr']
124
125 # Allowed symbol table. Add more if needed.
126 new_syms = {
127 'np_arange': getattr(np, 'arange'),
128 'ensemble_ExtraTreesClassifier': getattr(ensemble, 'ExtraTreesClassifier')
129 }
130
131 syms = make_symbol_table(use_numpy=False, **new_syms)
132
133 for method in FROM_SCIPY_STATS:
134 syms['scipy_stats_' + method] = getattr(scipy.stats, method)
135
136 for func in FROM_NUMPY_RANDOM:
137 syms['np_random_' + func] = getattr(np.random, func)
138
139 for key in UNWANTED:
140 syms.pop(key, None)
141
142 aeval = Interpreter(symtable=syms, use_numpy=False, minimal=False,
143 no_if=True, no_for=True, no_while=True, no_try=True,
144 no_functiondef=True, no_ifexp=True, no_listcomp=False,
145 no_augassign=False, no_assert=True, no_delete=True,
146 no_raise=True, no_print=True)
147
148 return aeval(literal)
149
150 for p in params_builder['param_set']:
151 search_p = p['search_param_selector']['search_p']
152 if search_p.strip() == '':
153 continue
154 param_type = p['search_param_selector']['selected_param_type']
155
156 lst = search_p.split(":")
157 assert (len(lst) == 2), "Error, make sure there is one and only one colon in search parameter input."
158 literal = lst[1].strip()
159 ev = safe_eval(literal)
160 if param_type == "final_estimator_p":
161 search_params["estimator__" + lst[0].strip()] = ev
162 else:
163 search_params["preprocessing_" + param_type[5:6] + "__" + lst[0].strip()] = ev
164
165 return search_params
166 </token>
167
168 <token name="@GET_ESTIMATOR_FUNCTION@">
169 def get_estimator(estimator_json):
170 estimator_module = estimator_json['selected_module']
171 estimator_cls = estimator_json['selected_estimator']
172
173 if estimator_module == "xgboost":
174 cls = getattr(xgboost, estimator_cls)
175 else:
176 module = getattr(sklearn, estimator_module)
177 cls = getattr(module, estimator_cls)
178
179 estimator = cls()
180
181 estimator_params = estimator_json['text_params'].strip()
182 if estimator_params != "":
183 try:
184 params = ast.literal_eval('{' + estimator_params + '}')
185 except ValueError:
186 sys.exit("Unsupported parameter input: `%s`" %estimator_params)
187 estimator.set_params(**params)
188
189 return estimator
190 </token>
191
192 <xml name="python_requirements">
193 <requirements>
194 <requirement type="package" version="2.7">python</requirement>
195 <requirement type="package" version="0.19.1">scikit-learn</requirement>
196 <requirement type="package" version="0.22.0">pandas</requirement>
197 <requirement type="package" version="0.72.1">xgboost</requirement>
198 <yield />
199 </requirements>
200 </xml>
201
202 <xml name="macro_stdio">
203 <stdio>
204 <exit_code range="1:" level="fatal" description="Error occurred. Please check Tool Standard Error"/>
205 </stdio>
206 </xml>
207
208
209 <!--Generic interface-->
210
211 <xml name="sl_Conditional" token_train="tabular" token_data="tabular" token_model="txt">
212 <conditional name="selected_tasks">
213 <param name="selected_task" type="select" label="Select a Classification Task">
214 <option value="train" selected="true">Train a model</option>
215 <option value="load">Load a model and predict</option>
216 </param>
217 <when value="load">
218 <param name="infile_model" type="data" format="@MODEL@" label="Models" help="Select a model file."/>
219 <param name="infile_data" type="data" format="@DATA@" label="Data (tabular)" help="Select the dataset you want to classify."/>
220 <param name="header" type="boolean" optional="True" truevalue="booltrue" falsevalue="boolfalse" checked="False" label="Does the dataset contain header:" />
221 <conditional name="prediction_options">
222 <param name="prediction_option" type="select" label="Select the type of prediction">
223 <option value="predict">Predict class labels</option>
224 <option value="advanced">Include advanced options</option>
225 </param>
226 <when value="predict">
227 </when>
228 <when value="advanced">
229 </when>
230 </conditional>
231 </when>
232 <when value="train">
233 <conditional name="selected_algorithms">
234 <yield />
235 </conditional>
236 </when>
237 </conditional>
238 </xml>
239
240 <xml name="advanced_section">
241 <section name="options" title="Advanced Options" expanded="False">
242 <yield />
243 </section>
244 </xml>
245
246
247 <!--Generalized Linear Models-->
248 <xml name="loss" token_help=" " token_select="false">
249 <param argument="loss" type="select" label="Loss function" help="@HELP@">
250 <option value="squared_loss" selected="@SELECT@">squared loss</option>
251 <option value="huber">huber</option>
252 <option value="epsilon_insensitive">epsilon insensitive</option>
253 <option value="squared_epsilon_insensitive">squared epsilon insensitive</option>
254 <yield/>
255 </param>
256 </xml>
257
258 <xml name="penalty" token_help=" ">
259 <param argument="penalty" type="select" label="Penalty (regularization term)" help="@HELP@">
260 <option value="l2" selected="true">l2</option>
261 <option value="l1">l1</option>
262 <option value="elasticnet">elastic net</option>
263 <option value="none">none</option>
264 <yield/>
265 </param>
266 </xml>
267
268 <xml name="l1_ratio" token_default_value="0.15" token_help=" ">
269 <param argument="l1_ratio" type="float" value="@DEFAULT_VALUE@" label="Elastic Net mixing parameter" help="@HELP@"/>
270 </xml>
271
272 <xml name="epsilon" token_default_value="0.1" token_help="Used if loss is ‘huber’, ‘epsilon_insensitive’, or ‘squared_epsilon_insensitive’. ">
273 <param argument="epsilon" type="float" value="@DEFAULT_VALUE@" label="Epsilon (epsilon-sensitive loss functions only)" help="@HELP@"/>
274 </xml>
275
276 <xml name="learning_rate_s" token_help=" " token_selected1="false" token_selected2="false">
277 <param argument="learning_rate" type="select" optional="true" label="Learning rate schedule" help="@HELP@">
278 <option value="optimal" selected="@SELECTED1@">optimal</option>
279 <option value="constant">constant</option>
280 <option value="invscaling" selected="@SELECTED2@">inverse scaling</option>
281 <yield/>
282 </param>
283 </xml>
284
285 <xml name="eta0" token_default_value="0.0" token_help="Used with ‘constant’ or ‘invscaling’ schedules. ">
286 <param argument="eta0" type="float" value="@DEFAULT_VALUE@" label="Initial learning rate" help="@HELP@"/>
287 </xml>
288
289 <xml name="power_t" token_default_value="0.5" token_help=" ">
290 <param argument="power_t" type="float" value="@DEFAULT_VALUE@" label="Exponent for inverse scaling learning rate" help="@HELP@"/>
291 </xml>
292
293 <xml name="normalize" token_checked="false" token_help=" ">
294 <param argument="normalize" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolfalse" checked="@CHECKED@" label="Normalize samples before training" help=" "/>
295 </xml>
296
297 <xml name="copy_X" token_checked="true" token_help=" ">
298 <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. "/>
299 </xml>
300
301 <xml name="ridge_params">
302 <expand macro="normalize"/>
303 <expand macro="alpha" default_value="1.0"/>
304 <expand macro="fit_intercept"/>
305 <expand macro="max_iter" default_value=""/>
306 <expand macro="tol" default_value="0.001" help_text="Precision of the solution. "/>
307 <!--class_weight-->
308 <expand macro="copy_X"/>
309 <param argument="solver" type="select" value="" label="Solver to use in the computational routines" help=" ">
310 <option value="auto" selected="true">auto</option>
311 <option value="svd">svd</option>
312 <option value="cholesky">cholesky</option>
313 <option value="lsqr">lsqr</option>
314 <option value="sparse_cg">sparse_cg</option>
315 <option value="sag">sag</option>
316 </param>
317 <expand macro="random_state"/>
318 </xml>
319
320 <!--Ensemble methods-->
321 <xml name="n_estimators" token_default_value="10" token_help=" ">
322 <param argument="n_estimators" type="integer" optional="true" value="@DEFAULT_VALUE@" label="Number of trees in the forest" help="@HELP@"/>
323 </xml>
324
325 <xml name="max_depth" token_default_value="" token_help=" ">
326 <param argument="max_depth" type="integer" optional="true" value="@DEFAULT_VALUE@" label="Maximum depth of the tree" help="@HELP@"/>
327 </xml>
328
329 <xml name="min_samples_split" token_type="integer" token_default_value="2" token_help=" ">
330 <param argument="min_samples_split" type="@TYPE@" optional="true" value="@DEFAULT_VALUE@" label="Minimum number of samples required to split an internal node" help="@HELP@"/>
331 </xml>
332
333 <xml name="min_samples_leaf" token_type="integer" token_default_value="1" token_label="Minimum number of samples in newly created leaves" token_help=" ">
334 <param argument="min_samples_leaf" type="@TYPE@" optional="true" value="@DEFAULT_VALUE@" label="@LABEL@" help="@HELP@"/>
335 </xml>
336
337 <xml name="min_weight_fraction_leaf" token_default_value="0.0" token_help=" ">
338 <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@"/>
339 </xml>
340
341 <xml name="max_leaf_nodes" token_default_value="" token_help=" ">
342 <param argument="max_leaf_nodes" type="integer" optional="true" value="@DEFAULT_VALUE@" label="Maximum number of leaf nodes in best-first method" help="@HELP@"/>
343 </xml>
344
345 <xml name="min_impurity_decrease" token_default_value="0" token_help=" ">
346 <param argument="min_impurity_decrease" type="float" value="@DEFAULT_VALUE@" optional="true" label="The threshold value of impurity for stopping node splitting" help="@HELP@"/>
347 </xml>
348
349 <xml name="bootstrap" token_checked="true" token_help=" ">
350 <param argument="bootstrap" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolflase" checked="@CHECKED@" label="Use bootstrap samples for building trees." help="@HELP@"/>
351 </xml>
352
353 <xml name="criterion" token_help=" ">
354 <param argument="criterion" type="select" label="Function to measure the quality of a split" help=" ">
355 <option value="gini" selected="true">Gini impurity</option>
356 <option value="entropy">Information gain</option>
