comparison main_macros.xml @ 0:03f61bb3ca43 draft

"planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/sklearn commit 5b2ac730ec6d3b762faa9034eddd19ad1b347476"
author bgruening
date Mon, 16 Dec 2019 05:36:53 -0500
parents
children 8ddb3557710d
comparison
equal deleted inserted replaced
-1:000000000000 0:03f61bb3ca43
1 <macros>
2 <token name="@VERSION@">1.0.8.1</token>
3
4 <xml name="python_requirements">
5 <requirements>
6 <requirement type="package" version="3.6">python</requirement>
7 <requirement type="package" version="0.8.1">Galaxy-ML</requirement>
8 <yield/>
9 </requirements>
10 </xml>
11
12 <xml name="macro_stdio">
13 <stdio>
14 <exit_code range="1:" level="fatal" description="Error occurred. Please check Tool Standard Error"/>
15 </stdio>
16 </xml>
17
18
19 <!--Generic interface-->
20
21 <xml name="sl_Conditional" token_train="tabular" token_data="tabular" token_model="txt">
22 <conditional name="selected_tasks">
23 <param name="selected_task" type="select" label="Select a Classification Task">
24 <option value="train" selected="true">Train a model</option>
25 <option value="load">Load a model and predict</option>
26 </param>
27 <when value="load">
28 <param name="infile_model" type="data" format="@MODEL@" label="Models" help="Select a model file."/>
29 <param name="infile_data" type="data" format="@DATA@" label="Data (tabular)" help="Select the dataset you want to classify."/>
30 <param name="header" type="boolean" optional="True" truevalue="booltrue" falsevalue="boolfalse" checked="False" label="Does the dataset contain header:" />
31 <conditional name="prediction_options">
32 <param name="prediction_option" type="select" label="Select the type of prediction">
33 <option value="predict">Predict class labels</option>
34 <option value="advanced">Include advanced options</option>
35 </param>
36 <when value="predict">
37 </when>
38 <when value="advanced">
39 </when>
40 </conditional>
41 </when>
42 <when value="train">
43 <conditional name="selected_algorithms">
44 <yield />
45 </conditional>
46 </when>
47 </conditional>
48 </xml>
49
50 <xml name="advanced_section">
51 <section name="options" title="Advanced Options" expanded="False">
52 <yield />
53 </section>
54 </xml>
55
56
57 <!--Generalized Linear Models-->
58 <xml name="loss" token_help=" " token_select="false">
59 <param argument="loss" type="select" label="Loss function" help="@HELP@">
60 <option value="squared_loss" selected="@SELECT@">squared loss</option>
61 <option value="huber">huber</option>
62 <option value="epsilon_insensitive">epsilon insensitive</option>
63 <option value="squared_epsilon_insensitive">squared epsilon insensitive</option>
64 <yield/>
65 </param>
66 </xml>
67
68 <xml name="penalty" token_help=" ">
69 <param argument="penalty" type="select" label="Penalty (regularization term)" help="@HELP@">
70 <option value="l2" selected="true">l2</option>
71 <option value="l1">l1</option>
72 <option value="elasticnet">elastic net</option>
73 <option value="none">none</option>
74 <yield/>
75 </param>
76 </xml>
77
78 <xml name="l1_ratio" token_default_value="0.15" token_help=" ">
79 <param argument="l1_ratio" type="float" value="@DEFAULT_VALUE@" label="Elastic Net mixing parameter" help="@HELP@"/>
80 </xml>
81
82 <xml name="epsilon" token_default_value="0.1" token_help="Used if loss is ‘huber’, ‘epsilon_insensitive’, or ‘squared_epsilon_insensitive’. ">
83 <param argument="epsilon" type="float" value="@DEFAULT_VALUE@" label="Epsilon (epsilon-sensitive loss functions only)" help="@HELP@"/>
84 </xml>
85
86 <xml name="learning_rate_s" token_help=" " token_selected1="false" token_selected2="false">
87 <param argument="learning_rate" type="select" optional="true" label="Learning rate schedule" help="@HELP@">
88 <option value="optimal" selected="@SELECTED1@">optimal</option>
89 <option value="constant">constant</option>
90 <option value="invscaling" selected="@SELECTED2@">inverse scaling</option>
91 <yield/>
92 </param>
93 </xml>
94
95 <xml name="eta0" token_default_value="0.0" token_help="Used with ‘constant’ or ‘invscaling’ schedules. ">
96 <param argument="eta0" type="float" value="@DEFAULT_VALUE@" label="Initial learning rate" help="@HELP@"/>
97 </xml>
98
99 <xml name="power_t" token_default_value="0.5" token_help=" ">
100 <param argument="power_t" type="float" value="@DEFAULT_VALUE@" label="Exponent for inverse scaling learning rate" help="@HELP@"/>
101 </xml>
102
103 <xml name="normalize" token_checked="false" token_help=" ">
104 <param argument="normalize" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolfalse" checked="@CHECKED@" label="Normalize samples before training" help=" "/>
105 </xml>
106
107 <xml name="copy_X" token_checked="true" token_help=" ">
108 <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. "/>
109 </xml>
110
111 <xml name="ridge_params">
112 <expand macro="normalize"/>
113 <expand macro="alpha" default_value="1.0"/>
114 <expand macro="fit_intercept"/>
115 <expand macro="max_iter" default_value=""/>
116 <expand macro="tol" default_value="0.001" help_text="Precision of the solution. "/>
117 <!--class_weight-->
118 <expand macro="copy_X"/>
119 <param argument="solver" type="select" value="" label="Solver to use in the computational routines" help=" ">
120 <option value="auto" selected="true">auto</option>
121 <option value="svd">svd</option>
122 <option value="cholesky">cholesky</option>
123 <option value="lsqr">lsqr</option>
124 <option value="sparse_cg">sparse_cg</option>
125 <option value="sag">sag</option>
126 </param>
127 <expand macro="random_state"/>
128 </xml>
129
130 <!--Ensemble methods-->
131 <xml name="n_estimators" token_default_value="10" token_help=" ">
132 <param argument="n_estimators" type="integer" optional="true" value="@DEFAULT_VALUE@" label="Number of trees in the forest" help="@HELP@"/>
133 </xml>
134
135 <xml name="max_depth" token_default_value="" token_help=" ">
136 <param argument="max_depth" type="integer" optional="true" value="@DEFAULT_VALUE@" label="Maximum depth of the tree" help="@HELP@"/>
137 </xml>
138
139 <xml name="min_samples_split" token_type="integer" token_default_value="2" token_help=" ">
140 <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@"/>
141 </xml>
142
143 <xml name="min_samples_leaf" token_type="integer" token_default_value="1" token_label="Minimum number of samples in newly created leaves" token_help=" ">
144 <param argument="min_samples_leaf" type="@TYPE@" optional="true" value="@DEFAULT_VALUE@" label="@LABEL@" help="@HELP@"/>
145 </xml>
146
147 <xml name="min_weight_fraction_leaf" token_default_value="0.0" token_help=" ">
148 <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@"/>
149 </xml>
150
151 <xml name="max_leaf_nodes" token_default_value="" token_help=" ">
152 <param argument="max_leaf_nodes" type="integer" optional="true" value="@DEFAULT_VALUE@" label="Maximum number of leaf nodes in best-first method" help="@HELP@"/>
153 </xml>
154
155 <xml name="min_impurity_decrease" token_default_value="0" token_help=" ">
156 <param argument="min_impurity_decrease" type="float" value="@DEFAULT_VALUE@" optional="true" label="The threshold value of impurity for stopping node splitting" help="@HELP@"/>
157 </xml>
158
159 <xml name="bootstrap" token_checked="true" token_help=" ">
160 <param argument="bootstrap" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolflase" checked="@CHECKED@" label="Use bootstrap samples for building trees." help="@HELP@"/>
161 </xml>
162
163 <xml name="criterion" token_help=" ">
164 <param argument="criterion" type="select" label="Function to measure the quality of a split" help=" ">
165 <option value="gini" selected="true">Gini impurity</option>
166 <option value="entropy">Information gain</option>
167 <yield/>
168 </param>
169 </xml>
170
171 <xml name="criterion2" token_help="">
172 <param argument="criterion" type="select" label="Function to measure the quality of a split" >
173 <option value="mse">mse - mean squared error</option>
174 <option value="mae">mae - mean absolute error</option>
175 <yield/>
176 </param>
177 </xml>
178
179 <xml name="oob_score" token_checked="false" token_help=" ">
180 <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@"/>
181 </xml>
182
183 <xml name="max_features">
184 <conditional name="select_max_features">
185 <param argument="max_features" type="select" label="max_features">
186 <option value="auto" selected="true">auto - max_features=n_features</option>
187 <option value="sqrt">sqrt - max_features=sqrt(n_features)</option>
188 <option value="log2">log2 - max_features=log2(n_features)</option>
189 <option value="number_input">I want to type the number in or input None type</option>
190 </param>
191 <when value="auto">
192 </when>
193 <when value="sqrt">
194 </when>
195 <when value="log2">
196 </when>
197 <when value="number_input">
198 <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."/>
199 </when>
200 </conditional>
201 </xml>
202
203 <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.">
204 <param argument="verbose" type="integer" value="@DEFAULT_VALUE@" optional="true" label="Enable verbose output" help="@HELP@"/>
205 </xml>
206
207 <xml name="learning_rate" token_default_value="1.0" token_help=" ">
208 <param argument="learning_rate" type="float" optional="true" value="@DEFAULT_VALUE@" label="Learning rate" help="@HELP@"/>
209 </xml>
210
211 <xml name="subsample" token_help=" ">
212 <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@"/>
213 </xml>
214
215 <xml name="presort">
216 <param argument="presort" type="select" label="Whether to presort the data to speed up the finding of best splits in fitting" >
217 <option value="auto" selected="true">auto</option>
218 <option value="true">true</option>
219 <option value="false">false</option>
220 </param>
221 </xml>
222
223 <!--Parameters-->
224 <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.">
225 <param argument="tol" type="float" optional="true" value="@DEFAULT_VALUE@" label="Tolerance" help="@HELP_TEXT@"/>
226 </xml>
227
228 <xml name="n_clusters" token_default_value="8">
229 <param argument="n_clusters" type="integer" optional="true" value="@DEFAULT_VALUE@" label="Number of clusters" help=" "/>
230 </xml>
231
232 <xml name="fit_intercept" token_checked="true">
233 <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."/>
234 </xml>
235
236 <xml name="n_iter_no_change" token_default_value="5" token_help_text="Number of iterations with no improvement to wait before early stopping. ">
237 <param argument="n_iter_no_change" type="integer" optional="true" value="@DEFAULT_VALUE@" label="Number of iterations" help="@HELP_TEXT@"/>
238 </xml>
239
240 <xml name="shuffle" token_checked="true" token_help_text=" " token_label="Shuffle data after each iteration">
241 <param argument="shuffle" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolfalse" checked="@CHECKED@" label="@LABEL@" help="@HELP_TEXT@"/>
242 </xml>
243
244 <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. default=None.">
245 <param argument="random_state" type="integer" optional="true" value="@DEFAULT_VALUE@" label="Random seed number" help="@HELP_TEXT@"/>
246 </xml>
247
248 <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.">
249 <param argument="warm_start" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolfalse" checked="@CHECKED@" label="Perform warm start" help="@HELP_TEXT@"/>
250 </xml>
251
252 <xml name="C" token_default_value="1.0" token_help_text="Penalty parameter C of the error term.">
253 <param argument="C" type="float" optional="true" value="@DEFAULT_VALUE@" label="Penalty parameter" help="@HELP_TEXT@"/>
254 </xml>
255
256 <!--xml name="class_weight" token_default_value="" token_help_text="">
257 <param argument="class_weight" type="" optional="true" value="@DEFAULT_VALUE@" label="" help="@HELP_TEXT@"/>
258 </xml-->
259
260 <xml name="alpha" token_default_value="0.0001" token_help_text="Constant that multiplies the regularization term if regularization is used. ">
261 <param argument="alpha" type="float" optional="true" value="@DEFAULT_VALUE@" label="Regularization coefficient" help="@HELP_TEXT@"/>
262 </xml>
263
264 <xml name="n_samples" token_default_value="100" token_help_text="The total number of points equally divided among clusters.">
265 <param argument="n_samples" type="integer" optional="true" value="@DEFAULT_VALUE@" label="Number of samples" help="@HELP_TEXT@"/>
266 </xml>
267
268 <xml name="n_features" token_default_value="2" token_help_text="Number of different numerical properties produced for each sample.">
269 <param argument="n_features" type="integer" optional="true" value="@DEFAULT_VALUE@" label="Number of features" help="@HELP_TEXT@"/>
270 </xml>
271
272 <xml name="noise" token_default_value="0.0" token_help_text="Floating point number. ">
273 <param argument="noise" type="float" optional="true" value="@DEFAULT_VALUE@" label="Standard deviation of the Gaussian noise added to the data" help="@HELP_TEXT@"/>
274 </xml>
275
276 <xml name="C" token_default_value="1.0" token_help_text="Penalty parameter C of the error term. ">
277 <param argument="C" type="float" optional="true" value="@DEFAULT_VALUE@" label="Penalty parameter" help="@HELP_TEXT@"/>
278 </xml>
279
280 <xml name="max_iter" token_default_value="300" token_label="Maximum number of iterations per single run" token_help_text=" ">
281 <param argument="max_iter" type="integer" optional="true" value="@DEFAULT_VALUE@" label="@LABEL@" help="@HELP_TEXT@"/>
282 </xml>
283
284 <xml name="n_init" token_default_value="10" >
285 <param argument="n_init" type="integer" optional="true" value="@DEFAULT_VALUE@" label="Number of runs with different centroid seeds" help=" "/>
286 </xml>
287
288 <xml name="init">
289 <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.">
290 <option value="k-means++">k-means++</option>
291 <option value="random">random</option>
292 </param>
293 </xml>
294
295 <xml name="gamma" token_default_value="1.0" token_label="Scaling parameter" token_help_text=" ">
296 <param argument="gamma" type="float" optional="true" value="@DEFAULT_VALUE@" label="@LABEL@" help="@HELP_TEXT@"/>
297 </xml>
298
299 <xml name="degree" token_default_value="3" token_label="Degree of the polynomial" token_help_text=" ">
300 <param argument="degree" type="integer" optional="true" value="@DEFAULT_VALUE@" label="@LABEL@" help="@HELP_TEXT@"/>
301 </xml>
302
303 <xml name="coef0" token_default_value="1" token_label="Zero coefficient" token_help_text=" ">
304 <param argument="coef0" type="integer" optional="true" value="@DEFAULT_VALUE@" label="@LABEL@" help="@HELP_TEXT@"/>
305 </xml>
306
307 <xml name="pos_label" token_default_value="">
