Mercurial > repos > bgruening > sklearn_model_validation

comparison main_macros.xml @ 28:9b017b0da56e draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
"planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/sklearn commit e2a5eade6d0e5ddf3a47630381a0ad90d80e8a04"
author bgruening
date Tue, 13 Apr 2021 19:01:30 +0000
parents 0474777be433
children 65f18ab91132
comparison
equal deleted inserted replaced
27:bfc7bdfcb423 28:9b017b0da56e
1 <macros> 1 <macros>
2 <token name="@VERSION@">1.0.8.2</token> 2 <token name="@VERSION@">1.0.8.3</token>
3 3
4 <xml name="python_requirements"> 4 <xml name="python_requirements">
5 <requirements> 5 <requirements>
6 <requirement type="package" version="3.6">python</requirement> 6 <requirement type="package" version="0.8.3">Galaxy-ML</requirement>
7 <requirement type="package" version="0.8.1">Galaxy-ML</requirement> 7 <yield />
8 <yield/> 8 </requirements>
9 </requirements> 9 </xml>
10 </xml> 10
11 11 <xml name="macro_stdio">
12 <xml name="macro_stdio"> 12 <stdio>
13 <stdio> 13 <exit_code range="1:" level="fatal" description="Error occurred. Please check Tool Standard Error" />
14 <exit_code range="1:" level="fatal" description="Error occurred. Please check Tool Standard Error"/> 14 </stdio>
15 </stdio> 15 </xml>
16 </xml> 16
17 17
18 18 <!--Generic interface-->
19 <!--Generic interface--> 19
20 20 <xml name="sl_Conditional" token_train="tabular" token_data="tabular" token_model="txt">
21 <xml name="sl_Conditional" token_train="tabular" token_data="tabular" token_model="txt"> 21 <conditional name="selected_tasks">
22 <conditional name="selected_tasks"> 22 <param name="selected_task" type="select" label="Select a Classification Task">
23 <param name="selected_task" type="select" label="Select a Classification Task"> 23 <option value="train" selected="true">Train a model</option>
24 <option value="train" selected="true">Train a model</option> 24 <option value="load">Load a model and predict</option>
25 <option value="load">Load a model and predict</option> 25 </param>
26 <when value="load">
27 <param name="infile_model" type="data" format="@MODEL@" label="Models" help="Select a model file." />
28 <param name="infile_data" type="data" format="@DATA@" label="Data (tabular)" help="Select the dataset you want to classify." />
29 <param name="header" type="boolean" optional="True" truevalue="booltrue" falsevalue="boolfalse" checked="False" label="Does the dataset contain header:" />
30 <conditional name="prediction_options">
31 <param name="prediction_option" type="select" label="Select the type of prediction">
32 <option value="predict">Predict class labels</option>
33 <option value="advanced">Include advanced options</option>
34 </param>
35 <when value="predict">
36 </when>
37 <when value="advanced">
38 </when>
39 </conditional>
40 </when>
41 <when value="train">
42 <conditional name="selected_algorithms">
43 <yield />
44 </conditional>
45 </when>
46 </conditional>
47 </xml>
48
49 <xml name="advanced_section">
50 <section name="options" title="Advanced Options" expanded="False">
51 <yield />
52 </section>
53 </xml>
54
55
56 <!--Generalized Linear Models-->
57 <xml name="loss" token_help=" " token_select="false">
58 <param argument="loss" type="select" label="Loss function" help="@HELP@">
59 <option value="squared_loss" selected="@SELECT@">squared loss</option>
60 <option value="huber">huber</option>
61 <option value="epsilon_insensitive">epsilon insensitive</option>
62 <option value="squared_epsilon_insensitive">squared epsilon insensitive</option>
63 <yield />
26 </param> 64 </param>
27 <when value="load"> 65 </xml>
28 <param name="infile_model" type="data" format="@MODEL@" label="Models" help="Select a model file."/> 66
29 <param name="infile_data" type="data" format="@DATA@" label="Data (tabular)" help="Select the dataset you want to classify."/> 67 <xml name="penalty" token_help=" ">
30 <param name="header" type="boolean" optional="True" truevalue="booltrue" falsevalue="boolfalse" checked="False" label="Does the dataset contain header:" /> 68 <param argument="penalty" type="select" label="Penalty (regularization term)" help="@HELP@">
31 <conditional name="prediction_options"> 69 <option value="l2" selected="true">l2</option>
32 <param name="prediction_option" type="select" label="Select the type of prediction"> 70 <option value="l1">l1</option>
33 <option value="predict">Predict class labels</option> 71 <option value="elasticnet">elastic net</option>
34 <option value="advanced">Include advanced options</option> 72 <option value="none">none</option>
73 <yield />
74 </param>
75 </xml>
76
77 <xml name="l1_ratio" token_default_value="0.15" token_help=" ">
78 <param argument="l1_ratio" type="float" value="@DEFAULT_VALUE@" label="Elastic Net mixing parameter" help="@HELP@" />
79 </xml>
80
81 <xml name="epsilon" token_default_value="0.1" token_help="Used if loss is ‘huber’, ‘epsilon_insensitive’, or ‘squared_epsilon_insensitive’. ">
82 <param argument="epsilon" type="float" value="@DEFAULT_VALUE@" label="Epsilon (epsilon-sensitive loss functions only)" help="@HELP@" />
83 </xml>
84
85 <xml name="learning_rate_s" token_help=" " token_selected1="false" token_selected2="false">
86 <param argument="learning_rate" type="select" optional="true" label="Learning rate schedule" help="@HELP@">
87 <option value="optimal" selected="@SELECTED1@">optimal</option>
88 <option value="constant">constant</option>
89 <option value="invscaling" selected="@SELECTED2@">inverse scaling</option>
90 <yield />
91 </param>
92 </xml>
93
94 <xml name="eta0" token_default_value="0.0" token_help="Used with ‘constant’ or ‘invscaling’ schedules. ">
95 <param argument="eta0" type="float" value="@DEFAULT_VALUE@" label="Initial learning rate" help="@HELP@" />
96 </xml>
97
98 <xml name="power_t" token_default_value="0.5" token_help=" ">
99 <param argument="power_t" type="float" value="@DEFAULT_VALUE@" label="Exponent for inverse scaling learning rate" help="@HELP@" />
100 </xml>
101
102 <xml name="normalize" token_checked="false" token_help=" ">
103 <param argument="normalize" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolfalse" checked="@CHECKED@" label="Normalize samples before training" help=" " />
104 </xml>
105
106 <xml name="copy_X" token_checked="true" token_help=" ">
107 <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. " />
108 </xml>
109
110 <xml name="ridge_params">
111 <expand macro="normalize" />
112 <expand macro="alpha" default_value="1.0" />
113 <expand macro="fit_intercept" />
114 <expand macro="max_iter" default_value="" />
115 <expand macro="tol" default_value="0.001" help_text="Precision of the solution. " />
116 <!--class_weight-->
117 <expand macro="copy_X" />
118 <param argument="solver" type="select" value="" label="Solver to use in the computational routines" help=" ">
119 <option value="auto" selected="true">auto</option>
120 <option value="svd">svd</option>
121 <option value="cholesky">cholesky</option>
122 <option value="lsqr">lsqr</option>
123 <option value="sparse_cg">sparse_cg</option>
124 <option value="sag">sag</option>
125 </param>
126 <expand macro="random_state" />
127 </xml>
128
129 <!--Ensemble methods-->
130 <xml name="n_estimators" token_default_value="10" token_help=" ">
131 <param argument="n_estimators" type="integer" optional="true" value="@DEFAULT_VALUE@" label="Number of trees in the forest" help="@HELP@" />
132 </xml>
133
134 <xml name="max_depth" token_default_value="" token_help=" ">
135 <param argument="max_depth" type="integer" optional="true" value="@DEFAULT_VALUE@" label="Maximum depth of the tree" help="@HELP@" />
136 </xml>
137
138 <xml name="min_samples_split" token_type="integer" token_default_value="2" token_help=" ">
139 <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@" />
140 </xml>
141
142 <xml name="min_samples_leaf" token_type="integer" token_default_value="1" token_label="Minimum number of samples in newly created leaves" token_help=" ">
143 <param argument="min_samples_leaf" type="@TYPE@" optional="true" value="@DEFAULT_VALUE@" label="@LABEL@" help="@HELP@" />
144 </xml>
145
146 <xml name="min_weight_fraction_leaf" token_default_value="0.0" token_help=" ">
147 <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@" />
148 </xml>
149
150 <xml name="max_leaf_nodes" token_default_value="" token_help=" ">
151 <param argument="max_leaf_nodes" type="integer" optional="true" value="@DEFAULT_VALUE@" label="Maximum number of leaf nodes in best-first method" help="@HELP@" />
152 </xml>
153
154 <xml name="min_impurity_decrease" token_default_value="0" token_help=" ">
155 <param argument="min_impurity_decrease" type="float" value="@DEFAULT_VALUE@" optional="true" label="The threshold value of impurity for stopping node splitting" help="@HELP@" />
156 </xml>
157
158 <xml name="bootstrap" token_checked="true" token_help=" ">
159 <param argument="bootstrap" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolflase" checked="@CHECKED@" label="Use bootstrap samples for building trees." help="@HELP@" />
160 </xml>
161
162 <xml name="criterion" token_help=" ">
163 <param argument="criterion" type="select" label="Function to measure the quality of a split" help=" ">
164 <option value="gini" selected="true">Gini impurity</option>
165 <option value="entropy">Information gain</option>
166 <yield />
167 </param>
168 </xml>
169
170 <xml name="criterion2" token_help="">
171 <param argument="criterion" type="select" label="Function to measure the quality of a split">
172 <option value="mse">mse - mean squared error</option>
173 <option value="mae">mae - mean absolute error</option>
174 <yield />
175 </param>
176 </xml>
177
178 <xml name="oob_score" token_checked="false" token_help=" ">
179 <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@" />
180 </xml>
181
182 <xml name="max_features">
183 <conditional name="select_max_features">
184 <param argument="max_features" type="select" label="max_features">
185 <option value="auto" selected="true">auto - max_features=n_features</option>
186 <option value="sqrt">sqrt - max_features=sqrt(n_features)</option>
187 <option value="log2">log2 - max_features=log2(n_features)</option>
188 <option value="number_input">I want to type the number in or input None type</option>
189 </param>
190 <when value="auto">
191 </when>
192 <when value="sqrt">
193 </when>
194 <when value="log2">
195 </when>
196 <when value="number_input">
197 <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." />
198 </when>
199 </conditional>
200 </xml>
201
202 <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.">
203 <param argument="verbose" type="integer" value="@DEFAULT_VALUE@" optional="true" label="Enable verbose output" help="@HELP@" />
204 </xml>
205
206 <xml name="learning_rate" token_default_value="1.0" token_help=" ">
207 <param argument="learning_rate" type="float" optional="true" value="@DEFAULT_VALUE@" label="Learning rate" help="@HELP@" />
208 </xml>
209
210 <xml name="subsample" token_help=" ">
211 <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@" />
212 </xml>
213
214 <xml name="presort">
215 <param argument="presort" type="select" label="Whether to presort the data to speed up the finding of best splits in fitting">
216 <option value="auto" selected="true">auto</option>
217 <option value="true">true</option>
218 <option value="false">false</option>
219 </param>
220 </xml>
221
222 <!-- LightGBM -->
223 <xml name="feature_fraction" token_help="LightGBM will randomly select part of the features for each iteration (tree) if feature_fraction is smaller than 1.0. For example, if you set it to 0.8, LightGBM will select 80% of features before training each tree.">
224 <param argument="feature_fraction" type="float" value="1.0" label="Proportion of features to train each tree" help="@HELP@" />
225 </xml>
226
227 <xml name="lambda_l1" token_help=" ">
228 <param argument="lambda_l1" type="float" value="0.0" label="L1 regularization" help="@HELP@" />
229 </xml>
230
231 <xml name="lambda_l2" token_help=" ">
232 <param argument="lambda_l2" type="float" value="0.0" label="L1 regularization" help="@HELP@" />
233 </xml>
234
235 <xml name="min_gain_to_split" token_help=" ">
236 <param argument="min_gain_to_split" type="float" value="0.0" label="Minimal gain to perform split" help="@HELP@" />
237 </xml>
238
239 <xml name="min_child_weight" token_help="Minimal sum hessian in one leaf. It can be used to deal with over-fitting.">
240 <param argument="min_child_weight" type="float" value="0.0" label="Minimal sum hessian in one leaf" help="@HELP@" />
241 </xml>
242
243
244 <!--Parameters-->
245 <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.">
246 <param argument="tol" type="float" optional="true" value="@DEFAULT_VALUE@" label="Tolerance" help="@HELP_TEXT@" />
247 </xml>
248
249 <xml name="n_clusters" token_default_value="8">
250 <param argument="n_clusters" type="integer" optional="true" value="@DEFAULT_VALUE@" label="Number of clusters" help=" " />
251 </xml>
252
253 <xml name="fit_intercept" token_checked="true">
254 <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." />
255 </xml>
256
257 <xml name="n_iter_no_change" token_default_value="5" token_help_text="Number of iterations with no improvement to wait before early stopping. ">
258 <param argument="n_iter_no_change" type="integer" optional="true" value="@DEFAULT_VALUE@" label="Number of iterations" help="@HELP_TEXT@" />
259 </xml>
260
261 <xml name="shuffle" token_checked="true" token_help_text=" " token_label="Shuffle data after each iteration">
262 <param argument="shuffle" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolfalse" checked="@CHECKED@" label="@LABEL@" help="@HELP_TEXT@" />
263 </xml>
264
265 <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.">
266 <param argument="random_state" type="integer" optional="true" value="@DEFAULT_VALUE@" label="Random seed number" help="@HELP_TEXT@" />
267 </xml>
268
269 <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.">
270 <param argument="warm_start" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolfalse" checked="@CHECKED@" label="Perform warm start" help="@HELP_TEXT@" />
271 </xml>
272
273 <xml name="C" token_default_value="1.0" token_help_text="Penalty parameter C of the error term.">
274 <param argument="C" type="float" optional="true" value="@DEFAULT_VALUE@" label="Penalty parameter" help="@HELP_TEXT@" />
275 </xml>
276
277 <!--xml name="class_weight" token_default_value="" token_help_text="">
278 <param argument="class_weight" type="" optional="true" value="@DEFAULT_VALUE@" label="" help="@HELP_TEXT@"/>
279 </xml-->
280
281 <xml name="alpha" token_default_value="0.0001" token_help_text="Constant that multiplies the regularization term if regularization is used. ">
282 <param argument="alpha" type="float" optional="true" value="@DEFAULT_VALUE@" label="Regularization coefficient" help="@HELP_TEXT@" />
283 </xml>
284
285 <xml name="n_samples" token_default_value="100" token_help_text="The total number of points equally divided among clusters.">
286 <param argument="n_samples" type="integer" optional="true" value="@DEFAULT_VALUE@" label="Number of samples" help="@HELP_TEXT@" />
287 </xml>
288
289 <xml name="n_features" token_default_value="2" token_help_text="Number of different numerical properties produced for each sample.">
290 <param argument="n_features" type="integer" optional="true" value="@DEFAULT_VALUE@" label="Number of features" help="@HELP_TEXT@" />
291 </xml>
292
293 <xml name="noise" token_default_value="0.0" token_help_text="Floating point number. ">
294 <param argument="noise" type="float" optional="true" value="@DEFAULT_VALUE@" label="Standard deviation of the Gaussian noise added to the data" help="@HELP_TEXT@" />
295 </xml>
296
297 <xml name="C" token_default_value="1.0" token_help_text="Penalty parameter C of the error term. ">
298 <param argument="C" type="float" optional="true" value="@DEFAULT_VALUE@" label="Penalty parameter" help="@HELP_TEXT@" />
299 </xml>
300
301 <xml name="max_iter" token_default_value="300" token_label="Maximum number of iterations per single run" token_help_text=" ">
302 <param argument="max_iter" type="integer" optional="true" value="@DEFAULT_VALUE@" label="@LABEL@" help="@HELP_TEXT@" />
303 </xml>
304
305 <xml name="n_init" token_default_value="10">
306 <param argument="n_init" type="integer" optional="true" value="@DEFAULT_VALUE@" label="Number of runs with different centroid seeds" help=" " />
307 </xml>
308
309 <xml name="init">
310 <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.">
311 <option value="k-means++">k-means++</option>
312 <option value="random">random</option>
313 </param>
314 </xml>
315
316 <xml name="gamma" token_default_value="1.0" token_label="Scaling parameter" token_help_text=" ">
317 <param argument="gamma" type="float" optional="true" value="@DEFAULT_VALUE@" label="@LABEL@" help="@HELP_TEXT@" />
318 </xml>
319
320 <xml name="degree" token_default_value="3" token_label="Degree of the polynomial" token_help_text=" ">
321 <param argument="degree" type="integer" optional="true" value="@DEFAULT_VALUE@" label="@LABEL@" help="@HELP_TEXT@" />
322 </xml>
323
324 <xml name="coef0" token_default_value="1" token_label="Zero coefficient" token_help_text=" ">
325 <param argument="coef0" type="integer" optional="true" value="@DEFAULT_VALUE@" label="@LABEL@" help="@HELP_TEXT@" />
326 </xml>
327
328 <xml name="pos_label" token_default_value="">
329 <param argument="pos_label" type="integer" optional="true" value="@DEFAULT_VALUE@" label="Label of the positive class" help=" " />
330 </xml>
331
332 <xml name="average">
333 <param argument="average" type="select" optional="true" label="Averaging type" help=" ">
334 <option value="micro">Calculate metrics globally by counting the total true positives, false negatives and false positives. (micro)</option>
335 <option value="samples">Calculate metrics for each instance, and find their average. Only meaningful for multilabel. (samples)</option>
336 <option value="macro">Calculate metrics for each label, and find their unweighted mean. This does not take label imbalance into account. (macro)</option>
337 <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>
338 <option value="None">None</option>
339 <yield />
340 </param>
341 </xml>
342
343 <xml name="beta">
344 <param argument="beta" type="float" value="1.0" label="The strength of recall versus precision in the F-score" help=" " />
345 </xml>
346
347
348 <!--Data interface-->
349
350 <xml name="samples_tabular" token_label1="Training samples dataset:" token_multiple1="false" token_multiple2="false">
351 <param name="infile1" type="data" format="tabular" label="@LABEL1@" />
352 <param name="header1" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolfalse" checked="False" label="Does the dataset contain header:" />
353 <conditional name="column_selector_options_1">
354 <expand macro="samples_column_selector_options" multiple="@MULTIPLE1@" />
355 </conditional>
356 <param name="infile2" type="data" format="tabular" label="Dataset containing class labels or target values:" />
357 <param name="header2" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolfalse" checked="False" label="Does the dataset contain header:" />
358 <conditional name="column_selector_options_2">
359 <expand macro="samples_column_selector_options" column_option="selected_column_selector_option2" col_name="col2" multiple="@MULTIPLE2@" infile="infile2" />
360 </conditional>
361 <yield />
362 </xml>
363
364 <xml name="samples_column_selector_options" token_column_option="selected_column_selector_option" token_col_name="col1" token_multiple="False" token_infile="infile1">
365 <param name="@COLUMN_OPTION@" type="select" label="Choose how to select data by column:">
366 <option value="by_index_number" selected="true">Select columns by column index number(s)</option>
367 <option value="all_but_by_index_number">All columns EXCLUDING some by column index number(s)</option>
368 <option value="by_header_name">Select columns by column header name(s)</option>
369 <option value="all_but_by_header_name">All columns EXCLUDING some by column header name(s)</option>
370 <option value="all_columns">All columns</option>
371 </param>
372 <when value="by_index_number">
373 <param name="@COL_NAME@" multiple="@MULTIPLE@" type="data_column" use_header_names="true" data_ref="@INFILE@" label="Select target column(s):" />
374 </when>
375 <when value="all_but_by_index_number">
376 <param name="@COL_NAME@" multiple="@MULTIPLE@" type="data_column" use_header_names="true" data_ref="@INFILE@" label="Select target column(s):" />
377 </when>
378 <when value="by_header_name">
379 <param name="@COL_NAME@" type="text" value="" label="Type header name(s):" help="Comma-separated string. For example: target1,target2" />
380 </when>
381 <when value="all_but_by_header_name">
382 <param name="@COL_NAME@" type="text" value="" label="Type header name(s):" help="Comma-separated string. For example: target1,target2" />
383 </when>
384 <when value="all_columns">
385 </when>
386 </xml>
387
388 <xml name="clf_inputs_extended" token_label1=" " token_label2=" " token_multiple="False">
389 <conditional name="true_columns">
390 <param name="selected_input1" type="select" label="Select the input type of true labels dataset:">
391 <option value="tabular" selected="true">Tabular</option>
392 <option value="sparse">Sparse</option>
393 </param>
394 <when value="tabular">
395 <param name="infile1" type="data" label="@LABEL1@" />
396 <param name="col1" type="data_column" data_ref="infile1" label="Select the target column:" />
397 </when>
398 <when value="sparse">
399 <param name="infile1" type="data" format="txt" label="@LABEL1@" />
400 </when>
401 </conditional>
402 <conditional name="predicted_columns">
403 <param name="selected_input2" type="select" label="Select the input type of predicted labels dataset:">
404 <option value="tabular" selected="true">Tabular</option>
405 <option value="sparse">Sparse</option>
406 </param>
407 <when value="tabular">
408 <param name="infile2" type="data" label="@LABEL2@" />
409 <param name="col2" multiple="@MULTIPLE@" type="data_column" data_ref="infile2" label="Select target column(s):" />
410 </when>
411 <when value="sparse">
412 <param name="infile2" type="data" format="txt" label="@LABEL1@" />
413 </when>
414 </conditional>
415 </xml>
416
417 <xml name="clf_inputs" token_label1="Dataset containing true labels (tabular):" token_label2="Dataset containing predicted values (tabular):" token_multiple1="False" token_multiple="False">
418 <param name="infile1" type="data" format="tabular" label="@LABEL1@" />
419 <param name="header1" type="boolean" optional="True" truevalue="booltrue" falsevalue="boolfalse" checked="False" label="Does the dataset contain header:" />
420 <conditional name="column_selector_options_1">
421 <expand macro="samples_column_selector_options" multiple="@MULTIPLE1@" />
422 </conditional>
423 <param name="infile2" type="data" format="tabular" label="@LABEL2@" />
424 <param name="header2" type="boolean" optional="True" truevalue="booltrue" falsevalue="boolfalse" checked="False" label="Does the dataset contain header:" />
425 <conditional name="column_selector_options_2">
426 <expand macro="samples_column_selector_options" column_option="selected_column_selector_option2" col_name="col2" multiple="@MULTIPLE@" infile="infile2" />
427 </conditional>
428 </xml>
429
430 <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.">
431 <repeat name="@NAME@" min="1" max="@MAX_NUM@" title="Select input file(s):">
432 <param name="input" type="data" format="@FORMAT@" label="@LABEL@" help="@HELP_TEXT@" />
433 </repeat>
434 </xml>
435
436 <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="">
437 <param name="infile1" type="data" format="@FORMAT1@" label="@LABEL1@" help="@HELP1@" />
438 <expand macro="input_tabular_target" />
439 </xml>
440
441 <xml name="sl_mixed_input">
442 <conditional name="input_options">
443 <expand macro="data_input_options" />
444 <expand macro="data_input_whens" />
445 </conditional>
446 </xml>
447
448 <xml name="sl_mixed_input_plus_sequence">
449 <conditional name="input_options">
450 <expand macro="data_input_options">
451 <option value="seq_fasta">sequnences in a fasta file</option>
452 <option value="refseq_and_interval">reference genome and intervals</option>
453 </expand>
454 <expand macro="data_input_whens">
455 <when value="seq_fasta">
456 <expand macro="inputs_seq_fasta" />
457 </when>
458 <when value="refseq_and_interval">
459 <expand macro="inputs_refseq_and_interval" />
460 </when>
461 </expand>
462 </conditional>
463 </xml>
464
465 <xml name="data_input_options">
466 <param name="selected_input" type="select" label="Select input type:">
467 <option value="tabular" selected="true">tabular data</option>
468 <option value="sparse">sparse matrix</option>
469 <yield />
470 </param>
471 </xml>
472
473 <xml name="data_input_whens">
474 <when value="tabular">
475 <expand macro="samples_tabular" multiple1="true" multiple2="false" />
476 </when>
477 <when value="sparse">
478 <expand macro="sparse_target" />
479 </when>
480 <yield />
481 </xml>
482
483 <xml name="input_tabular_target">
484 <param name="infile2" type="data" format="tabular" label="Dataset containing class labels or target values:" />
485 <param name="header2" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolfalse" checked="false" label="Does the dataset contain header:" />
486 <conditional name="column_selector_options_2">
487 <expand macro="samples_column_selector_options" column_option="selected_column_selector_option2" col_name="col2" multiple="false" infile="infile2" />
488 </conditional>
489 </xml>
490
491 <xml name="inputs_seq_fasta">
492 <param name="fasta_path" type="data" format="fasta" label="Dataset containing fasta genomic/protein sequences" help="Sequences will be one-hot encoded to arrays." />
493 <expand macro="input_tabular_target" />
494 </xml>
495
496 <xml name="inputs_refseq_and_interval">
497 <param name="ref_genome_file" type="data" format="fasta" label="Dataset containing reference genomic sequence" />
498 <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." />
499 <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`." />
500 <param name="infile2" type="data" format="tabular" label="Dataset containing the feature list for prediction" />
501 <param name="header2" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolfalse" checked="false" label="Does the dataset contain header:" />
502 <conditional name="column_selector_options_2">
503 <expand macro="samples_column_selector_options" column_option="selected_column_selector_option2" col_name="col2" multiple="true" infile="infile2" />
504 </conditional>
505 </xml>
506
507 <!--Advanced options-->
508 <xml name="nn_advanced_options">
509 <section name="options" title="Advanced Options" expanded="False">
510 <yield />
511 <param argument="weights" type="select" label="Weight function" help="Used in prediction.">
512 <option value="uniform" selected="true">Uniform weights. All points in each neighborhood are weighted equally. (Uniform)</option>
513 <option value="distance">Weight points by the inverse of their distance. (Distance)</option>
514 </param>
515 <param argument="algorithm" type="select" label="Neighbor selection algorithm" help=" ">
516 <option value="auto" selected="true">Auto</option>
517 <option value="ball_tree">BallTree</option>
518 <option value="kd_tree">KDTree</option>
519 <option value="brute">Brute-force</option>
520 </param>
521 <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." />
522 <!--param name="metric"-->
523 <!--param name="p"-->
524 <!--param name="metric_params"-->
525 </section>
526 </xml>
527
528 <xml name="svc_advanced_options">
529 <section name="options" title="Advanced Options" expanded="False">
530 <yield />
531 <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.">
532 <option value="rbf" selected="true">rbf</option>
533 <option value="linear">linear</option>
534 <option value="poly">poly</option>
535 <option value="sigmoid">sigmoid</option>
536 <option value="precomputed">precomputed</option>
537 </param>
538 <param argument="degree" type="integer" optional="true" value="3" label="Degree of the polynomial (polynomial kernel only)" help="Ignored by other kernels. dafault : 3 " />
539 <!--TODO: param argument="gamma" float, optional (default=’auto’) -->
540 <param argument="coef0" type="float" optional="true" value="0.0" label="Zero coefficient (polynomial and sigmoid kernels only)" help="Independent term in kernel function. dafault: 0.0 " />
541 <param argument="shrinking" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolfalse" checked="true" label="Use the shrinking heuristic" help=" " />
542 <param argument="probability" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolfalse" checked="false" label="Enable probability estimates. " help="This must be enabled prior to calling fit, and will slow down that method." />
543 <!-- param argument="cache_size"-->
544 <!--expand macro="class_weight"/-->
545 <expand macro="tol" default_value="0.001" help_text="Tolerance for stopping criterion. " />
546 <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." />
547 <!--param argument="decision_function_shape"-->
548 <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." />
549 </section>
550 </xml>
551
552 <xml name="spectral_clustering_advanced_options">
553 <section name="options" title="Advanced Options" expanded="False">
554 <expand macro="n_clusters" />
555 <param argument="eigen_solver" type="select" value="" label="Eigen solver" help="The eigenvalue decomposition strategy to use.">
556 <option value="arpack" selected="true">arpack</option>
557 <option value="lobpcg">lobpcg</option>
558 <option value="amg">amg</option>
559 <!--None-->
560 </param>
561 <expand macro="random_state" />
562 <expand macro="n_init" />
563 <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''." />
564 <param argument="affinity" type="select" label="Affinity" help="Affinity kernel to use. ">
565 <option value="rbf" selected="true">RBF</option>
566 <option value="precomputed">precomputed</option>
567 <option value="nearest_neighbors">Nearset neighbors</option>
568 </param>
569 <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''" />
570 <!--param argument="eigen_tol"-->
571 <param argument="assign_labels" type="select" label="Assign labels" help="The strategy to use to assign labels in the embedding space.">
572 <option value="kmeans" selected="true">kmeans</option>
573 <option value="discretize">discretize</option>
574 </param>
575 <param argument="degree" type="integer" optional="true" value="3" label="Degree of the polynomial (polynomial kernel only)" help="Ignored by other kernels. dafault : 3 " />
576 <param argument="coef0" type="integer" optional="true" value="1" label="Zero coefficient (polynomial and sigmoid kernels only)" help="Ignored by other kernels. dafault : 1 " />
577 <!--param argument="kernel_params"-->
578 </section>
579 </xml>
580
581 <xml name="minibatch_kmeans_advanced_options">
582 <section name="options" title="Advanced Options" expanded="False">
583 <expand macro="n_clusters" />
584 <expand macro="init" />
585 <expand macro="n_init" default_value="3" />
586 <expand macro="max_iter" default_value="100" />
587 <expand macro="tol" help_text="Early stopping heuristics based on normalized center change. To disable set to 0.0 ." />
588 <expand macro="random_state" />
589 <param argument="batch_size" type="integer" optional="true" value="100" label="Batch size" help="Size of the mini batches." />
590 <!--param argument="compute_labels"-->
591 <param argument="max_no_improvement" type="integer" optional="true" value="10" label="Maximum number of improvement attempts" help="
592 Convergence detection based on inertia (the consecutive number of mini batches that doe not yield an improvement on the smoothed inertia).