357 <yield/>
358 </param>
359 </xml>
360
361 <xml name="criterion2" token_help="">
362 <param argument="criterion" type="select" label="Function to measure the quality of a split" >
363 <option value="mse">mse - mean squared error</option>
364 <option value="mae">mae - mean absolute error</option>
365 <yield/>
366 </param>
367 </xml>
368
369 <xml name="oob_score" token_checked="false" token_help=" ">
370 <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@"/>
371 </xml>
372
373 <xml name="max_features">
374 <conditional name="select_max_features">
375 <param argument="max_features" type="select" label="max_features">
376 <option value="auto" selected="true">auto - max_features=n_features</option>
377 <option value="sqrt">sqrt - max_features=sqrt(n_features)</option>
378 <option value="log2">log2 - max_features=log2(n_features)</option>
379 <option value="number_input">I want to type the number in or input None type</option>
380 </param>
381 <when value="auto">
382 </when>
383 <when value="sqrt">
384 </when>
385 <when value="log2">
386 </when>
387 <when value="number_input">
388 <param name="num_max_features" type="float" value="" optional="true" label="Input max_features number:" help="If int, consider the number of features at each split; If float, then max_features is a percentage and int(max_features * n_features) features are considered at each split."/>
389 </when>
390 </conditional>
391 </xml>
392
393 <xml name="verbose" token_default_value="0" token_help="If 1 then it prints progress and performance once in a while. If greater than 1 then it prints progress and performance for every tree.">
394 <param argument="verbose" type="integer" value="@DEFAULT_VALUE@" optional="true" label="Enable verbose output" help="@HELP@"/>
395 </xml>
396
397 <xml name="learning_rate" token_default_value="1.0" token_help=" ">
398 <param argument="learning_rate" type="float" optional="true" value="@DEFAULT_VALUE@" label="Learning rate" help="@HELP@"/>
399 </xml>
400
401 <xml name="subsample" token_help=" ">
402 <param argument="subsample" type="float" value="1.0" optional="true" label="The fraction of samples to be used for fitting the individual base learners" help="@HELP@"/>
403 </xml>
404
405 <xml name="presort">
406 <param argument="presort" type="select" label="Whether to presort the data to speed up the finding of best splits in fitting" >
407 <option value="auto" selected="true">auto</option>
408 <option value="true">true</option>
409 <option value="false">false</option>
410 </param>
411 </xml>
412
413 <!--Parameters-->
414 <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.">
415 <param argument="tol" type="float" optional="true" value="@DEFAULT_VALUE@" label="Tolerance" help="@HELP_TEXT@"/>
416 </xml>
417
418 <xml name="n_clusters" token_default_value="8">
419 <param argument="n_clusters" type="integer" optional="true" value="@DEFAULT_VALUE@" label="Number of clusters" help=" "/>
420 </xml>
421
422 <xml name="fit_intercept" token_checked="true">
423 <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."/>
424 </xml>
425
426 <xml name="n_jobs" token_default_value="1" token_label="The number of jobs to run in parallel for both fit and predict">
427 <param argument="n_jobs" type="integer" value="@DEFAULT_VALUE@" optional="true" label="@LABEL@" help="If -1, then the number of jobs is set to the number of cores"/>
428 </xml>
429
430 <xml name="n_iter" token_default_value="5" token_help_text="The number of passes over the training data (aka epochs). ">
431 <param argument="n_iter" type="integer" optional="true" value="@DEFAULT_VALUE@" label="Number of iterations" help="@HELP_TEXT@"/>
432 </xml>
433
434 <xml name="shuffle" token_checked="true" token_help_text=" " token_label="Shuffle data after each iteration">
435 <param argument="shuffle" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolfalse" checked="@CHECKED@" label="@LABEL@" help="@HELP_TEXT@"/>
436 </xml>
437
438 <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.">
439 <param argument="random_state" type="integer" optional="true" value="@DEFAULT_VALUE@" label="Random seed number" help="@HELP_TEXT@"/>
440 </xml>
441
442 <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.">
443 <param argument="warm_start" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolfalse" checked="@CHECKED@" label="Perform warm start" help="@HELP_TEXT@"/>
444 </xml>
445
446 <xml name="C" token_default_value="1.0" token_help_text="Penalty parameter C of the error term.">
447 <param argument="C" type="float" optional="true" value="@DEFAULT_VALUE@" label="Penalty parameter" help="@HELP_TEXT@"/>
448 </xml>
449
450 <!--xml name="class_weight" token_default_value="" token_help_text="">
451 <param argument="class_weight" type="" optional="true" value="@DEFAULT_VALUE@" label="" help="@HELP_TEXT@"/>
452 </xml-->
453
454 <xml name="alpha" token_default_value="0.0001" token_help_text="Constant that multiplies the regularization term if regularization is used. ">
455 <param argument="alpha" type="float" optional="true" value="@DEFAULT_VALUE@" label="Regularization coefficient" help="@HELP_TEXT@"/>
456 </xml>
457
458 <xml name="n_samples" token_default_value="100" token_help_text="The total number of points equally divided among clusters.">
459 <param argument="n_samples" type="integer" optional="true" value="@DEFAULT_VALUE@" label="Number of samples" help="@HELP_TEXT@"/>
460 </xml>
461
462 <xml name="n_features" token_default_value="2" token_help_text="Number of different numerical properties produced for each sample.">
463 <param argument="n_features" type="integer" optional="true" value="@DEFAULT_VALUE@" label="Number of features" help="@HELP_TEXT@"/>
464 </xml>
465
466 <xml name="noise" token_default_value="0.0" token_help_text="Floating point number. ">
467 <param argument="noise" type="float" optional="true" value="@DEFAULT_VALUE@" label="Standard deviation of the Gaussian noise added to the data" help="@HELP_TEXT@"/>
468 </xml>
469
470 <xml name="C" token_default_value="1.0" token_help_text="Penalty parameter C of the error term. ">
471 <param argument="C" type="float" optional="true" value="@DEFAULT_VALUE@" label="Penalty parameter" help="@HELP_TEXT@"/>
472 </xml>
473
474 <xml name="max_iter" token_default_value="300" token_label="Maximum number of iterations per single run" token_help_text=" ">
475 <param argument="max_iter" type="integer" optional="true" value="@DEFAULT_VALUE@" label="@LABEL@" help="@HELP_TEXT@"/>
476 </xml>
477
478 <xml name="n_init" token_default_value="10" >
479 <param argument="n_init" type="integer" optional="true" value="@DEFAULT_VALUE@" label="Number of runs with different centroid seeds" help=" "/>
480 </xml>
481
482 <xml name="init">
483 <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.">
484 <option value="k-means++">k-means++</option>
485 <option value="random">random</option>
486 </param>
487 </xml>
488
489 <xml name="gamma" token_default_value="1.0" token_label="Scaling parameter" token_help_text=" ">
490 <param argument="gamma" type="float" optional="true" value="@DEFAULT_VALUE@" label="@LABEL@" help="@HELP_TEXT@"/>
491 </xml>
492
493 <xml name="degree" token_default_value="3" token_label="Degree of the polynomial" token_help_text=" ">
494 <param argument="degree" type="integer" optional="true" value="@DEFAULT_VALUE@" label="@LABEL@" help="@HELP_TEXT@"/>
495 </xml>
496
497 <xml name="coef0" token_default_value="1" token_label="Zero coefficient" token_help_text=" ">
498 <param argument="coef0" type="integer" optional="true" value="@DEFAULT_VALUE@" label="@LABEL@" help="@HELP_TEXT@"/>
499 </xml>
500
501 <xml name="pos_label" token_default_value="">
502 <param argument="pos_label" type="integer" optional="true" value="@DEFAULT_VALUE@" label="Label of the positive class" help=" "/>
503 </xml>
504
505 <xml name="average">
506 <param argument="average" type="select" optional="true" label="Averaging type" help=" ">
507 <option value="micro">Calculate metrics globally by counting the total true positives, false negatives and false positives. (micro)</option>
508 <option value="samples">Calculate metrics for each instance, and find their average. Only meaningful for multilabel. (samples)</option>
509 <option value="macro">Calculate metrics for each label, and find their unweighted mean. This does not take label imbalance into account. (macro)</option>
510 <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>
511 <option value="None">None</option>
512 <yield/>
513 </param>
514 </xml>
515
516 <xml name="beta">
517 <param argument="beta" type="float" value="1.0" label="The strength of recall versus precision in the F-score" help=" "/>
518 </xml>
519
520
521 <!--Data interface-->
522
523 <xml name="samples_tabular" token_multiple1="false" token_multiple2="false">
524 <param name="infile1" type="data" format="tabular" label="Training samples dataset:"/>
525 <param name="header1" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolfalse" checked="False" label="Does the dataset contain header:" />
526 <conditional name="column_selector_options_1">
527 <expand macro="samples_column_selector_options" multiple="@MULTIPLE1@"/>
528 </conditional>
529 <param name="infile2" type="data" format="tabular" label="Dataset containing class labels:"/>
530 <param name="header2" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolfalse" checked="False" label="Does the dataset contain header:" />
531 <conditional name="column_selector_options_2">
532 <expand macro="samples_column_selector_options" column_option="selected_column_selector_option2" col_name="col2" multiple="@MULTIPLE2@" infile="infile2"/>
533 </conditional>
534 <yield/>
535 </xml>
536
537 <xml name="samples_column_selector_options" token_column_option="selected_column_selector_option" token_col_name="col1" token_multiple="False" token_infile="infile1">
538 <param name="@COLUMN_OPTION@" type="select" label="Choose how to select data by column:">