308 <param argument="pos_label" type="integer" optional="true" value="@DEFAULT_VALUE@" label="Label of the positive class" help=" "/>
309 </xml>
310
311 <xml name="average">
312 <param argument="average" type="select" optional="true" label="Averaging type" help=" ">
313 <option value="micro">Calculate metrics globally by counting the total true positives, false negatives and false positives. (micro)</option>
314 <option value="samples">Calculate metrics for each instance, and find their average. Only meaningful for multilabel. (samples)</option>
315 <option value="macro">Calculate metrics for each label, and find their unweighted mean. This does not take label imbalance into account. (macro)</option>
316 <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>
317 <option value="None">None</option>
318 <yield/>
319 </param>
320 </xml>
321
322 <xml name="beta">
323 <param argument="beta" type="float" value="1.0" label="The strength of recall versus precision in the F-score" help=" "/>
324 </xml>
325
326
327 <!--Data interface-->
328
329 <xml name="samples_tabular" token_label1="Training samples dataset:" token_multiple1="false" token_multiple2="false">
330 <param name="infile1" type="data" format="tabular" label="@LABEL1@"/>
331 <param name="header1" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolfalse" checked="False" label="Does the dataset contain header:" />
332 <conditional name="column_selector_options_1">
333 <expand macro="samples_column_selector_options" multiple="@MULTIPLE1@"/>
334 </conditional>
335 <param name="infile2" type="data" format="tabular" label="Dataset containing class labels or target values:"/>
336 <param name="header2" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolfalse" checked="False" label="Does the dataset contain header:" />
337 <conditional name="column_selector_options_2">
338 <expand macro="samples_column_selector_options" column_option="selected_column_selector_option2" col_name="col2" multiple="@MULTIPLE2@" infile="infile2"/>
339 </conditional>
340 <yield/>
341 </xml>
342
343 <xml name="samples_column_selector_options" token_column_option="selected_column_selector_option" token_col_name="col1" token_multiple="False" token_infile="infile1">
344 <param name="@COLUMN_OPTION@" type="select" label="Choose how to select data by column:">
345 <option value="by_index_number" selected="true">Select columns by column index number(s)</option>
346 <option value="all_but_by_index_number">All columns EXCLUDING some by column index number(s)</option>
347 <option value="by_header_name">Select columns by column header name(s)</option>
348 <option value="all_but_by_header_name">All columns EXCLUDING some by column header name(s)</option>
349 <option value="all_columns">All columns</option>
350 </param>
351 <when value="by_index_number">
352 <param name="@COL_NAME@" multiple="@MULTIPLE@" type="data_column" use_header_names="true" data_ref="@INFILE@" label="Select target column(s):"/>
353 </when>
354 <when value="all_but_by_index_number">
355 <param name="@COL_NAME@" multiple="@MULTIPLE@" type="data_column" use_header_names="true" data_ref="@INFILE@" label="Select target column(s):"/>
356 </when>
357 <when value="by_header_name">
358 <param name="@COL_NAME@" type="text" value="" label="Type header name(s):" help="Comma-separated string. For example: target1,target2"/>
359 </when>
360 <when value="all_but_by_header_name">
361 <param name="@COL_NAME@" type="text" value="" label="Type header name(s):" help="Comma-separated string. For example: target1,target2"/>
362 </when>
363 <when value="all_columns">
364 </when>
365 </xml>
366
367 <xml name="clf_inputs_extended" token_label1=" " token_label2=" " token_multiple="False">
368 <conditional name="true_columns">
369 <param name="selected_input1" type="select" label="Select the input type of true labels dataset:">
370 <option value="tabular" selected="true">Tabular</option>
371 <option value="sparse">Sparse</option>
372 </param>
373 <when value="tabular">
374 <param name="infile1" type="data" label="@LABEL1@"/>
375 <param name="col1" type="data_column" data_ref="infile1" label="Select the target column:"/>
376 </when>
377 <when value="sparse">
378 <param name="infile1" type="data" format="txt" label="@LABEL1@"/>
379 </when>
380 </conditional>
381 <conditional name="predicted_columns">
382 <param name="selected_input2" type="select" label="Select the input type of predicted labels dataset:">
383 <option value="tabular" selected="true">Tabular</option>
384 <option value="sparse">Sparse</option>
385 </param>
386 <when value="tabular">
387 <param name="infile2" type="data" label="@LABEL2@"/>
388 <param name="col2" multiple="@MULTIPLE@" type="data_column" data_ref="infile2" label="Select target column(s):"/>
389 </when>
390 <when value="sparse">
391 <param name="infile2" type="data" format="txt" label="@LABEL1@"/>
392 </when>
393 </conditional>
394 </xml>
395
396 <xml name="clf_inputs" token_label1="Dataset containing true labels (tabular):" token_label2="Dataset containing predicted values (tabular):" token_multiple1="False" token_multiple="False">
397 <param name="infile1" type="data" format="tabular" label="@LABEL1@"/>
398 <param name="header1" type="boolean" optional="True" truevalue="booltrue" falsevalue="boolfalse" checked="False" label="Does the dataset contain header:" />
399 <conditional name="column_selector_options_1">
400 <expand macro="samples_column_selector_options" multiple="@MULTIPLE1@"/>
401 </conditional>
402 <param name="infile2" type="data" format="tabular" label="@LABEL2@"/>
403 <param name="header2" type="boolean" optional="True" truevalue="booltrue" falsevalue="boolfalse" checked="False" label="Does the dataset contain header:" />
404 <conditional name="column_selector_options_2">
405 <expand macro="samples_column_selector_options" column_option="selected_column_selector_option2" col_name="col2" multiple="@MULTIPLE@" infile="infile2"/>
406 </conditional>
407 </xml>
408
409 <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.">
410 <repeat name="@NAME@" min="1" max="@MAX_NUM@" title="Select input file(s):">
411 <param name="input" type="data" format="@FORMAT@" label="@LABEL@" help="@HELP_TEXT@"/>
412 </repeat>
413 </xml>
414
415 <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="">
416 <param name="infile1" type="data" format="@FORMAT1@" label="@LABEL1@" help="@HELP1@"/>
417 <expand macro="input_tabular_target"/>
418 </xml>
419
420 <xml name="sl_mixed_input">
421 <conditional name="input_options">
422 <expand macro="data_input_options"/>
423 <expand macro="data_input_whens"/>
424 </conditional>
425 </xml>
426
427 <xml name="sl_mixed_input_plus_sequence">
428 <conditional name="input_options">
429 <expand macro="data_input_options">
430 <option value="seq_fasta">sequnences in a fasta file</option>
431 <option value="refseq_and_interval">reference genome and intervals</option>
432 </expand>
433 <expand macro="data_input_whens">
434 <when value="seq_fasta">
435 <expand macro="inputs_seq_fasta"/>
436 </when>
437 <when value="refseq_and_interval">
438 <expand macro="inputs_refseq_and_interval"/>
439 </when>
440 </expand>
441 </conditional>
442 </xml>
443
444 <xml name="data_input_options">
445 <param name="selected_input" type="select" label="Select input type:">
446 <option value="tabular" selected="true">tabular data</option>
447 <option value="sparse">sparse matrix</option>
448 <yield/>
449 </param>
450 </xml>
451
452 <xml name="data_input_whens">
453 <when value="tabular">
454 <expand macro="samples_tabular" multiple1="true" multiple2="false"/>
455 </when>
456 <when value="sparse">
457 <expand macro="sparse_target"/>
458 </when>
459 <yield/>
460 </xml>
461
462 <xml name="input_tabular_target">
463 <param name="infile2" type="data" format="tabular" label="Dataset containing class labels or target values:"/>
464 <param name="header2" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolfalse" checked="false" label="Does the dataset contain header:" />
465 <conditional name="column_selector_options_2">
466 <expand macro="samples_column_selector_options" column_option="selected_column_selector_option2" col_name="col2" multiple="false" infile="infile2"/>
467 </conditional>
468 </xml>
469
470 <xml name="inputs_seq_fasta">
471 <param name="fasta_path" type="data" format="fasta" label="Dataset containing fasta genomic/protein sequences" help="Sequences will be one-hot encoded to arrays."/>
472 <expand macro="input_tabular_target"/>
473 </xml>
474
475 <xml name="inputs_refseq_and_interval">
476 <param name="ref_genome_file" type="data" format="fasta" label="Dataset containing reference genomic sequence"/>
477 <param name="interval_file" type="data" format="interval" label="Dataset containing sequence intervals for training" help="interval. Sequences will be retrieved from the reference genome and one-hot encoded to training arrays."/>
478 <param name="target_file" type="data" format="bed" label="Dataset containing positions and features for target values." help="bed. The file will be compressed with `bgzip` and then indexed using `tabix`."/>
479 <param name="infile2" type="data" format="tabular" label="Dataset containing the feature list for prediction"/>
480 <param name="header2" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolfalse" checked="false" label="Does the dataset contain header:" />
481 <conditional name="column_selector_options_2">
482 <expand macro="samples_column_selector_options" column_option="selected_column_selector_option2" col_name="col2" multiple="true" infile="infile2"/>
483 </conditional>
484 </xml>
485
486 <!--Advanced options-->
487 <xml name="nn_advanced_options">
488 <section name="options" title="Advanced Options" expanded="False">
489 <yield/>
490 <param argument="weights" type="select" label="Weight function" help="Used in prediction.">
491 <option value="uniform" selected="true">Uniform weights. All points in each neighborhood are weighted equally. (Uniform)</option>
492 <option value="distance">Weight points by the inverse of their distance. (Distance)</option>
493 </param>
494 <param argument="algorithm" type="select" label="Neighbor selection algorithm" help=" ">
495 <option value="auto" selected="true">Auto</option>
496 <option value="ball_tree">BallTree</option>
497 <option value="kd_tree">KDTree</option>
498 <option value="brute">Brute-force</option>
499 </param>
500 <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."/>
501 <!--param name="metric"-->
502 <!--param name="p"-->
503 <!--param name="metric_params"-->
504 </section>
505 </xml>
506
507 <xml name="svc_advanced_options">
508 <section name="options" title="Advanced Options" expanded="False">
509 <yield/>
510 <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.">
511 <option value="rbf" selected="true">rbf</option>
512 <option value="linear">linear</option>
513 <option value="poly">poly</option>
514 <option value="sigmoid">sigmoid</option>
515 <option value="precomputed">precomputed</option>
516 </param>
517 <param argument="degree" type="integer" optional="true" value="3" label="Degree of the polynomial (polynomial kernel only)" help="Ignored by other kernels. dafault : 3 "/>
518 <!--TODO: param argument="gamma" float, optional (default=’auto’) -->
519 <param argument="coef0" type="float" optional="true" value="0.0" label="Zero coefficient (polynomial and sigmoid kernels only)"
520 help="Independent term in kernel function. dafault: 0.0 "/>
521 <param argument="shrinking" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolfalse" checked="true"
522 label="Use the shrinking heuristic" help=" "/>
523 <param argument="probability" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolfalse" checked="false"
524 label="Enable probability estimates. " help="This must be enabled prior to calling fit, and will slow down that method."/>
525 <!-- param argument="cache_size"-->
526 <!--expand macro="class_weight"/-->
527 <expand macro="tol" default_value="0.001" help_text="Tolerance for stopping criterion. "/>
528 <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."/>
529 <!--param argument="decision_function_shape"-->
530 <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."/>
531 </section>
532 </xml>
533
534 <xml name="spectral_clustering_advanced_options">
535 <section name="options" title="Advanced Options" expanded="False">
536 <expand macro="n_clusters"/>
537 <param argument="eigen_solver" type="select" value="" label="Eigen solver" help="The eigenvalue decomposition strategy to use.">
538 <option value="arpack" selected="true">arpack</option>
539 <option value="lobpcg">lobpcg</option>
540 <option value="amg">amg</option>
541 <!--None-->
542 </param>
543 <expand macro="random_state"/>
544 <expand macro="n_init"/>
545 <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''."/>
546 <param argument="affinity" type="select" label="Affinity" help="Affinity kernel to use. ">
547 <option value="rbf" selected="true">RBF</option>
548 <option value="precomputed">precomputed</option>
549 <option value="nearest_neighbors">Nearset neighbors</option>
550 </param>
551 <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''"/>
552 <!--param argument="eigen_tol"-->
553 <param argument="assign_labels" type="select" label="Assign labels" help="The strategy to use to assign labels in the embedding space.">
554 <option value="kmeans" selected="true">kmeans</option>
555 <option value="discretize">discretize</option>
556 </param>
557 <param argument="degree" type="integer" optional="true" value="3"
558 label="Degree of the polynomial (polynomial kernel only)" help="Ignored by other kernels. dafault : 3 "/>
559 <param argument="coef0" type="integer" optional="true" value="1"
560 label="Zero coefficient (polynomial and sigmoid kernels only)" help="Ignored by other kernels. dafault : 1 "/>
561 <!--param argument="kernel_params"-->
562 </section>
563 </xml>
564
565 <xml name="minibatch_kmeans_advanced_options">
566 <section name="options" title="Advanced Options" expanded="False">
567 <expand macro="n_clusters"/>
568 <expand macro="init"/>
569 <expand macro="n_init" default_value="3"/>
570 <expand macro="max_iter" default_value="100"/>
571 <expand macro="tol" help_text="Early stopping heuristics based on normalized center change. To disable set to 0.0 ."/>
572 <expand macro="random_state"/>
573 <param argument="batch_size" type="integer" optional="true" value="100" label="Batch size" help="Size of the mini batches."/>
574 <!--param argument="compute_labels"-->
575 <param argument="max_no_improvement" type="integer" optional="true" value="10" label="Maximum number of improvement attempts" help="
576 Convergence detection based on inertia (the consecutive number of mini batches that doe not yield an improvement on the smoothed inertia).