593 To disable, set max_no_improvement to None. " />
594 <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 )" />
595 <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." />
596 </section>
597 </xml>
598
599 <xml name="kmeans_advanced_options">
600 <section name="options" title="Advanced Options" expanded="False">
601 <expand macro="n_clusters" />
602 <expand macro="init" />
603 <expand macro="n_init" />
604 <expand macro="max_iter" />
605 <expand macro="tol" default_value="0.0001" help_text="Relative tolerance with regards to inertia to declare convergence." />
606 <!--param argument="precompute_distances"/-->
607 <expand macro="random_state" />
608 <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." />
609 <expand macro="kmeans_algorithm" />
610 </section>
611 </xml>
612
613 <xml name="kmeans_algorithm">
614 <param argument="algorithm" type="select" label="K-means algorithm to use:">
615 <option value="auto" selected="true">auto</option>
616 <option value="full">full</option>
617 <option value="elkan">elkan</option>
618 </param>
619 </xml>
620
621 <xml name="birch_advanced_options">
622 <section name="options" title="Advanced Options" expanded="False">
623 <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." />
624 <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." />
625 <expand macro="n_clusters" default_value="3" />
626 <!--param argument="compute_labels"/-->
627 </section>
628 </xml>
629
630 <xml name="dbscan_advanced_options">
631 <section name="options" title="Advanced Options" expanded="False">
632 <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." />
633 <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." />
634 <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." />
635 <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.">
636 <option value="auto" selected="true">auto</option>
637 <option value="ball_tree">ball_tree</option>
638 <option value="kd_tree">kd_tree</option>
639 <option value="brute">brute</option>
640 </param>
641 <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." />
642 </section>
643 </xml>
644
645 <xml name="clustering_algorithms_options">
646 <conditional name="algorithm_options">
647 <param name="selected_algorithm" type="select" label="Clustering Algorithm">
648 <option value="KMeans" selected="true">KMeans</option>
649 <option value="SpectralClustering">Spectral Clustering</option>
650 <option value="MiniBatchKMeans">Mini Batch KMeans</option>
651 <option value="DBSCAN">DBSCAN</option>
652 <option value="Birch">Birch</option>
653 </param>
654 <when value="KMeans">
655 <expand macro="kmeans_advanced_options" />
656 </when>
657 <when value="DBSCAN">
658 <expand macro="dbscan_advanced_options" />
659 </when>
660 <when value="Birch">
661 <expand macro="birch_advanced_options" />
662 </when>
663 <when value="SpectralClustering">
664 <expand macro="spectral_clustering_advanced_options" />
665 </when>
666 <when value="MiniBatchKMeans">
667 <expand macro="minibatch_kmeans_advanced_options" />
668 </when>
669 </conditional>
670 </xml>
671
672 <xml name="distance_metrics">
673 <param argument="metric" type="select" label="Distance metric" help=" ">
674 <option value="euclidean" selected="true">euclidean</option>
675 <option value="cityblock">cityblock</option>
676 <option value="cosine">cosine</option>
677 <option value="l1">l1</option>
678 <option value="l2">l2</option>
679 <option value="manhattan">manhattan</option>
680 <yield />
681 </param>
682 </xml>
683
684 <xml name="distance_nonsparse_metrics">
685 <option value="braycurtis">braycurtis</option>
686 <option value="canberra">canberra</option>
687 <option value="chebyshev">chebyshev</option>
688 <option value="correlation">correlation</option>
689 <option value="dice">dice</option>
690 <option value="hamming">hamming</option>
691 <option value="jaccard">jaccard</option>
692 <option value="kulsinski">kulsinski</option>
693 <option value="mahalanobis">mahalanobis</option>
694 <option value="matching">matching</option>
695 <option value="minkowski">minkowski</option>
696 <option value="rogerstanimoto">rogerstanimoto</option>
697 <option value="russellrao">russellrao</option>
698 <option value="seuclidean">seuclidean</option>
699 <option value="sokalmichener">sokalmichener</option>
700 <option value="sokalsneath">sokalsneath</option>
701 <option value="sqeuclidean">sqeuclidean</option>
702 <option value="yule">yule</option>
703 </xml>
704
705 <xml name="pairwise_kernel_metrics">
706 <param argument="metric" type="select" label="Pirwise Kernel metric" help=" ">
707 <option value="rbf" selected="true">rbf</option>
708 <option value="sigmoid">sigmoid</option>
709 <option value="polynomial">polynomial</option>
710 <option value="linear" selected="true">linear</option>
711 <option value="chi2">chi2</option>
712 <option value="additive_chi2">additive_chi2</option>
713 </param>
714 </xml>
715
716 <xml name="sparse_pairwise_metric_functions">
717 <param name="selected_metric_function" type="select" label="Select the pairwise metric you want to compute:">
718 <option value="euclidean_distances" selected="true">Euclidean distance matrix</option>
719 <option value="pairwise_distances">Distance matrix</option>
720 <option value="pairwise_distances_argmin">Minimum distances between one point and a set of points</option>
721 <yield />
722 </param>
723 </xml>
724
725 <xml name="pairwise_metric_functions">
726 <option value="additive_chi2_kernel">Additive chi-squared kernel</option>
727 <option value="chi2_kernel">Exponential chi-squared kernel</option>
728 <option value="linear_kernel">Linear kernel</option>
729 <option value="manhattan_distances">L1 distances</option>
730 <option value="pairwise_kernels">Kernel</option>
731 <option value="polynomial_kernel">Polynomial kernel</option>
732 <option value="rbf_kernel">Gaussian (rbf) kernel</option>
733 <option value="laplacian_kernel">Laplacian kernel</option>
734 </xml>
735
736 <xml name="sparse_pairwise_condition">
737 <when value="pairwise_distances">
738 <section name="options" title="Advanced Options" expanded="False">
739 <expand macro="distance_metrics">
740 <yield />
741 </expand>
742 </section>
743 </when>
744 <when value="euclidean_distances">
745 <section name="options" title="Advanced Options" expanded="False">
746 <param argument="squared" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolfalse" checked="false" label="Return squared Euclidean distances" help=" " />
747 </section>
748 </when>
749 </xml>
750
751 <xml name="argmin_distance_condition">
752 <when value="pairwise_distances_argmin">
753 <section name="options" title="Advanced Options" expanded="False">
754 <param argument="axis" type="integer" optional="true" value="1" label="Axis" help="Axis along which the argmin and distances are to be computed." />
755 <expand macro="distance_metrics">
756 <yield />
757 </expand>
758 <param argument="batch_size" type="integer" optional="true" value="500" label="Batch size" help="Number of rows to be processed in each batch run." />
759 </section>
760 </when>
761 </xml>
762
763 <xml name="sparse_preprocessors">
764 <param name="selected_pre_processor" type="select" label="Select a preprocessor:">
765 <option value="StandardScaler" selected="true">Standard Scaler (Standardizes features by removing the mean and scaling to unit variance)</option>
766 <option value="Binarizer">Binarizer (Binarizes data)</option>
767 <option value="MaxAbsScaler">Max Abs Scaler (Scales features by their maximum absolute value)</option>
768 <option value="Normalizer">Normalizer (Normalizes samples individually to unit norm)</option>
769 <yield />
770 </param>
771 </xml>
772
773 <xml name="sparse_preprocessors_ext">
774 <expand macro="sparse_preprocessors">
775 <option value="KernelCenterer">Kernel Centerer (Centers a kernel matrix)</option>
776 <option value="MinMaxScaler">Minmax Scaler (Scales features to a range)</option>
777 <option value="PolynomialFeatures">Polynomial Features (Generates polynomial and interaction features)</option>
778 <option value="RobustScaler">Robust Scaler (Scales features using outlier-invariance statistics)</option>
779 <option value="QuantileTransformer">QuantileTransformer (Transform features using quantiles information)</option>
780 <option value="PowerTransformer">PowerTransformer (Apply a power transform featurewise to make data more Gaussian-like)</option>
781 <option value="KBinsDiscretizer">KBinsDiscretizer (Bin continuous data into intervals.)</option>
782 </expand>
783 </xml>
784
785 <xml name="sparse_preprocessor_options">
786 <when value="Binarizer">
787 <section name="options" title="Advanced Options" expanded="False">
788 <param argument="copy" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolfalse" checked="true" label="Use a copy of data for precomputing binarization" help=" " />
789 <param argument="threshold" type="float" optional="true" value="0.0" label="Threshold" 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. " />
790 </section>
791 </when>
792 <when value="StandardScaler">
793 <section name="options" title="Advanced Options" expanded="False">
794 <param argument="copy" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolfalse" checked="true" label="Use a copy of data for performing inplace scaling" help=" " />
795 <param argument="with_mean" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolfalse" checked="true" label="Center the data before scaling" help=" " />
796 <param argument="with_std" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolfalse" checked="true" label="Scale the data to unit variance (or unit standard deviation)" help=" " />
797 </section>
798 </when>
799 <when value="MaxAbsScaler">
800 <section name="options" title="Advanced Options" expanded="False">
801 <param argument="copy" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolfalse" checked="true" label="Use a copy of data for precomputing scaling" help=" " />
802 </section>
803 </when>
804 <when value="Normalizer">
805 <section name="options" title="Advanced Options" expanded="False">
806 <param argument="norm" type="select" optional="true" label="The norm to use to normalize non zero samples" help=" ">
807 <option value="l1" selected="true">l1</option>
808 <option value="l2">l2</option>
809 <option value="max">max</option>
35 </param> 810 </param>
36 <when value="predict"> 811 <param argument="copy" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolfalse" checked="true" label="Use a copy of data for precomputing row normalization" help=" " />
812 </section>
813 </when>
814 <yield />
815 </xml>
816
817 <xml name="sparse_preprocessor_options_ext">
818 <expand macro="sparse_preprocessor_options">
819 <when value="KernelCenterer">
820 <section name="options" title="Advanced Options" expanded="False">
821 </section>
822 </when>
823 <when value="MinMaxScaler">
824 <section name="options" title="Advanced Options" expanded="False">
825 <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)" />
826 <param argument="copy" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolflase" checked="true" label="Use a copy of data for precomputing normalization" help=" " />
827 </section>
828 </when>
829 <when value="PolynomialFeatures">
830 <section name="options" title="Advanced Options" expanded="False">
831 <param argument="degree" type="integer" optional="true" value="2" label="The degree of the polynomial features " help="" />
832 <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) " />
833 <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 " />
834 </section>
835 </when>
836 <when value="RobustScaler">
837 <section name="options" title="Advanced Options" expanded="False">
838 <!--=True, =True, copy=True-->
839 <param argument="with_centering" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolflase" checked="true" label="Center the data before scaling" help=" " />
840 <param argument="with_scaling" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolflase" checked="true" label="Scale the data to interquartile range" help=" " />
841 <param argument="copy" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolflase" checked="true" label="Use a copy of data for inplace scaling" help=" " />
842 </section>
843 </when>
844 <when value="QuantileTransformer">
845 <section name="options" title="Advanced Options" expanded="False">
846 <param name="n_quantiles" type="integer" value="1000" min="0" label="Number of quantiles to be computed" />
847 <param name="output_distribution" type="select" label="Marginal distribution for the transformed data">
848 <option value="uniform" selected="true">uniform</option>
849 <option value="normal">normal</option>
850 </param>
851 <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" />
852 <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." />
853 <expand macro="random_state" help_text="This is used by subsampling and smoothing noise" />
854 </section>
855 </when>
856 <when value="PowerTransformer">
857 <section name="options" title="Advanced Options" expanded="False">
858 <param name="method" type="select" label="The power transform method">
859 <option value="yeo-johnson" selected="true">yeo-johnson (works with positive and negative values)</option>
860 <option value="box-cox">box-cox (might perform better, but only works with strictly positive values)</option>
861 </param>
862 <param name="standardize" type="boolean" truevalue="booltrue" falsevalue="boolfalse" checked="true" label="Whether to apply zero-mean, unit-variance normalization to the transformed output." />
863 </section>
864 </when>
865 <when value="KBinsDiscretizer">
866 <section name="options" title="Advanced Options" expanded="False">
867 <param name="n_bins" type="integer" value="5" min="2" label="The number of bins to produce" />
868 <param name="encode" type="select" label="Method used to encode the transformed result">
869 <option value="onehot" selected="true">onehot (encode the transformed result with one-hot encoding and return a sparse matrix)</option>
870 <option value="onehot-dense">onehot-dense (encode the transformed result with one-hot encoding and return a dense array)</option>
871 <option value="ordinal">ordinal (return the bin identifier encoded as an integer value)</option>
872 </param>
873 <param name="strategy" type="select" label="Strategy used to define the widths of the bins">
874 <option value="uniform">uniform (all bins in each feature have identical widths)</option>
875 <option value="quantile" selected="true">quantile (all bins in each feature have the same number of points)</option>
876 <option value="kmeans">kmeans (values in each bin have the same nearest center of a 1D k-means cluster)</option>
877 </param>
878 </section>
879 </when>
880 </expand>
881 </xml>
882
883 <xml name="cv_splitter">
884 <option value="default" selected="true">default splitter</option>
885 <option value="KFold">KFold</option>
886 <option value="StratifiedKFold">StratifiedKFold</option>
887 <option value="LeaveOneOut">LeaveOneOut</option>
888 <option value="LeavePOut">LeavePOut</option>
889 <option value="RepeatedKFold">RepeatedKFold</option>
890 <option value="RepeatedStratifiedKFold">RepeatedStratifiedKFold</option>
891 <option value="ShuffleSplit">ShuffleSplit</option>
892 <option value="StratifiedShuffleSplit">StratifiedShuffleSplit</option>
893 <option value="TimeSeriesSplit">TimeSeriesSplit</option>
894 <option value="PredefinedSplit">PredefinedSplit</option>
895 <option value="OrderedKFold">OrderedKFold</option>
896 <option value="RepeatedOrderedKFold">RepeatedOrderedKFold</option>
897 <yield />
898 </xml>
899
900 <xml name="cv_splitter_options">
901 <when value="default">
902 <expand macro="cv_n_splits" />
903 </when>
904 <when value="KFold">
905 <expand macro="cv_n_splits" />
906 <expand macro="cv_shuffle" />
907 <expand macro="random_state" />
908 </when>
909 <when value="StratifiedKFold">
910 <expand macro="cv_n_splits" />
911 <expand macro="cv_shuffle" />
912 <expand macro="random_state" />
913 </when>
914 <when value="LeaveOneOut">
915 </when>
916 <when value="LeavePOut">
917 <param argument="p" type="integer" value="" label="p" help="Integer. Size of the test sets." />
918 </when>
919 <when value="RepeatedKFold">
920 <expand macro="cv_n_splits" value="5" />
921 <param argument="n_repeats" type="integer" value="10" label="n_repeats" help="Number of times cross-validator needs to be repeated." />
922 <expand macro="random_state" />
923 </when>
924 <when value="RepeatedStratifiedKFold">
925 <expand macro="cv_n_splits" value="5" />
926 <param argument="n_repeats" type="integer" value="10" label="n_repeats" help="Number of times cross-validator needs to be repeated." />
927 <expand macro="random_state" />
928 </when>
929 <when value="ShuffleSplit">
930 <expand macro="cv_n_splits" value="10" help="Number of re-shuffling and splitting iterations." />
931 <expand macro="cv_test_size" value="0.1" />
932 <expand macro="random_state" />
933 </when>
934 <when value="StratifiedShuffleSplit">
935 <expand macro="cv_n_splits" value="10" help="Number of re-shuffling and splitting iterations." />
936 <expand macro="cv_test_size" value="0.1" />
937 <expand macro="random_state" />
938 </when>
939 <when value="TimeSeriesSplit">
940 <expand macro="cv_n_splits" />
941 <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." />
942 </when>
943 <when value="PredefinedSplit">
944 <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'." />
945 </when>
946 <when value="OrderedKFold">
947 <expand macro="cv_n_splits" />
948 <expand macro="cv_shuffle" />
949 <expand macro="random_state" />
950 </when>
951 <when value="RepeatedOrderedKFold">
952 <expand macro="cv_n_splits" />
953 <param argument="n_repeats" type="integer" value="5" />
954 <expand macro="random_state" />
955 </when>
956 <yield />
957 </xml>
958
959 <xml name="cv">
960 <conditional name="cv_selector">
961 <param name="selected_cv" type="select" label="Select the cv splitter:">
962 <expand macro="cv_splitter">
963 <option value="GroupKFold">GroupKFold</option>
964 <option value="GroupShuffleSplit">GroupShuffleSplit</option>
965 <option value="LeaveOneGroupOut">LeaveOneGroupOut</option>
966 <option value="LeavePGroupsOut">LeavePGroupsOut</option>
967 </expand>
968 </param>
969 <expand macro="cv_splitter_options">
970 <when value="GroupKFold">
971 <expand macro="cv_n_splits" />
972 <expand macro="cv_groups" />
37 </when> 973 </when>
38 <when value="advanced"> 974 <when value="GroupShuffleSplit">
975 <expand macro="cv_n_splits" value="5" />
976 <expand macro="cv_test_size" />
977 <expand macro="random_state" />
978 <expand macro="cv_groups" />
979 </when>
980 <when value="LeaveOneGroupOut">
981 <expand macro="cv_groups" />
982 </when>
983 <when value="LeavePGroupsOut">
984 <param argument="n_groups" type="integer" value="" label="n_groups" help="Number of groups (p) to leave out in the test split." />
985 <expand macro="cv_groups" />
986 </when>
987 </expand>
988 </conditional>
989 </xml>
990
991 <xml name="cv_reduced" token_label="Select the cv splitter">
992 <conditional name="cv_selector">
993 <param name="selected_cv" type="select" label="@LABEL@">
994 <expand macro="cv_splitter" />
995 </param>
996 <expand macro="cv_splitter_options" />
997 </conditional>
998 </xml>
999
1000 <xml name="cv_n_splits" token_value="3" token_help="Number of folds. Must be at least 2.">
1001 <param argument="n_splits" type="integer" value="@VALUE@" min="1" label="n_splits" help="@HELP@" />
1002 </xml>
1003
1004 <xml name="cv_shuffle">
1005 <param argument="shuffle" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolfalse" checked="false" label="Whether to shuffle data before splitting" />
1006 </xml>
1007
1008 <xml name="cv_test_size" token_value="0.2">
1009 <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 " />
1010 </xml>
1011
1012 <xml name="cv_groups">
1013 <section name="groups_selector" title="Groups column selector" expanded="true">
1014 <param name="infile_g" type="data" format="tabular" label="Choose dataset containing groups info:" />
1015 <param name="header_g" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolfalse" checked="False" label="Does the dataset contain header:" />
1016 <conditional name="column_selector_options_g">
1017 <expand macro="samples_column_selector_options" column_option="selected_column_selector_option_g" col_name="col_g" multiple="False" infile="infile_g" />
1018 </conditional>
1019 </section>
1020 </xml>
1021
1022 <xml name="train_test_split_params">
1023 <conditional name="split_algos">
1024 <param name="shuffle" type="select" label="Select the splitting method">
1025 <option value="None">No shuffle</option>
1026 <option value="simple" selected="true">ShuffleSplit</option>
1027 <option value="stratified">StratifiedShuffleSplit -- target values serve as class labels</option>
1028 <option value="group">GroupShuffleSplit or split by group names</option>
1029 </param>
1030 <when value="None">
1031 <expand macro="train_test_split_test_size" />
1032 </when>
1033 <when value="simple">
1034 <expand macro="train_test_split_test_size" />
1035 <expand macro="random_state" />
1036 </when>
1037 <when value="stratified">
1038 <expand macro="train_test_split_test_size" />
1039 <expand macro="random_state" />
1040 </when>
1041 <when value="group">
1042 <expand macro="train_test_split_test_size" optional="true" />
1043 <expand macro="random_state" />
1044 <param argument="group_names" type="text" value="" optional="true" label="Type in group names instead" help="For example: chr6, chr7. This parameter is optional. If used, it will override the holdout size and random seed." />
1045 <yield />
1046 </when>
1047 </conditional>
1048 <!--param argument="train_size" type="float" optional="True" value="" label="Train size:"/>-->
1049 </xml>
1050
1051 <xml name="train_test_split_test_size" token_optional="false">
1052 <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." />
1053 </xml>
1054
1055 <xml name="feature_selection_algorithms">
1056 <option value="SelectKBest" selected="true">SelectKBest - Select features according to the k highest scores</option>
1057 <option value="GenericUnivariateSelect">GenericUnivariateSelect - Univariate feature selector with configurable strategy</option>
1058 <option value="SelectPercentile">SelectPercentile - Select features according to a percentile of the highest scores</option>
1059 <option value="SelectFpr">SelectFpr - Filter: Select the p-values below alpha based on a FPR test</option>
1060 <option value="SelectFdr">SelectFdr - Filter: Select the p-values for an estimated false discovery rate</option>
1061 <option value="SelectFwe">SelectFwe - Filter: Select the p-values corresponding to Family-wise error rate</option>
1062 <option value="VarianceThreshold">VarianceThreshold - Feature selector that removes all low-variance features</option>
1063 <option value="SelectFromModel">SelectFromModel - Meta-transformer for selecting features based on importance weights</option>
1064 <option value="RFE">RFE - Feature ranking with recursive feature elimination</option>
1065 <option value="RFECV">RFECV - Feature ranking with recursive feature elimination and cross-validated selection of the best number of features</option>
1066 <yield />
1067 </xml>
1068
1069 <xml name="feature_selection_algorithm_details">
1070 <when value="GenericUnivariateSelect">
1071 <expand macro="feature_selection_score_function" />
1072 <section name="options" title="Advanced Options" expanded="False">
1073 <param argument="mode" type="select" label="Feature selection mode">
1074 <option value="percentile">percentile</option>