539 <option value="by_index_number" selected="true">Select columns by column index number(s)</option>
540 <option value="by_header_name">Select columns by column header name(s)</option>
541 <option value="all_but_by_index_number">All columns but by column index number(s)</option>
542 <option value="all_but_by_header_name">All columns but by column header name(s)</option>
543 <option value="all_columns">All columns</option>
544 </param>
545 <when value="by_index_number">
546 <param name="@COL_NAME@" multiple="@MULTIPLE@" type="data_column" data_ref="@INFILE@" label="Select target column(s):"/>
547 </when>
548 <when value="by_header_name">
549 <param name="@COL_NAME@" type="text" value="" label="Type header name(s):" help="Comma-separated string. For example: target1,target2"/>
550 </when>
551 <when value="all_but_by_index_number">
552 <param name="@COL_NAME@" multiple="@MULTIPLE@" type="data_column" data_ref="@INFILE@" label="Select target column(s):"/>
553 </when>
554 <when value="all_but_by_header_name">
555 <param name="@COL_NAME@" type="text" value="" label="Type header name(s):" help="Comma-separated string. For example: target1,target2"/>
556 </when>
557 <when value="all_columns">
558 </when>
559 </xml>
560
561 <xml name="clf_inputs_extended" token_label1=" " token_label2=" " token_multiple="False">
562 <conditional name="true_columns">
563 <param name="selected_input1" type="select" label="Select the input type of true labels dataset:">
564 <option value="tabular" selected="true">Tabular</option>
565 <option value="sparse">Sparse</option>
566 </param>
567 <when value="tabular">
568 <param name="infile1" type="data" label="@LABEL1@"/>
569 <param name="col1" type="data_column" data_ref="infile1" label="Select the target column:"/>
570 </when>
571 <when value="sparse">
572 <param name="infile1" type="data" format="txt" label="@LABEL1@"/>
573 </when>
574 </conditional>
575 <conditional name="predicted_columns">
576 <param name="selected_input2" type="select" label="Select the input type of predicted labels dataset:">
577 <option value="tabular" selected="true">Tabular</option>
578 <option value="sparse">Sparse</option>
579 </param>
580 <when value="tabular">
581 <param name="infile2" type="data" label="@LABEL2@"/>
582 <param name="col2" multiple="@MULTIPLE@" type="data_column" data_ref="infile2" label="Select target column(s):"/>
583 </when>
584 <when value="sparse">
585 <param name="infile2" type="data" format="txt" label="@LABEL1@"/>
586 </when>
587 </conditional>
588 </xml>
589
590 <xml name="clf_inputs" token_label1="Dataset containing true labels (tabular):" token_label2="Dataset containing predicted values (tabular):" token_multiple1="False" token_multiple="False">
591 <param name="infile1" type="data" format="tabular" label="@LABEL1@"/>
592 <param name="header1" type="boolean" optional="True" truevalue="booltrue" falsevalue="boolfalse" checked="False" label="Does the dataset contain header:" />
593 <conditional name="column_selector_options_1">
594 <expand macro="samples_column_selector_options" multiple="@MULTIPLE1@"/>
595 </conditional>
596 <param name="infile2" type="data" format="tabular" label="@LABEL2@"/>
597 <param name="header2" type="boolean" optional="True" truevalue="booltrue" falsevalue="boolfalse" checked="False" label="Does the dataset contain header:" />
598 <conditional name="column_selector_options_2">
599 <expand macro="samples_column_selector_options" column_option="selected_column_selector_option2" col_name="col2" multiple="@MULTIPLE@" infile="infile2"/>
600 </conditional>
601 </xml>
602
603 <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.">
604 <repeat name="@NAME@" min="1" max="@MAX_NUM@" title="Select input file(s):">
605 <param name="input" type="data" format="@FORMAT@" label="@LABEL@" help="@HELP_TEXT@"/>
606 </repeat>
607 </xml>
608
609 <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="">
610 <param name="infile1" type="data" format="@FORMAT1@" label="@LABEL1@" help="@HELP1@"/>
611 <param name="infile2" type="data" format="@FORMAT2@" label="@LABEL2@" help="@HELP2@"/>
612 <param name="col2" multiple="@MULTIPLE@" type="data_column" data_ref="infile2" label="Select target column(s):"/>
613 </xml>
614
615 <xml name="sl_mixed_input">
616 <conditional name="input_options">
617 <param name="selected_input" type="select" label="Select input type:">
618 <option value="tabular" selected="true">tabular data</option>
619 <option value="sparse">sparse matrix</option>
620 </param>
621 <when value="tabular">
622 <expand macro="samples_tabular" multiple1="true"/>
623 </when>
624 <when value="sparse">
625 <expand macro="sparse_target"/>
626 </when>
627 </conditional>
628 </xml>
629
630 <!--Advanced options-->
631 <xml name="nn_advanced_options">
632 <section name="options" title="Advanced Options" expanded="False">
633 <yield/>
634 <param argument="weights" type="select" label="Weight function" help="Used in prediction.">
635 <option value="uniform" selected="true">Uniform weights. All points in each neighborhood are weighted equally. (Uniform)</option>
636 <option value="distance">Weight points by the inverse of their distance. (Distance)</option>
637 </param>
638 <param argument="algorithm" type="select" label="Neighbor selection algorithm" help=" ">
639 <option value="auto" selected="true">Auto</option>
640 <option value="ball_tree">BallTree</option>
641 <option value="kd_tree">KDTree</option>
642 <option value="brute">Brute-force</option>
643 </param>
644 <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."/>
645 <!--param name="metric"-->
646 <!--param name="p"-->
647 <!--param name="metric_params"-->
648 </section>
649 </xml>
650
651 <xml name="svc_advanced_options">
652 <section name="options" title="Advanced Options" expanded="False">
653 <yield/>
654 <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.">
655 <option value="rbf" selected="true">rbf</option>
656 <option value="linear">linear</option>
657 <option value="poly">poly</option>
658 <option value="sigmoid">sigmoid</option>
659 <option value="precomputed">precomputed</option>
660 </param>
661 <param argument="degree" type="integer" optional="true" value="3" label="Degree of the polynomial (polynomial kernel only)" help="Ignored by other kernels. dafault : 3 "/>
662 <!--TODO: param argument="gamma" float, optional (default=’auto’) -->
663 <param argument="coef0" type="float" optional="true" value="0.0" label="Zero coefficient (polynomial and sigmoid kernels only)"
664 help="Independent term in kernel function. dafault: 0.0 "/>
665 <param argument="shrinking" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolfalse" checked="true"
666 label="Use the shrinking heuristic" help=" "/>
667 <param argument="probability" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolfalse" checked="false"
668 label="Enable probability estimates. " help="This must be enabled prior to calling fit, and will slow down that method."/>
669 <!-- param argument="cache_size"-->
670 <!--expand macro="class_weight"/-->
671 <expand macro="tol" default_value="0.001" help_text="Tolerance for stopping criterion. "/>
672 <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."/>
673 <!--param argument="decision_function_shape"-->
674 <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."/>
675 </section>
676 </xml>
677
678 <xml name="spectral_clustering_advanced_options">
679 <section name="options" title="Advanced Options" expanded="False">
680 <expand macro="n_clusters"/>
681 <param argument="eigen_solver" type="select" value="" label="Eigen solver" help="The eigenvalue decomposition strategy to use.">
682 <option value="arpack" selected="true">arpack</option>
683 <option value="lobpcg">lobpcg</option>
684 <option value="amg">amg</option>
685 <!--None-->
686 </param>
687 <expand macro="random_state"/>
688 <expand macro="n_init"/>
689 <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''."/>
690 <param argument="affinity" type="select" label="Affinity" help="Affinity kernel to use. ">
691 <option value="rbf" selected="true">RBF</option>
692 <option value="precomputed">precomputed</option>
693 <option value="nearest_neighbors">Nearset neighbors</option>
694 </param>
695 <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''"/>
696 <!--param argument="eigen_tol"-->
697 <param argument="assign_labels" type="select" label="Assign labels" help="The strategy to use to assign labels in the embedding space.">
698 <option value="kmeans" selected="true">kmeans</option>
699 <option value="discretize">discretize</option>
700 </param>
701 <param argument="degree" type="integer" optional="true" value="3"
702 label="Degree of the polynomial (polynomial kernel only)" help="Ignored by other kernels. dafault : 3 "/>
703 <param argument="coef0" type="integer" optional="true" value="1"
704 label="Zero coefficient (polynomial and sigmoid kernels only)" help="Ignored by other kernels. dafault : 1 "/>
705 <!--param argument="kernel_params"-->
706 </section>
707 </xml>
708
709 <xml name="minibatch_kmeans_advanced_options">
710 <section name="options" title="Advanced Options" expanded="False">
711 <expand macro="n_clusters"/>
712 <expand macro="init"/>
713 <expand macro="n_init" default_value="3"/>
714 <expand macro="max_iter" default_value="100"/>
715 <expand macro="tol" help_text="Early stopping heuristics based on normalized center change. To disable set to 0.0 ."/>
716 <expand macro="random_state"/>
717 <param argument="batch_size" type="integer" optional="true" value="100" label="Batch size" help="Size of the mini batches."/>
718 <!--param argument="compute_labels"-->
719 <param argument="max_no_improvement" type="integer" optional="true" value="10" label="Maximum number of improvement attempts" help="
720 Convergence detection based on inertia (the consecutive number of mini batches that doe not yield an improvement on the smoothed inertia).