577 To disable, set max_no_improvement to None. "/>
578 <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 )"/>
579 <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."/>
580 </section>
581 </xml>
582
583 <xml name="kmeans_advanced_options">
584 <section name="options" title="Advanced Options" expanded="False">
585 <expand macro="n_clusters"/>
586 <expand macro="init"/>
587 <expand macro="n_init"/>
588 <expand macro="max_iter"/>
589 <expand macro="tol" default_value="0.0001" help_text="Relative tolerance with regards to inertia to declare convergence."/>
590 <!--param argument="precompute_distances"/-->
591 <expand macro="random_state"/>
592 <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."/>
593 <expand macro="kmeans_algorithm"/>
594 </section>
595 </xml>
596
597 <xml name="kmeans_algorithm">
598 <param argument="algorithm" type="select" label="K-means algorithm to use:">
599 <option value="auto" selected="true">auto</option>
600 <option value="full">full</option>
601 <option value="elkan">elkan</option>
602 </param>
603 </xml>
604
605 <xml name="birch_advanced_options">
606 <section name="options" title="Advanced Options" expanded="False">
607 <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."/>
608 <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."/>
609 <expand macro="n_clusters" default_value="3"/>
610 <!--param argument="compute_labels"/-->
611 </section>
612 </xml>
613
614 <xml name="dbscan_advanced_options">
615 <section name="options" title="Advanced Options" expanded="False">
616 <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."/>
617 <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."/>
618 <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."/>
619 <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.">
620 <option value="auto" selected="true">auto</option>
621 <option value="ball_tree">ball_tree</option>
622 <option value="kd_tree">kd_tree</option>
623 <option value="brute">brute</option>
624 </param>
625 <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."/>
626 </section>
627 </xml>
628
629 <xml name="clustering_algorithms_options">
630 <conditional name="algorithm_options">
631 <param name="selected_algorithm" type="select" label="Clustering Algorithm">
632 <option value="KMeans" selected="true">KMeans</option>
633 <option value="SpectralClustering">Spectral Clustering</option>
634 <option value="MiniBatchKMeans">Mini Batch KMeans</option>
635 <option value="DBSCAN">DBSCAN</option>
636 <option value="Birch">Birch</option>
637 </param>
638 <when value="KMeans">
639 <expand macro="kmeans_advanced_options"/>
640 </when>
641 <when value="DBSCAN">
642 <expand macro="dbscan_advanced_options"/>
643 </when>
644 <when value="Birch">
645 <expand macro="birch_advanced_options"/>
646 </when>
647 <when value="SpectralClustering">
648 <expand macro="spectral_clustering_advanced_options"/>
649 </when>
650 <when value="MiniBatchKMeans">
651 <expand macro="minibatch_kmeans_advanced_options"/>
652 </when>
653 </conditional>
654 </xml>
655
656 <xml name="distance_metrics">
657 <param argument="metric" type="select" label="Distance metric" help=" ">
658 <option value="euclidean" selected="true">euclidean</option>
659 <option value="cityblock">cityblock</option>
660 <option value="cosine">cosine</option>
661 <option value="l1">l1</option>
662 <option value="l2">l2</option>
663 <option value="manhattan">manhattan</option>
664 <yield/>
665 </param>
666 </xml>
667
668 <xml name="distance_nonsparse_metrics">
669 <option value="braycurtis">braycurtis</option>
670 <option value="canberra">canberra</option>
671 <option value="chebyshev">chebyshev</option>
672 <option value="correlation">correlation</option>
673 <option value="dice">dice</option>
674 <option value="hamming">hamming</option>
675 <option value="jaccard">jaccard</option>
676 <option value="kulsinski">kulsinski</option>
677 <option value="mahalanobis">mahalanobis</option>
678 <option value="matching">matching</option>
679 <option value="minkowski">minkowski</option>
680 <option value="rogerstanimoto">rogerstanimoto</option>
681 <option value="russellrao">russellrao</option>
682 <option value="seuclidean">seuclidean</option>
683 <option value="sokalmichener">sokalmichener</option>
684 <option value="sokalsneath">sokalsneath</option>
685 <option value="sqeuclidean">sqeuclidean</option>
686 <option value="yule">yule</option>
687 </xml>
688
689 <xml name="pairwise_kernel_metrics">
690 <param argument="metric" type="select" label="Pirwise Kernel metric" help=" ">
691 <option value="rbf" selected="true">rbf</option>
692 <option value="sigmoid">sigmoid</option>
693 <option value="polynomial">polynomial</option>
694 <option value="linear" selected="true">linear</option>
695 <option value="chi2">chi2</option>
696 <option value="additive_chi2">additive_chi2</option>
697 </param>
698 </xml>
699
700 <xml name="sparse_pairwise_metric_functions">
701 <param name="selected_metric_function" type="select" label="Select the pairwise metric you want to compute:">
702 <option value="euclidean_distances" selected="true">Euclidean distance matrix</option>
703 <option value="pairwise_distances">Distance matrix</option>
704 <option value="pairwise_distances_argmin">Minimum distances between one point and a set of points</option>
705 <yield/>
706 </param>
707 </xml>
708
709 <xml name="pairwise_metric_functions">
710 <option value="additive_chi2_kernel" >Additive chi-squared kernel</option>
711 <option value="chi2_kernel">Exponential chi-squared kernel</option>
712 <option value="linear_kernel">Linear kernel</option>
713 <option value="manhattan_distances">L1 distances</option>
714 <option value="pairwise_kernels">Kernel</option>
715 <option value="polynomial_kernel">Polynomial kernel</option>
716 <option value="rbf_kernel">Gaussian (rbf) kernel</option>
717 <option value="laplacian_kernel">Laplacian kernel</option>
718 </xml>
719
720 <xml name="sparse_pairwise_condition">
721 <when value="pairwise_distances">
722 <section name="options" title="Advanced Options" expanded="False">
723 <expand macro="distance_metrics">
724 <yield/>
725 </expand>
726 </section>
727 </when>
728 <when value="euclidean_distances">
729 <section name="options" title="Advanced Options" expanded="False">
730 <param argument="squared" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolfalse" checked="false"
731 label="Return squared Euclidean distances" help=" "/>
732 </section>
733 </when>
734 </xml>
735
736 <xml name="argmin_distance_condition">
737 <when value="pairwise_distances_argmin">
738 <section name="options" title="Advanced Options" expanded="False">
739 <param argument="axis" type="integer" optional="true" value="1" label="Axis" help="Axis along which the argmin and distances are to be computed."/>
740 <expand macro="distance_metrics">
741 <yield/>
742 </expand>
743 <param argument="batch_size" type="integer" optional="true" value="500" label="Batch size" help="Number of rows to be processed in each batch run."/>
744 </section>
745 </when>
746 </xml>
747
748 <xml name="sparse_preprocessors">
749 <param name="selected_pre_processor" type="select" label="Select a preprocessor:">
750 <option value="StandardScaler" selected="true">Standard Scaler (Standardizes features by removing the mean and scaling to unit variance)</option>
751 <option value="Binarizer">Binarizer (Binarizes data)</option>
752 <option value="MaxAbsScaler">Max Abs Scaler (Scales features by their maximum absolute value)</option>
753 <option value="Normalizer">Normalizer (Normalizes samples individually to unit norm)</option>
754 <yield/>
755 </param>
756 </xml>
757
758 <xml name="sparse_preprocessors_ext">
759 <expand macro="sparse_preprocessors">
760 <option value="KernelCenterer">Kernel Centerer (Centers a kernel matrix)</option>
761 <option value="MinMaxScaler">Minmax Scaler (Scales features to a range)</option>
762 <option value="PolynomialFeatures">Polynomial Features (Generates polynomial and interaction features)</option>
763 <option value="RobustScaler">Robust Scaler (Scales features using outlier-invariance statistics)</option>
764 <option value="QuantileTransformer">QuantileTransformer (Transform features using quantiles information)</option>
765 <option value="PowerTransformer">PowerTransformer (Apply a power transform featurewise to make data more Gaussian-like)</option>
766 <option value="KBinsDiscretizer">KBinsDiscretizer (Bin continuous data into intervals.)</option>
767 </expand>
768 </xml>
769
770 <xml name="sparse_preprocessor_options">
771 <when value="Binarizer">
772 <section name="options" title="Advanced Options" expanded="False">
773 <param argument="copy" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolfalse" checked="true"
774 label="Use a copy of data for precomputing binarization" help=" "/>
775 <param argument="threshold" type="float" optional="true" value="0.0"
776 label="Threshold"
777 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. "/>
778 </section>
779 </when>
780 <when value="StandardScaler">
781 <section name="options" title="Advanced Options" expanded="False">
782 <param argument="copy" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolfalse" checked="true"
783 label="Use a copy of data for performing inplace scaling" help=" "/>
784 <param argument="with_mean" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolfalse" checked="true"
785 label="Center the data before scaling" help=" "/>
786 <param argument="with_std" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolfalse" checked="true"
787 label="Scale the data to unit variance (or unit standard deviation)" help=" "/>
788 </section>
789 </when>
790 <when value="MaxAbsScaler">
791 <section name="options" title="Advanced Options" expanded="False">
792 <param argument="copy" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolfalse" checked="true"
793 label="Use a copy of data for precomputing scaling" help=" "/>
794 </section>
795 </when>
796 <when value="Normalizer">
797 <section name="options" title="Advanced Options" expanded="False">
798 <param argument="norm" type="select" optional="true" label="The norm to use to normalize non zero samples" help=" ">
799 <option value="l1" selected="true">l1</option>
800 <option value="l2">l2</option>
801 <option value="max">max</option>
802 </param>
803 <param argument="copy" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolfalse" checked="true"
804 label="Use a copy of data for precomputing row normalization" help=" "/>
805 </section>
806 </when>
807 <yield/>
808 </xml>
809
810 <xml name="sparse_preprocessor_options_ext">
811 <expand macro="sparse_preprocessor_options">
812 <when value="KernelCenterer">
813 <section name="options" title="Advanced Options" expanded="False">
814 </section>
815 </when>
816 <when value="MinMaxScaler">
817 <section name="options" title="Advanced Options" expanded="False">
818 <param argument="feature_range" type="text" value="(0, 1)" optional="true" help="Desired range of transformed data. None or tuple (min, max). None equals to (0, 1)"/>
819 <param argument="copy" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolflase" checked="true"
820 label="Use a copy of data for precomputing normalization" help=" "/>
821 </section>
822 </when>
823 <when value="PolynomialFeatures">
824 <section name="options" title="Advanced Options" expanded="False">
825 <param argument="degree" type="integer" optional="true" value="2" label="The degree of the polynomial features " help=""/>
826 <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) "/>
827 <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 "/>
828 </section>
829 </when>
830 <when value="RobustScaler">
831 <section name="options" title="Advanced Options" expanded="False">
832 <!--=True, =True, copy=True-->
833 <param argument="with_centering" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolflase" checked="true"
834 label="Center the data before scaling" help=" "/>
835 <param argument="with_scaling" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolflase" checked="true"
836 label="Scale the data to interquartile range" help=" "/>
837 <param argument="copy" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolflase" checked="true"
838 label="Use a copy of data for inplace scaling" help=" "/>
839 </section>
840 </when>
841 <when value="QuantileTransformer">