1075 <option value="k_best">k_best</option>
1076 <option value="fpr">fpr</option>
1077 <option value="fdr">fdr</option>
1078 <option value="fwe">fwe</option>
1079 </param>
1080 <param argument="param" type="float" value="" optional="true" label="Parameter of the corresponding mode" help="float or int depending on the feature selection mode" />
1081 </section>
1082 </when>
1083 <when value="SelectPercentile">
1084 <expand macro="feature_selection_score_function" />
1085 <section name="options" title="Advanced Options" expanded="False">
1086 <param argument="percentile" type="integer" value="10" optional="True" label="Percent of features to keep" />
1087 </section>
1088 </when>
1089 <when value="SelectKBest">
1090 <expand macro="feature_selection_score_function" />
1091 <section name="options" title="Advanced Options" expanded="False">
1092 <param argument="k" type="integer" value="10" optional="True" label="Number of top features to select" help="No 'all' option is supported." />
1093 </section>
1094 </when>
1095 <when value="SelectFpr">
1096 <expand macro="feature_selection_score_function" />
1097 <section name="options" title="Advanced Options" expanded="False">
1098 <param argument="alpha" type="float" value="" optional="True" label="Alpha" help="The highest p-value for features to be kept." />
1099 </section>
1100 </when>
1101 <when value="SelectFdr">
1102 <expand macro="feature_selection_score_function" />
1103 <section name="options" title="Advanced Options" expanded="False">
1104 <param argument="alpha" type="float" value="" optional="True" label="Alpha" help="The highest uncorrected p-value for features to keep." />
1105 </section>
1106 </when>
1107 <when value="SelectFwe">
1108 <expand macro="feature_selection_score_function" />
1109 <section name="options" title="Advanced Options" expanded="False">
1110 <param argument="alpha" type="float" value="" optional="True" label="Alpha" help="The highest uncorrected p-value for features to keep." />
1111 </section>
1112 </when>
1113 <when value="VarianceThreshold">
1114 <section name="options" title="Options" expanded="False">
1115 <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." />
1116 </section>
1117 </when>
1118 </xml>
1119
1120 <xml name="feature_selection_SelectFromModel">
1121 <when value="SelectFromModel">
1122 <conditional name="model_inputter">
1123 <param name="input_mode" type="select" label="Construct a new estimator from a selection list?">
1124 <option value="new" selected="true">Yes</option>
1125 <option value="prefitted">No. Load a prefitted estimator</option>
1126 </param>
1127 <when value="new">
1128 <expand macro="estimator_selector_fs" />
1129 </when>
1130 <when value="prefitted">
1131 <param name="fitted_estimator" type="data" format='zip' label="Load a prefitted estimator" />
39 </when> 1132 </when>
40 </conditional> 1133 </conditional>
41 </when> 1134 <expand macro="feature_selection_SelectFromModel_options" />
42 <when value="train"> 1135 </when>
43 <conditional name="selected_algorithms"> 1136 </xml>
44 <yield /> 1137
1138 <xml name="feature_selection_SelectFromModel_no_prefitted">
1139 <when value="SelectFromModel">
1140 <conditional name="model_inputter">
1141 <param name="input_mode" type="select" label="Construct a new estimator from a selection list?">
1142 <option value="new" selected="true">Yes</option>
1143 </param>
1144 <when value="new">
1145 <expand macro="estimator_selector_all" />
1146 </when>
45 </conditional> 1147 </conditional>
46 </when> 1148 <expand macro="feature_selection_SelectFromModel_options" />
47 </conditional> 1149 </when>
48 </xml> 1150 </xml>
49 1151
50 <xml name="advanced_section"> 1152 <xml name="feature_selection_SelectFromModel_options">
51 <section name="options" title="Advanced Options" expanded="False"> 1153 <section name="options" title="Advanced Options" expanded="False">
52 <yield /> 1154 <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'." />
53 </section> 1155 <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. " />
54 </xml> 1156 <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." />
55 1157 </section>
56 1158 </xml>
57 <!--Generalized Linear Models--> 1159
58 <xml name="loss" token_help=" " token_select="false"> 1160 <xml name="feature_selection_RFE">
59 <param argument="loss" type="select" label="Loss function" help="@HELP@"> 1161 <when value="RFE">
60 <option value="squared_loss" selected="@SELECT@">squared loss</option> 1162 <yield />
61 <option value="huber">huber</option> 1163 <section name="options" title="Advanced Options" expanded="False">
62 <option value="epsilon_insensitive">epsilon insensitive</option> 1164 <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." />
63 <option value="squared_epsilon_insensitive">squared epsilon insensitive</option> 1165 <param argument="step" type="float" value="1" label="step" optional="true" help="Default = 1. " />
64 <yield/> 1166 <param argument="verbose" type="integer" value="0" label="verbose" help="Controls verbosity of output." />
65 </param> 1167 </section>
66 </xml> 1168 </when>
67 1169 </xml>
68 <xml name="penalty" token_help=" "> 1170
69 <param argument="penalty" type="select" label="Penalty (regularization term)" help="@HELP@"> 1171 <xml name="feature_selection_RFECV_fs">
70 <option value="l2" selected="true">l2</option> 1172 <when value="RFECV">
71 <option value="l1">l1</option> 1173 <yield />
72 <option value="elasticnet">elastic net</option> 1174 <section name="options" title="Advanced Options" expanded="False">
73 <option value="none">none</option> 1175 <param argument="step" type="float" value="1" label="step" optional="true" help="Default = 1. " />
74 <yield/> 1176 <param argument="min_features_to_select" type="integer" value="1" optional="true" label="The minimum number of features to be selected" />
75 </param> 1177 <expand macro="cv" />
76 </xml> 1178 <expand macro="scoring_selection" />
77 1179 <param argument="verbose" type="integer" value="0" label="verbose" help="Controls verbosity of output." />
78 <xml name="l1_ratio" token_default_value="0.15" token_help=" "> 1180 </section>
79 <param argument="l1_ratio" type="float" value="@DEFAULT_VALUE@" label="Elastic Net mixing parameter" help="@HELP@"/> 1181 </when>
80 </xml> 1182 </xml>
81 1183
82 <xml name="epsilon" token_default_value="0.1" token_help="Used if loss is ‘huber’, ‘epsilon_insensitive’, or ‘squared_epsilon_insensitive’. "> 1184 <xml name="feature_selection_RFECV_pipeline">
83 <param argument="epsilon" type="float" value="@DEFAULT_VALUE@" label="Epsilon (epsilon-sensitive loss functions only)" help="@HELP@"/> 1185 <when value="RFECV">
84 </xml> 1186 <yield />
85 1187 <section name="options" title="Advanced Options" expanded="False">
86 <xml name="learning_rate_s" token_help=" " token_selected1="false" token_selected2="false"> 1188 <param argument="step" type="float" value="1" label="step" optional="true" help="Default = 1. " />
87 <param argument="learning_rate" type="select" optional="true" label="Learning rate schedule" help="@HELP@"> 1189 <param argument="min_features_to_select" type="integer" value="1" optional="true" label="The minimum number of features to be selected" />
88 <option value="optimal" selected="@SELECTED1@">optimal</option> 1190 <expand macro="cv_reduced" />
89 <option value="constant">constant</option> 1191 <!-- TODO: group splitter support-->
90 <option value="invscaling" selected="@SELECTED2@">inverse scaling</option> 1192 <expand macro="scoring_selection" />
91 <yield/> 1193 <param argument="verbose" type="integer" value="0" label="verbose" help="Controls verbosity of output." />
92 </param> 1194 </section>
93 </xml> 1195 </when>
94 1196 </xml>
95 <xml name="eta0" token_default_value="0.0" token_help="Used with ‘constant’ or ‘invscaling’ schedules. "> 1197
96 <param argument="eta0" type="float" value="@DEFAULT_VALUE@" label="Initial learning rate" help="@HELP@"/> 1198 <xml name="feature_selection_DyRFECV_fs">
97 </xml> 1199 <when value="DyRFECV">
98 1200 <yield />
99 <xml name="power_t" token_default_value="0.5" token_help=" "> 1201 <section name="options" title="Advanced Options" expanded="False">
100 <param argument="power_t" type="float" value="@DEFAULT_VALUE@" label="Exponent for inverse scaling learning rate" help="@HELP@"/> 1202 <param argument="step" type="text" size="30" value="1" label="step" optional="true" help="Default = 1. Support float, int and list.">
101 </xml> 1203 <sanitizer>
102 1204 <valid initial="default">
103 <xml name="normalize" token_checked="false" token_help=" "> 1205 <add value="[" />
104 <param argument="normalize" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolfalse" checked="@CHECKED@" label="Normalize samples before training" help=" "/> 1206 <add value="]" />
105 </xml> 1207 </valid>
106 1208 </sanitizer>
107 <xml name="copy_X" token_checked="true" token_help=" "> 1209 </param>
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. "/> 1210 <param argument="min_features_to_select" type="integer" value="1" optional="true" label="The minimum number of features to be selected" />
109 </xml> 1211 <expand macro="cv" />
110 1212 <expand macro="scoring_selection" />
111 <xml name="ridge_params"> 1213 <param argument="verbose" type="integer" value="0" label="verbose" help="Controls verbosity of output." />
112 <expand macro="normalize"/> 1214 </section>
113 <expand macro="alpha" default_value="1.0"/> 1215 </when>
114 <expand macro="fit_intercept"/> 1216 </xml>
115 <expand macro="max_iter" default_value=""/> 1217
116 <expand macro="tol" default_value="0.001" help_text="Precision of the solution. "/> 1218 <xml name="feature_selection_pipeline">
117 <!--class_weight--> 1219 <!--compare to `feature_selection_fs`, no fitted estimator for SelectFromModel and no custom estimator for RFE and RFECV-->
118 <expand macro="copy_X"/> 1220 <conditional name="fs_algorithm_selector">
119 <param argument="solver" type="select" value="" label="Solver to use in the computational routines" help=" "> 1221 <param name="selected_algorithm" type="select" label="Select a feature selection algorithm">
120 <option value="auto" selected="true">auto</option> 1222 <expand macro="feature_selection_algorithms" />
121 <option value="svd">svd</option> 1223 </param>
122 <option value="cholesky">cholesky</option> 1224 <expand macro="feature_selection_algorithm_details" />
123 <option value="lsqr">lsqr</option> 1225 <expand macro="feature_selection_SelectFromModel_no_prefitted" />
124 <option value="sparse_cg">sparse_cg</option> 1226 <expand macro="feature_selection_RFE">
125 <option value="sag">sag</option> 1227 <expand macro="estimator_selector_all" />
126 </param> 1228 </expand>
127 <expand macro="random_state"/> 1229 <expand macro="feature_selection_RFECV_pipeline">
128 </xml> 1230 <expand macro="estimator_selector_all" />
129 1231 </expand>
130 <!--Ensemble methods--> 1232 <!-- TODO: add DyRFECV to pipeline-->
131 <xml name="n_estimators" token_default_value="10" token_help=" "> 1233 </conditional>
132 <param argument="n_estimators" type="integer" optional="true" value="@DEFAULT_VALUE@" label="Number of trees in the forest" help="@HELP@"/> 1234 </xml>
133 </xml> 1235
134 1236 <xml name="feature_selection_fs">
135 <xml name="max_depth" token_default_value="" token_help=" "> 1237 <conditional name="fs_algorithm_selector">
136 <param argument="max_depth" type="integer" optional="true" value="@DEFAULT_VALUE@" label="Maximum depth of the tree" help="@HELP@"/> 1238 <param name="selected_algorithm" type="select" label="Select a feature selection algorithm">
137 </xml> 1239 <expand macro="feature_selection_algorithms">
138 1240 <option value="DyRFECV">DyRFECV - Extended RFECV with changeable steps</option>
139 <xml name="min_samples_split" token_type="integer" token_default_value="2" token_help=" "> 1241 </expand>
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@"/> 1242 </param>
141 </xml> 1243 <expand macro="feature_selection_algorithm_details" />
142 1244 <expand macro="feature_selection_SelectFromModel" />
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=" "> 1245 <expand macro="feature_selection_RFE">
144 <param argument="min_samples_leaf" type="@TYPE@" optional="true" value="@DEFAULT_VALUE@" label="@LABEL@" help="@HELP@"/> 1246 <expand macro="estimator_selector_fs" />
145 </xml> 1247 </expand>
146 1248 <expand macro="feature_selection_RFECV_fs">
147 <xml name="min_weight_fraction_leaf" token_default_value="0.0" token_help=" "> 1249 <expand macro="estimator_selector_fs" />
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@"/> 1250 </expand>
149 </xml> 1251 <expand macro="feature_selection_DyRFECV_fs">
150 1252 <expand macro="estimator_selector_fs" />
151 <xml name="max_leaf_nodes" token_default_value="" token_help=" "> 1253 </expand>
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@"/> 1254 </conditional>
153 </xml> 1255 </xml>
154 1256
155 <xml name="min_impurity_decrease" token_default_value="0" token_help=" "> 1257 <xml name="feature_selection_score_function">
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@"/> 1258 <param argument="score_func" type="select" label="Select a score function">
157 </xml> 1259 <option value="chi2">chi2 - Compute chi-squared stats between each non-negative feature and class</option>
158 1260 <option value="f_classif">f_classif - Compute the ANOVA F-value for the provided sample</option>
159 <xml name="bootstrap" token_checked="true" token_help=" "> 1261 <option value="f_regression">f_regression - Univariate linear regression tests</option>
160 <param argument="bootstrap" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolflase" checked="@CHECKED@" label="Use bootstrap samples for building trees." help="@HELP@"/> 1262 <option value="mutual_info_classif">mutual_info_classif - Estimate mutual information for a discrete target variable</option>
161 </xml> 1263 <option value="mutual_info_regression">mutual_info_regression - Estimate mutual information for a continuous target variable</option>
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 <!-- LightGBM -->
224 <xml name="feature_fraction" token_help="LightGBM will randomly select part of the features for each iteration (tree) if feature_fraction is smaller than 1.0. For example, if you set it to 0.8, LightGBM will select 80% of features before training each tree.">
225 <param argument="feature_fraction" type="float" value="1.0" label="Proportion of features to train each tree" help="@HELP@"/>
226 </xml>
227
228 <xml name="lambda_l1" token_help=" ">
229 <param argument="lambda_l1" type="float" value="0.0" label="L1 regularization" help="@HELP@"/>
230 </xml>
231
232 <xml name="lambda_l2" token_help=" ">
233 <param argument="lambda_l2" type="float" value="0.0" label="L1 regularization" help="@HELP@"/>
234 </xml>
235
236 <xml name="min_gain_to_split" token_help=" ">
237 <param argument="min_gain_to_split" type="float" value="0.0" label="Minimal gain to perform split" help="@HELP@"/>
238 </xml>
239
240 <xml name="min_child_weight" token_help="Minimal sum hessian in one leaf. It can be used to deal with over-fitting.">
241 <param argument="min_child_weight" type="float" value="0.0" label="Minimal sum hessian in one leaf" help="@HELP@"/>
242 </xml>
243
244
245 <!--Parameters-->
246 <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.">
247 <param argument="tol" type="float" optional="true" value="@DEFAULT_VALUE@" label="Tolerance" help="@HELP_TEXT@"/>
248 </xml>
249
250 <xml name="n_clusters" token_default_value="8">
251 <param argument="n_clusters" type="integer" optional="true" value="@DEFAULT_VALUE@" label="Number of clusters" help=" "/>
252 </xml>
253
254 <xml name="fit_intercept" token_checked="true">
255 <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."/>
256 </xml>
257
258 <xml name="n_iter_no_change" token_default_value="5" token_help_text="Number of iterations with no improvement to wait before early stopping. ">
259 <param argument="n_iter_no_change" type="integer" optional="true" value="@DEFAULT_VALUE@" label="Number of iterations" help="@HELP_TEXT@"/>
260 </xml>
261
262 <xml name="shuffle" token_checked="true" token_help_text=" " token_label="Shuffle data after each iteration">
263 <param argument="shuffle" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolfalse" checked="@CHECKED@" label="@LABEL@" help="@HELP_TEXT@"/>
264 </xml>
265
266 <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.">
267 <param argument="random_state" type="integer" optional="true" value="@DEFAULT_VALUE@" label="Random seed number" help="@HELP_TEXT@"/>
268 </xml>
269
270 <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.">
271 <param argument="warm_start" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolfalse" checked="@CHECKED@" label="Perform warm start" help="@HELP_TEXT@"/>
272 </xml>
273
274 <xml name="C" token_default_value="1.0" token_help_text="Penalty parameter C of the error term.">
275 <param argument="C" type="float" optional="true" value="@DEFAULT_VALUE@" label="Penalty parameter" help="@HELP_TEXT@"/>
276 </xml>
277
278 <!--xml name="class_weight" token_default_value="" token_help_text="">
279 <param argument="class_weight" type="" optional="true" value="@DEFAULT_VALUE@" label="" help="@HELP_TEXT@"/>
280 </xml-->
281
282 <xml name="alpha" token_default_value="0.0001" token_help_text="Constant that multiplies the regularization term if regularization is used. ">
283 <param argument="alpha" type="float" optional="true" value="@DEFAULT_VALUE@" label="Regularization coefficient" help="@HELP_TEXT@"/>
284 </xml>
285
286 <xml name="n_samples" token_default_value="100" token_help_text="The total number of points equally divided among clusters.">
287 <param argument="n_samples" type="integer" optional="true" value="@DEFAULT_VALUE@" label="Number of samples" help="@HELP_TEXT@"/>
288 </xml>
289
290 <xml name="n_features" token_default_value="2" token_help_text="Number of different numerical properties produced for each sample.">
291 <param argument="n_features" type="integer" optional="true" value="@DEFAULT_VALUE@" label="Number of features" help="@HELP_TEXT@"/>
292 </xml>
293
294 <xml name="noise" token_default_value="0.0" token_help_text="Floating point number. ">
295 <param argument="noise" type="float" optional="true" value="@DEFAULT_VALUE@" label="Standard deviation of the Gaussian noise added to the data" help="@HELP_TEXT@"/>
296 </xml>
297
298 <xml name="C" token_default_value="1.0" token_help_text="Penalty parameter C of the error term. ">
299 <param argument="C" type="float" optional="true" value="@DEFAULT_VALUE@" label="Penalty parameter" help="@HELP_TEXT@"/>
300 </xml>
301
302 <xml name="max_iter" token_default_value="300" token_label="Maximum number of iterations per single run" token_help_text=" ">
303 <param argument="max_iter" type="integer" optional="true" value="@DEFAULT_VALUE@" label="@LABEL@" help="@HELP_TEXT@"/>
304 </xml>
305
306 <xml name="n_init" token_default_value="10" >
307 <param argument="n_init" type="integer" optional="true" value="@DEFAULT_VALUE@" label="Number of runs with different centroid seeds" help=" "/>
308 </xml>
309
310 <xml name="init">
311 <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.">
312 <option value="k-means++">k-means++</option>
313 <option value="random">random</option>
314 </param>
315 </xml>
316
317 <xml name="gamma" token_default_value="1.0" token_label="Scaling parameter" token_help_text=" ">
318 <param argument="gamma" type="float" optional="true" value="@DEFAULT_VALUE@" label="@LABEL@" help="@HELP_TEXT@"/>
319 </xml>
320
321 <xml name="degree" token_default_value="3" token_label="Degree of the polynomial" token_help_text=" ">
322 <param argument="degree" type="integer" optional="true" value="@DEFAULT_VALUE@" label="@LABEL@" help="@HELP_TEXT@"/>
323 </xml>
324
325 <xml name="coef0" token_default_value="1" token_label="Zero coefficient" token_help_text=" ">
326 <param argument="coef0" type="integer" optional="true" value="@DEFAULT_VALUE@" label="@LABEL@" help="@HELP_TEXT@"/>
327 </xml>
328
329 <xml name="pos_label" token_default_value="">
330 <param argument="pos_label" type="integer" optional="true" value="@DEFAULT_VALUE@" label="Label of the positive class" help=" "/>
331 </xml>
332
333 <xml name="average">
334 <param argument="average" type="select" optional="true" label="Averaging type" help=" ">
335 <option value="micro">Calculate metrics globally by counting the total true positives, false negatives and false positives. (micro)</option>
336 <option value="samples">Calculate metrics for each instance, and find their average. Only meaningful for multilabel. (samples)</option>
337 <option value="macro">Calculate metrics for each label, and find their unweighted mean. This does not take label imbalance into account. (macro)</option>
338 <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>
339 <option value="None">None</option>
340 <yield/>
341 </param>
342 </xml>
343
344 <xml name="beta">
345 <param argument="beta" type="float" value="1.0" label="The strength of recall versus precision in the F-score" help=" "/>
346 </xml>
347
348
349 <!--Data interface-->
350
351 <xml name="samples_tabular" token_label1="Training samples dataset:" token_multiple1="false" token_multiple2="false">
352 <param name="infile1" type="data" format="tabular" label="@LABEL1@"/>
353 <param name="header1" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolfalse" checked="False" label="Does the dataset contain header:" />
354 <conditional name="column_selector_options_1">
355 <expand macro="samples_column_selector_options" multiple="@MULTIPLE1@"/>
356 </conditional>
357 <param name="infile2" type="data" format="tabular" label="Dataset containing class labels or target values:"/>
358 <param name="header2" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolfalse" checked="False" label="Does the dataset contain header:" />
359 <conditional name="column_selector_options_2">
360 <expand macro="samples_column_selector_options" column_option="selected_column_selector_option2" col_name="col2" multiple="@MULTIPLE2@" infile="infile2"/>
361 </conditional>
362 <yield/>
363 </xml>
364
365 <xml name="samples_column_selector_options" token_column_option="selected_column_selector_option" token_col_name="col1" token_multiple="False" token_infile="infile1">
366 <param name="@COLUMN_OPTION@" type="select" label="Choose how to select data by column:">
367 <option value="by_index_number" selected="true">Select columns by column index number(s)</option>
368 <option value="all_but_by_index_number">All columns EXCLUDING some by column index number(s)</option>
369 <option value="by_header_name">Select columns by column header name(s)</option>
370 <option value="all_but_by_header_name">All columns EXCLUDING some by column header name(s)</option>
371 <option value="all_columns">All columns</option>
372 </param>
373 <when value="by_index_number">
374 <param name="@COL_NAME@" multiple="@MULTIPLE@" type="data_column" use_header_names="true" data_ref="@INFILE@" label="Select target column(s):"/>
375 </when>
376 <when value="all_but_by_index_number">
377 <param name="@COL_NAME@" multiple="@MULTIPLE@" type="data_column" use_header_names="true" data_ref="@INFILE@" label="Select target column(s):"/>
378 </when>
379 <when value="by_header_name">
380 <param name="@COL_NAME@" type="text" value="" label="Type header name(s):" help="Comma-separated string. For example: target1,target2"/>
381 </when>
382 <when value="all_but_by_header_name">
383 <param name="@COL_NAME@" type="text" value="" label="Type header name(s):" help="Comma-separated string. For example: target1,target2"/>
384 </when>