721 To disable, set max_no_improvement to None. "/>
722 <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 )"/>
723 <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."/>
724 </section>
725 </xml>
726
727 <xml name="kmeans_advanced_options">
728 <section name="options" title="Advanced Options" expanded="False">
729 <expand macro="n_clusters"/>
730 <expand macro="init"/>
731 <expand macro="n_init"/>
732 <expand macro="max_iter"/>
733 <expand macro="tol" default_value="0.0001" help_text="Relative tolerance with regards to inertia to declare convergence."/>
734 <!--param argument="precompute_distances"/-->
735 <expand macro="random_state"/>
736 <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."/>
737 </section>
738 </xml>
739
740 <xml name="birch_advanced_options">
741 <section name="options" title="Advanced Options" expanded="False">
742 <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."/>
743 <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."/>
744 <expand macro="n_clusters" default_value="3"/>
745 <!--param argument="compute_labels"/-->
746 </section>
747 </xml>
748
749 <xml name="dbscan_advanced_options">
750 <section name="options" title="Advanced Options" expanded="False">
751 <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."/>
752 <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."/>
753 <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."/>
754 <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.">
755 <option value="auto" selected="true">auto</option>
756 <option value="ball_tree">ball_tree</option>
757 <option value="kd_tree">kd_tree</option>
758 <option value="brute">brute</option>
759 </param>
760 <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."/>
761 </section>
762 </xml>
763
764 <xml name="clustering_algorithms_options">
765 <conditional name="algorithm_options">
766 <param name="selected_algorithm" type="select" label="Clustering Algorithm">
767 <option value="KMeans" selected="true">KMeans</option>
768 <option value="SpectralClustering">Spectral Clustering</option>
769 <option value="MiniBatchKMeans">Mini Batch KMeans</option>
770 <option value="DBSCAN">DBSCAN</option>
771 <option value="Birch">Birch</option>
772 </param>
773 <when value="KMeans">
774 <expand macro="kmeans_advanced_options"/>
775 </when>
776 <when value="DBSCAN">
777 <expand macro="dbscan_advanced_options"/>
778 </when>
779 <when value="Birch">
780 <expand macro="birch_advanced_options"/>
781 </when>
782 <when value="SpectralClustering">
783 <expand macro="spectral_clustering_advanced_options"/>
784 </when>
785 <when value="MiniBatchKMeans">
786 <expand macro="minibatch_kmeans_advanced_options"/>
787 </when>
788 </conditional>
789 </xml>
790
791 <xml name="distance_metrics">
792 <param argument="metric" type="select" label="Distance metric" help=" ">
793 <option value="euclidean" selected="true">euclidean</option>
794 <option value="cityblock">cityblock</option>
795 <option value="cosine">cosine</option>
796 <option value="l1">l1</option>
797 <option value="l2">l2</option>
798 <option value="manhattan">manhattan</option>
799 <yield/>
800 </param>
801 </xml>
802
803 <xml name="distance_nonsparse_metrics">
804 <option value="braycurtis">braycurtis</option>
805 <option value="canberra">canberra</option>
806 <option value="chebyshev">chebyshev</option>
807 <option value="correlation">correlation</option>
808 <option value="dice">dice</option>
809 <option value="hamming">hamming</option>
810 <option value="jaccard">jaccard</option>
811 <option value="kulsinski">kulsinski</option>
812 <option value="mahalanobis">mahalanobis</option>
813 <option value="matching">matching</option>
814 <option value="minkowski">minkowski</option>
815 <option value="rogerstanimoto">rogerstanimoto</option>
816 <option value="russellrao">russellrao</option>
817 <option value="seuclidean">seuclidean</option>
818 <option value="sokalmichener">sokalmichener</option>
819 <option value="sokalsneath">sokalsneath</option>
820 <option value="sqeuclidean">sqeuclidean</option>
821 <option value="yule">yule</option>
822 </xml>
823
824 <xml name="pairwise_kernel_metrics">
825 <param argument="metric" type="select" label="Pirwise Kernel metric" help=" ">
826 <option value="rbf" selected="true">rbf</option>
827 <option value="sigmoid">sigmoid</option>
828 <option value="polynomial">polynomial</option>
829 <option value="linear" selected="true">linear</option>
830 <option value="chi2">chi2</option>
831 <option value="additive_chi2">additive_chi2</option>
832 </param>
833 </xml>
834
835 <xml name="sparse_pairwise_metric_functions">
836 <param name="selected_metric_function" type="select" label="Select the pairwise metric you want to compute:">
837 <option value="euclidean_distances" selected="true">Euclidean distance matrix</option>
838 <option value="pairwise_distances">Distance matrix</option>
839 <option value="pairwise_distances_argmin">Minimum distances between one point and a set of points</option>
840 <yield/>
841 </param>
842 </xml>
843
844 <xml name="pairwise_metric_functions">
845 <option value="additive_chi2_kernel" >Additive chi-squared kernel</option>
846 <option value="chi2_kernel">Exponential chi-squared kernel</option>
847 <option value="linear_kernel">Linear kernel</option>
848 <option value="manhattan_distances">L1 distances</option>
849 <option value="pairwise_kernels">Kernel</option>
850 <option value="polynomial_kernel">Polynomial kernel</option>
851 <option value="rbf_kernel">Gaussian (rbf) kernel</option>
852 <option value="laplacian_kernel">Laplacian kernel</option>
853 </xml>
854
855 <xml name="sparse_pairwise_condition">
856 <when value="pairwise_distances">
857 <section name="options" title="Advanced Options" expanded="False">
858 <expand macro="distance_metrics">
859 <yield/>
860 </expand>
861 </section>
862 </when>
863 <when value="euclidean_distances">
864 <section name="options" title="Advanced Options" expanded="False">
865 <param argument="squared" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolfalse" checked="false"
866 label="Return squared Euclidean distances" help=" "/>
867 </section>
868 </when>
869 </xml>
870
871 <xml name="argmin_distance_condition">
872 <when value="pairwise_distances_argmin">
873 <section name="options" title="Advanced Options" expanded="False">
874 <param argument="axis" type="integer" optional="true" value="1" label="Axis" help="Axis along which the argmin and distances are to be computed."/>
875 <expand macro="distance_metrics">
876 <yield/>
877 </expand>
878 <param argument="batch_size" type="integer" optional="true" value="500" label="Batch size" help="Number of rows to be processed in each batch run."/>
879 </section>
880 </when>
881 </xml>
882
883 <xml name="sparse_preprocessors">
884 <param name="selected_pre_processor" type="select" label="Select a preprocessor:">
885 <option value="StandardScaler" selected="true">Standard Scaler (Standardizes features by removing the mean and scaling to unit variance)</option>
886 <option value="Binarizer">Binarizer (Binarizes data)</option>
887 <option value="Imputer">Imputer (Completes missing values)</option>
888 <option value="MaxAbsScaler">Max Abs Scaler (Scales features by their maximum absolute value)</option>
889 <option value="Normalizer">Normalizer (Normalizes samples individually to unit norm)</option>
890 <yield/>
891 </param>
892 </xml>
893
894 <xml name="sparse_preprocessors_ext">
895 <expand macro="sparse_preprocessors">
896 <option value="KernelCenterer">Kernel Centerer (Centers a kernel matrix)</option>
897 <option value="MinMaxScaler">Minmax Scaler (Scales features to a range)</option>
898 <option value="PolynomialFeatures">Polynomial Features (Generates polynomial and interaction features)</option>
899 <option value="RobustScaler">Robust Scaler (Scales features using outlier-invariance statistics)</option>
900 </expand>
901 </xml>
902
903 <xml name="sparse_preprocessor_options">
904 <when value="Binarizer">
905 <section name="options" title="Advanced Options" expanded="False">
906 <param argument="copy" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolfalse" checked="true"
907 label="Use a copy of data for precomputing binarization" help=" "/>
908 <param argument="threshold" type="float" optional="true" value="0.0"
909 label="Threshold"
910 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. "/>
911 </section>
912 </when>
913 <when value="Imputer">