842 <section name="options" title="Advanced Options" expanded="False">
843 <param name="n_quantiles" type="integer" value="1000" min="0" label="Number of quantiles to be computed" />
844 <param name="output_distribution" type="select" label="Marginal distribution for the transformed data">
845 <option value="uniform" selected="true">uniform</option>
846 <option value="normal">normal</option>
847 </param>
848 <param name="ignore_implicit_zeros" type="boolean" truevalue="booltrue" falsevalue="boolfalse" checked="false" label="Whether to discard sparse entries" help="Only applies to sparse matrices. If False, sparse entries are treated as zeros"/>
849 <param name="subsample" type="integer" value="100000" label="Maximum number of samples used to estimate the quantiles for computational efficiency" help="Note that the subsampling procedure may differ for value-identical sparse and dense matrices."/>
850 <expand macro="random_state" help_text="This is used by subsampling and smoothing noise"/>
851 </section>
852 </when>
853 <when value="PowerTransformer">
854 <section name="options" title="Advanced Options" expanded="False">
855 <param name="method" type="select" label="The power transform method">
856 <option value="yeo-johnson" selected="true">yeo-johnson (works with positive and negative values)</option>
857 <option value="box-cox">box-cox (might perform better, but only works with strictly positive values)</option>
858 </param>
859 <param name="standardize" type="boolean" truevalue="booltrue" falsevalue="boolfalse" checked="true" label="Whether to apply zero-mean, unit-variance normalization to the transformed output."/>
860 </section>
861 </when>
862 <when value="KBinsDiscretizer">
863 <section name="options" title="Advanced Options" expanded="False">
864 <param name="n_bins" type="integer" value="5" min="2" label="The number of bins to produce"/>
865 <param name="encode" type="select" label="Method used to encode the transformed result">
866 <option value="onehot" selected="true">onehot (encode the transformed result with one-hot encoding and return a sparse matrix)</option>
867 <option value="onehot-dense">onehot-dense (encode the transformed result with one-hot encoding and return a dense array)</option>
868 <option value="ordinal">ordinal (return the bin identifier encoded as an integer value)</option>
869 </param>
870 <param name="strategy" type="select" label="Strategy used to define the widths of the bins">
871 <option value="uniform">uniform (all bins in each feature have identical widths)</option>
872 <option value="quantile" selected="true">quantile (all bins in each feature have the same number of points)</option>
873 <option value="kmeans">kmeans (values in each bin have the same nearest center of a 1D k-means cluster)</option>
874 </param>
875 </section>
876 </when>
877 </expand>
878 </xml>
879
880 <xml name="cv_splitter">
881 <option value="default" selected="true">default splitter</option>
882 <option value="KFold">KFold</option>
883 <option value="StratifiedKFold">StratifiedKFold</option>
884 <option value="LeaveOneOut">LeaveOneOut</option>
885 <option value="LeavePOut">LeavePOut</option>
886 <option value="RepeatedKFold">RepeatedKFold</option>
887 <option value="RepeatedStratifiedKFold">RepeatedStratifiedKFold</option>
888 <option value="ShuffleSplit">ShuffleSplit</option>
889 <option value="StratifiedShuffleSplit">StratifiedShuffleSplit</option>
890 <option value="TimeSeriesSplit">TimeSeriesSplit</option>
891 <option value="PredefinedSplit">PredefinedSplit</option>
892 <option value="OrderedKFold">OrderedKFold</option>
893 <option value="RepeatedOrderedKFold">RepeatedOrderedKFold</option>
894 <yield/>
895 </xml>
896
897 <xml name="cv_splitter_options">
898 <when value="default">
899 <expand macro="cv_n_splits"/>
900 </when>
901 <when value="KFold">
902 <expand macro="cv_n_splits"/>
903 <expand macro="cv_shuffle"/>
904 <expand macro="random_state"/>
905 </when>
906 <when value="StratifiedKFold">
907 <expand macro="cv_n_splits"/>
908 <expand macro="cv_shuffle"/>
909 <expand macro="random_state"/>
910 </when>
911 <when value="LeaveOneOut">
912 </when>
913 <when value="LeavePOut">
914 <param argument="p" type="integer" value="" label="p" help="Integer. Size of the test sets."/>
915 </when>
916 <when value="RepeatedKFold">
917 <expand macro="cv_n_splits" value="5"/>
918 <param argument="n_repeats" type="integer" value="10" label="n_repeats" help="Number of times cross-validator needs to be repeated." />
919 <expand macro="random_state" />
920 </when>
921 <when value="RepeatedStratifiedKFold">
922 <expand macro="cv_n_splits" value="5"/>
923 <param argument="n_repeats" type="integer" value="10" label="n_repeats" help="Number of times cross-validator needs to be repeated." />
924 <expand macro="random_state" />
925 </when>
926 <when value="ShuffleSplit">
927 <expand macro="cv_n_splits" value="10" help="Number of re-shuffling and splitting iterations."/>
928 <expand macro="cv_test_size" value="0.1" />
929 <expand macro="random_state"/>
930 </when>
931 <when value="StratifiedShuffleSplit">
932 <expand macro="cv_n_splits" value="10" help="Number of re-shuffling and splitting iterations."/>
933 <expand macro="cv_test_size" value="0.1" />
934 <expand macro="random_state"/>
935 </when>
936 <when value="TimeSeriesSplit">
937 <expand macro="cv_n_splits"/>
938 <param argument="max_train_size" type="integer" value="" optional="true" label="Maximum size of the training set" help="Maximum size for a single training set." />
939 </when>
940 <when value="PredefinedSplit">
941 <param argument="test_fold" type="text" value="" area="true" label="test_fold" help="List, e.g., [0, 1, -1, 1], represents two test sets, [X[0]] and [X[1], X[3]], X[2] is excluded from any test set due to '-1'."/>
942 </when>
943 <when value="OrderedKFold">
944 <expand macro="cv_n_splits"/>
945 <expand macro="cv_shuffle"/>
946 <expand macro="random_state"/>
947 </when>
948 <when value="RepeatedOrderedKFold">
949 <expand macro="cv_n_splits"/>
950 <param argument="n_repeats" type="integer" value="5"/>
951 <expand macro="random_state"/>
952 </when>
953 <yield/>
954 </xml>
955
956 <xml name="cv">
957 <conditional name="cv_selector">
958 <param name="selected_cv" type="select" label="Select the cv splitter:">
959 <expand macro="cv_splitter">
960 <option value="GroupKFold">GroupKFold</option>
961 <option value="GroupShuffleSplit">GroupShuffleSplit</option>
962 <option value="LeaveOneGroupOut">LeaveOneGroupOut</option>
963 <option value="LeavePGroupsOut">LeavePGroupsOut</option>
964 </expand>
965 </param>
966 <expand macro="cv_splitter_options">
967 <when value="GroupKFold">
968 <expand macro="cv_n_splits"/>
969 <expand macro="cv_groups" />
970 </when>
971 <when value="GroupShuffleSplit">
972 <expand macro="cv_n_splits" value="5"/>
973 <expand macro="cv_test_size"/>
974 <expand macro="random_state"/>
975 <expand macro="cv_groups"/>
976 </when>
977 <when value="LeaveOneGroupOut">
978 <expand macro="cv_groups"/>
979 </when>
980 <when value="LeavePGroupsOut">
981 <param argument="n_groups" type="integer" value="" label="n_groups" help="Number of groups (p) to leave out in the test split." />
982 <expand macro="cv_groups"/>
983 </when>
984 </expand>
985 </conditional>
986 </xml>
987
988 <xml name="cv_reduced" token_label="Select the cv splitter">
989 <conditional name="cv_selector">
990 <param name="selected_cv" type="select" label="@LABEL@">
991 <expand macro="cv_splitter"/>
992 </param>
993 <expand macro="cv_splitter_options"/>
994 </conditional>
995 </xml>
996
997 <xml name="cv_n_splits" token_value="3" token_help="Number of folds. Must be at least 2.">
998 <param argument="n_splits" type="integer" value="@VALUE@" min="1" label="n_splits" help="@HELP@"/>
999 </xml>
1000
1001 <xml name="cv_shuffle">
1002 <param argument="shuffle" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolfalse" checked="false" label="Whether to shuffle data before splitting" />
1003 </xml>
1004
1005 <xml name="cv_test_size" token_value="0.2">
1006 <param argument="test_size" type="float" value="@VALUE@" min="0.0" label="Portion or number of the test set" help="0.0-1.0, proportion of the dataset to include in the test split; >1, integer only, the absolute number of test samples "/>
1007 </xml>
1008
1009 <xml name="cv_groups" >
1010 <section name="groups_selector" title="Groups column selector" expanded="true">
1011 <param name="infile_g" type="data" format="tabular" label="Choose dataset containing groups info:"/>
1012 <param name="header_g" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolfalse" checked="False" label="Does the dataset contain header:" />
1013 <conditional name="column_selector_options_g">
1014 <expand macro="samples_column_selector_options" column_option="selected_column_selector_option_g" col_name="col_g" multiple="False" infile="infile_g"/>
1015 </conditional>
1016 </section>
1017 </xml>
1018
1019 <xml name="train_test_split_params">
1020 <conditional name="split_algos">
1021 <param name="shuffle" type="select" label="Select the splitting method">
1022 <option value="None">No shuffle</option>
1023 <option value="simple" selected="true">ShuffleSplit</option>
1024 <option value="stratified">StratifiedShuffleSplit -- target values serve as class labels</option>
1025 <option value="group">GroupShuffleSplit or split by group names</option>
1026 </param>
1027 <when value="None">
1028 <expand macro="train_test_split_test_size"/>
1029 </when>
1030 <when value="simple">
1031 <expand macro="train_test_split_test_size"/>
1032 <expand macro="random_state"/>
1033 </when>
1034 <when value="stratified">
1035 <expand macro="train_test_split_test_size"/>
1036 <expand macro="random_state"/>
1037 </when>
1038 <when value="group">
1039 <expand macro="train_test_split_test_size" optional="true"/>
1040 <expand macro="random_state"/>
1041 <param argument="group_names" type="text" value="" optional="true" label="Type in group names instead"
1042 help="For example: chr6, chr7. This parameter is optional. If used, it will override the holdout size and random seed."/>
1043 <yield/>
1044 </when>
1045 </conditional>
1046 <!--param argument="train_size" type="float" optional="True" value="" label="Train size:"/>-->
1047 </xml>
1048
1049 <xml name="train_test_split_test_size" token_optional="false">
1050 <param name="test_size" type="float" value="0.2" optional="@OPTIONAL@" label="Holdout size" help="Leass than 1, for preportion; greater than 1 (integer), for number of samples."/>
1051 </xml>
1052
1053 <xml name="feature_selection_algorithms">
1054 <option value="SelectKBest" selected="true">SelectKBest - Select features according to the k highest scores</option>
1055 <option value="GenericUnivariateSelect">GenericUnivariateSelect - Univariate feature selector with configurable strategy</option>
1056 <option value="SelectPercentile">SelectPercentile - Select features according to a percentile of the highest scores</option>
1057 <option value="SelectFpr">SelectFpr - Filter: Select the p-values below alpha based on a FPR test</option>
1058 <option value="SelectFdr">SelectFdr - Filter: Select the p-values for an estimated false discovery rate</option>
1059 <option value="SelectFwe">SelectFwe - Filter: Select the p-values corresponding to Family-wise error rate</option>
1060 <option value="VarianceThreshold">VarianceThreshold - Feature selector that removes all low-variance features</option>
1061 <option value="SelectFromModel">SelectFromModel - Meta-transformer for selecting features based on importance weights</option>
1062 <option value="RFE">RFE - Feature ranking with recursive feature elimination</option>
1063 <option value="RFECV">RFECV - Feature ranking with recursive feature elimination and cross-validated selection of the best number of features</option>
1064 <yield/>
1065 </xml>
1066
1067 <xml name="feature_selection_algorithm_details">
1068 <when value="GenericUnivariateSelect">
1069 <expand macro="feature_selection_score_function" />
1070 <section name="options" title="Advanced Options" expanded="False">
1071 <param argument="mode" type="select" label="Feature selection mode">
1072 <option value="percentile">percentile</option>
1073 <option value="k_best">k_best</option>
1074 <option value="fpr">fpr</option>
1075 <option value="fdr">fdr</option>
1076 <option value="fwe">fwe</option>
1077 </param>
