comparison main_macros.xml @ 0:fcc5eaaec401 draft

planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/sklearn commit ab963ec9498bd05d2fb2f24f75adb2fccae7958c
author bgruening
date Wed, 15 May 2019 07:25:29 -0400
parents
children 6717e5cc4d05
comparison
equal deleted inserted replaced
-1:000000000000 0:fcc5eaaec401
1 <macros>
2 <token name="@VERSION@">1.0.0.4</token>
3
4 <xml name="python_requirements">
5 <requirements>
6 <requirement type="package" version="3.6">python</requirement>
7 <requirement type="package" version="0.20.3">scikit-learn</requirement>
8 <requirement type="package" version="0.24.2">pandas</requirement>
9 <requirement type="package" version="0.80">xgboost</requirement>
10 <requirement type="package" version="0.9.13">asteval</requirement>
11 <requirement type="package" version="0.6">skrebate</requirement>
12 <requirement type="package" version="0.4.2">imbalanced-learn</requirement>
13 <requirement type="package" version="0.16.0">mlxtend</requirement>
14 <yield/>
15 </requirements>
16 </xml>
17
18 <xml name="macro_stdio">
19 <stdio>
20 <exit_code range="1:" level="fatal" description="Error occurred. Please check Tool Standard Error"/>
21 </stdio>
22 </xml>
23
24
25 <!--Generic interface-->
26
27 <xml name="sl_Conditional" token_train="tabular" token_data="tabular" token_model="txt">
28 <conditional name="selected_tasks">
29 <param name="selected_task" type="select" label="Select a Classification Task">
30 <option value="train" selected="true">Train a model</option>
31 <option value="load">Load a model and predict</option>
32 </param>
33 <when value="load">
34 <param name="infile_model" type="data" format="@MODEL@" label="Models" help="Select a model file."/>
35 <param name="infile_data" type="data" format="@DATA@" label="Data (tabular)" help="Select the dataset you want to classify."/>
36 <param name="header" type="boolean" optional="True" truevalue="booltrue" falsevalue="boolfalse" checked="False" label="Does the dataset contain header:" />
37 <conditional name="prediction_options">
38 <param name="prediction_option" type="select" label="Select the type of prediction">
39 <option value="predict">Predict class labels</option>
40 <option value="advanced">Include advanced options</option>
41 </param>
42 <when value="predict">
43 </when>
44 <when value="advanced">
45 </when>
46 </conditional>
47 </when>
48 <when value="train">
49 <conditional name="selected_algorithms">
50 <yield />
51 </conditional>
52 </when>
53 </conditional>
54 </xml>
55
56 <xml name="advanced_section">
57 <section name="options" title="Advanced Options" expanded="False">
58 <yield />
59 </section>
60 </xml>
61
62
63 <!--Generalized Linear Models-->
64 <xml name="loss" token_help=" " token_select="false">
65 <param argument="loss" type="select" label="Loss function" help="@HELP@">
66 <option value="squared_loss" selected="@SELECT@">squared loss</option>
67 <option value="huber">huber</option>
68 <option value="epsilon_insensitive">epsilon insensitive</option>
69 <option value="squared_epsilon_insensitive">squared epsilon insensitive</option>
70 <yield/>
71 </param>
72 </xml>
73
74 <xml name="penalty" token_help=" ">
75 <param argument="penalty" type="select" label="Penalty (regularization term)" help="@HELP@">
76 <option value="l2" selected="true">l2</option>
77 <option value="l1">l1</option>
78 <option value="elasticnet">elastic net</option>
79 <option value="none">none</option>
80 <yield/>
81 </param>
82 </xml>
83
84 <xml name="l1_ratio" token_default_value="0.15" token_help=" ">
85 <param argument="l1_ratio" type="float" value="@DEFAULT_VALUE@" label="Elastic Net mixing parameter" help="@HELP@"/>
86 </xml>
87
88 <xml name="epsilon" token_default_value="0.1" token_help="Used if loss is ‘huber’, ‘epsilon_insensitive’, or ‘squared_epsilon_insensitive’. ">
89 <param argument="epsilon" type="float" value="@DEFAULT_VALUE@" label="Epsilon (epsilon-sensitive loss functions only)" help="@HELP@"/>
90 </xml>
91
92 <xml name="learning_rate_s" token_help=" " token_selected1="false" token_selected2="false">
93 <param argument="learning_rate" type="select" optional="true" label="Learning rate schedule" help="@HELP@">
94 <option value="optimal" selected="@SELECTED1@">optimal</option>
95 <option value="constant">constant</option>
96 <option value="invscaling" selected="@SELECTED2@">inverse scaling</option>
97 <yield/>
98 </param>
99 </xml>
100
101 <xml name="eta0" token_default_value="0.0" token_help="Used with ‘constant’ or ‘invscaling’ schedules. ">
102 <param argument="eta0" type="float" value="@DEFAULT_VALUE@" label="Initial learning rate" help="@HELP@"/>
103 </xml>
104