914 <section name="options" title="Advanced Options" expanded="False">
915 <param argument="copy" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolfalse" checked="true"
916 label="Use a copy of data for precomputing imputation" help=" "/>
917 <param argument="strategy" type="select" optional="true" label="Imputation strategy" help=" ">
918 <option value="mean" selected="true">Replace missing values using the mean along the axis</option>
919 <option value="median">Replace missing values using the median along the axis</option>
920 <option value="most_frequent">Replace missing using the most frequent value along the axis</option>
921 </param>
922 <param argument="missing_values" type="text" optional="true" value="NaN"
923 label="Placeholder for missing values" help="For missing values encoded as numpy.nan, use the string value “NaN”"/>
924 <param argument="axis" type="boolean" optional="true" truevalue="1" falsevalue="0"
925 label="Impute along axis = 1" help="If fasle, axis = 0 is selected for imputation. "/>
926 <!--param argument="axis" type="select" optional="true" label="The axis along which to impute" help=" ">
927 <option value="0" selected="true">Impute along columns</option>
928 <option value="1">Impute along rows</option>
929 </param-->
930 </section>
931 </when>
932 <when value="StandardScaler">
933 <section name="options" title="Advanced Options" expanded="False">
934 <param argument="copy" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolfalse" checked="true"
935 label="Use a copy of data for performing inplace scaling" help=" "/>
936 <param argument="with_mean" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolfalse" checked="true"
937 label="Center the data before scaling" help=" "/>
938 <param argument="with_std" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolfalse" checked="true"
939 label="Scale the data to unit variance (or unit standard deviation)" help=" "/>
940 </section>
941 </when>
942 <when value="MaxAbsScaler">
943 <section name="options" title="Advanced Options" expanded="False">
944 <param argument="copy" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolfalse" checked="true"
945 label="Use a copy of data for precomputing scaling" help=" "/>
946 </section>
947 </when>
948 <when value="Normalizer">
949 <section name="options" title="Advanced Options" expanded="False">
950 <param argument="norm" type="select" optional="true" label="The norm to use to normalize non zero samples" help=" ">
951 <option value="l1" selected="true">l1</option>
952 <option value="l2">l2</option>
953 <option value="max">max</option>
954 </param>
955 <param argument="copy" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolfalse" checked="true"
956 label="Use a copy of data for precomputing row normalization" help=" "/>
957 </section>
958 </when>
959 <yield/>
960 </xml>
961
962 <xml name="sparse_preprocessor_options_ext">
963 <expand macro="sparse_preprocessor_options">
964 <when value="KernelCenterer">
965 <section name="options" title="Advanced Options" expanded="False">
966 </section>
967 </when>
968 <when value="MinMaxScaler">
969 <section name="options" title="Advanced Options" expanded="False">
970 <!--feature_range-->
971 <param argument="copy" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolflase" checked="true"
972 label="Use a copy of data for precomputing normalization" help=" "/>
973 </section>
974 </when>
975 <when value="PolynomialFeatures">
976 <section name="options" title="Advanced Options" expanded="False">
977 <param argument="degree" type="integer" optional="true" value="2" label="The degree of the polynomial features " help=""/>
978 <param argument="interaction_only" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolflase" checked="false" label="Produce interaction features only" help="(Features that are products of at most degree distinct input features) "/>
979 <param argument="include_bias" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolflase" checked="true" label="Include a bias column" help="Feature in which all polynomial powers are zero "/>
980 </section>
981 </when>
982 <when value="RobustScaler">
983 <section name="options" title="Advanced Options" expanded="False">
984 <!--=True, =True, copy=True-->
985 <param argument="with_centering" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolflase" checked="true"
986 label="Center the data before scaling" help=" "/>
987 <param argument="with_scaling" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolflase" checked="true"
988 label="Scale the data to interquartile range" help=" "/>
989 <param argument="copy" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolflase" checked="true"
990 label="Use a copy of data for inplace scaling" help=" "/>
991 </section>
992 </when>
993 </expand>
994 </xml>
995
996 <xml name="fs_selectfrommodel_prefitted">
997 <param name="input_mode" type="select" label="Construct a new estimator from a selection list?" >
998 <option value="new" selected="true">Yes</option>
999 <option value="prefitted">No. Load a prefitted estimator</option>
1000 </param>
1001 <when value="new">
1002 <expand macro="estimator_selector_all"/>
1003 </when>
1004 <when value="prefitted">
1005 <param name="fitted_estimator" type="data" format='zip' label="Load a prefitted estimator" />
1006 </when>
1007 </xml>
1008
1009 <xml name="fs_selectfrommodel_no_prefitted">
1010 <param name="input_mode" type="select" label="Construct a new estimator from a selection list?" >
1011 <option value="new" selected="true">Yes</option>
1012 </param>
1013 <when value="new">
1014 <expand macro="estimator_selector_all"/>
1015 </when>
1016 </xml>
1017
1018 <xml name="feature_selection_all">
1019 <conditional name="fs_algorithm_selector">
1020 <param name="selected_algorithm" type="select" label="Select a feature selection algorithm">
1021 <option value="SelectKBest" selected="true">SelectKBest - Select features according to the k highest scores</option>
1022 <option value="SelectFromModel">SelectFromModel - Meta-transformer for selecting features based on importance weights</option>
1023 <option value="GenericUnivariateSelect">GenericUnivariateSelect - Univariate feature selector with configurable strategy</option>
1024 <option value="SelectPercentile">SelectPercentile - Select features according to a percentile of the highest scores</option>
1025 <option value="SelectFpr">SelectFpr - Filter: Select the p-values below alpha based on a FPR test</option>
1026 <option value="SelectFdr">SelectFdr - Filter: Select the p-values for an estimated false discovery rate</option>
1027 <option value="SelectFwe">SelectFwe - Filter: Select the p-values corresponding to Family-wise error rate</option>
1028 <option value="RFE">RFE - Feature ranking with recursive feature elimination</option>
1029 <option value="RFECV">RFECV - Feature ranking with recursive feature elimination and cross-validated selection of the best number of features</option>
1030 <option value="VarianceThreshold">VarianceThreshold - Feature selector that removes all low-variance features</option>
1031 </param>
1032 <when value="SelectFromModel">
1033 <conditional name="model_inputter">
1034 <yield/>
1035 </conditional>
1036 <section name="options" title="Advanced Options" expanded="False">
1037 <param argument="threshold" type="text" value="" optional="true" label="threshold" help="The threshold value to use for feature selection. e.g. 'mean', 'median', '1.25*mean'." />
1038 <param argument="norm_order" type="integer" value="1" label="norm_order" help="Order of the norm used to filter the vectors of coefficients below threshold in the case where the coef_ attribute of the estimator is of dimension 2. " />
1039 </section>
1040 </when>
1041 <when value="GenericUnivariateSelect">
1042 <expand macro="feature_selection_score_function" />
1043 <section name="options" title="Advanced Options" expanded="False">
1044 <param argument="mode" type="select" label="Feature selection mode">
1045 <option value="percentile">percentile</option>
1046 <option value="k_best">k_best</option>
1047 <option value="fpr">fpr</option>
1048 <option value="fdr">fdr</option>
1049 <option value="fwe">fwe</option>
1050 </param>
1051 <param argument="param" type="float" value="" optional="true" label="Parameter of the corresponding mode" help="float or int depending on the feature selection mode" />
1052 </section>
1053 </when>
1054 <when value="SelectPercentile">
1055 <expand macro="feature_selection_score_function" />