385 <when value="all_columns">
386 </when>
387 </xml>
388
389 <xml name="clf_inputs_extended" token_label1=" " token_label2=" " token_multiple="False">
390 <conditional name="true_columns">
391 <param name="selected_input1" type="select" label="Select the input type of true labels dataset:">
392 <option value="tabular" selected="true">Tabular</option>
393 <option value="sparse">Sparse</option>
394 </param>
395 <when value="tabular">
396 <param name="infile1" type="data" label="@LABEL1@"/>
397 <param name="col1" type="data_column" data_ref="infile1" label="Select the target column:"/>
398 </when>
399 <when value="sparse">
400 <param name="infile1" type="data" format="txt" label="@LABEL1@"/>
401 </when>
402 </conditional>
403 <conditional name="predicted_columns">
404 <param name="selected_input2" type="select" label="Select the input type of predicted labels dataset:">
405 <option value="tabular" selected="true">Tabular</option>
406 <option value="sparse">Sparse</option>
407 </param>
408 <when value="tabular">
409 <param name="infile2" type="data" label="@LABEL2@"/>
410 <param name="col2" multiple="@MULTIPLE@" type="data_column" data_ref="infile2" label="Select target column(s):"/>
411 </when>
412 <when value="sparse">
413 <param name="infile2" type="data" format="txt" label="@LABEL1@"/>
414 </when>
415 </conditional>
416 </xml>
417
418 <xml name="clf_inputs" token_label1="Dataset containing true labels (tabular):" token_label2="Dataset containing predicted values (tabular):" token_multiple1="False" token_multiple="False">
419 <param name="infile1" type="data" format="tabular" label="@LABEL1@"/>
420 <param name="header1" type="boolean" optional="True" truevalue="booltrue" falsevalue="boolfalse" checked="False" label="Does the dataset contain header:" />
421 <conditional name="column_selector_options_1">
422 <expand macro="samples_column_selector_options" multiple="@MULTIPLE1@"/>
423 </conditional>
424 <param name="infile2" type="data" format="tabular" label="@LABEL2@"/>
425 <param name="header2" type="boolean" optional="True" truevalue="booltrue" falsevalue="boolfalse" checked="False" label="Does the dataset contain header:" />
426 <conditional name="column_selector_options_2">
427 <expand macro="samples_column_selector_options" column_option="selected_column_selector_option2" col_name="col2" multiple="@MULTIPLE@" infile="infile2"/>
428 </conditional>
429 </xml>
430
431 <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.">
432 <repeat name="@NAME@" min="1" max="@MAX_NUM@" title="Select input file(s):">
433 <param name="input" type="data" format="@FORMAT@" label="@LABEL@" help="@HELP_TEXT@"/>
434 </repeat>
435 </xml>
436
437 <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="">
438 <param name="infile1" type="data" format="@FORMAT1@" label="@LABEL1@" help="@HELP1@"/>
439 <expand macro="input_tabular_target"/>
440 </xml>
441
442 <xml name="sl_mixed_input">
443 <conditional name="input_options">
444 <expand macro="data_input_options"/>
445 <expand macro="data_input_whens"/>
446 </conditional>
447 </xml>
448
449 <xml name="sl_mixed_input_plus_sequence">
450 <conditional name="input_options">
451 <expand macro="data_input_options">
452 <option value="seq_fasta">sequnences in a fasta file</option>
453 <option value="refseq_and_interval">reference genome and intervals</option>
454 </expand>
455 <expand macro="data_input_whens">
456 <when value="seq_fasta">
457 <expand macro="inputs_seq_fasta"/>
458 </when>
459 <when value="refseq_and_interval">
460 <expand macro="inputs_refseq_and_interval"/>
461 </when>
462 </expand>
463 </conditional>
464 </xml>
465
466 <xml name="data_input_options">
467 <param name="selected_input" type="select" label="Select input type:">
468 <option value="tabular" selected="true">tabular data</option>
469 <option value="sparse">sparse matrix</option>
470 <yield/>
471 </param>
472 </xml>
473
474 <xml name="data_input_whens">
475 <when value="tabular">
476 <expand macro="samples_tabular" multiple1="true" multiple2="false"/>
477 </when>
478 <when value="sparse">
479 <expand macro="sparse_target"/>
480 </when>
481 <yield/>
482 </xml>
483
484 <xml name="input_tabular_target">
485 <param name="infile2" type="data" format="tabular" label="Dataset containing class labels or target values:"/>
486 <param name="header2" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolfalse" checked="false" label="Does the dataset contain header:" />
487 <conditional name="column_selector_options_2">
488 <expand macro="samples_column_selector_options" column_option="selected_column_selector_option2" col_name="col2" multiple="false" infile="infile2"/>
489 </conditional>
490 </xml>
491
492 <xml name="inputs_seq_fasta">
493 <param name="fasta_path" type="data" format="fasta" label="Dataset containing fasta genomic/protein sequences" help="Sequences will be one-hot encoded to arrays."/>
494 <expand macro="input_tabular_target"/>
495 </xml>
496
497 <xml name="inputs_refseq_and_interval">
498 <param name="ref_genome_file" type="data" format="fasta" label="Dataset containing reference genomic sequence"/>
499 <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."/>
500 <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`."/>
501 <param name="infile2" type="data" format="tabular" label="Dataset containing the feature list for prediction"/>
502 <param name="header2" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolfalse" checked="false" label="Does the dataset contain header:" />
503 <conditional name="column_selector_options_2">
504 <expand macro="samples_column_selector_options" column_option="selected_column_selector_option2" col_name="col2" multiple="true" infile="infile2"/>
505 </conditional>
506 </xml>
507
508 <!--Advanced options-->
509 <xml name="nn_advanced_options">
510 <section name="options" title="Advanced Options" expanded="False">
511 <yield/>
512 <param argument="weights" type="select" label="Weight function" help="Used in prediction.">
513 <option value="uniform" selected="true">Uniform weights. All points in each neighborhood are weighted equally. (Uniform)</option>
514 <option value="distance">Weight points by the inverse of their distance. (Distance)</option>
515 </param>
516 <param argument="algorithm" type="select" label="Neighbor selection algorithm" help=" ">
517 <option value="auto" selected="true">Auto</option>
518 <option value="ball_tree">BallTree</option>
519 <option value="kd_tree">KDTree</option>
520 <option value="brute">Brute-force</option>
521 </param>
522 <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."/>
523 <!--param name="metric"-->
524 <!--param name="p"-->
525 <!--param name="metric_params"-->
526 </section>
527 </xml>
528
529 <xml name="svc_advanced_options">
530 <section name="options" title="Advanced Options" expanded="False">
531 <yield/>
532 <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.">
533 <option value="rbf" selected="true">rbf</option>
534 <option value="linear">linear</option>
535 <option value="poly">poly</option>
536 <option value="sigmoid">sigmoid</option>
537 <option value="precomputed">precomputed</option>
538 </param> 1264 </param>
539 <param argument="degree" type="integer" optional="true" value="3" label="Degree of the polynomial (polynomial kernel only)" help="Ignored by other kernels. dafault : 3 "/> 1265 </xml>
540 <!--TODO: param argument="gamma" float, optional (default=’auto’) --> 1266
541 <param argument="coef0" type="float" optional="true" value="0.0" label="Zero coefficient (polynomial and sigmoid kernels only)" 1267 <xml name="model_validation_common_options">
542 help="Independent term in kernel function. dafault: 0.0 "/> 1268 <expand macro="cv" />
543 <param argument="shrinking" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolfalse" checked="true" 1269 <expand macro="verbose" />
544 label="Use the shrinking heuristic" help=" "/> 1270 <yield />
545 <param argument="probability" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolfalse" checked="false" 1271 </xml>
546 label="Enable probability estimates. " help="This must be enabled prior to calling fit, and will slow down that method."/> 1272
547 <!-- param argument="cache_size"--> 1273 <xml name="scoring_selection">
548 <!--expand macro="class_weight"/--> 1274 <conditional name="scoring">
549 <expand macro="tol" default_value="0.001" help_text="Tolerance for stopping criterion. "/> 1275 <param name="primary_scoring" type="select" multiple="false" label="Select the primary metric (scoring):" help="Metric to refit the best estimator.">
550 <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."/> 1276 <option value="default" selected="true">default with estimator</option>
551 <!--param argument="decision_function_shape"--> 1277 <option value="accuracy">Classification -- 'accuracy'</option>
552 <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."/> 1278 <option value="balanced_accuracy">Classification -- 'balanced_accuracy'</option>
553 </section> 1279 <option value="average_precision">Classification -- 'average_precision'</option>
554 </xml> 1280 <option value="f1">Classification -- 'f1'</option>
555 1281 <option value="f1_micro">Classification -- 'f1_micro'</option>
556 <xml name="spectral_clustering_advanced_options"> 1282 <option value="f1_macro">Classification -- 'f1_macro'</option>
557 <section name="options" title="Advanced Options" expanded="False"> 1283 <option value="f1_weighted">Classification -- 'f1_weighted'</option>
558 <expand macro="n_clusters"/> 1284 <option value="f1_samples">Classification -- 'f1_samples'</option>
559 <param argument="eigen_solver" type="select" value="" label="Eigen solver" help="The eigenvalue decomposition strategy to use."> 1285 <option value="neg_log_loss">Classification -- 'neg_log_loss'</option>
560 <option value="arpack" selected="true">arpack</option> 1286 <option value="precision">Classification -- 'precision'</option>
561 <option value="lobpcg">lobpcg</option> 1287 <option value="precision_micro">Classification -- 'precision_micro'</option>
562 <option value="amg">amg</option> 1288 <option value="precision_macro">Classification -- 'precision_macro'</option>
563 <!--None--> 1289 <option value="precision_wighted">Classification -- 'precision_wighted'</option>
1290 <option value="precision_samples">Classification -- 'precision_samples'</option>
1291 <option value="recall">Classification -- 'recall'</option>
1292 <option value="recall_micro">Classification -- 'recall_micro'</option>
1293 <option value="recall_macro">Classification -- 'recall_macro'</option>
1294 <option value="recall_wighted">Classification -- 'recall_wighted'</option>
1295 <option value="recall_samples">Classification -- 'recall_samples'</option>
1296 <option value="roc_auc">Classification -- 'roc_auc'</option>
1297 <option value="explained_variance">Regression -- 'explained_variance'</option>
1298 <option value="neg_mean_absolute_error">Regression -- 'neg_mean_absolute_error'</option>
1299 <option value="neg_mean_squared_error">Regression -- 'neg_mean_squared_error'</option>
1300 <option value="neg_mean_squared_log_error">Regression -- 'neg_mean_squared_log_error'</option>
1301 <option value="neg_median_absolute_error">Regression -- 'neg_median_absolute_error'</option>
1302 <option value="r2">Regression -- 'r2'</option>
1303 <option value="max_error">Regression -- 'max_error'</option>
1304 <option value="binarize_auc_scorer">anomaly detection -- binarize_auc_scorer</option>
1305 <option value="binarize_average_precision_scorer">anomaly detection -- binarize_average_precision_scorer</option>
1306 </param>
1307 <when value="default" />
1308 <when value="accuracy">
1309 <expand macro="secondary_scoring_selection_classification" />
1310 </when>
1311 <when value="balanced_accuracy">
1312 <expand macro="secondary_scoring_selection_classification" />
1313 </when>
1314 <when value="average_precision">
1315 <expand macro="secondary_scoring_selection_classification" />
1316 </when>
1317 <when value="f1">
1318 <expand macro="secondary_scoring_selection_classification" />
1319 </when>
1320 <when value="f1_micro">
1321 <expand macro="secondary_scoring_selection_classification" />
1322 </when>
1323 <when value="f1_macro">
1324 <expand macro="secondary_scoring_selection_classification" />
1325 </when>
1326 <when value="f1_weighted">
1327 <expand macro="secondary_scoring_selection_classification" />
1328 </when>
1329 <when value="f1_samples">
1330 <expand macro="secondary_scoring_selection_classification" />
1331 </when>
1332 <when value="neg_log_loss">
1333 <expand macro="secondary_scoring_selection_classification" />
1334 </when>
1335 <when value="precision">
1336 <expand macro="secondary_scoring_selection_classification" />
1337 </when>
1338 <when value="precision_micro">
1339 <expand macro="secondary_scoring_selection_classification" />
1340 </when>
1341 <when value="precision_macro">
1342 <expand macro="secondary_scoring_selection_classification" />
1343 </when>
1344 <when value="precision_wighted">
1345 <expand macro="secondary_scoring_selection_classification" />
1346 </when>
1347 <when value="precision_samples">
1348 <expand macro="secondary_scoring_selection_classification" />
1349 </when>
1350 <when value="recall">
1351 <expand macro="secondary_scoring_selection_classification" />
1352 </when>
1353 <when value="recall_micro">
1354 <expand macro="secondary_scoring_selection_classification" />
1355 </when>
1356 <when value="recall_macro">
1357 <expand macro="secondary_scoring_selection_classification" />
1358 </when>
1359 <when value="recall_wighted">
1360 <expand macro="secondary_scoring_selection_classification" />
1361 </when>
1362 <when value="recall_samples">
1363 <expand macro="secondary_scoring_selection_classification" />
1364 </when>
1365 <when value="roc_auc">
1366 <expand macro="secondary_scoring_selection_classification" />
1367 </when>
1368 <when value="explained_variance">
1369 <expand macro="secondary_scoring_selection_regression" />
1370 </when>
1371 <when value="neg_mean_absolute_error">
1372 <expand macro="secondary_scoring_selection_regression" />
1373 </when>
1374 <when value="neg_mean_squared_error">
1375 <expand macro="secondary_scoring_selection_regression" />
1376 </when>
1377 <when value="neg_mean_squared_log_error">
1378 <expand macro="secondary_scoring_selection_regression" />
1379 </when>
1380 <when value="neg_median_absolute_error">
1381 <expand macro="secondary_scoring_selection_regression" />
1382 </when>
1383 <when value="r2">
1384 <expand macro="secondary_scoring_selection_regression" />
1385 </when>
1386 <when value="max_error">
1387 <expand macro="secondary_scoring_selection_regression" />
1388 </when>
1389 <when value="binarize_auc_scorer">
1390 <expand macro="secondary_scoring_selection_anormaly" />
1391 </when>
1392 <when value="binarize_average_precision_scorer">
1393 <expand macro="secondary_scoring_selection_anormaly" />
1394 </when>
1395 </conditional>
1396 </xml>
1397
1398 <xml name="secondary_scoring_selection_classification">
1399 <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.">
1400 <option value="accuracy">Classification -- 'accuracy'</option>
1401 <option value="balanced_accuracy">Classification -- 'balanced_accuracy'</option>
1402 <option value="average_precision">Classification -- 'average_precision'</option>
1403 <option value="f1">Classification -- 'f1'</option>
1404 <option value="f1_micro">Classification -- 'f1_micro'</option>
1405 <option value="f1_macro">Classification -- 'f1_macro'</option>
1406 <option value="f1_weighted">Classification -- 'f1_weighted'</option>
1407 <option value="f1_samples">Classification -- 'f1_samples'</option>
1408 <option value="neg_log_loss">Classification -- 'neg_log_loss'</option>
1409 <option value="precision">Classification -- 'precision'</option>
1410 <option value="precision_micro">Classification -- 'precision_micro'</option>
1411 <option value="precision_macro">Classification -- 'precision_macro'</option>
1412 <option value="precision_wighted">Classification -- 'precision_wighted'</option>
1413 <option value="precision_samples">Classification -- 'precision_samples'</option>
1414 <option value="recall">Classification -- 'recall'</option>
1415 <option value="recall_micro">Classification -- 'recall_micro'</option>
1416 <option value="recall_macro">Classification -- 'recall_macro'</option>
1417 <option value="recall_wighted">Classification -- 'recall_wighted'</option>
1418 <option value="recall_samples">Classification -- 'recall_samples'</option>
1419 <option value="roc_auc">Classification -- 'roc_auc'</option>
564 </param> 1420 </param>
565 <expand macro="random_state"/> 1421 </xml>
566 <expand macro="n_init"/> 1422
567 <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''."/> 1423 <xml name="secondary_scoring_selection_regression">
568 <param argument="affinity" type="select" label="Affinity" help="Affinity kernel to use. "> 1424 <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.">
569 <option value="rbf" selected="true">RBF</option> 1425 <option value="explained_variance">Regression -- 'explained_variance'</option>
570 <option value="precomputed">precomputed</option> 1426 <option value="neg_mean_absolute_error">Regression -- 'neg_mean_absolute_error'</option>
571 <option value="nearest_neighbors">Nearset neighbors</option> 1427 <option value="neg_mean_squared_error">Regression -- 'neg_mean_squared_error'</option>
1428 <option value="neg_mean_squared_log_error">Regression -- 'neg_mean_squared_log_error'</option>
1429 <option value="neg_median_absolute_error">Regression -- 'neg_median_absolute_error'</option>
1430 <option value="r2">Regression -- 'r2'</option>
1431 <option value="max_error">Regression -- 'max_error'</option>
572 </param> 1432 </param>
573 <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''"/> 1433 </xml>
574 <!--param argument="eigen_tol"--> 1434
575 <param argument="assign_labels" type="select" label="Assign labels" help="The strategy to use to assign labels in the embedding space."> 1435 <xml name="secondary_scoring_selection_anormaly">
576 <option value="kmeans" selected="true">kmeans</option> 1436 <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.">
577 <option value="discretize">discretize</option> 1437 <option value="binarize_auc_scorer">anomaly detection -- binarize_auc_scorer</option>
1438 <option value="binarize_average_precision_scorer">anomaly detection -- binarize_average_precision_scorer</option>
578 </param> 1439 </param>
579 <param argument="degree" type="integer" optional="true" value="3" 1440 </xml>
580 label="Degree of the polynomial (polynomial kernel only)" help="Ignored by other kernels. dafault : 3 "/> 1441
581 <param argument="coef0" type="integer" optional="true" value="1" 1442 <xml name="pre_dispatch" token_type="hidden" token_default_value="all" token_help="Number of predispatched jobs for parallel execution">
582 label="Zero coefficient (polynomial and sigmoid kernels only)" help="Ignored by other kernels. dafault : 1 "/> 1443 <param argument="pre_dispatch" type="@TYPE@" value="@DEFAULT_VALUE@" optional="true" label="pre_dispatch" help="@HELP@" />
583 <!--param argument="kernel_params"--> 1444 </xml>
584 </section> 1445
585 </xml> 1446 <xml name="estimator_and_hyperparameter">
586 1447 <param name="infile_estimator" type="data" format="zip" label="Choose the dataset containing pipeline/estimator object" />
587 <xml name="minibatch_kmeans_advanced_options"> 1448 <section name="hyperparams_swapping" title="Hyperparameter Swapping" expanded="false">
588 <section name="options" title="Advanced Options" expanded="False"> 1449 <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." />
589 <expand macro="n_clusters"/> 1450 <repeat name="param_set" min="1" max="30" title="New hyperparameter setting">
590 <expand macro="init"/> 1451 <param name="sp_name" type="select" optional="true" label="Choose a parameter name (with current value)">
591 <expand macro="n_init" default_value="3"/> 1452 <options from_dataset="infile_params" startswith="@">
592 <expand macro="max_iter" default_value="100"/> 1453 <column name="name" index="2" />
593 <expand macro="tol" help_text="Early stopping heuristics based on normalized center change. To disable set to 0.0 ."/> 1454 <column name="value" index="1" />
594 <expand macro="random_state"/> 1455 <filter type="unique_value" name="unique_param" column="1" />
595 <param argument="batch_size" type="integer" optional="true" value="100" label="Batch size" help="Size of the mini batches."/> 1456 </options>
596 <!--param argument="compute_labels"--> 1457 </param>
597 <param argument="max_no_improvement" type="integer" optional="true" value="10" label="Maximum number of improvement attempts" help=" 1458 <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.">
598 Convergence detection based on inertia (the consecutive number of mini batches that doe not yield an improvement on the smoothed inertia). 1459 <sanitizer>
599 To disable, set max_no_improvement to None. "/> 1460 <valid initial="default">
600 <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 )"/> 1461 <add value="&apos;" />
601 <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."/> 1462 <add value="&quot;" />
602 </section> 1463 </valid>
603 </xml> 1464 </sanitizer>
604 1465 </param>
605 <xml name="kmeans_advanced_options"> 1466 </repeat>
606 <section name="options" title="Advanced Options" expanded="False">
607 <expand macro="n_clusters"/>
608 <expand macro="init"/>
609 <expand macro="n_init"/>
610 <expand macro="max_iter"/>
611 <expand macro="tol" default_value="0.0001" help_text="Relative tolerance with regards to inertia to declare convergence."/>
612 <!--param argument="precompute_distances"/-->
613 <expand macro="random_state"/>
614 <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."/>
615 <expand macro="kmeans_algorithm"/>
616 </section>
617 </xml>
618
619 <xml name="kmeans_algorithm">
620 <param argument="algorithm" type="select" label="K-means algorithm to use:">
621 <option value="auto" selected="true">auto</option>
622 <option value="full">full</option>
623 <option value="elkan">elkan</option>
624 </param>
625 </xml>
626
627 <xml name="birch_advanced_options">
628 <section name="options" title="Advanced Options" expanded="False">
629 <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."/>
630 <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."/>
631 <expand macro="n_clusters" default_value="3"/>
632 <!--param argument="compute_labels"/-->
633 </section>
634 </xml>
635
636 <xml name="dbscan_advanced_options">
637 <section name="options" title="Advanced Options" expanded="False">
638 <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."/>
639 <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."/>
640 <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."/>
641 <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.">
642 <option value="auto" selected="true">auto</option>
643 <option value="ball_tree">ball_tree</option>
644 <option value="kd_tree">kd_tree</option>
645 <option value="brute">brute</option>
646 </param>
647 <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."/>
648 </section>
649 </xml>
650
651 <xml name="clustering_algorithms_options">
652 <conditional name="algorithm_options">
653 <param name="selected_algorithm" type="select" label="Clustering Algorithm">
654 <option value="KMeans" selected="true">KMeans</option>
655 <option value="SpectralClustering">Spectral Clustering</option>
656 <option value="MiniBatchKMeans">Mini Batch KMeans</option>
657 <option value="DBSCAN">DBSCAN</option>
658 <option value="Birch">Birch</option>
659 </param>
660 <when value="KMeans">