1078 <param argument="param" type="float" value="" optional="true" label="Parameter of the corresponding mode" help="float or int depending on the feature selection mode" />
1079 </section>
1080 </when>
1081 <when value="SelectPercentile">
1082 <expand macro="feature_selection_score_function" />
1083 <section name="options" title="Advanced Options" expanded="False">
1084 <param argument="percentile" type="integer" value="10" optional="True" label="Percent of features to keep" />
1085 </section>
1086 </when>
1087 <when value="SelectKBest">
1088 <expand macro="feature_selection_score_function" />
1089 <section name="options" title="Advanced Options" expanded="False">
1090 <param argument="k" type="integer" value="10" optional="True" label="Number of top features to select" help="No 'all' option is supported." />
1091 </section>
1092 </when>
1093 <when value="SelectFpr">
1094 <expand macro="feature_selection_score_function" />
1095 <section name="options" title="Advanced Options" expanded="False">
1096 <param argument="alpha" type="float" value="" optional="True" label="Alpha" help="The highest p-value for features to be kept."/>
1097 </section>
1098 </when>
1099 <when value="SelectFdr">
1100 <expand macro="feature_selection_score_function" />
1101 <section name="options" title="Advanced Options" expanded="False">
1102 <param argument="alpha" type="float" value="" optional="True" label="Alpha" help="The highest uncorrected p-value for features to keep."/>
1103 </section>
1104 </when>
1105 <when value="SelectFwe">
1106 <expand macro="feature_selection_score_function" />
1107 <section name="options" title="Advanced Options" expanded="False">
1108 <param argument="alpha" type="float" value="" optional="True" label="Alpha" help="The highest uncorrected p-value for features to keep."/>
1109 </section>
1110 </when>
1111 <when value="VarianceThreshold">
1112 <section name="options" title="Options" expanded="False">
1113 <param argument="threshold" type="float" value="0.0" optional="True" label="Threshold" help="Features with a training-set variance lower than this threshold will be removed."/>
1114 </section>
1115 </when>
1116 </xml>
1117
1118 <xml name="feature_selection_SelectFromModel">
1119 <when value="SelectFromModel">
1120 <conditional name="model_inputter">
1121 <param name="input_mode" type="select" label="Construct a new estimator from a selection list?" >
1122 <option value="new" selected="true">Yes</option>
1123 <option value="prefitted">No. Load a prefitted estimator</option>
1124 </param>
1125 <when value="new">
1126 <expand macro="estimator_selector_fs"/>
1127 </when>
1128 <when value="prefitted">
1129 <param name="fitted_estimator" type="data" format='zip' label="Load a prefitted estimator" />
1130 </when>
1131 </conditional>
1132 <expand macro="feature_selection_SelectFromModel_options"/>
1133 </when>
1134 </xml>
1135
1136 <xml name="feature_selection_SelectFromModel_no_prefitted">
1137 <when value="SelectFromModel">
1138 <conditional name="model_inputter">
1139 <param name="input_mode" type="select" label="Construct a new estimator from a selection list?" >
1140 <option value="new" selected="true">Yes</option>
1141 </param>
1142 <when value="new">
1143 <expand macro="estimator_selector_all"/>
1144 </when>
1145 </conditional>
1146 <expand macro="feature_selection_SelectFromModel_options"/>
1147 </when>
1148 </xml>
1149
1150 <xml name="feature_selection_SelectFromModel_options">
1151 <section name="options" title="Advanced Options" expanded="False">
1152 <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'." />
1153 <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. " />
1154 <param argument="max_features" type="integer" value="" optional="true" label="The maximum number of features selected scoring above threshold" help="To disable threshold and only select based on max_features, set threshold=-np.inf."/>
1155 </section>
1156 </xml>
1157
1158 <xml name="feature_selection_RFE">
1159 <when value="RFE">
1160 <yield/>
1161 <section name="options" title="Advanced Options" expanded="False">
1162 <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." />
1163 <param argument="step" type="float" value="1" label="step" optional="true" help="Default = 1. " />
1164 <param argument="verbose" type="integer" value="0" label="verbose" help="Controls verbosity of output." />
1165 </section>
1166 </when>
1167 </xml>
1168
1169 <xml name="feature_selection_RFECV_fs">
1170 <when value="RFECV">
1171 <yield/>
1172 <section name="options" title="Advanced Options" expanded="False">
1173 <param argument="step" type="float" value="1" label="step" optional="true" help="Default = 1. " />
1174 <param argument="min_features_to_select" type="integer" value="1" optional="true" label="The minimum number of features to be selected"/>
1175 <expand macro="cv"/>
1176 <expand macro="scoring_selection"/>
1177 <param argument="verbose" type="integer" value="0" label="verbose" help="Controls verbosity of output." />
1178 </section>
1179 </when>
1180 </xml>
1181
1182 <xml name="feature_selection_RFECV_pipeline">
1183 <when value="RFECV">
1184 <yield/>
1185 <section name="options" title="Advanced Options" expanded="False">
1186 <param argument="step" type="float" value="1" label="step" optional="true" help="Default = 1. " />
1187 <param argument="min_features_to_select" type="integer" value="1" optional="true" label="The minimum number of features to be selected"/>
1188 <expand macro="cv_reduced"/>
1189 <!-- TODO: group splitter support-->
1190 <expand macro="scoring_selection"/>
1191 <param argument="verbose" type="integer" value="0" label="verbose" help="Controls verbosity of output." />
1192 </section>
1193 </when>
1194 </xml>
1195
1196 <xml name="feature_selection_DyRFECV_fs">
1197 <when value="DyRFECV">
1198 <yield/>
1199 <section name="options" title="Advanced Options" expanded="False">
1200 <param argument="step" type="text" size="30" value="1" label="step" optional="true" help="Default = 1. Support float, int and list." >
1201 <sanitizer>
1202 <valid initial="default">
1203 <add value="["/>
1204 <add value="]"/>
1205 </valid>
1206 </sanitizer>
1207 </param>
1208 <param argument="min_features_to_select" type="integer" value="1" optional="true" label="The minimum number of features to be selected"/>
1209 <expand macro="cv"/>
1210 <expand macro="scoring_selection"/>
1211 <param argument="verbose" type="integer" value="0" label="verbose" help="Controls verbosity of output." />
1212 </section>
1213 </when>
1214 </xml>
1215
1216 <xml name="feature_selection_pipeline">
1217 <!--compare to `feature_selection_fs`, no fitted estimator for SelectFromModel and no custom estimator for RFE and RFECV-->
1218 <conditional name="fs_algorithm_selector">
1219 <param name="selected_algorithm" type="select" label="Select a feature selection algorithm">
1220 <expand macro="feature_selection_algorithms"/>
1221 </param>
1222 <expand macro="feature_selection_algorithm_details"/>
1223 <expand macro="feature_selection_SelectFromModel_no_prefitted"/>
1224 <expand macro="feature_selection_RFE">
1225 <expand macro="estimator_selector_all"/>
1226 </expand>
1227 <expand macro="feature_selection_RFECV_pipeline">
1228 <expand macro="estimator_selector_all"/>
1229 </expand>
1230 <!-- TODO: add DyRFECV to pipeline-->
1231 </conditional>
1232 </xml>
1233
1234 <xml name="feature_selection_fs">
1235 <conditional name="fs_algorithm_selector">
1236 <param name="selected_algorithm" type="select" label="Select a feature selection algorithm">
1237 <expand macro="feature_selection_algorithms">
1238 <option value="DyRFECV">DyRFECV - Extended RFECV with changeable steps</option>
1239 </expand>
1240 </param>
1241 <expand macro="feature_selection_algorithm_details"/>
1242 <expand macro="feature_selection_SelectFromModel"/>
1243 <expand macro="feature_selection_RFE">
1244 <expand macro="estimator_selector_fs"/>
1245 </expand>
1246 <expand macro="feature_selection_RFECV_fs">
1247 <expand macro="estimator_selector_fs"/>
1248 </expand>
1249 <expand macro="feature_selection_DyRFECV_fs">
1250 <expand macro="estimator_selector_fs"/>
1251 </expand>
1252 </conditional>
1253 </xml>
1254
1255 <xml name="feature_selection_score_function">
1256 <param argument="score_func" type="select" label="Select a score function">
1257 <option value="chi2">chi2 - Compute chi-squared stats between each non-negative feature and class</option>
1258 <option value="f_classif">f_classif - Compute the ANOVA F-value for the provided sample</option>
1259 <option value="f_regression">f_regression - Univariate linear regression tests</option>
1260 <option value="mutual_info_classif">mutual_info_classif - Estimate mutual information for a discrete target variable</option>
1261 <option value="mutual_info_regression">mutual_info_regression - Estimate mutual information for a continuous target variable</option>
1262 </param>
1263 </xml>
1264
1265 <xml name="model_validation_common_options">
1266 <expand macro="cv"/>
1267 <expand macro="verbose"/>
1268 <yield/>
1269 </xml>
1270
1271 <xml name="scoring_selection">
1272 <conditional name="scoring">
1273 <param name="primary_scoring" type="select" multiple="false" label="Select the primary metric (scoring):" help="Metric to refit the best estimator.">
1274 <option value="default" selected="true">default with estimator</option>
1275 <option value="accuracy">Classification -- 'accuracy'</option>
1276 <option value="balanced_accuracy">Classification -- 'balanced_accuracy'</option>
1277 <option value="average_precision">Classification -- 'average_precision'</option>
1278 <option value="f1">Classification -- 'f1'</option>
1279 <option value="f1_micro">Classification -- 'f1_micro'</option>
1280 <option value="f1_macro">Classification -- 'f1_macro'</option>
1281 <option value="f1_weighted">Classification -- 'f1_weighted'</option>
1282 <option value="f1_samples">Classification -- 'f1_samples'</option>
1283 <option value="neg_log_loss">Classification -- 'neg_log_loss'</option>
1284 <option value="precision">Classification -- 'precision'</option>
1285 <option value="precision_micro">Classification -- 'precision_micro'</option>
1286 <option value="precision_macro">Classification -- 'precision_macro'</option>
1287 <option value="precision_wighted">Classification -- 'precision_wighted'</option>
1288 <option value="precision_samples">Classification -- 'precision_samples'</option>
1289 <option value="recall">Classification -- 'recall'</option>
1290 <option value="recall_micro">Classification -- 'recall_micro'</option>
1291 <option value="recall_macro">Classification -- 'recall_macro'</option>
1292 <option value="recall_wighted">Classification -- 'recall_wighted'</option>
1293 <option value="recall_samples">Classification -- 'recall_samples'</option>
1294 <option value="roc_auc">Classification -- 'roc_auc'</option>
1295 <option value="explained_variance">Regression -- 'explained_variance'</option>
1296 <option value="neg_mean_absolute_error">Regression -- 'neg_mean_absolute_error'</option>
1297 <option value="neg_mean_squared_error">Regression -- 'neg_mean_squared_error'</option>
1298 <option value="neg_mean_squared_log_error">Regression -- 'neg_mean_squared_log_error'</option>
1299 <option value="neg_median_absolute_error">Regression -- 'neg_median_absolute_error'</option>
1300 <option value="r2">Regression -- 'r2'</option>
1301 <option value="max_error">Regression -- 'max_error'</option>
1302 <option value="binarize_auc_scorer">anomaly detection -- binarize_auc_scorer</option>
1303 <option value="binarize_average_precision_scorer">anomaly detection -- binarize_average_precision_scorer</option>
1304 </param>
1305 <when value="default"/>
1306 <when value="accuracy"><expand macro="secondary_scoring_selection_classification"/></when>
1307 <when value="balanced_accuracy"><expand macro="secondary_scoring_selection_classification"/></when>
1308 <when value="average_precision"><expand macro="secondary_scoring_selection_classification"/></when>
1309 <when value="f1"><expand macro="secondary_scoring_selection_classification"/></when>
1310 <when value="f1_micro"><expand macro="secondary_scoring_selection_classification"/></when>
1311 <when value="f1_macro"><expand macro="secondary_scoring_selection_classification"/></when>
1312 <when value="f1_weighted"><expand macro="secondary_scoring_selection_classification"/></when>