1056 <section name="options" title="Advanced Options" expanded="False">
1057 <param argument="percentile" type="integer" value="10" optional="True" label="Percent of features to keep" />
1058 </section>
1059 </when>
1060 <when value="SelectKBest">
1061 <expand macro="feature_selection_score_function" />
1062 <section name="options" title="Advanced Options" expanded="False">
1063 <param argument="k" type="integer" value="10" optional="True" label="Number of top features to select" help="No 'all' option is supported." />
1064 </section>
1065 </when>
1066 <when value="SelectFpr">
1067 <expand macro="feature_selection_score_function" />
1068 <section name="options" title="Advanced Options" expanded="False">
1069 <param argument="alpha" type="float" value="" optional="True" label="Alpha" help="The highest p-value for features to be kept."/>
1070 </section>
1071 </when>
1072 <when value="SelectFdr">
1073 <expand macro="feature_selection_score_function" />
1074 <section name="options" title="Advanced Options" expanded="False">
1075 <param argument="alpha" type="float" value="" optional="True" label="Alpha" help="The highest uncorrected p-value for features to keep."/>
1076 </section>
1077 </when>
1078 <when value="SelectFwe">
1079 <expand macro="feature_selection_score_function" />
1080 <section name="options" title="Advanced Options" expanded="False">
1081 <param argument="alpha" type="float" value="" optional="True" label="Alpha" help="The highest uncorrected p-value for features to keep."/>
1082 </section>
1083 </when>
1084 <when value="RFE">
1085 <expand macro="estimator_selector_all"/>
1086 <section name="options" title="Advanced Options" expanded="False">
1087 <param argument="n_features_to_select" type="integer" value="" optional="true" label="n_features_to_select" help="The number of features to select. If None, half of the features are selected." />
1088 <param argument="step" type="float" value="1" label="step" optional="true" help="Default = 1. " />
1089 <param argument="verbose" type="integer" value="0" label="verbose" help="Controls verbosity of output." />
1090 </section>
1091 </when>
1092 <when value="RFECV">
1093 <expand macro="estimator_selector_all"/>
1094 <section name="options" title="Advanced Options" expanded="False">
1095 <param argument="step" type="float" value="1" label="step" optional="true" help="Default = 1. " />
1096 <param argument="cv" type="integer" value="" optional="true" label="cv" help="Determines the cross-validation splitting strategy" />
1097 <param argument="scoring" type="text" value="" optional="true" label="scoring" help="A string (see model evaluation documentation) or a scorer callable object / function with signature scorer(estimator, X, y)."/>
1098 <param argument="verbose" type="integer" value="0" label="verbose" help="Controls verbosity of output." />
1099 <param argument="n_jobs" type="integer" value="1" label="n_jobs" help="Number of cores to run in parallel while fitting across folds. Defaults to 1 core."/>
1100 </section>
1101 </when>
1102 <when value="VarianceThreshold">
1103 <section name="options" title="Options" expanded="False">
1104 <param argument="threshold" type="float" value="" optional="True" label="Threshold" help="Features with a training-set variance lower than this threshold will be removed."/>
1105 </section>
1106 </when>
1107 <!--when value="chi2">
1108 </when>
1109 <when value="f_classif">
1110 </when>
1111 <when value="f_regression">
1112 </when>
1113 <when value="mutual_info_classif">
1114 </when>
1115 <when value="mutual_info_regression">
1116 </when-->
1117 </conditional>
1118 </xml>
1119
1120 <xml name="feature_selection_score_function">
1121 <param argument="score_func" type="select" label="Select a score function">
1122 <option value="chi2">chi2 - Compute chi-squared stats between each non-negative feature and class</option>
1123 <option value="f_classif">f_classif - Compute the ANOVA F-value for the provided sample</option>
1124 <option value="f_regression">f_regression - Univariate linear regression tests</option>
1125 <option value="mutual_info_classif">mutual_info_classif - Estimate mutual information for a discrete target variable</option>
1126 <option value="mutual_info_regression">mutual_info_regression - Estimate mutual information for a continuous target variable</option>
1127 </param>
1128 </xml>
1129
1130 <xml name="feature_selection_output_mothods">
1131 <conditional name="output_method_selector">
1132 <param name="selected_method" type="select" label="Select an output method:">
1133 <option value="fit_transform">fit_transform - Fit to data, then transform it</option>
1134 <option value="get_support">get_support - Get a mask, or integer index, of the features selected</option>
1135 </param>
1136 <when value="fit_transform">
1137 <!--**fit_params-->
1138 </when>
1139 <when value="get_support">
1140 <param name="indices" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolfalse" checked="false" label="Indices" help="If True, the return value will be an array of integers, rather than a boolean mask."/>
1141 </when>
1142 </conditional>
1143 </xml>
1144
1145 <xml name="model_validation_common_options">
1146 <param argument="cv" type="integer" value="" optional="true" label="cv" help="The number of folds in a (Stratified)KFold" />
1147 <expand macro="n_jobs"/>
1148 <expand macro="verbose"/>
1149 <yield/>
1150 </xml>
1151
1152 <xml name="scoring">
1153 <param argument="scoring" type="text" value="" optional="true" label="scoring" help="A metric used to evaluate the estimator"/>
1154 </xml>
1155
1156 <xml name="pre_dispatch" token_type="hidden" token_default_value="all" token_help="Number of predispatched jobs for parallel execution">
1157 <param argument="pre_dispatch" type="@TYPE@" value="@DEFAULT_VALUE@" optional="true" label="pre_dispatch" help="@HELP@"/>
1158 </xml>
1159
1160 <xml name="search_cv_estimator">
1161 <param name="infile_pipeline" type="data" format="zip" label="Choose the dataset containing pipeline object:"/>
1162 <section name="search_params_builder" title="Search parameters Builder" expanded="true">
1163 <repeat name="param_set" min="1" max="20" title="Parameter setting for search:">
1164 <conditional name="search_param_selector">
1165 <param name="selected_param_type" type="select" label="Choose the transformation the parameter belongs to">
1166 <option value="final_estimator_p" selected="true">Final estimator</option>
1167 <option value="prep_1_p">Pre-processing step #1</option>
1168 <option value="prep_2_p">Pre-processing step #2</option>
1169 <option value="prep_3_p">Pre-processing step #3</option>
1170 <option value="prep_4_p">Pre-processing step #4</option>
1171 <option value="prep_5_p">Pre-processing step #5</option>
1172 </param>
1173 <when value="final_estimator_p">
1174 <expand macro="search_param_input" />
1175 </when>
1176 <when value="prep_1_p">
1177 <expand macro="search_param_input" label="Pre_processing component #1 parameter:" help="One parameter per box. For example: with_centering: [True, False]."/>
1178 </when>
1179 <when value="prep_2_p">
1180 <expand macro="search_param_input" label="Pre_processing component #2 parameter:" help="One parameter per box. For example: k: [3, 5, 7, 9]. See bottom for more examples"/>
1181 </when>
1182 <when value="prep_3_p">
1183 <expand macro="search_param_input" label="Pre_processing component #3 parameter:" help="One parameter per box. For example: n_components: [1, 10, 100, 1000]. See bottom for more examples"/>
1184 </when>
1185 <when value="prep_4_p">
1186 <expand macro="search_param_input" label="Pre_processing component #4 parameter:" help="One parameter per box. For example: n_components: [1, 10, 100, 1000]. See bottom for more examples"/>
1187 </when>
1188 <when value="prep_5_p">
1189 <expand macro="search_param_input" label="Pre_processing component #5 parameter:" help="One parameter per box. For example: affinity: ['euclidean', 'l1', 'l2', 'manhattan']. See bottom for more examples"/>
1190 </when>
1191 </conditional>
1192 </repeat>
1193 </section>
1194 </xml>
1195
1196 <xml name="search_param_input" token_label="Estimator parameter:" token_help="One parameter per box. For example: C: [1, 10, 100, 1000]. See bottom for more examples">
1197 <param name="search_p" type="text" value="" size="100" optional="true" label="@LABEL@" help="@HELP@">
1198 <sanitizer>
1199 <valid initial="default">
1200 <add value="&apos;"/>
1201 <add value="&quot;"/>