661 <expand macro="kmeans_advanced_options"/>
662 </when>
663 <when value="DBSCAN">
664 <expand macro="dbscan_advanced_options"/>
665 </when>
666 <when value="Birch">
667 <expand macro="birch_advanced_options"/>
668 </when>
669 <when value="SpectralClustering">
670 <expand macro="spectral_clustering_advanced_options"/>
671 </when>
672 <when value="MiniBatchKMeans">
673 <expand macro="minibatch_kmeans_advanced_options"/>
674 </when>
675 </conditional>
676 </xml>
677
678 <xml name="distance_metrics">
679 <param argument="metric" type="select" label="Distance metric" help=" ">
680 <option value="euclidean" selected="true">euclidean</option>
681 <option value="cityblock">cityblock</option>
682 <option value="cosine">cosine</option>
683 <option value="l1">l1</option>
684 <option value="l2">l2</option>
685 <option value="manhattan">manhattan</option>
686 <yield/>
687 </param>
688 </xml>
689
690 <xml name="distance_nonsparse_metrics">
691 <option value="braycurtis">braycurtis</option>
692 <option value="canberra">canberra</option>
693 <option value="chebyshev">chebyshev</option>
694 <option value="correlation">correlation</option>
695 <option value="dice">dice</option>
696 <option value="hamming">hamming</option>
697 <option value="jaccard">jaccard</option>
698 <option value="kulsinski">kulsinski</option>
699 <option value="mahalanobis">mahalanobis</option>
700 <option value="matching">matching</option>
701 <option value="minkowski">minkowski</option>
702 <option value="rogerstanimoto">rogerstanimoto</option>
703 <option value="russellrao">russellrao</option>
704 <option value="seuclidean">seuclidean</option>
705 <option value="sokalmichener">sokalmichener</option>
706 <option value="sokalsneath">sokalsneath</option>
707 <option value="sqeuclidean">sqeuclidean</option>
708 <option value="yule">yule</option>
709 </xml>
710
711 <xml name="pairwise_kernel_metrics">
712 <param argument="metric" type="select" label="Pirwise Kernel metric" help=" ">
713 <option value="rbf" selected="true">rbf</option>
714 <option value="sigmoid">sigmoid</option>
715 <option value="polynomial">polynomial</option>
716 <option value="linear" selected="true">linear</option>
717 <option value="chi2">chi2</option>
718 <option value="additive_chi2">additive_chi2</option>
719 </param>
720 </xml>
721
722 <xml name="sparse_pairwise_metric_functions">
723 <param name="selected_metric_function" type="select" label="Select the pairwise metric you want to compute:">
724 <option value="euclidean_distances" selected="true">Euclidean distance matrix</option>
725 <option value="pairwise_distances">Distance matrix</option>
726 <option value="pairwise_distances_argmin">Minimum distances between one point and a set of points</option>
727 <yield/>
728 </param>
729 </xml>
730
731 <xml name="pairwise_metric_functions">
732 <option value="additive_chi2_kernel" >Additive chi-squared kernel</option>
733 <option value="chi2_kernel">Exponential chi-squared kernel</option>
734 <option value="linear_kernel">Linear kernel</option>
735 <option value="manhattan_distances">L1 distances</option>
736 <option value="pairwise_kernels">Kernel</option>
737 <option value="polynomial_kernel">Polynomial kernel</option>
738 <option value="rbf_kernel">Gaussian (rbf) kernel</option>
739 <option value="laplacian_kernel">Laplacian kernel</option>
740 </xml>
741
742 <xml name="sparse_pairwise_condition">
743 <when value="pairwise_distances">
744 <section name="options" title="Advanced Options" expanded="False">
745 <expand macro="distance_metrics">
746 <yield/>
747 </expand>
748 </section>
749 </when>
750 <when value="euclidean_distances">
751 <section name="options" title="Advanced Options" expanded="False">
752 <param argument="squared" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolfalse" checked="false"
753 label="Return squared Euclidean distances" help=" "/>
754 </section>
755 </when>
756 </xml>
757
758 <xml name="argmin_distance_condition">
759 <when value="pairwise_distances_argmin">
760 <section name="options" title="Advanced Options" expanded="False">
761 <param argument="axis" type="integer" optional="true" value="1" label="Axis" help="Axis along which the argmin and distances are to be computed."/>
762 <expand macro="distance_metrics">
763 <yield/>
764 </expand>
765 <param argument="batch_size" type="integer" optional="true" value="500" label="Batch size" help="Number of rows to be processed in each batch run."/>
766 </section>
767 </when>
768 </xml>
769
770 <xml name="sparse_preprocessors">
771 <param name="selected_pre_processor" type="select" label="Select a preprocessor:">
772 <option value="StandardScaler" selected="true">Standard Scaler (Standardizes features by removing the mean and scaling to unit variance)</option>
773 <option value="Binarizer">Binarizer (Binarizes data)</option>
774 <option value="MaxAbsScaler">Max Abs Scaler (Scales features by their maximum absolute value)</option>
775 <option value="Normalizer">Normalizer (Normalizes samples individually to unit norm)</option>
776 <yield/>
777 </param>
778 </xml>
779
780 <xml name="sparse_preprocessors_ext">
781 <expand macro="sparse_preprocessors">
782 <option value="KernelCenterer">Kernel Centerer (Centers a kernel matrix)</option>
783 <option value="MinMaxScaler">Minmax Scaler (Scales features to a range)</option>
784 <option value="PolynomialFeatures">Polynomial Features (Generates polynomial and interaction features)</option>
785 <option value="RobustScaler">Robust Scaler (Scales features using outlier-invariance statistics)</option>
786 <option value="QuantileTransformer">QuantileTransformer (Transform features using quantiles information)</option>
787 <option value="PowerTransformer">PowerTransformer (Apply a power transform featurewise to make data more Gaussian-like)</option>
788 <option value="KBinsDiscretizer">KBinsDiscretizer (Bin continuous data into intervals.)</option>
789 </expand>
790 </xml>
791
792 <xml name="sparse_preprocessor_options">
793 <when value="Binarizer">
794 <section name="options" title="Advanced Options" expanded="False">
795 <param argument="copy" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolfalse" checked="true"
796 label="Use a copy of data for precomputing binarization" help=" "/>
797 <param argument="threshold" type="float" optional="true" value="0.0"
798 label="Threshold"
799 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. "/>
800 </section> 1467 </section>
801 </when> 1468 </xml>
802 <when value="StandardScaler"> 1469
803 <section name="options" title="Advanced Options" expanded="False"> 1470 <xml name="search_cv_options">
804 <param argument="copy" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolfalse" checked="true" 1471 <expand macro="scoring_selection" />
805 label="Use a copy of data for performing inplace scaling" help=" "/> 1472 <expand macro="model_validation_common_options" />
806 <param argument="with_mean" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolfalse" checked="true" 1473 <!--expand macro="pre_dispatch" default_value="2*n_jobs" help="Controls the number of jobs that get dispatched during parallel execution"/-->
807 label="Center the data before scaling" help=" "/> 1474 <param argument="iid" type="boolean" truevalue="booltrue" falsevalue="boolfalse" checked="true" label="iid" help="If True, data is identically distributed across the folds" />
808 <param argument="with_std" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolfalse" checked="true" 1475 <!--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!"/> -->
809 label="Scale the data to unit variance (or unit standard deviation)" help=" "/> 1476 <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." />
810 </section> 1477 <param argument="return_train_score" type="boolean" truevalue="booltrue" falsevalue="boolfalse" checked="false" label="return_train_score" help="" />
811 </when> 1478 </xml>
812 <when value="MaxAbsScaler"> 1479
813 <section name="options" title="Advanced Options" expanded="False"> 1480 <xml name="estimator_module_options">
814 <param argument="copy" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolfalse" checked="true" 1481 <option value="svm" selected="true">sklearn.svm</option>
815 label="Use a copy of data for precomputing scaling" help=" "/> 1482 <option value="linear_model">sklearn.linear_model</option>
816 </section> 1483 <option value="ensemble">sklearn.ensemble</option>
817 </when> 1484 <option value="naive_bayes">sklearn.naive_bayes</option>
818 <when value="Normalizer"> 1485 <option value="tree">sklearn.tree</option>
819 <section name="options" title="Advanced Options" expanded="False"> 1486 <option value="neighbors">sklearn.neighbors</option>
820 <param argument="norm" type="select" optional="true" label="The norm to use to normalize non zero samples" help=" "> 1487 <option value="xgboost">xgboost</option>
821 <option value="l1" selected="true">l1</option> 1488 <yield />
822 <option value="l2">l2</option> 1489 </xml>
823 <option value="max">max</option> 1490
1491 <xml name="estimator_suboptions">
1492 <when value="svm">
1493 <param name="selected_estimator" type="select" label="Choose estimator class:">
1494 <option value="LinearSVC" selected="true">LinearSVC</option>
1495 <option value="LinearSVR">LinearSVR</option>
1496 <option value="NuSVC">NuSVC</option>
1497 <option value="NuSVR">NuSVR</option>
1498 <option value="OneClassSVM">OneClassSVM</option>
1499 <option value="SVC">SVC</option>
1500 <option value="SVR">SVR</option>
1501 </param>
1502 <expand macro="estimator_params_text" />
1503 </when>
1504 <when value="linear_model">
1505 <param name="selected_estimator" type="select" label="Choose estimator class:">
1506 <option value="ARDRegression" selected="true">ARDRegression</option>
1507 <option value="BayesianRidge">BayesianRidge</option>
1508 <option value="ElasticNet">ElasticNet</option>
1509 <option value="ElasticNetCV">ElasticNetCV</option>
1510 <option value="HuberRegressor">HuberRegressor</option>
1511 <option value="Lars">Lars</option>
1512 <option value="LarsCV">LarsCV</option>
1513 <option value="Lasso">Lasso</option>
1514 <option value="LassoCV">LassoCV</option>
1515 <option value="LassoLars">LassoLars</option>
1516 <option value="LassoLarsCV">LassoLarsCV</option>
1517 <option value="LassoLarsIC">LassoLarsIC</option>
1518 <option value="LinearRegression">LinearRegression</option>
1519 <option value="LogisticRegression">LogisticRegression</option>
1520 <option value="LogisticRegressionCV">LogisticRegressionCV</option>
1521 <option value="MultiTaskLasso">MultiTaskLasso</option>
1522 <option value="MultiTaskElasticNet">MultiTaskElasticNet</option>
1523 <option value="MultiTaskLassoCV">MultiTaskLassoCV</option>
1524 <option value="MultiTaskElasticNetCV">MultiTaskElasticNetCV</option>
1525 <option value="OrthogonalMatchingPursuit">OrthogonalMatchingPursuit</option>
1526 <option value="OrthogonalMatchingPursuitCV">OrthogonalMatchingPursuitCV</option>
1527 <option value="PassiveAggressiveClassifier">PassiveAggressiveClassifier</option>
1528 <option value="PassiveAggressiveRegressor">PassiveAggressiveRegressor</option>
1529 <option value="Perceptron">Perceptron</option>
1530 <option value="RANSACRegressor">RANSACRegressor</option>
1531 <option value="Ridge">Ridge</option>
1532 <option value="RidgeClassifier">RidgeClassifier</option>
1533 <option value="RidgeClassifierCV">RidgeClassifierCV</option>
1534 <option value="RidgeCV">RidgeCV</option>
1535 <option value="SGDClassifier">SGDClassifier</option>
1536 <option value="SGDRegressor">SGDRegressor</option>
1537 <option value="TheilSenRegressor">TheilSenRegressor</option>
1538 </param>
1539 <expand macro="estimator_params_text" />
1540 </when>
1541 <when value="ensemble">
1542 <param name="selected_estimator" type="select" label="Choose estimator class:">
1543 <option value="AdaBoostClassifier" selected="true">AdaBoostClassifier</option>
1544 <option value="AdaBoostRegressor">AdaBoostRegressor</option>
1545 <option value="BaggingClassifier">BaggingClassifier</option>
1546 <option value="BaggingRegressor">BaggingRegressor</option>
1547 <option value="ExtraTreesClassifier">ExtraTreesClassifier</option>
1548 <option value="ExtraTreesRegressor">ExtraTreesRegressor</option>
1549 <option value="GradientBoostingClassifier">GradientBoostingClassifier</option>
1550 <option value="GradientBoostingRegressor">GradientBoostingRegressor</option>
1551 <option value="IsolationForest">IsolationForest</option>
1552 <option value="HistGradientBoostingClassifier">HistGradientBoostingClassifier</option>
1553 <option value="HistGradientBoostingRegressor">HistGradientBoostingRegressor</option>
1554 <option value="RandomForestClassifier">RandomForestClassifier</option>
1555 <option value="RandomForestRegressor">RandomForestRegressor</option>
1556 <option value="RandomTreesEmbedding">RandomTreesEmbedding</option>
1557 <!--option value="VotingClassifier">VotingClassifier</option-->
1558 </param>
1559 <expand macro="estimator_params_text" />
1560 </when>
1561 <when value="naive_bayes">
1562 <param name="selected_estimator" type="select" label="Choose estimator class:">
1563 <option value="BernoulliNB" selected="true">BernoulliNB</option>
1564 <option value="GaussianNB">GaussianNB</option>
1565 <option value="MultinomialNB">MultinomialNB</option>
1566 </param>
1567 <expand macro="estimator_params_text" />
1568 </when>
1569 <when value="tree">
1570 <param name="selected_estimator" type="select" label="Choose estimator class:">
1571 <option value="DecisionTreeClassifier" selected="true">DecisionTreeClassifier</option>
1572 <option value="DecisionTreeRegressor">DecisionTreeRegressor</option>
1573 <option value="ExtraTreeClassifier">ExtraTreeClassifier</option>
1574 <option value="ExtraTreeRegressor">ExtraTreeRegressor</option>
1575 </param>
1576 <expand macro="estimator_params_text" />
1577 </when>
1578 <when value="neighbors">
1579 <param name="selected_estimator" type="select" label="Choose estimator class:">
1580 <option value="KNeighborsClassifier" selected="true">KNeighborsClassifier</option>
1581 <option value="KNeighborsRegressor">KNeighborsRegressor</option>
1582 <!--option value="BallTree">BallTree</option-->
1583 <!--option value="KDTree">KDTree</option-->
1584 <option value="KernelDensity">KernelDensity</option>
1585 <option value="LocalOutlierFactor">LocalOutlierFactor</option>
1586 <option value="RadiusNeighborsClassifier">RadiusNeighborsClassifier</option>
1587 <option value="RadiusNeighborsRegressor">RadiusNeighborsRegressor</option>
1588 <option value="NearestCentroid">NearestCentroid</option>
1589 <option value="NearestNeighbors">NearestNeighbors</option>
1590 </param>
1591 <expand macro="estimator_params_text" />
1592 </when>
1593 <when value="xgboost">
1594 <param name="selected_estimator" type="select" label="Choose estimator class:">
1595 <option value="XGBRegressor" selected="true">XGBRegressor</option>
1596 <option value="XGBClassifier">XGBClassifier</option>
1597 </param>
1598 <expand macro="estimator_params_text" />
1599 </when>
1600 <yield />
1601 </xml>
1602
1603 <xml name="estimator_selector_all">
1604 <conditional name="estimator_selector">
1605 <param name="selected_module" type="select" label="Choose the module that contains target estimator:">
1606 <expand macro="estimator_module_options" />
1607 </param>
1608 <expand macro="estimator_suboptions" />
1609 </conditional>
1610 </xml>
1611
1612 <xml name="estimator_selector_fs">
1613 <conditional name="estimator_selector">
1614 <param name="selected_module" type="select" label="Choose the module that contains target estimator:">
1615 <expand macro="estimator_module_options">
1616 <option value="custom_estimator">Load a custom estimator</option>
1617 </expand>
1618 </param>
1619 <expand macro="estimator_suboptions">
1620 <when value="custom_estimator">
1621 <param name="c_estimator" type="data" format="zip" label="Choose the dataset containing the custom estimator or pipeline:" />
1622 </when>
1623 </expand>
1624 </conditional>
1625 </xml>
1626
1627 <xml name="estimator_params_text" token_label="Type in parameter settings if different from default:" token_default_value='' token_help="Dictionary-capable, e.g., C=1, kernel='linear'. No double quotes. Leave this box blank for default estimator.">
1628 <param name="text_params" type="text" value="@DEFAULT_VALUE@" optional="true" label="@LABEL@" help="@HELP@">
1629 <sanitizer>
1630 <valid initial="default">
1631 <add value="&apos;" />
1632 </valid>
1633 </sanitizer>
824 </param> 1634 </param>
825 <param argument="copy" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolfalse" checked="true" 1635 </xml>
826 label="Use a copy of data for precomputing row normalization" help=" "/> 1636
827 </section> 1637 <xml name="kernel_approximation_all">
828 </when> 1638 <conditional name="kernel_approximation_selector">
829 <yield/> 1639 <param name="select_algorithm" type="select" label="Choose a kernel approximation algorithm:">
830 </xml> 1640 <option value="Nystroem" selected="true">Nystroem</option>
831 1641 <option value="RBFSampler">RBFSampler</option>
832 <xml name="sparse_preprocessor_options_ext"> 1642 <option value="AdditiveChi2Sampler">AdditiveChi2Sampler</option>
833 <expand macro="sparse_preprocessor_options"> 1643 <option value="SkewedChi2Sampler">SkewedChi2Sampler</option>
834 <when value="KernelCenterer"> 1644 </param>
835 <section name="options" title="Advanced Options" expanded="False"> 1645 <when value="Nystroem">
1646 <expand macro="estimator_params_text" help="Default(=blank): coef0=None, degree=None, gamma=None, kernel='rbf', kernel_params=None, n_components=100, random_state=None. No double quotes" />
1647 </when>
1648 <when value="RBFSampler">
1649 <expand macro="estimator_params_text" help="Default(=blank): gamma=1.0, n_components=100, random_state=None." />
1650 </when>
1651 <when value="AdditiveChi2Sampler">
1652 <expand macro="estimator_params_text" help="Default(=blank): sample_interval=None, sample_steps=2." />
1653 </when>
1654 <when value="SkewedChi2Sampler">
1655 <expand macro="estimator_params_text" help="Default(=blank): n_components=100, random_state=None, skewedness=1.0." />
1656 </when>
1657 </conditional>
1658 </xml>
1659
1660 <xml name="matrix_decomposition_all">
1661 <conditional name="matrix_decomposition_selector">
1662 <param name="select_algorithm" type="select" label="Choose a matrix decomposition algorithm:">
1663 <option value="DictionaryLearning" selected="true">DictionaryLearning</option>
1664 <option value="FactorAnalysis">FactorAnalysis</option>
1665 <option value="FastICA">FastICA</option>
1666 <option value="IncrementalPCA">IncrementalPCA</option>
1667 <option value="KernelPCA">KernelPCA</option>
1668 <option value="LatentDirichletAllocation">LatentDirichletAllocation</option>
1669 <option value="MiniBatchDictionaryLearning">MiniBatchDictionaryLearning</option>
1670 <option value="MiniBatchSparsePCA">MiniBatchSparsePCA</option>
1671 <option value="NMF">NMF</option>
1672 <option value="PCA">PCA</option>
1673 <option value="SparsePCA">SparsePCA</option>
1674 <!--option value="SparseCoder">SparseCoder</option-->
1675 <option value="TruncatedSVD">TruncatedSVD</option>
1676 </param>
1677 <when value="DictionaryLearning">
1678 <expand macro="estimator_params_text" 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." />
1679 </when>
1680 <when value="FactorAnalysis">
1681 <expand macro="estimator_params_text" 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." />
1682 </when>
1683 <when value="FastICA">
1684 <expand macro="estimator_params_text" 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." />
1685 </when>
1686 <when value="IncrementalPCA">
1687 <expand macro="estimator_params_text" help="Default(=blank): batch_size=None, copy=True, n_components=None, whiten=False." />
1688 </when>
1689 <when value="KernelPCA">
1690 <expand macro="estimator_params_text" 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." />
1691 </when>
1692 <when value="LatentDirichletAllocation">
1693 <expand macro="estimator_params_text" 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." />
1694 </when>
1695 <when value="MiniBatchDictionaryLearning">
1696 <expand macro="estimator_params_text" 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." />
1697 </when>
1698 <when value="MiniBatchSparsePCA">
1699 <expand macro="estimator_params_text" 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." />
1700 </when>
1701 <when value="NMF">
1702 <expand macro="estimator_params_text" 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." />
1703 </when>
1704 <when value="PCA">
1705 <expand macro="estimator_params_text" help="Default(=blank): copy=True, iterated_power='auto', n_components=None, random_state=None, svd_solver='auto', tol=0.0, whiten=False." />
1706 </when>
1707 <when value="SparsePCA">
1708 <expand macro="estimator_params_text" 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." />
1709 </when>
1710 <when value="TruncatedSVD">
1711 <expand macro="estimator_params_text" help="Default(=blank): algorithm='randomized', n_components=2, n_iter=5, random_state=None, tol=0.0." />
1712 </when>
1713 </conditional>
1714 </xml>
1715
1716 <xml name="FeatureAgglomeration">
1717 <conditional name="FeatureAgglomeration_selector">
1718 <param name="select_algorithm" type="select" label="Choose the algorithm:">
1719 <option value="FeatureAgglomeration" selected="true">FeatureAgglomeration</option>
1720 </param>
1721 <when value="FeatureAgglomeration">
1722 <expand macro="estimator_params_text" help="Default(=blank): affinity='euclidean', compute_full_tree='auto', connectivity=None, linkage='ward', memory=None, n_clusters=2, pooling_func=np.mean." />
1723 </when>
1724 </conditional>
1725 </xml>
1726
1727 <xml name="skrebate">
1728 <conditional name="skrebate_selector">
1729 <param name="select_algorithm" type="select" label="Choose the algorithm:">
1730 <option value="ReliefF">ReliefF</option>
1731 <option value="SURF">SURF</option>
1732 <option value="SURFstar">SURFstar</option>
1733 <option value="MultiSURF">MultiSURF</option>
1734 <option value="MultiSURFstar">MultiSURFstar</option>
1735 <!--option value="TuRF">TuRF</option> -->
1736 </param>
1737 <when value="ReliefF">
1738 <expand macro="estimator_params_text" help="Default(=blank): discrete_threshold=10, n_features_to_select=10, n_neighbors=100, verbose=False." />
1739 </when>
1740 <when value="SURF">
1741 <expand macro="estimator_params_text" help="Default(=blank): discrete_threshold=10, n_features_to_select=10, verbose=False." />
1742 </when>
1743 <when value="SURFstar">
1744 <expand macro="estimator_params_text" help="Default(=blank): discrete_threshold=10, n_features_to_select=10, verbose=False." />
1745 </when>
1746 <when value="MultiSURF">
1747 <expand macro="estimator_params_text" help="Default(=blank): discrete_threshold=10, n_features_to_select=10, verbose=False." />
1748 </when>
1749 <when value="MultiSURFstar">
1750 <expand macro="estimator_params_text" help="Default(=blank): discrete_threshold=10, n_features_to_select=10, verbose=False." />
1751 </when>
1752 <!--when value="TuRF">
1753 <expand macro="estimator_params_text" help="Default(=blank): core_algorithm='ReliefF', discrete_threshold=10, n_features_to_select=10, n_neighbors=100, pct=0.5, verbose=False."/>
1754 </when> -->
1755 </conditional>
1756 </xml>
1757
1758 <xml name="imbalanced_learn_sampling">
1759 <conditional name="imblearn_selector">
1760 <param name="select_algorithm" type="select" label="Choose the algorithm:">
1761 <option value="under_sampling.ClusterCentroids" selected="true">under_sampling.ClusterCentroids</option>