1313 <when value="f1_samples"><expand macro="secondary_scoring_selection_classification"/></when>
1314 <when value="neg_log_loss"><expand macro="secondary_scoring_selection_classification"/></when>
1315 <when value="precision"><expand macro="secondary_scoring_selection_classification"/></when>
1316 <when value="precision_micro"><expand macro="secondary_scoring_selection_classification"/></when>
1317 <when value="precision_macro"><expand macro="secondary_scoring_selection_classification"/></when>
1318 <when value="precision_wighted"><expand macro="secondary_scoring_selection_classification"/></when>
1319 <when value="precision_samples"><expand macro="secondary_scoring_selection_classification"/></when>
1320 <when value="recall"><expand macro="secondary_scoring_selection_classification"/></when>
1321 <when value="recall_micro"><expand macro="secondary_scoring_selection_classification"/></when>
1322 <when value="recall_macro"><expand macro="secondary_scoring_selection_classification"/></when>
1323 <when value="recall_wighted"><expand macro="secondary_scoring_selection_classification"/></when>
1324 <when value="recall_samples"><expand macro="secondary_scoring_selection_classification"/></when>
1325 <when value="roc_auc"><expand macro="secondary_scoring_selection_classification"/></when>
1326 <when value="explained_variance"><expand macro="secondary_scoring_selection_regression"/></when>
1327 <when value="neg_mean_absolute_error"><expand macro="secondary_scoring_selection_regression"/></when>
1328 <when value="neg_mean_squared_error"><expand macro="secondary_scoring_selection_regression"/></when>
1329 <when value="neg_mean_squared_log_error"><expand macro="secondary_scoring_selection_regression"/></when>
1330 <when value="neg_median_absolute_error"><expand macro="secondary_scoring_selection_regression"/></when>
1331 <when value="r2"><expand macro="secondary_scoring_selection_regression"/></when>
1332 <when value="max_error"><expand macro="secondary_scoring_selection_regression"/></when>
1333 <when value="binarize_auc_scorer"><expand macro="secondary_scoring_selection_anormaly"/></when>
1334 <when value="binarize_average_precision_scorer"><expand macro="secondary_scoring_selection_anormaly"/></when>
1335 </conditional>
1336 </xml>
1337
1338 <xml name="secondary_scoring_selection_classification">
1339 <param name="secondary_scoring" type="select" multiple="true" label="Additional scoring used in multi-metric mode:" help="If the same metric with the primary is chosen, the metric will be ignored.">
1340 <option value="accuracy">Classification -- 'accuracy'</option>
1341 <option value="balanced_accuracy">Classification -- 'balanced_accuracy'</option>
1342 <option value="average_precision">Classification -- 'average_precision'</option>
1343 <option value="f1">Classification -- 'f1'</option>
1344 <option value="f1_micro">Classification -- 'f1_micro'</option>
1345 <option value="f1_macro">Classification -- 'f1_macro'</option>
1346 <option value="f1_weighted">Classification -- 'f1_weighted'</option>
1347 <option value="f1_samples">Classification -- 'f1_samples'</option>
1348 <option value="neg_log_loss">Classification -- 'neg_log_loss'</option>
1349 <option value="precision">Classification -- 'precision'</option>
1350 <option value="precision_micro">Classification -- 'precision_micro'</option>
1351 <option value="precision_macro">Classification -- 'precision_macro'</option>
1352 <option value="precision_wighted">Classification -- 'precision_wighted'</option>
1353 <option value="precision_samples">Classification -- 'precision_samples'</option>
1354 <option value="recall">Classification -- 'recall'</option>
1355 <option value="recall_micro">Classification -- 'recall_micro'</option>
1356 <option value="recall_macro">Classification -- 'recall_macro'</option>
1357 <option value="recall_wighted">Classification -- 'recall_wighted'</option>
1358 <option value="recall_samples">Classification -- 'recall_samples'</option>
1359 <option value="roc_auc">Classification -- 'roc_auc'</option>
1360 </param>
1361 </xml>
1362
1363 <xml name="secondary_scoring_selection_regression">
1364 <param name="secondary_scoring" type="select" multiple="true" label="Additional scoring used in multi-metric mode:" help="If the same metric with the primary is chosen, the metric will be ignored.">
1365 <option value="explained_variance">Regression -- 'explained_variance'</option>
1366 <option value="neg_mean_absolute_error">Regression -- 'neg_mean_absolute_error'</option>
1367 <option value="neg_mean_squared_error">Regression -- 'neg_mean_squared_error'</option>
1368 <option value="neg_mean_squared_log_error">Regression -- 'neg_mean_squared_log_error'</option>
1369 <option value="neg_median_absolute_error">Regression -- 'neg_median_absolute_error'</option>
1370 <option value="r2">Regression -- 'r2'</option>
1371 <option value="max_error">Regression -- 'max_error'</option>
1372 </param>
1373 </xml>
1374
1375 <xml name="secondary_scoring_selection_anormaly">
1376 <param name="secondary_scoring" type="select" multiple="true" label="Additional scoring used in multi-metric mode:" help="If the same metric with the primary is chosen, the metric will be ignored.">
1377 <option value="binarize_auc_scorer">anomaly detection -- binarize_auc_scorer</option>
1378 <option value="binarize_average_precision_scorer">anomaly detection -- binarize_average_precision_scorer</option>
1379 </param>
1380 </xml>
1381
1382 <xml name="pre_dispatch" token_type="hidden" token_default_value="all" token_help="Number of predispatched jobs for parallel execution">
1383 <param argument="pre_dispatch" type="@TYPE@" value="@DEFAULT_VALUE@" optional="true" label="pre_dispatch" help="@HELP@"/>
1384 </xml>
1385
1386 <xml name="estimator_and_hyperparameter">
1387 <param name="infile_estimator" type="data" format="zip" label="Choose the dataset containing pipeline/estimator object"/>
1388 <section name="hyperparams_swapping" title="Hyperparameter Swapping" expanded="false">
1389 <param name="infile_params" type="data" format="tabular" optional="true" label="Choose the dataset containing hyperparameters for the pipeline/estimator above" help="This dataset could be the output of `get_params` in the `Estimator Attributes` tool."/>
1390 <repeat name="param_set" min="1" max="30" title="New hyperparameter setting">
1391 <param name="sp_name" type="select" optional="true" label="Choose a parameter name (with current value)">
1392 <options from_dataset="infile_params" startswith="@">
1393 <column name="name" index="2"/>
1394 <column name="value" index="1"/>
1395 <filter type="unique_value" name="unique_param" column="1"/>
1396 </options>
1397 </param>
1398 <param name="sp_value" type="text" value="" optional="true" label="New value" help="Supports int, float, boolean, single quoted string, and selected object constructor. Similar to the `Parameter settings for search` section in `searchcv` tool except that only single value is expected here.">
1399 <sanitizer>
1400 <valid initial="default">
1401 <add value="&apos;"/>
1402 <add value="&quot;"/>
1403 </valid>
1404 </sanitizer>
1405 </param>
1406 </repeat>
1407 </section>
1408 </xml>
1409
1410 <xml name="search_cv_options">
1411 <expand macro="scoring_selection"/>
1412 <expand macro="model_validation_common_options"/>
1413 <!--expand macro="pre_dispatch" default_value="2*n_jobs" help="Controls the number of jobs that get dispatched during parallel execution"/-->
1414 <param argument="iid" type="boolean" truevalue="booltrue" falsevalue="boolfalse" checked="true" label="iid" help="If True, data is identically distributed across the folds"/>
1415 <!--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. Be aware that `refit=True` invokes extra computation, but it's REQUIRED for outputting the best estimator!"/> -->
1416 <param argument="error_score" type="boolean" truevalue="booltrue" falsevalue="boolfalse" checked="true" label="Raise fit error:" help="If false, the metric score is assigned to NaN if an error occurs in estimator fitting and FitFailedWarning is raised."/>
1417 <param argument="return_train_score" type="boolean" truevalue="booltrue" falsevalue="boolfalse" checked="false" label="return_train_score" help=""/>
1418 </xml>
1419
1420 <xml name="estimator_module_options">
1421 <option value="svm" selected="true">sklearn.svm</option>
1422 <option value="linear_model">sklearn.linear_model</option>
1423 <option value="ensemble">sklearn.ensemble</option>
1424 <option value="naive_bayes">sklearn.naive_bayes</option>
1425 <option value="tree">sklearn.tree</option>
1426 <option value="neighbors">sklearn.neighbors</option>
1427 <option value="xgboost">xgboost</option>
1428 <yield/>
1429 </xml>
1430
1431 <xml name="estimator_suboptions">
1432 <when value="svm">
1433 <param name="selected_estimator" type="select" label="Choose estimator class:">
1434 <option value="LinearSVC" selected="true">LinearSVC</option>
1435 <option value="LinearSVR">LinearSVR</option>
1436 <option value="NuSVC">NuSVC</option>
1437 <option value="NuSVR">NuSVR</option>
1438 <option value="OneClassSVM">OneClassSVM</option>
1439 <option value="SVC">SVC</option>
1440 <option value="SVR">SVR</option>
1441 </param>
1442 <expand macro="estimator_params_text"/>
1443 </when>
1444 <when value="linear_model">
1445 <param name="selected_estimator" type="select" label="Choose estimator class:">
1446 <option value="ARDRegression" selected="true">ARDRegression</option>
1447 <option value="BayesianRidge">BayesianRidge</option>
1448 <option value="ElasticNet">ElasticNet</option>
1449 <option value="ElasticNetCV">ElasticNetCV</option>
1450 <option value="HuberRegressor">HuberRegressor</option>
1451 <option value="Lars">Lars</option>
1452 <option value="LarsCV">LarsCV</option>
1453 <option value="Lasso">Lasso</option>
1454 <option value="LassoCV">LassoCV</option>
1455 <option value="LassoLars">LassoLars</option>
1456 <option value="LassoLarsCV">LassoLarsCV</option>
1457 <option value="LassoLarsIC">LassoLarsIC</option>
1458 <option value="LinearRegression">LinearRegression</option>
1459 <option value="LogisticRegression">LogisticRegression</option>
1460 <option value="LogisticRegressionCV">LogisticRegressionCV</option>
1461 <option value="MultiTaskLasso">MultiTaskLasso</option>
1462 <option value="MultiTaskElasticNet">MultiTaskElasticNet</option>
1463 <option value="MultiTaskLassoCV">MultiTaskLassoCV</option>
1464 <option value="MultiTaskElasticNetCV">MultiTaskElasticNetCV</option>
1465 <option value="OrthogonalMatchingPursuit">OrthogonalMatchingPursuit</option>
1466 <option value="OrthogonalMatchingPursuitCV">OrthogonalMatchingPursuitCV</option>
1467 <option value="PassiveAggressiveClassifier">PassiveAggressiveClassifier</option>
1468 <option value="PassiveAggressiveRegressor">PassiveAggressiveRegressor</option>
1469 <option value="Perceptron">Perceptron</option>
1470 <option value="RANSACRegressor">RANSACRegressor</option>
1471 <option value="Ridge">Ridge</option>
1472 <option value="RidgeClassifier">RidgeClassifier</option>
1473 <option value="RidgeClassifierCV">RidgeClassifierCV</option>
1474 <option value="RidgeCV">RidgeCV</option>
1475 <option value="SGDClassifier">SGDClassifier</option>
1476 <option value="SGDRegressor">SGDRegressor</option>
1477 <option value="TheilSenRegressor">TheilSenRegressor</option>
1478 </param>
1479 <expand macro="estimator_params_text"/>
1480 </when>
1481 <when value="ensemble">
1482 <param name="selected_estimator" type="select" label="Choose estimator class:">
1483 <option value="AdaBoostClassifier" selected="true">AdaBoostClassifier</option>
1484 <option value="AdaBoostRegressor">AdaBoostRegressor</option>
1485 <option value="BaggingClassifier">BaggingClassifier</option>
1486 <option value="BaggingRegressor">BaggingRegressor</option>
1487 <option value="ExtraTreesClassifier">ExtraTreesClassifier</option>
1488 <option value="ExtraTreesRegressor">ExtraTreesRegressor</option>
1489 <option value="GradientBoostingClassifier">GradientBoostingClassifier</option>
1490 <option value="GradientBoostingRegressor">GradientBoostingRegressor</option>
1491 <option value="IsolationForest">IsolationForest</option>
1492 <option value="HistGradientBoostingClassifier">HistGradientBoostingClassifier</option>
1493 <option value="HistGradientBoostingRegressor">HistGradientBoostingRegressor</option>