1202 <add value="["/>
1203 <add value="]"/>
1204 </valid>
1205 </sanitizer>
1206 </param>
1207 </xml>
1208
1209 <xml name="search_cv_options">
1210 <expand macro="scoring"/>
1211 <expand macro="model_validation_common_options"/>
1212 <expand macro="pre_dispatch" value="2*n_jobs" help="Controls the number of jobs that get dispatched during parallel execution"/>
1213 <param argument="iid" type="boolean" truevalue="booltrue" falsevalue="boolfalse" checked="true" label="iid" help="If True, data is identically distributed across the folds"/>
1214 <param argument="refit" type="boolean" truevalue="booltrue" falsevalue="boolfalse" checked="true" label="refit" help="Refit an estimator using the best found parameters on the whole dataset."/>
1215 <!--error_score-->
1216 <param argument="return_train_score" type="boolean" truevalue="booltrue" falsevalue="boolfalse" checked="false" label="return_train_score" help=""/>
1217 </xml>
1218
1219 <xml name="estimator_selector_all">
1220 <conditional name="estimator_selector">
1221 <param name="selected_module" type="select" label="Choose the module that contains target estimator:" >
1222 <option value="svm" selected="true">sklearn.svm</option>
1223 <option value="linear_model">sklearn.linear_model</option>
1224 <option value="ensemble">sklearn.ensemble</option>
1225 <option value="naive_bayes">sklearn.naive_bayes</option>
1226 <option value="tree">sklearn.tree</option>
1227 <option value="neighbors">sklearn.neighbors</option>
1228 <option value="xgboost">xgboost</option>
1229 <!--more-->
1230 </param>
1231 <when value="svm">
1232 <param name="selected_estimator" type="select" label="Choose estimator class:">
1233 <option value="LinearSVC" selected="true">LinearSVC</option>
1234 <option value="LinearSVR">LinearSVR</option>
1235 <option value="NuSVC">NuSVC</option>
1236 <option value="NuSVR">NuSVR</option>
1237 <option value="OneClassSVM">OneClassSVM</option>
1238 <option value="SVC">SVC</option>
1239 <option value="SVR">SVR</option>
1240 </param>
1241 <expand macro="estimator_params_text"/>
1242 </when>
1243 <when value="linear_model">
1244 <param name="selected_estimator" type="select" label="Choose estimator class:">
1245 <option value="ARDRegression" selected="true">ARDRegression</option>
1246 <option value="BayesianRidge">BayesianRidge</option>
1247 <option value="ElasticNet">ElasticNet</option>
1248 <option value="ElasticNetCV">ElasticNetCV</option>
1249 <option value="HuberRegressor">HuberRegressor</option>
1250 <option value="Lars">Lars</option>
1251 <option value="LarsCV">LarsCV</option>
1252 <option value="Lasso">Lasso</option>
1253 <option value="LassoCV">LassoCV</option>
1254 <option value="LassoLars">LassoLars</option>
1255 <option value="LassoLarsCV">LassoLarsCV</option>
1256 <option value="LassoLarsIC">LassoLarsIC</option>
1257 <option value="LinearRegression">LinearRegression</option>
1258 <option value="LogisticRegression">LogisticRegression</option>
1259 <option value="LogisticRegressionCV">LogisticRegressionCV</option>
1260 <option value="MultiTaskLasso">MultiTaskLasso</option>
1261 <option value="MultiTaskElasticNet">MultiTaskElasticNet</option>
1262 <option value="MultiTaskLassoCV">MultiTaskLassoCV</option>
1263 <option value="MultiTaskElasticNetCV">MultiTaskElasticNetCV</option>
1264 <option value="OrthogonalMatchingPursuit">OrthogonalMatchingPursuit</option>
1265 <option value="OrthogonalMatchingPursuitCV">OrthogonalMatchingPursuitCV</option>
1266 <option value="PassiveAggressiveClassifier">PassiveAggressiveClassifier</option>
1267 <option value="PassiveAggressiveRegressor">PassiveAggressiveRegressor</option>
1268 <option value="Perceptron">Perceptron</option>
1269 <option value="RANSACRegressor">RANSACRegressor</option>
1270 <option value="Ridge">Ridge</option>
1271 <option value="RidgeClassifier">RidgeClassifier</option>
1272 <option value="RidgeClassifierCV">RidgeClassifierCV</option>
1273 <option value="RidgeCV">RidgeCV</option>
1274 <option value="SGDClassifier">SGDClassifier</option>
1275 <option value="SGDRegressor">SGDRegressor</option>
1276 <option value="TheilSenRegressor">TheilSenRegressor</option>
1277 </param>
1278 <expand macro="estimator_params_text"/>
1279 </when>
1280 <when value="ensemble">
1281 <param name="selected_estimator" type="select" label="Choose estimator class:">
1282 <option value="AdaBoostClassifier" selected="true">AdaBoostClassifier</option>
1283 <option value="AdaBoostRegressor">AdaBoostRegressor</option>
1284 <option value="BaggingClassifier">BaggingClassifier</option>
1285 <option value="BaggingRegressor">BaggingRegressor</option>
1286 <option value="ExtraTreesClassifier">ExtraTreesClassifier</option>
1287 <option value="ExtraTreesRegressor">ExtraTreesRegressor</option>
1288 <option value="GradientBoostingClassifier">GradientBoostingClassifier</option>
1289 <option value="GradientBoostingRegressor">GradientBoostingRegressor</option>
1290 <option value="IsolationForest">IsolationForest</option>
1291 <option value="RandomForestClassifier">RandomForestClassifier</option>
1292 <option value="RandomForestRegressor">RandomForestRegressor</option>
1293 <option value="RandomTreesEmbedding">RandomTreesEmbedding</option>
1294 <option value="VotingClassifier">VotingClassifier</option>
1295 </param>
1296 <expand macro="estimator_params_text"/>
1297 </when>
1298 <when value="naive_bayes">
1299 <param name="selected_estimator" type="select" label="Choose estimator class:">
1300 <option value="BernoulliNB" selected="true">BernoulliNB</option>
1301 <option value="GaussianNB">GaussianNB</option>
1302 <option value="MultinomialNB">MultinomialNB</option>
1303 </param>
1304 <expand macro="estimator_params_text"/>
1305 </when>
1306 <when value="tree">
1307 <param name="selected_estimator" type="select" label="Choose estimator class:">
1308 <option value="DecisionTreeClassifier" selected="true">DecisionTreeClassifier</option>
1309 <option value="DecisionTreeRegressor">DecisionTreeRegressor</option>
1310 <option value="ExtraTreeClassifier">ExtraTreeClassifier</option>
1311 <option value="ExtraTreeRegressor">ExtraTreeRegressor</option>
1312 </param>
1313 <expand macro="estimator_params_text"/>
1314 </when>
1315 <when value="neighbors">
1316 <param name="selected_estimator" type="select" label="Choose estimator class:">
1317 <option value="BallTree" selected="true">BallTree</option>
1318 <option value="DistanceMetric">DistanceMetric</option>
1319 <option value="KDTree">KDTree</option>
1320 <option value="KernelDensity">KernelDensity</option>
1321 <option value="KNeighborsClassifier">KNeighborsClassifier</option>
1322 <option value="KNeighborsRegressor">KNeighborsRegressor</option>
1323 <option value="LocalOutlierFactor">LocalOutlierFactor</option>
1324 <option value="RadiusNeighborsClassifier">RadiusNeighborsClassifier</option>
1325 <option value="RadiusNeighborsRegressor">RadiusNeighborsRegressor</option>
1326 <option value="NearestCentroid">NearestCentroid</option>
1327 <option value="NearestNeighbors">NearestNeighbors</option>
1328 </param>
1329 <expand macro="estimator_params_text"/>
1330 </when>
1331 <when value="xgboost">
1332 <param name="selected_estimator" type="select" label="Choose estimator class:">
1333 <option value="XGBRegressor" selected="true">XGBRegressor</option>
1334 <option value="XGBClassifier">XGBClassifier</option>
1335 </param>
1336 <expand macro="estimator_params_text"/>
1337 </when>
1338 </conditional>
1339 </xml>
1340
1341 <xml name="estimator_params_text" token_label="Type in estimator parameters:"
1342 token_help="Parameters in dictionary without braces ('{}'), e.g., 'C': 1, 'kernel': 'linear'. No double quotes. Leave this box blank for default estimator.">
1343 <param name="text_params" type="text" value="" size="50" optional="true" label="@LABEL@" help="@HELP@">
1344 <sanitizer>
1345 <valid initial="default">
1346 <add value="&apos;"/>
1347 </valid>
1348 </sanitizer>
1349 </param>
1350 </xml>
1351
1352 <xml name="kernel_approximation_all">
1353 <conditional name="kernel_approximation_selector">
1354 <param name="select_algorithm" type="select" label="Choose a kernel approximation algorithm:">
1355 <option value="Nystroem" selected="true">Nystroem</option>
1356 <option value="RBFSampler">RBFSampler</option>
1357 <option value="AdditiveChi2Sampler">AdditiveChi2Sampler</option>
1358 <option value="SkewedChi2Sampler">SkewedChi2Sampler</option>
1359 </param>
1360 <when value="Nystroem">