1762 <option value="under_sampling.CondensedNearestNeighbour">under_sampling.CondensedNearestNeighbour</option>
1763 <option value="under_sampling.EditedNearestNeighbours">under_sampling.EditedNearestNeighbours</option>
1764 <option value="under_sampling.RepeatedEditedNearestNeighbours">under_sampling.RepeatedEditedNearestNeighbours</option>
1765 <option value="under_sampling.AllKNN">under_sampling.AllKNN</option>
1766 <option value="under_sampling.InstanceHardnessThreshold">under_sampling.InstanceHardnessThreshold</option>
1767 <option value="under_sampling.NearMiss">under_sampling.NearMiss</option>
1768 <option value="under_sampling.NeighbourhoodCleaningRule">under_sampling.NeighbourhoodCleaningRule</option>
1769 <option value="under_sampling.OneSidedSelection">under_sampling.OneSidedSelection</option>
1770 <option value="under_sampling.RandomUnderSampler">under_sampling.RandomUnderSampler</option>
1771 <option value="under_sampling.TomekLinks">under_sampling.TomekLinks</option>
1772 <option value="over_sampling.ADASYN">over_sampling.ADASYN</option>
1773 <option value="over_sampling.RandomOverSampler">over_sampling.RandomOverSampler</option>
1774 <option value="over_sampling.SMOTE">over_sampling.SMOTE</option>
1775 <option value="over_sampling.SVMSMOTE">over_sampling.SVMSMOTE</option>
1776 <option value="over_sampling.BorderlineSMOTE">over_sampling.BorderlineSMOTE</option>
1777 <option value="over_sampling.SMOTENC">over_sampling.SMOTENC</option>
1778 <option value="combine.SMOTEENN">combine.SMOTEENN</option>
1779 <option value="combine.SMOTETomek">combine.SMOTETomek</option>
1780 <option value="Z_RandomOverSampler">Z_RandomOverSampler - for regression</option>
1781 </param>
1782 <when value="under_sampling.ClusterCentroids">
1783 <expand macro="estimator_params_text" help="Default(=blank): sampling_strategy='auto', random_state=None, estimator=None, voting='auto'." />
1784 </when>
1785 <when value="under_sampling.CondensedNearestNeighbour">
1786 <expand macro="estimator_params_text" help="Default(=blank): sampling_strategy='auto', random_state=None, n_neighbors=None, n_seeds_S=1." />
1787 </when>
1788 <when value="under_sampling.EditedNearestNeighbours">
1789 <expand macro="estimator_params_text" help="Default(=blank): sampling_strategy='auto', random_state=None, n_neighbors=3, max_iter=100, kind_sel='all'." />
1790 </when>
1791 <when value="under_sampling.RepeatedEditedNearestNeighbours">
1792 <expand macro="estimator_params_text" help="Default(=blank): sampling_strategy='auto', random_state=None, n_neighbors=3, max_iter=100, kind_sel='all'." />
1793 </when>
1794 <when value="under_sampling.AllKNN">
1795 <expand macro="estimator_params_text" help="Default(=blank): sampling_strategy='auto', random_state=None, n_neighbors=3, kind_sel='all', allow_minority=False." />
1796 </when>
1797 <when value="under_sampling.InstanceHardnessThreshold">
1798 <expand macro="estimator_params_text" help="Default(=blank): estimator=None, sampling_strategy='auto', random_state=None, cv=5." />
1799 </when>
1800 <when value="under_sampling.NearMiss">
1801 <expand macro="estimator_params_text" help="Default(=blank): sampling_strategy='auto', random_state=None, version=1, n_neighbors=3, n_neighbors_ver3=3." />
1802 </when>
1803 <when value="under_sampling.NeighbourhoodCleaningRule">
1804 <expand macro="estimator_params_text" help="Default(=blank): sampling_strategy='auto', random_state=None, n_neighbors=3, kind_sel='all', threshold_cleaning=0.5." />
1805 </when>
1806 <when value="under_sampling.OneSidedSelection">
1807 <expand macro="estimator_params_text" help="Default(=blank): sampling_strategy='auto', random_state=None, n_neighbors=None, n_seeds_S=1." />
1808 </when>
1809 <when value="under_sampling.RandomUnderSampler">
1810 <expand macro="estimator_params_text" help="Default(=blank): sampling_strategy='auto', random_state=None, replacement=False." />
1811 </when>
1812 <when value="under_sampling.TomekLinks">
1813 <expand macro="estimator_params_text" help="Default(=blank): sampling_strategy='auto', random_state=None." />
1814 </when>
1815 <when value="over_sampling.ADASYN">
1816 <expand macro="estimator_params_text" help="Default(=blank): sampling_strategy='auto', random_state=None, n_neighbors=5." />
1817 </when>
1818 <when value="over_sampling.RandomOverSampler">
1819 <expand macro="estimator_params_text" help="Default(=blank): sampling_strategy='auto', random_state=None." />
1820 </when>
1821 <when value="over_sampling.SMOTE">
1822 <expand macro="estimator_params_text" help="Default(=blank): sampling_strategy='auto', random_state=None, k_neighbors=5." />
1823 </when>
1824 <when value="over_sampling.SVMSMOTE">
1825 <expand macro="estimator_params_text" help="Default(=blank): sampling_strategy='auto', k_neighbors=5, m_neighbors=10, out_step=0.5, random_state=None, svm_estimator=None." />
1826 </when>
1827 <when value="over_sampling.BorderlineSMOTE">
1828 <expand macro="estimator_params_text" help="Default(=blank): sampling_strategy='auto', k_neighbors=5, kind='borderline-1', m_neighbors=10, random_state=None." />
1829 </when>
1830 <when value="over_sampling.SMOTENC">
1831 <expand macro="estimator_params_text" help="Default: categorical_features=[], sampling_strategy='auto', random_state=None, k_neighbors=5." />
1832 </when>
1833 <when value="combine.SMOTEENN">
1834 <expand macro="estimator_params_text" help="Default(=blank): sampling_strategy='auto', random_state=None, smote=None, enn=None." />
1835 </when>
1836 <when value="combine.SMOTETomek">
1837 <expand macro="estimator_params_text" help="Default(=blank): sampling_strategy='auto', random_state=None, smote=None, tomek=None." />
1838 </when>
1839 <when value="Z_RandomOverSampler">
1840 <expand macro="estimator_params_text" help="Default(=blank): sampling_strategy='auto', random_state=None, negative_thres=0, positive_thres=-1." />
1841 </when>
1842 </conditional>
1843 </xml>
1844
1845 <xml name="stacking_ensemble_inputs">
1846 <section name="options" title="Advanced Options" expanded="false">
1847 <yield />
1848 <param argument="use_features_in_secondary" type="boolean" truevalue="booltrue" falsevalue="boolfalse" checked="false" />
1849 <param argument="store_train_meta_features" type="boolean" truevalue="booltrue" falsevalue="boolfalse" checked="false" />
836 </section> 1850 </section>
837 </when> 1851 </xml>
838 <when value="MinMaxScaler"> 1852
839 <section name="options" title="Advanced Options" expanded="False"> 1853 <xml name="stacking_base_estimator">
840 <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)"/> 1854 <conditional name="estimator_selector">
841 <param argument="copy" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolflase" checked="true" 1855 <param name="selected_module" type="select" label="Choose the module that contains target estimator:">
842 label="Use a copy of data for precomputing normalization" help=" "/> 1856 <expand macro="estimator_module_options">
843 </section> 1857 <option value="custom_estimator">Load a custom estimator</option>
844 </when> 1858 </expand>
845 <when value="PolynomialFeatures"> 1859 </param>
846 <section name="options" title="Advanced Options" expanded="False"> 1860 <expand macro="estimator_suboptions">
847 <param argument="degree" type="integer" optional="true" value="2" label="The degree of the polynomial features " help=""/> 1861 <when value="custom_estimator">
848 <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) "/> 1862 <param name="c_estimator" type="data" format="zip" label="Choose the dataset containing the custom estimator or pipeline" />
849 <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 "/> 1863 </when>
850 </section>
851 </when>
852 <when value="RobustScaler">
853 <section name="options" title="Advanced Options" expanded="False">
854 <!--=True, =True, copy=True-->
855 <param argument="with_centering" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolflase" checked="true"
856 label="Center the data before scaling" help=" "/>
857 <param argument="with_scaling" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolflase" checked="true"
858 label="Scale the data to interquartile range" help=" "/>
859 <param argument="copy" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolflase" checked="true"
860 label="Use a copy of data for inplace scaling" help=" "/>
861 </section>
862 </when>
863 <when value="QuantileTransformer">
864 <section name="options" title="Advanced Options" expanded="False">
865 <param name="n_quantiles" type="integer" value="1000" min="0" label="Number of quantiles to be computed" />
866 <param name="output_distribution" type="select" label="Marginal distribution for the transformed data">
867 <option value="uniform" selected="true">uniform</option>
868 <option value="normal">normal</option>
869 </param>
870 <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"/>
871 <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."/>
872 <expand macro="random_state" help_text="This is used by subsampling and smoothing noise"/>
873 </section>
874 </when>
875 <when value="PowerTransformer">
876 <section name="options" title="Advanced Options" expanded="False">
877 <param name="method" type="select" label="The power transform method">
878 <option value="yeo-johnson" selected="true">yeo-johnson (works with positive and negative values)</option>
879 <option value="box-cox">box-cox (might perform better, but only works with strictly positive values)</option>
880 </param>
881 <param name="standardize" type="boolean" truevalue="booltrue" falsevalue="boolfalse" checked="true" label="Whether to apply zero-mean, unit-variance normalization to the transformed output."/>
882 </section>
883 </when>
884 <when value="KBinsDiscretizer">
885 <section name="options" title="Advanced Options" expanded="False">
886 <param name="n_bins" type="integer" value="5" min="2" label="The number of bins to produce"/>
887 <param name="encode" type="select" label="Method used to encode the transformed result">
888 <option value="onehot" selected="true">onehot (encode the transformed result with one-hot encoding and return a sparse matrix)</option>
889 <option value="onehot-dense">onehot-dense (encode the transformed result with one-hot encoding and return a dense array)</option>
890 <option value="ordinal">ordinal (return the bin identifier encoded as an integer value)</option>
891 </param>
892 <param name="strategy" type="select" label="Strategy used to define the widths of the bins">
893 <option value="uniform">uniform (all bins in each feature have identical widths)</option>
894 <option value="quantile" selected="true">quantile (all bins in each feature have the same number of points)</option>
895 <option value="kmeans">kmeans (values in each bin have the same nearest center of a 1D k-means cluster)</option>
896 </param>
897 </section>
898 </when>
899 </expand>
900 </xml>
901
902 <xml name="cv_splitter">
903 <option value="default" selected="true">default splitter</option>
904 <option value="KFold">KFold</option>
905 <option value="StratifiedKFold">StratifiedKFold</option>
906 <option value="LeaveOneOut">LeaveOneOut</option>
907 <option value="LeavePOut">LeavePOut</option>
908 <option value="RepeatedKFold">RepeatedKFold</option>
909 <option value="RepeatedStratifiedKFold">RepeatedStratifiedKFold</option>
910 <option value="ShuffleSplit">ShuffleSplit</option>
911 <option value="StratifiedShuffleSplit">StratifiedShuffleSplit</option>
912 <option value="TimeSeriesSplit">TimeSeriesSplit</option>
913 <option value="PredefinedSplit">PredefinedSplit</option>
914 <option value="OrderedKFold">OrderedKFold</option>
915 <option value="RepeatedOrderedKFold">RepeatedOrderedKFold</option>
916 <yield/>
917 </xml>
918
919 <xml name="cv_splitter_options">
920 <when value="default">
921 <expand macro="cv_n_splits"/>
922 </when>
923 <when value="KFold">
924 <expand macro="cv_n_splits"/>
925 <expand macro="cv_shuffle"/>
926 <expand macro="random_state"/>
927 </when>
928 <when value="StratifiedKFold">
929 <expand macro="cv_n_splits"/>
930 <expand macro="cv_shuffle"/>
931 <expand macro="random_state"/>
932 </when>
933 <when value="LeaveOneOut">
934 </when>
935 <when value="LeavePOut">
936 <param argument="p" type="integer" value="" label="p" help="Integer. Size of the test sets."/>
937 </when>
938 <when value="RepeatedKFold">
939 <expand macro="cv_n_splits" value="5"/>
940 <param argument="n_repeats" type="integer" value="10" label="n_repeats" help="Number of times cross-validator needs to be repeated." />
941 <expand macro="random_state" />
942 </when>
943 <when value="RepeatedStratifiedKFold">
944 <expand macro="cv_n_splits" value="5"/>
945 <param argument="n_repeats" type="integer" value="10" label="n_repeats" help="Number of times cross-validator needs to be repeated." />
946 <expand macro="random_state" />
947 </when>
948 <when value="ShuffleSplit">
949 <expand macro="cv_n_splits" value="10" help="Number of re-shuffling and splitting iterations."/>
950 <expand macro="cv_test_size" value="0.1" />
951 <expand macro="random_state"/>
952 </when>
953 <when value="StratifiedShuffleSplit">
954 <expand macro="cv_n_splits" value="10" help="Number of re-shuffling and splitting iterations."/>
955 <expand macro="cv_test_size" value="0.1" />
956 <expand macro="random_state"/>
957 </when>
958 <when value="TimeSeriesSplit">
959 <expand macro="cv_n_splits"/>
960 <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." />
961 </when>
962 <when value="PredefinedSplit">
963 <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'."/>
964 </when>
965 <when value="OrderedKFold">
966 <expand macro="cv_n_splits"/>
967 <expand macro="cv_shuffle"/>
968 <expand macro="random_state"/>
969 </when>
970 <when value="RepeatedOrderedKFold">
971 <expand macro="cv_n_splits"/>
972 <param argument="n_repeats" type="integer" value="5"/>
973 <expand macro="random_state"/>
974 </when>
975 <yield/>
976 </xml>
977
978 <xml name="cv">
979 <conditional name="cv_selector">
980 <param name="selected_cv" type="select" label="Select the cv splitter:">
981 <expand macro="cv_splitter">
982 <option value="GroupKFold">GroupKFold</option>
983 <option value="GroupShuffleSplit">GroupShuffleSplit</option>
984 <option value="LeaveOneGroupOut">LeaveOneGroupOut</option>
985 <option value="LeavePGroupsOut">LeavePGroupsOut</option>
986 </expand>
987 </param>
988 <expand macro="cv_splitter_options">
989 <when value="GroupKFold">
990 <expand macro="cv_n_splits"/>
991 <expand macro="cv_groups" />
992 </when>
993 <when value="GroupShuffleSplit">
994 <expand macro="cv_n_splits" value="5"/>
995 <expand macro="cv_test_size"/>
996 <expand macro="random_state"/>
997 <expand macro="cv_groups"/>
998 </when>
999 <when value="LeaveOneGroupOut">
1000 <expand macro="cv_groups"/>
1001 </when>
1002 <when value="LeavePGroupsOut">
1003 <param argument="n_groups" type="integer" value="" label="n_groups" help="Number of groups (p) to leave out in the test split." />
1004 <expand macro="cv_groups"/>
1005 </when>
1006 </expand>
1007 </conditional>
1008 </xml>
1009
1010 <xml name="cv_reduced" token_label="Select the cv splitter">
1011 <conditional name="cv_selector">
1012 <param name="selected_cv" type="select" label="@LABEL@">
1013 <expand macro="cv_splitter"/>
1014 </param>
1015 <expand macro="cv_splitter_options"/>
1016 </conditional>
1017 </xml>
1018
1019 <xml name="cv_n_splits" token_value="3" token_help="Number of folds. Must be at least 2.">
1020 <param argument="n_splits" type="integer" value="@VALUE@" min="1" label="n_splits" help="@HELP@"/>
1021 </xml>
1022
1023 <xml name="cv_shuffle">
1024 <param argument="shuffle" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolfalse" checked="false" label="Whether to shuffle data before splitting" />
1025 </xml>
1026
1027 <xml name="cv_test_size" token_value="0.2">
1028 <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 "/>
1029 </xml>
1030
1031 <xml name="cv_groups" >
1032 <section name="groups_selector" title="Groups column selector" expanded="true">
1033 <param name="infile_g" type="data" format="tabular" label="Choose dataset containing groups info:"/>
1034 <param name="header_g" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolfalse" checked="False" label="Does the dataset contain header:" />
1035 <conditional name="column_selector_options_g">
1036 <expand macro="samples_column_selector_options" column_option="selected_column_selector_option_g" col_name="col_g" multiple="False" infile="infile_g"/>
1037 </conditional>
1038 </section>
1039 </xml>
1040
1041 <xml name="train_test_split_params">
1042 <conditional name="split_algos">
1043 <param name="shuffle" type="select" label="Select the splitting method">
1044 <option value="None">No shuffle</option>
1045 <option value="simple" selected="true">ShuffleSplit</option>
1046 <option value="stratified">StratifiedShuffleSplit -- target values serve as class labels</option>
1047 <option value="group">GroupShuffleSplit or split by group names</option>
1048 </param>
1049 <when value="None">
1050 <expand macro="train_test_split_test_size"/>
1051 </when>
1052 <when value="simple">
1053 <expand macro="train_test_split_test_size"/>
1054 <expand macro="random_state"/>
1055 </when>
1056 <when value="stratified">
1057 <expand macro="train_test_split_test_size"/>
1058 <expand macro="random_state"/>
1059 </when>
1060 <when value="group">
1061 <expand macro="train_test_split_test_size" optional="true"/>
1062 <expand macro="random_state"/>
1063 <param argument="group_names" type="text" value="" optional="true" label="Type in group names instead"
1064 help="For example: chr6, chr7. This parameter is optional. If used, it will override the holdout size and random seed."/>
1065 <yield/>
1066 </when>
1067 </conditional>
1068 <!--param argument="train_size" type="float" optional="True" value="" label="Train size:"/>-->
1069 </xml>
1070
1071 <xml name="train_test_split_test_size" token_optional="false">
1072 <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."/>
1073 </xml>
1074
1075 <xml name="feature_selection_algorithms">
1076 <option value="SelectKBest" selected="true">SelectKBest - Select features according to the k highest scores</option>
1077 <option value="GenericUnivariateSelect">GenericUnivariateSelect - Univariate feature selector with configurable strategy</option>
1078 <option value="SelectPercentile">SelectPercentile - Select features according to a percentile of the highest scores</option>
1079 <option value="SelectFpr">SelectFpr - Filter: Select the p-values below alpha based on a FPR test</option>
1080 <option value="SelectFdr">SelectFdr - Filter: Select the p-values for an estimated false discovery rate</option>
1081 <option value="SelectFwe">SelectFwe - Filter: Select the p-values corresponding to Family-wise error rate</option>
1082 <option value="VarianceThreshold">VarianceThreshold - Feature selector that removes all low-variance features</option>
1083 <option value="SelectFromModel">SelectFromModel - Meta-transformer for selecting features based on importance weights</option>
1084 <option value="RFE">RFE - Feature ranking with recursive feature elimination</option>
1085 <option value="RFECV">RFECV - Feature ranking with recursive feature elimination and cross-validated selection of the best number of features</option>
1086 <yield/>
1087 </xml>
1088
1089 <xml name="feature_selection_algorithm_details">
1090 <when value="GenericUnivariateSelect">
1091 <expand macro="feature_selection_score_function" />
1092 <section name="options" title="Advanced Options" expanded="False">
1093 <param argument="mode" type="select" label="Feature selection mode">
1094 <option value="percentile">percentile</option>
1095 <option value="k_best">k_best</option>
1096 <option value="fpr">fpr</option>
1097 <option value="fdr">fdr</option>
1098 <option value="fwe">fwe</option>
1099 </param>
1100 <param argument="param" type="float" value="" optional="true" label="Parameter of the corresponding mode" help="float or int depending on the feature selection mode" />
1101 </section>
1102 </when>
1103 <when value="SelectPercentile">
1104 <expand macro="feature_selection_score_function" />
1105 <section name="options" title="Advanced Options" expanded="False">
1106 <param argument="percentile" type="integer" value="10" optional="True" label="Percent of features to keep" />
1107 </section>
1108 </when>
1109 <when value="SelectKBest">
1110 <expand macro="feature_selection_score_function" />
1111 <section name="options" title="Advanced Options" expanded="False">
1112 <param argument="k" type="integer" value="10" optional="True" label="Number of top features to select" help="No 'all' option is supported." />
1113 </section>
1114 </when>
1115 <when value="SelectFpr">
1116 <expand macro="feature_selection_score_function" />
1117 <section name="options" title="Advanced Options" expanded="False">
1118 <param argument="alpha" type="float" value="" optional="True" label="Alpha" help="The highest p-value for features to be kept."/>
1119 </section>
1120 </when>
1121 <when value="SelectFdr">
1122 <expand macro="feature_selection_score_function" />
1123 <section name="options" title="Advanced Options" expanded="False">
1124 <param argument="alpha" type="float" value="" optional="True" label="Alpha" help="The highest uncorrected p-value for features to keep."/>
1125 </section>
1126 </when>
1127 <when value="SelectFwe">
1128 <expand macro="feature_selection_score_function" />
1129 <section name="options" title="Advanced Options" expanded="False">
1130 <param argument="alpha" type="float" value="" optional="True" label="Alpha" help="The highest uncorrected p-value for features to keep."/>
1131 </section>
1132 </when>
1133 <when value="VarianceThreshold">
1134 <section name="options" title="Options" expanded="False">
1135 <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."/>
1136 </section>
1137 </when>
1138 </xml>
1139
1140 <xml name="feature_selection_SelectFromModel">
1141 <when value="SelectFromModel">
1142 <conditional name="model_inputter">
1143 <param name="input_mode" type="select" label="Construct a new estimator from a selection list?" >
1144 <option value="new" selected="true">Yes</option>
1145 <option value="prefitted">No. Load a prefitted estimator</option>
1146 </param>
1147 <when value="new">
1148 <expand macro="estimator_selector_fs"/>
1149 </when>
1150 <when value="prefitted">
1151 <param name="fitted_estimator" type="data" format='zip' label="Load a prefitted estimator" />
1152 </when>
1153 </conditional>
1154 <expand macro="feature_selection_SelectFromModel_options"/>
1155 </when>
1156 </xml>
1157
1158 <xml name="feature_selection_SelectFromModel_no_prefitted">
1159 <when value="SelectFromModel">
1160 <conditional name="model_inputter">
1161 <param name="input_mode" type="select" label="Construct a new estimator from a selection list?" >
1162 <option value="new" selected="true">Yes</option>
1163 </param>
1164 <when value="new">
1165 <expand macro="estimator_selector_all"/>
1166 </when>
1167 </conditional>
1168 <expand macro="feature_selection_SelectFromModel_options"/>
1169 </when>
1170 </xml>
1171
1172 <xml name="feature_selection_SelectFromModel_options">
1173 <section name="options" title="Advanced Options" expanded="False">
1174 <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'." />
1175 <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. " />
1176 <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."/>
1177 </section>
1178 </xml>
1179
1180 <xml name="feature_selection_RFE">
1181 <when value="RFE">
1182 <yield/>
1183 <section name="options" title="Advanced Options" expanded="False">