1494 <option value="RandomForestClassifier">RandomForestClassifier</option>
1495 <option value="RandomForestRegressor">RandomForestRegressor</option>
1496 <option value="RandomTreesEmbedding">RandomTreesEmbedding</option>
1497 <!--option value="VotingClassifier">VotingClassifier</option-->
1498 </param>
1499 <expand macro="estimator_params_text"/>
1500 </when>
1501 <when value="naive_bayes">
1502 <param name="selected_estimator" type="select" label="Choose estimator class:">
1503 <option value="BernoulliNB" selected="true">BernoulliNB</option>
1504 <option value="GaussianNB">GaussianNB</option>
1505 <option value="MultinomialNB">MultinomialNB</option>
1506 </param>
1507 <expand macro="estimator_params_text"/>
1508 </when>
1509 <when value="tree">
1510 <param name="selected_estimator" type="select" label="Choose estimator class:">
1511 <option value="DecisionTreeClassifier" selected="true">DecisionTreeClassifier</option>
1512 <option value="DecisionTreeRegressor">DecisionTreeRegressor</option>
1513 <option value="ExtraTreeClassifier">ExtraTreeClassifier</option>
1514 <option value="ExtraTreeRegressor">ExtraTreeRegressor</option>
1515 </param>
1516 <expand macro="estimator_params_text"/>
1517 </when>
1518 <when value="neighbors">
1519 <param name="selected_estimator" type="select" label="Choose estimator class:">
1520 <option value="KNeighborsClassifier" selected="true">KNeighborsClassifier</option>
1521 <option value="KNeighborsRegressor">KNeighborsRegressor</option>
1522 <!--option value="BallTree">BallTree</option-->
1523 <!--option value="KDTree">KDTree</option-->
1524 <option value="KernelDensity">KernelDensity</option>
1525 <option value="LocalOutlierFactor">LocalOutlierFactor</option>
1526 <option value="RadiusNeighborsClassifier">RadiusNeighborsClassifier</option>
1527 <option value="RadiusNeighborsRegressor">RadiusNeighborsRegressor</option>
1528 <option value="NearestCentroid">NearestCentroid</option>
1529 <option value="NearestNeighbors">NearestNeighbors</option>
1530 </param>
1531 <expand macro="estimator_params_text"/>
1532 </when>
1533 <when value="xgboost">
1534 <param name="selected_estimator" type="select" label="Choose estimator class:">
1535 <option value="XGBRegressor" selected="true">XGBRegressor</option>
1536 <option value="XGBClassifier">XGBClassifier</option>
1537 </param>
1538 <expand macro="estimator_params_text"/>
1539 </when>
1540 <yield/>
1541 </xml>
1542
1543 <xml name="estimator_selector_all">
1544 <conditional name="estimator_selector">
1545 <param name="selected_module" type="select" label="Choose the module that contains target estimator:" >
1546 <expand macro="estimator_module_options"/>
1547 </param>
1548 <expand macro="estimator_suboptions"/>
1549 </conditional>
1550 </xml>
1551
1552 <xml name="estimator_selector_fs">
1553 <conditional name="estimator_selector">
1554 <param name="selected_module" type="select" label="Choose the module that contains target estimator:" >
1555 <expand macro="estimator_module_options">
1556 <option value="custom_estimator">Load a custom estimator</option>
1557 </expand>
1558 </param>
1559 <expand macro="estimator_suboptions">
1560 <when value="custom_estimator">
1561 <param name="c_estimator" type="data" format="zip" label="Choose the dataset containing the custom estimator or pipeline:"/>
1562 </when>
1563 </expand>
1564 </conditional>
1565 </xml>
1566
1567 <xml name="estimator_params_text" token_label="Type in parameter settings if different from default:" token_default_value=''
1568 token_help="Dictionary-capable, e.g., C=1, kernel='linear'. No double quotes. Leave this box blank for default estimator.">
1569 <param name="text_params" type="text" value="@DEFAULT_VALUE@" optional="true" label="@LABEL@" help="@HELP@">
1570 <sanitizer>
1571 <valid initial="default">
1572 <add value="&apos;"/>
1573 </valid>
1574 </sanitizer>
1575 </param>
1576 </xml>
1577
1578 <xml name="kernel_approximation_all">
1579 <conditional name="kernel_approximation_selector">
1580 <param name="select_algorithm" type="select" label="Choose a kernel approximation algorithm:">
1581 <option value="Nystroem" selected="true">Nystroem</option>
1582 <option value="RBFSampler">RBFSampler</option>
1583 <option value="AdditiveChi2Sampler">AdditiveChi2Sampler</option>
1584 <option value="SkewedChi2Sampler">SkewedChi2Sampler</option>
1585 </param>
1586 <when value="Nystroem">
1587 <expand macro="estimator_params_text"
1588 help="Default(=blank): coef0=None, degree=None, gamma=None, kernel='rbf', kernel_params=None, n_components=100, random_state=None. No double quotes"/>
1589 </when>
1590 <when value="RBFSampler">
1591 <expand macro="estimator_params_text"
1592 help="Default(=blank): gamma=1.0, n_components=100, random_state=None."/>
1593 </when>
1594 <when value="AdditiveChi2Sampler">
1595 <expand macro="estimator_params_text"
1596 help="Default(=blank): sample_interval=None, sample_steps=2."/>
1597 </when>
1598 <when value="SkewedChi2Sampler">
1599 <expand macro="estimator_params_text"
1600 help="Default(=blank): n_components=100, random_state=None, skewedness=1.0."/>
1601 </when>
1602 </conditional>
1603 </xml>
1604
1605 <xml name="matrix_decomposition_all">
1606 <conditional name="matrix_decomposition_selector">
1607 <param name="select_algorithm" type="select" label="Choose a matrix decomposition algorithm:">
1608 <option value="DictionaryLearning" selected="true">DictionaryLearning</option>
1609 <option value="FactorAnalysis">FactorAnalysis</option>
1610 <option value="FastICA">FastICA</option>
1611 <option value="IncrementalPCA">IncrementalPCA</option>
1612 <option value="KernelPCA">KernelPCA</option>
1613 <option value="LatentDirichletAllocation">LatentDirichletAllocation</option>
1614 <option value="MiniBatchDictionaryLearning">MiniBatchDictionaryLearning</option>
1615 <option value="MiniBatchSparsePCA">MiniBatchSparsePCA</option>
1616 <option value="NMF">NMF</option>
1617 <option value="PCA">PCA</option>
1618 <option value="SparsePCA">SparsePCA</option>
1619 <!--option value="SparseCoder">SparseCoder</option-->
1620 <option value="TruncatedSVD">TruncatedSVD</option>
1621 </param>
1622 <when value="DictionaryLearning">
1623 <expand macro="estimator_params_text"
1624 help="Default(=blank): alpha=1, code_init=None, dict_init=None, fit_algorithm='lars', max_iter=1000, n_components=None, random_state=None, split_sign=False, tol=1e-08, transform_algorithm='omp', transform_alpha=None, transform_n_nonzero_coefs=None, verbose=False."/>
1625 </when>
1626 <when value="FactorAnalysis">
1627 <expand macro="estimator_params_text"
1628 help="Default(=blank): copy=True, iterated_power=3, max_iter=1000, n_components=None, noise_variance_init=None, random_state=0, svd_method='randomized', tol=0.01."/>
1629 </when>
1630 <when value="FastICA">
1631 <expand macro="estimator_params_text"
1632 help="Default(=blank): algorithm='parallel', fun='logcosh', fun_args=None, max_iter=200, n_components=None, random_state=None, tol=0.0001, w_init=None, whiten=True. No double quotes."/>
1633 </when>
1634 <when value="IncrementalPCA">
1635 <expand macro="estimator_params_text"
1636 help="Default(=blank): batch_size=None, copy=True, n_components=None, whiten=False."/>
1637 </when>
1638 <when value="KernelPCA">
1639 <expand macro="estimator_params_text"
1640 help="Default(=blank): alpha=1.0, coef0=1, copy_X=True, degree=3, eigen_solver='auto', fit_inverse_transform=False, gamma=None, kernel='linear', kernel_params=None, max_iter=None, n_components=None, random_state=None, remove_zero_eig=False, tol=0. No double quotes."/>
1641 </when>
1642 <when value="LatentDirichletAllocation">
1643 <expand macro="estimator_params_text"
1644 help="Default(=blank): batch_size=128, doc_topic_prior=None, evaluate_every=-1, learning_decay=0.7, learning_method=None, learning_offset=10.0, max_doc_update_iter=100, max_iter=10, mean_change_tol=0.001, n_components=10, n_topics=None, perp_tol=0.1, random_state=None, topic_word_prior=None, total_samples=1000000.0, verbose=0."/>
1645 </when>
1646 <when value="MiniBatchDictionaryLearning">
1647 <expand macro="estimator_params_text"
1648 help="Default(=blank): alpha=1, batch_size=3, dict_init=None, fit_algorithm='lars', n_components=None, n_iter=1000, random_state=None, shuffle=True, split_sign=False, transform_algorithm='omp', transform_alpha=None, transform_n_nonzero_coefs=None, verbose=False."/>
1649 </when>
1650 <when value="MiniBatchSparsePCA">
1651 <expand macro="estimator_params_text"
1652 help="Default(=blank): alpha=1, batch_size=3, callback=None, method='lars', n_components=None, n_iter=100, random_state=None, ridge_alpha=0.01, shuffle=True, verbose=False."/>
1653 </when>
1654 <when value="NMF">
1655 <expand macro="estimator_params_text"
1656 help="Default(=blank): alpha=0.0, beta_loss='frobenius', init=None, l1_ratio=0.0, max_iter=200, n_components=None, random_state=None, shuffle=False, solver='cd', tol=0.0001, verbose=0."/>
1657 </when>
1658 <when value="PCA">
1659 <expand macro="estimator_params_text"
1660 help="Default(=blank): copy=True, iterated_power='auto', n_components=None, random_state=None, svd_solver='auto', tol=0.0, whiten=False."/>
1661 </when>
1662 <when value="SparsePCA">
1663 <expand macro="estimator_params_text"
1664 help="Default(=blank): U_init=None, V_init=None, alpha=1, max_iter=1000, method='lars', n_components=None, random_state=None, ridge_alpha=0.01, tol=1e-08, verbose=False."/>
1665 </when>
1666 <when value="TruncatedSVD">
1667 <expand macro="estimator_params_text"
1668 help="Default(=blank): algorithm='randomized', n_components=2, n_iter=5, random_state=None, tol=0.0."/>
1669 </when>
1670 </conditional>
1671 </xml>
1672
1673 <xml name="FeatureAgglomeration">
1674 <conditional name="FeatureAgglomeration_selector">
1675 <param name="select_algorithm" type="select" label="Choose the algorithm:">
1676 <option value="FeatureAgglomeration" selected="true">FeatureAgglomeration</option>
1677 </param>
1678 <when value="FeatureAgglomeration">
1679 <expand macro="estimator_params_text"
1680 help="Default(=blank): affinity='euclidean', compute_full_tree='auto', connectivity=None, linkage='ward', memory=None, n_clusters=2, pooling_func=np.mean."/>
1681 </when>
1682 </conditional>
1683 </xml>
1684
1685 <xml name="skrebate">
1686 <conditional name="skrebate_selector">
1687 <param name="select_algorithm" type="select" label="Choose the algorithm:">
1688 <option value="ReliefF">ReliefF</option>
1689 <option value="SURF">SURF</option>
1690 <option value="SURFstar">SURFstar</option>
1691 <option value="MultiSURF">MultiSURF</option>
1692 <option value="MultiSURFstar">MultiSURFstar</option>
1693 <!--option value="TuRF">TuRF</option> -->
1694 </param>
1695 <when value="ReliefF">
1696 <expand macro="estimator_params_text"
1697 help="Default(=blank): discrete_threshold=10, n_features_to_select=10, n_neighbors=100, verbose=False."/>
1698 </when>
1699 <when value="SURF">
1700 <expand macro="estimator_params_text"
1701 help="Default(=blank): discrete_threshold=10, n_features_to_select=10, verbose=False."/>
1702 </when>
1703 <when value="SURFstar">
1704 <expand macro="estimator_params_text"
1705 help="Default(=blank): discrete_threshold=10, n_features_to_select=10, verbose=False."/>
1706 </when>
1707 <when value="MultiSURF">
1708 <expand macro="estimator_params_text"
1709 help="Default(=blank): discrete_threshold=10, n_features_to_select=10, verbose=False."/>
1710 </when>
1711 <when value="MultiSURFstar">
1712 <expand macro="estimator_params_text"
1713 help="Default(=blank): discrete_threshold=10, n_features_to_select=10, verbose=False."/>
1714 </when>
1715 <!--when value="TuRF">
1716 <expand macro="estimator_params_text"
1717 help="Default(=blank): core_algorithm='ReliefF', discrete_threshold=10, n_features_to_select=10, n_neighbors=100, pct=0.5, verbose=False."/>
1718 </when> -->
1719 </conditional>
1720 </xml>
1721
1722 <xml name="imbalanced_learn_sampling">
1723 <conditional name="imblearn_selector">
1724 <param name="select_algorithm" type="select" label="Choose the algorithm:">
1725 <option value="under_sampling.ClusterCentroids" selected="true">under_sampling.ClusterCentroids</option>
1726 <option value="under_sampling.CondensedNearestNeighbour">under_sampling.CondensedNearestNeighbour</option>
1727 <option value="under_sampling.EditedNearestNeighbours">under_sampling.EditedNearestNeighbours</option>