1361 <expand macro="estimator_params_text" label="Type in kernel approximater parameters:"
1362 help="Parameters in dictionary without braces ('{}'), e.g., 'n_components': 100, 'kernel': 'rbf'. No double quotes. Leave this box blank for class default."/>
1363 </when>
1364 <when value="RBFSampler">
1365 <expand macro="estimator_params_text" label="Type in kernel approximater parameters:"
1366 help="Parameters in dictionary without braces ('{}'), e.g., 'n_components': 100, 'gamma': 1.0. No double quotes. Leave this box blank for class default."/>
1367 </when>
1368 <when value="AdditiveChi2Sampler">
1369 <expand macro="estimator_params_text" label="Type in kernel approximater parameters:"
1370 help="Parameters in dictionary without braces ('{}'), e.g., 'sample_steps': 2, 'sample_interval': None. No double quotes. Leave this box blank for class default."/>
1371 </when>
1372 <when value="SkewedChi2Sampler">
1373 <expand macro="estimator_params_text" label="Type in kernel approximater parameters:"
1374 help="Parameters in dictionary without braces ('{}'), e.g., 'n_components': 100, 'skewedness': 1.0. No double quotes. Leave this box blank for class default."/>
1375 </when>
1376 </conditional>
1377 </xml>
1378
1379 <xml name="matrix_decomposition_all">
1380 <conditional name="matrix_decomposition_selector">
1381 <param name="select_algorithm" type="select" label="Choose a matrix decomposition algorithm:">
1382 <option value="DictionaryLearning" selected="true">DictionaryLearning</option>
1383 <option value="FactorAnalysis">FactorAnalysis</option>
1384 <option value="FastICA">FastICA</option>
1385 <option value="IncrementalPCA">IncrementalPCA</option>
1386 <option value="KernelPCA">KernelPCA</option>
1387 <option value="LatentDirichletAllocation">LatentDirichletAllocation</option>
1388 <option value="MiniBatchDictionaryLearning">MiniBatchDictionaryLearning</option>
1389 <option value="MiniBatchSparsePCA">MiniBatchSparsePCA</option>
1390 <option value="NMF">NMF</option>
1391 <option value="PCA">PCA</option>
1392 <option value="SparsePCA">SparsePCA</option>
1393 <option value="SparseCoder">SparseCoder</option>
1394 <option value="TruncatedSVD">TruncatedSVD</option>
1395 </param>
1396 <when value="DictionaryLearning">
1397 <expand macro="estimator_params_text" label="Type in maxtrix decomposition parameters:"
1398 help="Parameters in dictionary without braces ('{}'), e.g., 'n_components': None, 'alpha': 1.0. No double quotes. Leave this box blank for class default."/>
1399 </when>
1400 <when value="FactorAnalysis">
1401 <expand macro="estimator_params_text" label="Type in maxtrix decomposition parameters:"
1402 help="Parameters in dictionary without braces ('{}'), e.g., 'n_components': 100, 'random_state': 42. No double quotes. Leave this box blank for class default."/>
1403 </when>
1404 <when value="FastICA">
1405 <expand macro="estimator_params_text" label="Type in maxtrix decomposition parameters:"
1406 help="Parameters in dictionary without braces ('{}'), e.g., 'n_components': 100, 'random_state': 42. No double quotes. Leave this box blank for class default."/>
1407 </when>
1408 <when value="IncrementalPCA">
1409 <expand macro="estimator_params_text" label="Type in maxtrix decomposition parameters:"
1410 help="Parameters in dictionary without braces ('{}'), e.g., 'n_components': 100, 'whiten': False. No double quotes. Leave this box blank for class default."/>
1411 </when>
1412 <when value="KernelPCA">
1413 <expand macro="estimator_params_text" label="Type in maxtrix decomposition parameters:"
1414 help="Parameters in dictionary without braces ('{}'), e.g., 'n_components': 100, 'random_state': 42. No double quotes. Leave this box blank for class default."/>
1415 </when>
1416 <when value="LatentDirichletAllocation">
1417 <expand macro="estimator_params_text" label="Type in maxtrix decomposition parameters:"
1418 help="Parameters in dictionary without braces ('{}'), e.g., 'n_components': 100, 'random_state': 42. No double quotes. Leave this box blank for class default."/>
1419 </when>
1420 <when value="MiniBatchDictionaryLearning">
1421 <expand macro="estimator_params_text" label="Type in maxtrix decomposition parameters:"
1422 help="Parameters in dictionary without braces ('{}'), e.g., 'n_components': 100, 'random_state': 42. No double quotes. Leave this box blank for class default."/>
1423 </when>
1424 <when value="MiniBatchSparsePCA">
1425 <expand macro="estimator_params_text" label="Type in maxtrix decomposition parameters:"
1426 help="Parameters in dictionary without braces ('{}'), e.g., 'n_components': 100, 'random_state': 42. No double quotes. Leave this box blank for class default."/>
1427 </when>
1428 <when value="NMF">
1429 <expand macro="estimator_params_text" label="Type in maxtrix decomposition parameters:"
1430 help="Parameters in dictionary without braces ('{}'), e.g., 'n_components': 100, 'init': 'random'. No double quotes. Leave this box blank for class default."/>
1431 </when>
1432 <when value="PCA">
1433 <expand macro="estimator_params_text" label="Type in maxtrix decomposition parameters:"
1434 help="Parameters in dictionary without braces ('{}'), e.g., 'n_components': 100, 'random_state': 42. No double quotes. Leave this box blank for class default."/>
1435 </when>
1436 <when value="SparsePCA">
1437 <expand macro="estimator_params_text" label="Type in maxtrix decomposition parameters:"
1438 help="Parameters in dictionary without braces ('{}'), e.g., 'n_components': 100, 'random_state': 42. No double quotes. Leave this box blank for class default."/>
1439 </when>
1440 <when value="SparseCoder">
1441 <expand macro="estimator_params_text" label="Type in maxtrix decomposition parameters:"
1442 help="Parameters in dictionary without braces ('{}'), e.g., 'transform_algorithm': 'omp', 'transform_alpha': 1.0. No double quotes. Leave this box blank for class default."/>
1443 </when>
1444 <when value="TruncatedSVD">
1445 <expand macro="estimator_params_text" label="Type in maxtrix decomposition parameters:"
1446 help="Parameters in dictionary without braces ('{}'), e.g., 'n_components': 2, 'algorithm': 'randomized'. No double quotes. Leave this box blank for default estimator."/>
1447 </when>
1448 </conditional>
1449 </xml>
1450
1451 <xml name="FeatureAgglomeration">
1452 <conditional name="FeatureAgglomeration_selector">
1453 <param name="select_algorithm" type="select" label="Choose the algorithm:">
1454 <option value="FeatureAgglomeration" selected="true">FeatureAgglomeration</option>
1455 </param>
1456 <when value="FeatureAgglomeration">
1457 <expand macro="estimator_params_text" label="Type in parameters:"
1458 help="Parameters in dictionary without braces ('{}'), e.g., 'n_clusters': 2, 'affinity': 'euclidean'. No double quotes. Leave this box blank for class default."/>
1459 </when>
1460 </conditional>
1461 </xml>
1462 <!-- Outputs -->
1463
1464 <xml name="output">
1465 <outputs>
1466 <data format="tabular" name="outfile_predict">
1467 <filter>selected_tasks['selected_task'] == 'load'</filter>
1468 </data>
1469 <data format="zip" name="outfile_fit">
1470 <filter>selected_tasks['selected_task'] == 'train'</filter>
1471 </data>
1472 </outputs>
1473 </xml>
1474
1475 <!--Citations-->
1476 <xml name="eden_citation">
1477 <citations>
1478 <citation type="doi">10.5281/zenodo.15094</citation>
1479 </citations>
1480 </xml>
1481
1482 <xml name="sklearn_citation">
1483 <citations>
1484 <citation type="bibtex">
1485 @article{scikit-learn,
1486 title={Scikit-learn: Machine Learning in {P}ython},
1487 author={Pedregosa, F. and Varoquaux, G. and Gramfort, A. and Michel, V.
1488 and Thirion, B. and Grisel, O. and Blondel, M. and Prettenhofer, P.
1489 and Weiss, R. and Dubourg, V. and Vanderplas, J. and Passos, A. and
1490 Cournapeau, D. and Brucher, M. and Perrot, M. and Duchesnay, E.},
1491 journal={Journal of Machine Learning Research},
1492 volume={12},
1493 pages={2825--2830},
1494 year={2011}
1495 url = {https://github.com/scikit-learn/scikit-learn}
1496 }
1497 </citation>
1498 </citations>
1499 </xml>
1500
1501 <xml name="scipy_citation">
1502 <citations>
1503 <citation type="bibtex">
1504 @Misc{,
1505 author = {Eric Jones and Travis Oliphant and Pearu Peterson and others},
1506 title = {{SciPy}: Open source scientific tools for {Python}},
1507 year = {2001--},
1508 url = "http://www.scipy.org/",
1509 note = {[Online; accessed 2016-04-09]}
1510 }
1511 </citation>
1512 </citations>
1513 </xml>
1514
1515 </macros>