1184 <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." />
1185 <param argument="step" type="float" value="1" label="step" optional="true" help="Default = 1. " />
1186 <param argument="verbose" type="integer" value="0" label="verbose" help="Controls verbosity of output." />
1187 </section>
1188 </when>
1189 </xml>
1190
1191 <xml name="feature_selection_RFECV_fs">
1192 <when value="RFECV">
1193 <yield/>
1194 <section name="options" title="Advanced Options" expanded="False">
1195 <param argument="step" type="float" value="1" label="step" optional="true" help="Default = 1. " />
1196 <param argument="min_features_to_select" type="integer" value="1" optional="true" label="The minimum number of features to be selected"/>
1197 <expand macro="cv"/>
1198 <expand macro="scoring_selection"/>
1199 <param argument="verbose" type="integer" value="0" label="verbose" help="Controls verbosity of output." />
1200 </section>
1201 </when>
1202 </xml>
1203
1204 <xml name="feature_selection_RFECV_pipeline">
1205 <when value="RFECV">
1206 <yield/>
1207 <section name="options" title="Advanced Options" expanded="False">
1208 <param argument="step" type="float" value="1" label="step" optional="true" help="Default = 1. " />
1209 <param argument="min_features_to_select" type="integer" value="1" optional="true" label="The minimum number of features to be selected"/>
1210 <expand macro="cv_reduced"/>
1211 <!-- TODO: group splitter support-->
1212 <expand macro="scoring_selection"/>
1213 <param argument="verbose" type="integer" value="0" label="verbose" help="Controls verbosity of output." />
1214 </section>
1215 </when>
1216 </xml>
1217
1218 <xml name="feature_selection_DyRFECV_fs">
1219 <when value="DyRFECV">
1220 <yield/>
1221 <section name="options" title="Advanced Options" expanded="False">
1222 <param argument="step" type="text" size="30" value="1" label="step" optional="true" help="Default = 1. Support float, int and list." >
1223 <sanitizer>
1224 <valid initial="default">
1225 <add value="["/>
1226 <add value="]"/>
1227 </valid>
1228 </sanitizer>
1229 </param>
1230 <param argument="min_features_to_select" type="integer" value="1" optional="true" label="The minimum number of features to be selected"/>
1231 <expand macro="cv"/>
1232 <expand macro="scoring_selection"/>
1233 <param argument="verbose" type="integer" value="0" label="verbose" help="Controls verbosity of output." />
1234 </section>
1235 </when>
1236 </xml>
1237
1238 <xml name="feature_selection_pipeline">
1239 <!--compare to `feature_selection_fs`, no fitted estimator for SelectFromModel and no custom estimator for RFE and RFECV-->
1240 <conditional name="fs_algorithm_selector">
1241 <param name="selected_algorithm" type="select" label="Select a feature selection algorithm">
1242 <expand macro="feature_selection_algorithms"/>
1243 </param>
1244 <expand macro="feature_selection_algorithm_details"/>
1245 <expand macro="feature_selection_SelectFromModel_no_prefitted"/>
1246 <expand macro="feature_selection_RFE">
1247 <expand macro="estimator_selector_all"/>
1248 </expand>
1249 <expand macro="feature_selection_RFECV_pipeline">
1250 <expand macro="estimator_selector_all"/>
1251 </expand>
1252 <!-- TODO: add DyRFECV to pipeline-->
1253 </conditional>
1254 </xml>
1255
1256 <xml name="feature_selection_fs">
1257 <conditional name="fs_algorithm_selector">
1258 <param name="selected_algorithm" type="select" label="Select a feature selection algorithm">
1259 <expand macro="feature_selection_algorithms">
1260 <option value="DyRFECV">DyRFECV - Extended RFECV with changeable steps</option>
1261 </expand>
1262 </param>
1263 <expand macro="feature_selection_algorithm_details"/>
1264 <expand macro="feature_selection_SelectFromModel"/>
1265 <expand macro="feature_selection_RFE">
1266 <expand macro="estimator_selector_fs"/>
1267 </expand>
1268 <expand macro="feature_selection_RFECV_fs">
1269 <expand macro="estimator_selector_fs"/>
1270 </expand>
1271 <expand macro="feature_selection_DyRFECV_fs">
1272 <expand macro="estimator_selector_fs"/>
1273 </expand>
1274 </conditional>
1275 </xml>
1276
1277 <xml name="feature_selection_score_function">
1278 <param argument="score_func" type="select" label="Select a score function">
1279 <option value="chi2">chi2 - Compute chi-squared stats between each non-negative feature and class</option>
1280 <option value="f_classif">f_classif - Compute the ANOVA F-value for the provided sample</option>
1281 <option value="f_regression">f_regression - Univariate linear regression tests</option>
1282 <option value="mutual_info_classif">mutual_info_classif - Estimate mutual information for a discrete target variable</option>
1283 <option value="mutual_info_regression">mutual_info_regression - Estimate mutual information for a continuous target variable</option>
1284 </param>
1285 </xml>
1286
1287 <xml name="model_validation_common_options">
1288 <expand macro="cv"/>
1289 <expand macro="verbose"/>
1290 <yield/>
1291 </xml>
1292
1293 <xml name="scoring_selection">
1294 <conditional name="scoring">
1295 <param name="primary_scoring" type="select" multiple="false" label="Select the primary metric (scoring):" help="Metric to refit the best estimator.">
1296 <option value="default" selected="true">default with estimator</option>
1297 <option value="accuracy">Classification -- 'accuracy'</option>
1298 <option value="balanced_accuracy">Classification -- 'balanced_accuracy'</option>
1299 <option value="average_precision">Classification -- 'average_precision'</option>
1300 <option value="f1">Classification -- 'f1'</option>
1301 <option value="f1_micro">Classification -- 'f1_micro'</option>
1302 <option value="f1_macro">Classification -- 'f1_macro'</option>
1303 <option value="f1_weighted">Classification -- 'f1_weighted'</option>
1304 <option value="f1_samples">Classification -- 'f1_samples'</option>
1305 <option value="neg_log_loss">Classification -- 'neg_log_loss'</option>
1306 <option value="precision">Classification -- 'precision'</option>
1307 <option value="precision_micro">Classification -- 'precision_micro'</option>
1308 <option value="precision_macro">Classification -- 'precision_macro'</option>
1309 <option value="precision_wighted">Classification -- 'precision_wighted'</option>
1310 <option value="precision_samples">Classification -- 'precision_samples'</option>
1311 <option value="recall">Classification -- 'recall'</option>
1312 <option value="recall_micro">Classification -- 'recall_micro'</option>
1313 <option value="recall_macro">Classification -- 'recall_macro'</option>
1314 <option value="recall_wighted">Classification -- 'recall_wighted'</option>
1315 <option value="recall_samples">Classification -- 'recall_samples'</option>
1316 <option value="roc_auc">Classification -- 'roc_auc'</option>
1317 <option value="explained_variance">Regression -- 'explained_variance'</option>
1318 <option value="neg_mean_absolute_error">Regression -- 'neg_mean_absolute_error'</option>
1319 <option value="neg_mean_squared_error">Regression -- 'neg_mean_squared_error'</option>
1320 <option value="neg_mean_squared_log_error">Regression -- 'neg_mean_squared_log_error'</option>
1321 <option value="neg_median_absolute_error">Regression -- 'neg_median_absolute_error'</option>
1322 <option value="r2">Regression -- 'r2'</option>
1323 <option value="max_error">Regression -- 'max_error'</option>
1324 <option value="binarize_auc_scorer">anomaly detection -- binarize_auc_scorer</option>
1325 <option value="binarize_average_precision_scorer">anomaly detection -- binarize_average_precision_scorer</option>
1326 </param>
1327 <when value="default"/>
1328 <when value="accuracy"><expand macro="secondary_scoring_selection_classification"/></when>
1329 <when value="balanced_accuracy"><expand macro="secondary_scoring_selection_classification"/></when>
1330 <when value="average_precision"><expand macro="secondary_scoring_selection_classification"/></when>
1331 <when value="f1"><expand macro="secondary_scoring_selection_classification"/></when>
1332 <when value="f1_micro"><expand macro="secondary_scoring_selection_classification"/></when>
1333 <when value="f1_macro"><expand macro="secondary_scoring_selection_classification"/></when>
1334 <when value="f1_weighted"><expand macro="secondary_scoring_selection_classification"/></when>
1335 <when value="f1_samples"><expand macro="secondary_scoring_selection_classification"/></when>
1336 <when value="neg_log_loss"><expand macro="secondary_scoring_selection_classification"/></when>
1337 <when value="precision"><expand macro="secondary_scoring_selection_classification"/></when>
1338 <when value="precision_micro"><expand macro="secondary_scoring_selection_classification"/></when>
1339 <when value="precision_macro"><expand macro="secondary_scoring_selection_classification"/></when>
1340 <when value="precision_wighted"><expand macro="secondary_scoring_selection_classification"/></when>
1341 <when value="precision_samples"><expand macro="secondary_scoring_selection_classification"/></when>
1342 <when value="recall"><expand macro="secondary_scoring_selection_classification"/></when>
1343 <when value="recall_micro"><expand macro="secondary_scoring_selection_classification"/></when>
1344 <when value="recall_macro"><expand macro="secondary_scoring_selection_classification"/></when>
1345 <when value="recall_wighted"><expand macro="secondary_scoring_selection_classification"/></when>
1346 <when value="recall_samples"><expand macro="secondary_scoring_selection_classification"/></when>
1347 <when value="roc_auc"><expand macro="secondary_scoring_selection_classification"/></when>
1348 <when value="explained_variance"><expand macro="secondary_scoring_selection_regression"/></when>
1349 <when value="neg_mean_absolute_error"><expand macro="secondary_scoring_selection_regression"/></when>
1350 <when value="neg_mean_squared_error"><expand macro="secondary_scoring_selection_regression"/></when>
1351 <when value="neg_mean_squared_log_error"><expand macro="secondary_scoring_selection_regression"/></when>
1352 <when value="neg_median_absolute_error"><expand macro="secondary_scoring_selection_regression"/></when>
1353 <when value="r2"><expand macro="secondary_scoring_selection_regression"/></when>
1354 <when value="max_error"><expand macro="secondary_scoring_selection_regression"/></when>
1355 <when value="binarize_auc_scorer"><expand macro="secondary_scoring_selection_anormaly"/></when>
1356 <when value="binarize_average_precision_scorer"><expand macro="secondary_scoring_selection_anormaly"/></when>
1357 </conditional>
1358 </xml>
1359
1360 <xml name="secondary_scoring_selection_classification">
1361 <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.">
1362 <option value="accuracy">Classification -- 'accuracy'</option>
1363 <option value="balanced_accuracy">Classification -- 'balanced_accuracy'</option>
1364 <option value="average_precision">Classification -- 'average_precision'</option>
1365 <option value="f1">Classification -- 'f1'</option>
1366 <option value="f1_micro">Classification -- 'f1_micro'</option>
1367 <option value="f1_macro">Classification -- 'f1_macro'</option>
1368 <option value="f1_weighted">Classification -- 'f1_weighted'</option>
1369 <option value="f1_samples">Classification -- 'f1_samples'</option>
1370 <option value="neg_log_loss">Classification -- 'neg_log_loss'</option>
1371 <option value="precision">Classification -- 'precision'</option>
1372 <option value="precision_micro">Classification -- 'precision_micro'</option>
1373 <option value="precision_macro">Classification -- 'precision_macro'</option>
1374 <option value="precision_wighted">Classification -- 'precision_wighted'</option>
1375 <option value="precision_samples">Classification -- 'precision_samples'</option>
1376 <option value="recall">Classification -- 'recall'</option>
1377 <option value="recall_micro">Classification -- 'recall_micro'</option>
1378 <option value="recall_macro">Classification -- 'recall_macro'</option>
1379 <option value="recall_wighted">Classification -- 'recall_wighted'</option>
1380 <option value="recall_samples">Classification -- 'recall_samples'</option>
1381 <option value="roc_auc">Classification -- 'roc_auc'</option>
1382 </param>
1383 </xml>
1384
1385 <xml name="secondary_scoring_selection_regression">
1386 <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.">
1387 <option value="explained_variance">Regression -- 'explained_variance'</option>
1388 <option value="neg_mean_absolute_error">Regression -- 'neg_mean_absolute_error'</option>
1389 <option value="neg_mean_squared_error">Regression -- 'neg_mean_squared_error'</option>
1390 <option value="neg_mean_squared_log_error">Regression -- 'neg_mean_squared_log_error'</option>
1391 <option value="neg_median_absolute_error">Regression -- 'neg_median_absolute_error'</option>
1392 <option value="r2">Regression -- 'r2'</option>
1393 <option value="max_error">Regression -- 'max_error'</option>
1394 </param>
1395 </xml>
1396
1397 <xml name="secondary_scoring_selection_anormaly">
1398 <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.">
1399 <option value="binarize_auc_scorer">anomaly detection -- binarize_auc_scorer</option>
1400 <option value="binarize_average_precision_scorer">anomaly detection -- binarize_average_precision_scorer</option>
1401 </param>
1402 </xml>
1403
1404 <xml name="pre_dispatch" token_type="hidden" token_default_value="all" token_help="Number of predispatched jobs for parallel execution">
1405 <param argument="pre_dispatch" type="@TYPE@" value="@DEFAULT_VALUE@" optional="true" label="pre_dispatch" help="@HELP@"/>
1406 </xml>
1407
1408 <xml name="estimator_and_hyperparameter">
1409 <param name="infile_estimator" type="data" format="zip" label="Choose the dataset containing pipeline/estimator object"/>
1410 <section name="hyperparams_swapping" title="Hyperparameter Swapping" expanded="false">
1411 <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."/>
1412 <repeat name="param_set" min="1" max="30" title="New hyperparameter setting">
1413 <param name="sp_name" type="select" optional="true" label="Choose a parameter name (with current value)">
1414 <options from_dataset="infile_params" startswith="@">
1415 <column name="name" index="2"/>
1416 <column name="value" index="1"/>
1417 <filter type="unique_value" name="unique_param" column="1"/>
1418 </options>
1419 </param>
1420 <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.">
1421 <sanitizer>
1422 <valid initial="default">
1423 <add value="&apos;"/>
1424 <add value="&quot;"/>
1425 </valid>
1426 </sanitizer>
1427 </param>
1428 </repeat>
1429 </section>
1430 </xml>
1431
1432 <xml name="search_cv_options">
1433 <expand macro="scoring_selection"/>
1434 <expand macro="model_validation_common_options"/>
1435 <!--expand macro="pre_dispatch" default_value="2*n_jobs" help="Controls the number of jobs that get dispatched during parallel execution"/-->
1436 <param argument="iid" type="boolean" truevalue="booltrue" falsevalue="boolfalse" checked="true" label="iid" help="If True, data is identically distributed across the folds"/>
1437 <!--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!"/> -->
1438 <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."/>
1439 <param argument="return_train_score" type="boolean" truevalue="booltrue" falsevalue="boolfalse" checked="false" label="return_train_score" help=""/>
1440 </xml>
1441
1442 <xml name="estimator_module_options">
1443 <option value="svm" selected="true">sklearn.svm</option>
1444 <option value="linear_model">sklearn.linear_model</option>
1445 <option value="ensemble">sklearn.ensemble</option>
1446 <option value="naive_bayes">sklearn.naive_bayes</option>
1447 <option value="tree">sklearn.tree</option>
1448 <option value="neighbors">sklearn.neighbors</option>
1449 <option value="xgboost">xgboost</option>
1450 <yield/>
1451 </xml>
1452
1453 <xml name="estimator_suboptions">
1454 <when value="svm">
1455 <param name="selected_estimator" type="select" label="Choose estimator class:">
1456 <option value="LinearSVC" selected="true">LinearSVC</option>
1457 <option value="LinearSVR">LinearSVR</option>
1458 <option value="NuSVC">NuSVC</option>
1459 <option value="NuSVR">NuSVR</option>
1460 <option value="OneClassSVM">OneClassSVM</option>
1461 <option value="SVC">SVC</option>
1462 <option value="SVR">SVR</option>
1463 </param>
1464 <expand macro="estimator_params_text"/>
1465 </when>
1466 <when value="linear_model">
1467 <param name="selected_estimator" type="select" label="Choose estimator class:">
1468 <option value="ARDRegression" selected="true">ARDRegression</option>
1469 <option value="BayesianRidge">BayesianRidge</option>
1470 <option value="ElasticNet">ElasticNet</option>
1471 <option value="ElasticNetCV">ElasticNetCV</option>
1472 <option value="HuberRegressor">HuberRegressor</option>
1473 <option value="Lars">Lars</option>
1474 <option value="LarsCV">LarsCV</option>
1475 <option value="Lasso">Lasso</option>
1476 <option value="LassoCV">LassoCV</option>
1477 <option value="LassoLars">LassoLars</option>
1478 <option value="LassoLarsCV">LassoLarsCV</option>
1479 <option value="LassoLarsIC">LassoLarsIC</option>
1480 <option value="LinearRegression">LinearRegression</option>
1481 <option value="LogisticRegression">LogisticRegression</option>
1482 <option value="LogisticRegressionCV">LogisticRegressionCV</option>
1483 <option value="MultiTaskLasso">MultiTaskLasso</option>
1484 <option value="MultiTaskElasticNet">MultiTaskElasticNet</option>
1485 <option value="MultiTaskLassoCV">MultiTaskLassoCV</option>
1486 <option value="MultiTaskElasticNetCV">MultiTaskElasticNetCV</option>
1487 <option value="OrthogonalMatchingPursuit">OrthogonalMatchingPursuit</option>
1488 <option value="OrthogonalMatchingPursuitCV">OrthogonalMatchingPursuitCV</option>
1489 <option value="PassiveAggressiveClassifier">PassiveAggressiveClassifier</option>
1490 <option value="PassiveAggressiveRegressor">PassiveAggressiveRegressor</option>
1491 <option value="Perceptron">Perceptron</option>
1492 <option value="RANSACRegressor">RANSACRegressor</option>
1493 <option value="Ridge">Ridge</option>
1494 <option value="RidgeClassifier">RidgeClassifier</option>
1495 <option value="RidgeClassifierCV">RidgeClassifierCV</option>
1496 <option value="RidgeCV">RidgeCV</option>
1497 <option value="SGDClassifier">SGDClassifier</option>
1498 <option value="SGDRegressor">SGDRegressor</option>
1499 <option value="TheilSenRegressor">TheilSenRegressor</option>
1500 </param>
1501 <expand macro="estimator_params_text"/>
1502 </when>
1503 <when value="ensemble">
1504 <param name="selected_estimator" type="select" label="Choose estimator class:">
1505 <option value="AdaBoostClassifier" selected="true">AdaBoostClassifier</option>
1506 <option value="AdaBoostRegressor">AdaBoostRegressor</option>
1507 <option value="BaggingClassifier">BaggingClassifier</option>
1508 <option value="BaggingRegressor">BaggingRegressor</option>
1509 <option value="ExtraTreesClassifier">ExtraTreesClassifier</option>
1510 <option value="ExtraTreesRegressor">ExtraTreesRegressor</option>
1511 <option value="GradientBoostingClassifier">GradientBoostingClassifier</option>
1512 <option value="GradientBoostingRegressor">GradientBoostingRegressor</option>
1513 <option value="IsolationForest">IsolationForest</option>
1514 <option value="HistGradientBoostingClassifier">HistGradientBoostingClassifier</option>
1515 <option value="HistGradientBoostingRegressor">HistGradientBoostingRegressor</option>
1516 <option value="RandomForestClassifier">RandomForestClassifier</option>
1517 <option value="RandomForestRegressor">RandomForestRegressor</option>
1518 <option value="RandomTreesEmbedding">RandomTreesEmbedding</option>
1519 <!--option value="VotingClassifier">VotingClassifier</option-->
1520 </param>
1521 <expand macro="estimator_params_text"/>
1522 </when>
1523 <when value="naive_bayes">
1524 <param name="selected_estimator" type="select" label="Choose estimator class:">
1525 <option value="BernoulliNB" selected="true">BernoulliNB</option>
1526 <option value="GaussianNB">GaussianNB</option>
1527 <option value="MultinomialNB">MultinomialNB</option>
1528 </param>
1529 <expand macro="estimator_params_text"/>
1530 </when>
1531 <when value="tree">
1532 <param name="selected_estimator" type="select" label="Choose estimator class:">
1533 <option value="DecisionTreeClassifier" selected="true">DecisionTreeClassifier</option>
1534 <option value="DecisionTreeRegressor">DecisionTreeRegressor</option>
1535 <option value="ExtraTreeClassifier">ExtraTreeClassifier</option>
1536 <option value="ExtraTreeRegressor">ExtraTreeRegressor</option>
1537 </param>
1538 <expand macro="estimator_params_text"/>
1539 </when>
1540 <when value="neighbors">
1541 <param name="selected_estimator" type="select" label="Choose estimator class:">
1542 <option value="KNeighborsClassifier" selected="true">KNeighborsClassifier</option>
1543 <option value="KNeighborsRegressor">KNeighborsRegressor</option>
1544 <!--option value="BallTree">BallTree</option-->
1545 <!--option value="KDTree">KDTree</option-->
1546 <option value="KernelDensity">KernelDensity</option>
1547 <option value="LocalOutlierFactor">LocalOutlierFactor</option>
1548 <option value="RadiusNeighborsClassifier">RadiusNeighborsClassifier</option>
1549 <option value="RadiusNeighborsRegressor">RadiusNeighborsRegressor</option>
1550 <option value="NearestCentroid">NearestCentroid</option>
1551 <option value="NearestNeighbors">NearestNeighbors</option>
1552 </param>
1553 <expand macro="estimator_params_text"/>
1554 </when>
1555 <when value="xgboost">
1556 <param name="selected_estimator" type="select" label="Choose estimator class:">
1557 <option value="XGBRegressor" selected="true">XGBRegressor</option>
1558 <option value="XGBClassifier">XGBClassifier</option>
1559 </param>
1560 <expand macro="estimator_params_text"/>
1561 </when>
1562 <yield/>
1563 </xml>
1564
1565 <xml name="estimator_selector_all">
1566 <conditional name="estimator_selector">
1567 <param name="selected_module" type="select" label="Choose the module that contains target estimator:" >
1568 <expand macro="estimator_module_options"/>
1569 </param>
1570 <expand macro="estimator_suboptions"/>
1571 </conditional>
1572 </xml>
1573
1574 <xml name="estimator_selector_fs">
1575 <conditional name="estimator_selector">
1576 <param name="selected_module" type="select" label="Choose the module that contains target estimator:" >
1577 <expand macro="estimator_module_options">
1578 <option value="custom_estimator">Load a custom estimator</option>
1579 </expand>
1580 </param>
1581 <expand macro="estimator_suboptions">
1582 <when value="custom_estimator">
1583 <param name="c_estimator" type="data" format="zip" label="Choose the dataset containing the custom estimator or pipeline:"/>
1584 </when>
1585 </expand>
1586 </conditional>
1587 </xml>
1588
1589 <xml name="estimator_params_text" token_label="Type in parameter settings if different from default:" token_default_value=''
1590 token_help="Dictionary-capable, e.g., C=1, kernel='linear'. No double quotes. Leave this box blank for default estimator.">
1591 <param name="text_params" type="text" value="@DEFAULT_VALUE@" optional="true" label="@LABEL@" help="@HELP@">
1592 <sanitizer>
1593 <valid initial="default">
1594 <add value="&apos;"/>
1595 </valid>
1596 </sanitizer>
1597 </param>
1598 </xml>
1599
1600 <xml name="kernel_approximation_all">
1601 <conditional name="kernel_approximation_selector">
1602 <param name="select_algorithm" type="select" label="Choose a kernel approximation algorithm:">
1603 <option value="Nystroem" selected="true">Nystroem</option>