105 <xml name="power_t" token_default_value="0.5" token_help=" ">
106 <param argument="power_t" type="float" value="@DEFAULT_VALUE@" label="Exponent for inverse scaling learning rate" help="@HELP@"/>
107 </xml>
108
109 <xml name="normalize" token_checked="false" token_help=" ">
110 <param argument="normalize" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolfalse" checked="@CHECKED@" label="Normalize samples before training" help=" "/>
111 </xml>
112
113 <xml name="copy_X" token_checked="true" token_help=" ">
114 <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. "/>
115 </xml>
116
117 <xml name="ridge_params">
118 <expand macro="normalize"/>
119 <expand macro="alpha" default_value="1.0"/>
120 <expand macro="fit_intercept"/>
121 <expand macro="max_iter" default_value=""/>
122 <expand macro="tol" default_value="0.001" help_text="Precision of the solution. "/>
123 <!--class_weight-->
124 <expand macro="copy_X"/>
125 <param argument="solver" type="select" value="" label="Solver to use in the computational routines" help=" ">
126 <option value="auto" selected="true">auto</option>
127 <option value="svd">svd</option>
128 <option value="cholesky">cholesky</option>
129 <option value="lsqr">lsqr</option>
130 <option value="sparse_cg">sparse_cg</option>
131 <option value="sag">sag</option>
132 </param>
133 <expand macro="random_state"/>
134 </xml>
135
136 <!--Ensemble methods-->
137 <xml name="n_estimators" token_default_value="10" token_help=" ">
138 <param argument="n_estimators" type="integer" optional="true" value="@DEFAULT_VALUE@" label="Number of trees in the forest" help="@HELP@"/>
139 </xml>
140
141 <xml name="max_depth" token_default_value="" token_help=" ">
142 <param argument="max_depth" type="integer" optional="true" value="@DEFAULT_VALUE@" label="Maximum depth of the tree" help="@HELP@"/>
143 </xml>
144
145 <xml name="min_samples_split" token_type="integer" token_default_value="2" token_help=" ">
146 <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@"/>
147 </xml>
148
149 <xml name="min_samples_leaf" token_type="integer" token_default_value="1" token_label="Minimum number of samples in newly created leaves" token_help=" ">
150 <param argument="min_samples_leaf" type="@TYPE@" optional="true" value="@DEFAULT_VALUE@" label="@LABEL@" help="@HELP@"/>
151 </xml>
152
153 <xml name="min_weight_fraction_leaf" token_default_value="0.0" token_help=" ">
154 <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@"/>
155 </xml>
156
157 <xml name="max_leaf_nodes" token_default_value="" token_help=" ">
158 <param argument="max_leaf_nodes" type="integer" optional="true" value="@DEFAULT_VALUE@" label="Maximum number of leaf nodes in best-first method" help="@HELP@"/>
159 </xml>
160
161 <xml name="min_impurity_decrease" token_default_value="0" token_help=" ">
162 <param argument="min_impurity_decrease" type="float" value="@DEFAULT_VALUE@" optional="true" label="The threshold value of impurity for stopping node splitting" help="@HELP@"/>
163 </xml>
164
165 <xml name="bootstrap" token_checked="true" token_help=" ">
166 <param argument="bootstrap" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolflase" checked="@CHECKED@" label="Use bootstrap samples for building trees." help="@HELP@"/>
167 </xml>
168
169 <xml name="criterion" token_help=" ">
170 <param argument="criterion" type="select" label="Function to measure the quality of a split" help=" ">
171 <option value="gini" selected="true">Gini impurity</option>
172 <option value="entropy">Information gain</option>
173 <yield/>
174 </param>
175 </xml>
176
177 <xml name="criterion2" token_help="">
178 <param argument="criterion" type="select" label="Function to measure the quality of a split" >
179 <option value="mse">mse - mean squared error</option>
180 <option value="mae">mae - mean absolute error</option>
181 <yield/>
182 </param>
183 </xml>
184
185 <xml name="oob_score" token_checked="false" token_help=" ">
186 <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@"/>
187 </xml>
188
189 <xml name="max_features">
190 <conditional name="select_max_features">
191 <param argument="max_features" type="select" label="max_features">
192 <option value="auto" selected="true">auto - max_features=n_features</option>
193 <option value="sqrt">sqrt - max_features=sqrt(n_features)</option>
194 <option value="log2">log2 - max_features=log2(n_features)</option>
195 <option value="number_input">I want to type the number in or input None type</option>
196 </param>
197 <when value="auto">
198 </when>
199 <when value="sqrt">
200 </when>
201 <when value="log2">
202 </when>
203 <when value="number_input">
204 <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."/>
205 </when>