1728 <option value="under_sampling.RepeatedEditedNearestNeighbours">under_sampling.RepeatedEditedNearestNeighbours</option>
1729 <option value="under_sampling.AllKNN">under_sampling.AllKNN</option>
1730 <option value="under_sampling.InstanceHardnessThreshold">under_sampling.InstanceHardnessThreshold</option>
1731 <option value="under_sampling.NearMiss">under_sampling.NearMiss</option>
1732 <option value="under_sampling.NeighbourhoodCleaningRule">under_sampling.NeighbourhoodCleaningRule</option>
1733 <option value="under_sampling.OneSidedSelection">under_sampling.OneSidedSelection</option>
1734 <option value="under_sampling.RandomUnderSampler">under_sampling.RandomUnderSampler</option>
1735 <option value="under_sampling.TomekLinks">under_sampling.TomekLinks</option>
1736 <option value="over_sampling.ADASYN">over_sampling.ADASYN</option>
1737 <option value="over_sampling.RandomOverSampler">over_sampling.RandomOverSampler</option>
1738 <option value="over_sampling.SMOTE">over_sampling.SMOTE</option>
1739 <option value="over_sampling.SVMSMOTE">over_sampling.SVMSMOTE</option>
1740 <option value="over_sampling.BorderlineSMOTE">over_sampling.BorderlineSMOTE</option>
1741 <option value="over_sampling.SMOTENC">over_sampling.SMOTENC</option>
1742 <option value="combine.SMOTEENN">combine.SMOTEENN</option>
1743 <option value="combine.SMOTETomek">combine.SMOTETomek</option>
1744 <option value="Z_RandomOverSampler">Z_RandomOverSampler - for regression</option>
1745 </param>
1746 <when value="under_sampling.ClusterCentroids">
1747 <expand macro="estimator_params_text"
1748 help="Default(=blank): sampling_strategy='auto', random_state=None, estimator=None, voting='auto'."/>
1749 </when>
1750 <when value="under_sampling.CondensedNearestNeighbour">
1751 <expand macro="estimator_params_text"
1752 help="Default(=blank): sampling_strategy='auto', random_state=None, n_neighbors=None, n_seeds_S=1."/>
1753 </when>
1754 <when value="under_sampling.EditedNearestNeighbours">
1755 <expand macro="estimator_params_text"
1756 help="Default(=blank): sampling_strategy='auto', random_state=None, n_neighbors=3, max_iter=100, kind_sel='all'."/>
1757 </when>
1758 <when value="under_sampling.RepeatedEditedNearestNeighbours">
1759 <expand macro="estimator_params_text"
1760 help="Default(=blank): sampling_strategy='auto', random_state=None, n_neighbors=3, max_iter=100, kind_sel='all'."/>
1761 </when>
1762 <when value="under_sampling.AllKNN">
1763 <expand macro="estimator_params_text"
1764 help="Default(=blank): sampling_strategy='auto', random_state=None, n_neighbors=3, kind_sel='all', allow_minority=False."/>
1765 </when>
1766 <when value="under_sampling.InstanceHardnessThreshold">
1767 <expand macro="estimator_params_text"
1768 help="Default(=blank): estimator=None, sampling_strategy='auto', random_state=None, cv=5."/>
1769 </when>
1770 <when value="under_sampling.NearMiss">
1771 <expand macro="estimator_params_text"
1772 help="Default(=blank): sampling_strategy='auto', random_state=None, version=1, n_neighbors=3, n_neighbors_ver3=3."/>
1773 </when>
1774 <when value="under_sampling.NeighbourhoodCleaningRule">
1775 <expand macro="estimator_params_text"
1776 help="Default(=blank): sampling_strategy='auto', random_state=None, n_neighbors=3, kind_sel='all', threshold_cleaning=0.5."/>
1777 </when>
1778 <when value="under_sampling.OneSidedSelection">
1779 <expand macro="estimator_params_text"
1780 help="Default(=blank): sampling_strategy='auto', random_state=None, n_neighbors=None, n_seeds_S=1."/>
1781 </when>
1782 <when value="under_sampling.RandomUnderSampler">
1783 <expand macro="estimator_params_text"
1784 help="Default(=blank): sampling_strategy='auto', random_state=None, replacement=False."/>
1785 </when>
1786 <when value="under_sampling.TomekLinks">
1787 <expand macro="estimator_params_text"
1788 help="Default(=blank): sampling_strategy='auto', random_state=None."/>
1789 </when>
1790 <when value="over_sampling.ADASYN">
1791 <expand macro="estimator_params_text"
1792 help="Default(=blank): sampling_strategy='auto', random_state=None, n_neighbors=5."/>
1793 </when>
1794 <when value="over_sampling.RandomOverSampler">
1795 <expand macro="estimator_params_text"
1796 help="Default(=blank): sampling_strategy='auto', random_state=None."/>
1797 </when>
1798 <when value="over_sampling.SMOTE">
1799 <expand macro="estimator_params_text"
1800 help="Default(=blank): sampling_strategy='auto', random_state=None, k_neighbors=5."/>
1801 </when>
1802 <when value="over_sampling.SVMSMOTE">
1803 <expand macro="estimator_params_text"
1804 help="Default(=blank): sampling_strategy='auto', k_neighbors=5, m_neighbors=10, out_step=0.5, random_state=None, svm_estimator=None."/>
1805 </when>
1806 <when value="over_sampling.BorderlineSMOTE">
1807 <expand macro="estimator_params_text"
1808 help="Default(=blank): sampling_strategy='auto', k_neighbors=5, kind='borderline-1', m_neighbors=10, random_state=None."/>
1809 </when>
1810 <when value="over_sampling.SMOTENC">
1811 <expand macro="estimator_params_text"
1812 help="Default: categorical_features=[], sampling_strategy='auto', random_state=None, k_neighbors=5."/>
1813 </when>
1814 <when value="combine.SMOTEENN">
1815 <expand macro="estimator_params_text"
1816 help="Default(=blank): sampling_strategy='auto', random_state=None, smote=None, enn=None."/>
1817 </when>
1818 <when value="combine.SMOTETomek">
1819 <expand macro="estimator_params_text"
1820 help="Default(=blank): sampling_strategy='auto', random_state=None, smote=None, tomek=None."/>
1821 </when>
1822 <when value="Z_RandomOverSampler">
1823 <expand macro="estimator_params_text"
1824 help="Default(=blank): sampling_strategy='auto', random_state=None, negative_thres=0, positive_thres=-1."/>
1825 </when>
1826 </conditional>
1827 </xml>
1828
1829 <xml name="stacking_ensemble_inputs">
1830 <section name="options" title="Advanced Options" expanded="false">
1831 <yield/>
1832 <param argument="use_features_in_secondary" type="boolean" truevalue="booltrue" falsevalue="boolfalse" checked="false"/>
1833 <param argument="store_train_meta_features" type="boolean" truevalue="booltrue" falsevalue="boolfalse" checked="false"/>
1834 </section>
1835 </xml>
1836
1837 <xml name="stacking_base_estimator">
1838 <conditional name="estimator_selector">
1839 <param name="selected_module" type="select" label="Choose the module that contains target estimator:" >
1840 <expand macro="estimator_module_options">
1841 <option value="custom_estimator">Load a custom estimator</option>
1842 </expand>
1843 </param>
1844 <expand macro="estimator_suboptions">
1845 <when value="custom_estimator">
1846 <param name="c_estimator" type="data" format="zip" label="Choose the dataset containing the custom estimator or pipeline"/>
1847 </when>
1848 </expand>
1849 </conditional>
1850 </xml>
1851
1852 <xml name="stacking_voting_weights">
1853 <section name="options" title="Advanced Options" expanded="false">
1854 <param argument="weights" type="text" value="[]" optional="true" help="Sequence of weights (float or int). Uses uniform weights if None (`[]`).">
1855 <sanitizer>
1856 <valid initial="default">
1857 <add value="["/>
1858 <add value="]"/>
1859 </valid>
1860 </sanitizer>
1861 </param>
1862 <yield/>
1863 </section>
1864 </xml>
1865
1866 <xml name="preprocessors_sequence_encoders">
1867 <conditional name="encoder_selection">
1868 <param name="encoder_type" type="select" label="Choose the sequence encoder class">
1869 <option value="GenomeOneHotEncoder">GenomeOneHotEncoder</option>
1870 <option value="ProteinOneHotEncoder">ProteinOneHotEncoder</option>
1871 </param>
1872 <when value="GenomeOneHotEncoder">
1873 <expand macro="preprocessors_sequence_encoder_arguments"/>
1874 </when>
1875 <when value="ProteinOneHotEncoder">
1876 <expand macro="preprocessors_sequence_encoder_arguments"/>
1877 </when>
1878 </conditional>
1879 </xml>
1880
1881 <xml name="preprocessors_sequence_encoder_arguments">
1882 <param argument="seq_length" type="integer" value="" min="0" optional="true" help="Integer. Sequence length"/>
1883 <param argument="padding" type="boolean" truevalue="booltrue" falsevalue="boolfalse" checked="true" help="Whether to pad or truncate sequence to meet the sequence length."/>
1884 </xml>
1885
1886 <!-- Outputs -->
1887
1888 <xml name="output">
1889 <outputs>
1890 <data format="tabular" name="outfile_predict">
1891 <filter>selected_tasks['selected_task'] == 'load'</filter>
1892 </data>
1893 <data format="zip" name="outfile_fit" label="${tool.name}.${selected_tasks.selected_algorithms.selected_algorithm}">
1894 <filter>selected_tasks['selected_task'] == 'train'</filter>
1895 </data>
1896 </outputs>
1897 </xml>
1898
1899 <!--Citations-->
1900 <xml name="eden_citation">
1901 <citations>
1902 <citation type="doi">10.5281/zenodo.15094</citation>
1903 </citations>
1904 </xml>
1905
1906 <xml name="sklearn_citation">
1907 <citations>
1908 <citation type="bibtex">
1909 @article{scikit-learn,
1910 title={Scikit-learn: Machine Learning in {P}ython},
1911 author={Pedregosa, F. and Varoquaux, G. and Gramfort, A. and Michel, V.
1912 and Thirion, B. and Grisel, O. and Blondel, M. and Prettenhofer, P.
1913 and Weiss, R. and Dubourg, V. and Vanderplas, J. and Passos, A. and
1914 Cournapeau, D. and Brucher, M. and Perrot, M. and Duchesnay, E.},
1915 journal={Journal of Machine Learning Research},
1916 volume={12},
1917 pages={2825--2830},
1918 year={2011}
1919 }
1920 </citation>
1921 <yield/>
1922 </citations>
1923 </xml>
1924
1925 <xml name="scipy_citation">
1926 <citations>
1927 <citation type="bibtex">
1928 @Misc{,
1929 author = {Eric Jones and Travis Oliphant and Pearu Peterson and others},
1930 title = {{SciPy}: Open source scientific tools for {Python}},
1931 year = {2001--},
1932 url = "http://www.scipy.org/",
1933 note = {[Online; accessed 2016-04-09]}
1934 }
1935 </citation>
1936 </citations>
1937 </xml>
1938
1939 <xml name="skrebate_citation">
1940 <citation type="bibtex">
1941 @article{DBLP:journals/corr/abs-1711-08477,
1942 author = {Ryan J. Urbanowicz and
1943 Randal S. Olson and
1944 Peter Schmitt and
1945 Melissa Meeker and
1946 Jason H. Moore},
1947 title = {Benchmarking Relief-Based Feature Selection Methods},
1948 journal = {CoRR},
1949 volume = {abs/1711.08477},
1950 year = {2017},
1951 url = {http://arxiv.org/abs/1711.08477},
1952 archivePrefix = {arXiv},
1953 eprint = {1711.08477},
1954 timestamp = {Mon, 13 Aug 2018 16:46:04 +0200},
1955 biburl = {https://dblp.org/rec/bib/journals/corr/abs-1711-08477},
1956 bibsource = {dblp computer science bibliography, https://dblp.org}
1957 }
1958 </citation>
1959 </xml>
1960
1961 <xml name="xgboost_citation">
1962 <citation type="bibtex">
1963 @inproceedings{Chen:2016:XST:2939672.2939785,
1964 author = {Chen, Tianqi and Guestrin, Carlos},
1965 title = {{XGBoost}: A Scalable Tree Boosting System},
1966 booktitle = {Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining},
1967 series = {KDD '16},
1968 year = {2016},
1969 isbn = {978-1-4503-4232-2},
1970 location = {San Francisco, California, USA},
1971 pages = {785--794},
1972 numpages = {10},
1973 url = {http://doi.acm.org/10.1145/2939672.2939785},
1974 doi = {10.1145/2939672.2939785},
1975 acmid = {2939785},
1976 publisher = {ACM},
1977 address = {New York, NY, USA},
1978 keywords = {large-scale machine learning},
1979 }
1980 </citation>
1981 </xml>
1982
1983 <xml name="imblearn_citation">
1984 <citation type="bibtex">
1985 @article{JMLR:v18:16-365,
1986 author = {Guillaume Lema{{\^i}}tre and Fernando Nogueira and Christos K. Aridas},
1987 title = {Imbalanced-learn: A Python Toolbox to Tackle the Curse of Imbalanced Datasets in Machine Learning},
1988 journal = {Journal of Machine Learning Research},
1989 year = {2017},
1990 volume = {18},
1991 number = {17},
1992 pages = {1-5},
1993 url = {http://jmlr.org/papers/v18/16-365.html}
1994 }
1995 </citation>
1996 </xml>
1997
1998 <xml name="selene_citation">
1999 <citation type="bibtex">
2000 @article{chen2019selene,
2001 title={Selene: a PyTorch-based deep learning library for sequence data},
2002 author={Chen, Kathleen M and Cofer, Evan M and Zhou, Jian and Troyanskaya, Olga G},
2003 journal={Nature methods},
2004 volume={16},
2005 number={4},
2006 pages={315},
2007 year={2019},
2008 publisher={Nature Publishing Group}
2009 }
2010 </citation>
2011 </xml>
2012
2013 </macros>