1604 <option value="RBFSampler">RBFSampler</option>
1605 <option value="AdditiveChi2Sampler">AdditiveChi2Sampler</option>
1606 <option value="SkewedChi2Sampler">SkewedChi2Sampler</option>
1607 </param>
1608 <when value="Nystroem">
1609 <expand macro="estimator_params_text"
1610 help="Default(=blank): coef0=None, degree=None, gamma=None, kernel='rbf', kernel_params=None, n_components=100, random_state=None. No double quotes"/>
1611 </when>
1612 <when value="RBFSampler">
1613 <expand macro="estimator_params_text"
1614 help="Default(=blank): gamma=1.0, n_components=100, random_state=None."/>
1615 </when>
1616 <when value="AdditiveChi2Sampler">
1617 <expand macro="estimator_params_text"
1618 help="Default(=blank): sample_interval=None, sample_steps=2."/>
1619 </when>
1620 <when value="SkewedChi2Sampler">
1621 <expand macro="estimator_params_text"
1622 help="Default(=blank): n_components=100, random_state=None, skewedness=1.0."/>
1623 </when>
1624 </conditional>
1625 </xml>
1626
1627 <xml name="matrix_decomposition_all">
1628 <conditional name="matrix_decomposition_selector">
1629 <param name="select_algorithm" type="select" label="Choose a matrix decomposition algorithm:">
1630 <option value="DictionaryLearning" selected="true">DictionaryLearning</option>
1631 <option value="FactorAnalysis">FactorAnalysis</option>
1632 <option value="FastICA">FastICA</option>
1633 <option value="IncrementalPCA">IncrementalPCA</option>
1634 <option value="KernelPCA">KernelPCA</option>
1635 <option value="LatentDirichletAllocation">LatentDirichletAllocation</option>
1636 <option value="MiniBatchDictionaryLearning">MiniBatchDictionaryLearning</option>
1637 <option value="MiniBatchSparsePCA">MiniBatchSparsePCA</option>
1638 <option value="NMF">NMF</option>
1639 <option value="PCA">PCA</option>
1640 <option value="SparsePCA">SparsePCA</option>
1641 <!--option value="SparseCoder">SparseCoder</option-->
1642 <option value="TruncatedSVD">TruncatedSVD</option>
1643 </param>
1644 <when value="DictionaryLearning">
1645 <expand macro="estimator_params_text"
1646 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."/>
1647 </when>
1648 <when value="FactorAnalysis">
1649 <expand macro="estimator_params_text"
1650 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."/>
1651 </when>
1652 <when value="FastICA">
1653 <expand macro="estimator_params_text"
1654 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."/>
1655 </when>
1656 <when value="IncrementalPCA">
1657 <expand macro="estimator_params_text"
1658 help="Default(=blank): batch_size=None, copy=True, n_components=None, whiten=False."/>
1659 </when>
1660 <when value="KernelPCA">
1661 <expand macro="estimator_params_text"
1662 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."/>
1663 </when>
1664 <when value="LatentDirichletAllocation">
1665 <expand macro="estimator_params_text"
1666 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."/>
1667 </when>
1668 <when value="MiniBatchDictionaryLearning">
1669 <expand macro="estimator_params_text"
1670 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."/>
1671 </when>
1672 <when value="MiniBatchSparsePCA">
1673 <expand macro="estimator_params_text"
1674 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."/>
1675 </when>
1676 <when value="NMF">
1677 <expand macro="estimator_params_text"
1678 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."/>
1679 </when>
1680 <when value="PCA">
1681 <expand macro="estimator_params_text"
1682 help="Default(=blank): copy=True, iterated_power='auto', n_components=None, random_state=None, svd_solver='auto', tol=0.0, whiten=False."/>
1683 </when>
1684 <when value="SparsePCA">
1685 <expand macro="estimator_params_text"
1686 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."/>
1687 </when>
1688 <when value="TruncatedSVD">
1689 <expand macro="estimator_params_text"
1690 help="Default(=blank): algorithm='randomized', n_components=2, n_iter=5, random_state=None, tol=0.0."/>
1691 </when>
1692 </conditional>
1693 </xml>
1694
1695 <xml name="FeatureAgglomeration">
1696 <conditional name="FeatureAgglomeration_selector">
1697 <param name="select_algorithm" type="select" label="Choose the algorithm:">
1698 <option value="FeatureAgglomeration" selected="true">FeatureAgglomeration</option>
1699 </param>
1700 <when value="FeatureAgglomeration">
1701 <expand macro="estimator_params_text"
1702 help="Default(=blank): affinity='euclidean', compute_full_tree='auto', connectivity=None, linkage='ward', memory=None, n_clusters=2, pooling_func=np.mean."/>
1703 </when>
1704 </conditional>
1705 </xml>
1706
1707 <xml name="skrebate">
1708 <conditional name="skrebate_selector">
1709 <param name="select_algorithm" type="select" label="Choose the algorithm:">
1710 <option value="ReliefF">ReliefF</option>
1711 <option value="SURF">SURF</option>
1712 <option value="SURFstar">SURFstar</option>
1713 <option value="MultiSURF">MultiSURF</option>
1714 <option value="MultiSURFstar">MultiSURFstar</option>
1715 <!--option value="TuRF">TuRF</option> -->
1716 </param>
1717 <when value="ReliefF">
1718 <expand macro="estimator_params_text"
1719 help="Default(=blank): discrete_threshold=10, n_features_to_select=10, n_neighbors=100, verbose=False."/>
1720 </when>
1721 <when value="SURF">
1722 <expand macro="estimator_params_text"
1723 help="Default(=blank): discrete_threshold=10, n_features_to_select=10, verbose=False."/>
1724 </when>
1725 <when value="SURFstar">
1726 <expand macro="estimator_params_text"
1727 help="Default(=blank): discrete_threshold=10, n_features_to_select=10, verbose=False."/>
1728 </when>
1729 <when value="MultiSURF">
1730 <expand macro="estimator_params_text"
1731 help="Default(=blank): discrete_threshold=10, n_features_to_select=10, verbose=False."/>
1732 </when>
1733 <when value="MultiSURFstar">
1734 <expand macro="estimator_params_text"
1735 help="Default(=blank): discrete_threshold=10, n_features_to_select=10, verbose=False."/>
1736 </when>
1737 <!--when value="TuRF">
1738 <expand macro="estimator_params_text"
1739 help="Default(=blank): core_algorithm='ReliefF', discrete_threshold=10, n_features_to_select=10, n_neighbors=100, pct=0.5, verbose=False."/>
1740 </when> -->
1741 </conditional>
1742 </xml>
1743
1744 <xml name="imbalanced_learn_sampling">
1745 <conditional name="imblearn_selector">
1746 <param name="select_algorithm" type="select" label="Choose the algorithm:">
1747 <option value="under_sampling.ClusterCentroids" selected="true">under_sampling.ClusterCentroids</option>
1748 <option value="under_sampling.CondensedNearestNeighbour">under_sampling.CondensedNearestNeighbour</option>
1749 <option value="under_sampling.EditedNearestNeighbours">under_sampling.EditedNearestNeighbours</option>
1750 <option value="under_sampling.RepeatedEditedNearestNeighbours">under_sampling.RepeatedEditedNearestNeighbours</option>
1751 <option value="under_sampling.AllKNN">under_sampling.AllKNN</option>
1752 <option value="under_sampling.InstanceHardnessThreshold">under_sampling.InstanceHardnessThreshold</option>
1753 <option value="under_sampling.NearMiss">under_sampling.NearMiss</option>
1754 <option value="under_sampling.NeighbourhoodCleaningRule">under_sampling.NeighbourhoodCleaningRule</option>
1755 <option value="under_sampling.OneSidedSelection">under_sampling.OneSidedSelection</option>
1756 <option value="under_sampling.RandomUnderSampler">under_sampling.RandomUnderSampler</option>
1757 <option value="under_sampling.TomekLinks">under_sampling.TomekLinks</option>
1758 <option value="over_sampling.ADASYN">over_sampling.ADASYN</option>
1759 <option value="over_sampling.RandomOverSampler">over_sampling.RandomOverSampler</option>
1760 <option value="over_sampling.SMOTE">over_sampling.SMOTE</option>
1761 <option value="over_sampling.SVMSMOTE">over_sampling.SVMSMOTE</option>
1762 <option value="over_sampling.BorderlineSMOTE">over_sampling.BorderlineSMOTE</option>
1763 <option value="over_sampling.SMOTENC">over_sampling.SMOTENC</option>
1764 <option value="combine.SMOTEENN">combine.SMOTEENN</option>
1765 <option value="combine.SMOTETomek">combine.SMOTETomek</option>
1766 <option value="Z_RandomOverSampler">Z_RandomOverSampler - for regression</option>
1767 </param>
1768 <when value="under_sampling.ClusterCentroids">
1769 <expand macro="estimator_params_text"
1770 help="Default(=blank): sampling_strategy='auto', random_state=None, estimator=None, voting='auto'."/>
1771 </when>
1772 <when value="under_sampling.CondensedNearestNeighbour">
1773 <expand macro="estimator_params_text"
1774 help="Default(=blank): sampling_strategy='auto', random_state=None, n_neighbors=None, n_seeds_S=1."/>
1775 </when>
1776 <when value="under_sampling.EditedNearestNeighbours">
1777 <expand macro="estimator_params_text"
1778 help="Default(=blank): sampling_strategy='auto', random_state=None, n_neighbors=3, max_iter=100, kind_sel='all'."/>
1779 </when>
1780 <when value="under_sampling.RepeatedEditedNearestNeighbours">
1781 <expand macro="estimator_params_text"
1782 help="Default(=blank): sampling_strategy='auto', random_state=None, n_neighbors=3, max_iter=100, kind_sel='all'."/>
1783 </when>
1784 <when value="under_sampling.AllKNN">
1785 <expand macro="estimator_params_text"
1786 help="Default(=blank): sampling_strategy='auto', random_state=None, n_neighbors=3, kind_sel='all', allow_minority=False."/>
1787 </when>
1788 <when value="under_sampling.InstanceHardnessThreshold">
1789 <expand macro="estimator_params_text"
1790 help="Default(=blank): estimator=None, sampling_strategy='auto', random_state=None, cv=5."/>
1791 </when>
1792 <when value="under_sampling.NearMiss">
1793 <expand macro="estimator_params_text"
1794 help="Default(=blank): sampling_strategy='auto', random_state=None, version=1, n_neighbors=3, n_neighbors_ver3=3."/>
1795 </when>
1796 <when value="under_sampling.NeighbourhoodCleaningRule">
1797 <expand macro="estimator_params_text"
1798 help="Default(=blank): sampling_strategy='auto', random_state=None, n_neighbors=3, kind_sel='all', threshold_cleaning=0.5."/>
1799 </when>
1800 <when value="under_sampling.OneSidedSelection">
1801 <expand macro="estimator_params_text"
1802 help="Default(=blank): sampling_strategy='auto', random_state=None, n_neighbors=None, n_seeds_S=1."/>
1803 </when>
1804 <when value="under_sampling.RandomUnderSampler">
1805 <expand macro="estimator_params_text"
1806 help="Default(=blank): sampling_strategy='auto', random_state=None, replacement=False."/>
1807 </when>
1808 <when value="under_sampling.TomekLinks">
1809 <expand macro="estimator_params_text"
1810 help="Default(=blank): sampling_strategy='auto', random_state=None."/>
1811 </when>
1812 <when value="over_sampling.ADASYN">
1813 <expand macro="estimator_params_text"
1814 help="Default(=blank): sampling_strategy='auto', random_state=None, n_neighbors=5."/>
1815 </when>
1816 <when value="over_sampling.RandomOverSampler">
1817 <expand macro="estimator_params_text"
1818 help="Default(=blank): sampling_strategy='auto', random_state=None."/>
1819 </when>
1820 <when value="over_sampling.SMOTE">
1821 <expand macro="estimator_params_text"
1822 help="Default(=blank): sampling_strategy='auto', random_state=None, k_neighbors=5."/>
1823 </when>
1824 <when value="over_sampling.SVMSMOTE">
1825 <expand macro="estimator_params_text"
1826 help="Default(=blank): sampling_strategy='auto', k_neighbors=5, m_neighbors=10, out_step=0.5, random_state=None, svm_estimator=None."/>
1827 </when>
1828 <when value="over_sampling.BorderlineSMOTE">
1829 <expand macro="estimator_params_text"
1830 help="Default(=blank): sampling_strategy='auto', k_neighbors=5, kind='borderline-1', m_neighbors=10, random_state=None."/>
1831 </when>
1832 <when value="over_sampling.SMOTENC">
1833 <expand macro="estimator_params_text"
1834 help="Default: categorical_features=[], sampling_strategy='auto', random_state=None, k_neighbors=5."/>
1835 </when>
1836 <when value="combine.SMOTEENN">
1837 <expand macro="estimator_params_text"
1838 help="Default(=blank): sampling_strategy='auto', random_state=None, smote=None, enn=None."/>
1839 </when>
1840 <when value="combine.SMOTETomek">
1841 <expand macro="estimator_params_text"
1842 help="Default(=blank): sampling_strategy='auto', random_state=None, smote=None, tomek=None."/>
1843 </when>
1844 <when value="Z_RandomOverSampler">
1845 <expand macro="estimator_params_text"
1846 help="Default(=blank): sampling_strategy='auto', random_state=None, negative_thres=0, positive_thres=-1."/>
1847 </when>
1848 </conditional>
1849 </xml>
1850
1851 <xml name="stacking_ensemble_inputs">
1852 <section name="options" title="Advanced Options" expanded="false">
1853 <yield/>
1854 <param argument="use_features_in_secondary" type="boolean" truevalue="booltrue" falsevalue="boolfalse" checked="false"/>
1855 <param argument="store_train_meta_features" type="boolean" truevalue="booltrue" falsevalue="boolfalse" checked="false"/>
1856 </section>
1857 </xml>
1858
1859 <xml name="stacking_base_estimator">
1860 <conditional name="estimator_selector">
1861 <param name="selected_module" type="select" label="Choose the module that contains target estimator:" >
1862 <expand macro="estimator_module_options">
1863 <option value="custom_estimator">Load a custom estimator</option>
1864 </expand> 1864 </expand>
1865 </param> 1865 </conditional>
1866 <expand macro="estimator_suboptions"> 1866 </xml>
1867 <when value="custom_estimator"> 1867
1868 <param name="c_estimator" type="data" format="zip" label="Choose the dataset containing the custom estimator or pipeline"/> 1868 <xml name="stacking_voting_weights">
1869 </when> 1869 <section name="options" title="Advanced Options" expanded="false">
1870 </expand> 1870 <param argument="weights" type="text" value="[]" optional="true" help="Sequence of weights (float or int). Uses uniform weights if None (`[]`).">
1871 </conditional> 1871 <sanitizer>
1872 </xml> 1872 <valid initial="default">
1873 1873 <add value="[" />
1874 <xml name="stacking_voting_weights"> 1874 <add value="]" />
1875 <section name="options" title="Advanced Options" expanded="false"> 1875 </valid>
1876 <param argument="weights" type="text" value="[]" optional="true" help="Sequence of weights (float or int). Uses uniform weights if None (`[]`)."> 1876 </sanitizer>
1877 <sanitizer> 1877 </param>
1878 <valid initial="default"> 1878 <yield />
1879 <add value="["/> 1879 </section>
1880 <add value="]"/> 1880 </xml>
1881 </valid> 1881
1882 </sanitizer> 1882 <xml name="preprocessors_sequence_encoders">
1883 </param> 1883 <conditional name="encoder_selection">
1884 <yield/> 1884 <param name="encoder_type" type="select" label="Choose the sequence encoder class">
1885 </section> 1885 <option value="GenomeOneHotEncoder">GenomeOneHotEncoder</option>
1886 </xml> 1886 <option value="ProteinOneHotEncoder">ProteinOneHotEncoder</option>
1887 1887 </param>
1888 <xml name="preprocessors_sequence_encoders"> 1888 <when value="GenomeOneHotEncoder">
1889 <conditional name="encoder_selection"> 1889 <expand macro="preprocessors_sequence_encoder_arguments" />
1890 <param name="encoder_type" type="select" label="Choose the sequence encoder class"> 1890 </when>
1891 <option value="GenomeOneHotEncoder">GenomeOneHotEncoder</option> 1891 <when value="ProteinOneHotEncoder">
1892 <option value="ProteinOneHotEncoder">ProteinOneHotEncoder</option> 1892 <expand macro="preprocessors_sequence_encoder_arguments" />
1893 </param> 1893 </when>
1894 <when value="GenomeOneHotEncoder"> 1894 </conditional>
1895 <expand macro="preprocessors_sequence_encoder_arguments"/> 1895 </xml>
1896 </when> 1896
1897 <when value="ProteinOneHotEncoder"> 1897 <xml name="preprocessors_sequence_encoder_arguments">
1898 <expand macro="preprocessors_sequence_encoder_arguments"/> 1898 <param argument="seq_length" type="integer" value="" min="0" optional="true" help="Integer. Sequence length" />
1899 </when> 1899 <param argument="padding" type="boolean" truevalue="booltrue" falsevalue="boolfalse" checked="true" help="Whether to pad or truncate sequence to meet the sequence length." />
1900 </conditional> 1900 </xml>
1901 </xml> 1901
1902 1902 <!-- Outputs -->
1903 <xml name="preprocessors_sequence_encoder_arguments"> 1903
1904 <param argument="seq_length" type="integer" value="" min="0" optional="true" help="Integer. Sequence length"/> 1904 <xml name="output">
1905 <param argument="padding" type="boolean" truevalue="booltrue" falsevalue="boolfalse" checked="true" help="Whether to pad or truncate sequence to meet the sequence length."/> 1905 <outputs>
1906 </xml> 1906 <data format="tabular" name="outfile_predict">
1907 1907 <filter>selected_tasks['selected_task'] == 'load'</filter>
1908 <!-- Outputs --> 1908 </data>
1909 1909 <data format="zip" name="outfile_fit" label="${tool.name}.${selected_tasks.selected_algorithms.selected_algorithm}">
1910 <xml name="output"> 1910 <filter>selected_tasks['selected_task'] == 'train'</filter>
1911 <outputs> 1911 </data>
1912 <data format="tabular" name="outfile_predict"> 1912 </outputs>
1913 <filter>selected_tasks['selected_task'] == 'load'</filter> 1913 </xml>
1914 </data> 1914
1915 <data format="zip" name="outfile_fit" label="${tool.name}.${selected_tasks.selected_algorithms.selected_algorithm}"> 1915 <!--Citations-->
1916 <filter>selected_tasks['selected_task'] == 'train'</filter> 1916 <xml name="eden_citation">
1917 </data> 1917 <citations>
1918 </outputs> 1918 <citation type="doi">10.5281/zenodo.15094</citation>
1919 </xml> 1919 </citations>
1920 1920 </xml>
1921 <!--Citations--> 1921
1922 <xml name="eden_citation"> 1922 <xml name="sklearn_citation">
1923 <citations> 1923 <citations>
1924 <citation type="doi">10.5281/zenodo.15094</citation> 1924 <citation type="bibtex">
1925 </citations> 1925 @article{scikit-learn, title={Scikit-learn: Machine Learning in {P}ython}, author={Pedregosa, F. and Varoquaux, G. and Gramfort, A. and Michel, V.
1926 </xml>
1927
1928 <xml name="sklearn_citation">
1929 <citations>
1930 <citation type="bibtex">
1931 @article{scikit-learn,
1932 title={Scikit-learn: Machine Learning in {P}ython},
1933 author={Pedregosa, F. and Varoquaux, G. and Gramfort, A. and Michel, V.
1934 and Thirion, B. and Grisel, O. and Blondel, M. and Prettenhofer, P. 1926 and Thirion, B. and Grisel, O. and Blondel, M. and Prettenhofer, P.
1935 and Weiss, R. and Dubourg, V. and Vanderplas, J. and Passos, A. and 1927 and Weiss, R. and Dubourg, V. and Vanderplas, J. and Passos, A. and
1936 Cournapeau, D. and Brucher, M. and Perrot, M. and Duchesnay, E.}, 1928 Cournapeau, D. and Brucher, M. and Perrot, M. and Duchesnay, E.}, journal={Journal of Machine Learning Research}, volume={12}, pages={2825--2830}, year={2011}
1937 journal={Journal of Machine Learning Research},
1938 volume={12},
1939 pages={2825--2830},
1940 year={2011}
1941 } 1929 }
1942 </citation> 1930 </citation>
1943 <yield/> 1931 <yield />
1944 </citations> 1932 </citations>
1945 </xml> 1933 </xml>
1946 1934
1947 <xml name="scipy_citation"> 1935 <xml name="scipy_citation">
1948 <citations> 1936 <citations>
1949 <citation type="bibtex"> 1937 <citation type="bibtex">
1950 @Misc{, 1938 @Misc{,
1951 author = {Eric Jones and Travis Oliphant and Pearu Peterson and others}, 1939 author = {Eric Jones and Travis Oliphant and Pearu Peterson and others},
1952 title = {{SciPy}: Open source scientific tools for {Python}}, 1940 title = {{SciPy}: Open source scientific tools for {Python}},
1953 year = {2001--}, 1941 year = {2001--},
1954 url = "http://www.scipy.org/", 1942 url = "http://www.scipy.org/",
1955 note = {[Online; accessed 2016-04-09]} 1943 note = {[Online; accessed 2016-04-09]}
1956 } 1944 }
1957 </citation> 1945 </citation>
1958 </citations> 1946 </citations>
1959 </xml> 1947 </xml>
1960 1948
1961 <xml name="skrebate_citation"> 1949 <xml name="skrebate_citation">
1962 <citation type="bibtex"> 1950 <citation type="bibtex">
1963 @article{DBLP:journals/corr/abs-1711-08477, 1951 @article{DBLP:journals/corr/abs-1711-08477,
1964 author = {Ryan J. Urbanowicz and 1952 author = {Ryan J. Urbanowicz and
1965 Randal S. Olson and 1953 Randal S. Olson and
1966 Peter Schmitt and 1954 Peter Schmitt and
1967 Melissa Meeker and 1955 Melissa Meeker and
1975 eprint = {1711.08477}, 1963 eprint = {1711.08477},
1976 timestamp = {Mon, 13 Aug 2018 16:46:04 +0200}, 1964 timestamp = {Mon, 13 Aug 2018 16:46:04 +0200},
1977 biburl = {https://dblp.org/rec/bib/journals/corr/abs-1711-08477}, 1965 biburl = {https://dblp.org/rec/bib/journals/corr/abs-1711-08477},
1978 bibsource = {dblp computer science bibliography, https://dblp.org} 1966 bibsource = {dblp computer science bibliography, https://dblp.org}
1979 } 1967 }
1980 </citation> 1968 </citation>
1981 </xml> 1969 </xml>
1982 1970
1983 <xml name="xgboost_citation"> 1971 <xml name="xgboost_citation">
1984 <citation type="bibtex"> 1972 <citation type="bibtex">
1985 @inproceedings{Chen:2016:XST:2939672.2939785, 1973 @inproceedings{Chen:2016:XST:2939672.2939785,
1986 author = {Chen, Tianqi and Guestrin, Carlos}, 1974 author = {Chen, Tianqi and Guestrin, Carlos},
1987 title = {{XGBoost}: A Scalable Tree Boosting System}, 1975 title = {{XGBoost}: A Scalable Tree Boosting System},
1988 booktitle = {Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining}, 1976 booktitle = {Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining},
1989 series = {KDD '16}, 1977 series = {KDD '16},
1997 acmid = {2939785}, 1985 acmid = {2939785},
1998 publisher = {ACM}, 1986 publisher = {ACM},
1999 address = {New York, NY, USA}, 1987 address = {New York, NY, USA},
2000 keywords = {large-scale machine learning}, 1988 keywords = {large-scale machine learning},
2001 } 1989 }
2002 </citation> 1990 </citation>
2003 </xml> 1991 </xml>
2004 1992
2005 <xml name="imblearn_citation"> 1993 <xml name="imblearn_citation">
2006 <citation type="bibtex"> 1994 <citation type="bibtex">
2007 @article{JMLR:v18:16-365, 1995 @article{JMLR:v18:16-365,
2008 author = {Guillaume Lema{{\^i}}tre and Fernando Nogueira and Christos K. Aridas}, 1996 author = {Guillaume Lema{{\^i}}tre and Fernando Nogueira and Christos K. Aridas},
2009 title = {Imbalanced-learn: A Python Toolbox to Tackle the Curse of Imbalanced Datasets in Machine Learning}, 1997 title = {Imbalanced-learn: A Python Toolbox to Tackle the Curse of Imbalanced Datasets in Machine Learning},
2010 journal = {Journal of Machine Learning Research}, 1998 journal = {Journal of Machine Learning Research},
2011 year = {2017}, 1999 year = {2017},
2012 volume = {18}, 2000 volume = {18},
2013 number = {17}, 2001 number = {17},
2014 pages = {1-5}, 2002 pages = {1-5},
2015 url = {http://jmlr.org/papers/v18/16-365.html} 2003 url = {http://jmlr.org/papers/v18/16-365.html}
2016 } 2004 }
2017 </citation> 2005 </citation>
2018 </xml> 2006 </xml>
2019 2007
2020 <xml name="selene_citation"> 2008 <xml name="selene_citation">
2021 <citation type="bibtex"> 2009 <citation type="bibtex">
2022 @article{chen2019selene, 2010 @article{chen2019selene, title={Selene: a PyTorch-based deep learning library for sequence data}, author={Chen, Kathleen M and Cofer, Evan M and Zhou, Jian and Troyanskaya, Olga G}, journal={Nature methods}, volume={16}, number={4}, pages={315}, year={2019}, publisher={Nature Publishing Group}
2023 title={Selene: a PyTorch-based deep learning library for sequence data},
2024 author={Chen, Kathleen M and Cofer, Evan M and Zhou, Jian and Troyanskaya, Olga G},
2025 journal={Nature methods},
2026 volume={16},
2027 number={4},
2028 pages={315},
2029 year={2019},
2030 publisher={Nature Publishing Group}
2031 } 2011 }
2032 </citation> 2012 </citation>
2033 </xml> 2013 </xml>
2034 2014
2035 </macros> 2015 </macros>