206 </conditional>
207 </xml>
208
209 <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.">
210 <param argument="verbose" type="integer" value="@DEFAULT_VALUE@" optional="true" label="Enable verbose output" help="@HELP@"/>
211 </xml>
212
213 <xml name="learning_rate" token_default_value="1.0" token_help=" ">
214 <param argument="learning_rate" type="float" optional="true" value="@DEFAULT_VALUE@" label="Learning rate" help="@HELP@"/>
215 </xml>
216
217 <xml name="subsample" token_help=" ">
218 <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@"/>
219 </xml>
220
221 <xml name="presort">
222 <param argument="presort" type="select" label="Whether to presort the data to speed up the finding of best splits in fitting" >
223 <option value="auto" selected="true">auto</option>
224 <option value="true">true</option>
225 <option value="false">false</option>
226 </param>
227 </xml>
228
229 <!--Parameters-->
230 <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.">
231 <param argument="tol" type="float" optional="true" value="@DEFAULT_VALUE@" label="Tolerance" help="@HELP_TEXT@"/>
232 </xml>
233
234 <xml name="n_clusters" token_default_value="8">
235 <param argument="n_clusters" type="integer" optional="true" value="@DEFAULT_VALUE@" label="Number of clusters" help=" "/>
236 </xml>
237
238 <xml name="fit_intercept" token_checked="true">
239 <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."/>
240 </xml>
241
242 <xml name="n_iter" token_default_value="5" token_help_text="The number of passes over the training data (aka epochs). ">
243 <param argument="n_iter" type="integer" optional="true" value="@DEFAULT_VALUE@" label="Number of iterations" help="@HELP_TEXT@"/>
244 </xml>
245
246 <xml name="shuffle" token_checked="true" token_help_text=" " token_label="Shuffle data after each iteration">
247 <param argument="shuffle" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolfalse" checked="@CHECKED@" label="@LABEL@" help="@HELP_TEXT@"/>
248 </xml>
249
250 <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.">
251 <param argument="random_state" type="integer" optional="true" value="@DEFAULT_VALUE@" label="Random seed number" help="@HELP_TEXT@"/>
252 </xml>
253
254 <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.">
255 <param argument="warm_start" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolfalse" checked="@CHECKED@" label="Perform warm start" help="@HELP_TEXT@"/>
256 </xml>
257
258 <xml name="C" token_default_value="1.0" token_help_text="Penalty parameter C of the error term.">
259 <param argument="C" type="float" optional="true" value="@DEFAULT_VALUE@" label="Penalty parameter" help="@HELP_TEXT@"/>
260 </xml>
261
262 <!--xml name="class_weight" token_default_value="" token_help_text="">
263 <param argument="class_weight" type="" optional="true" value="@DEFAULT_VALUE@" label="" help="@HELP_TEXT@"/>
264 </xml-->
265
266 <xml name="alpha" token_default_value="0.0001" token_help_text="Constant that multiplies the regularization term if regularization is used. ">
267 <param argument="alpha" type="float" optional="true" value="@DEFAULT_VALUE@" label="Regularization coefficient" help="@HELP_TEXT@"/>
268 </xml>
269
270 <xml name="n_samples" token_default_value="100" token_help_text="The total number of points equally divided among clusters.">
271 <param argument="n_samples" type="integer" optional="true" value="@DEFAULT_VALUE@" label="Number of samples" help="@HELP_TEXT@"/>
272 </xml>
273
274 <xml name="n_features" token_default_value="2" token_help_text="Number of different numerical properties produced for each sample.">
275 <param argument="n_features" type="integer" optional="true" value="@DEFAULT_VALUE@" label="Number of features" help="@HELP_TEXT@"/>
276 </xml>
277
278 <xml name="noise" token_default_value="0.0" token_help_text="Floating point number. ">
279 <param argument="noise" type="float" optional="true" value="@DEFAULT_VALUE@" label="Standard deviation of the Gaussian noise added to the data" help="@HELP_TEXT@"/>
280 </xml>
281
282 <xml name="C" token_default_value="1.0" token_help_text="Penalty parameter C of the error term. ">
283 <param argument="C" type="float" optional="true" value="@DEFAULT_VALUE@" label="Penalty parameter" help="@HELP_TEXT@"/>
284 </xml>
285
286 <xml name="max_iter" token_default_value="300" token_label="Maximum number of iterations per single run" token_help_text=" ">
287 <param argument="max_iter" type="integer" optional="true" value="@DEFAULT_VALUE@" label="@LABEL@" help="@HELP_TEXT@"/>
288 </xml>
289
290 <xml name="n_init" token_default_value="10" >
291 <param argument="n_init" type="integer" optional="true" value="@DEFAULT_VALUE@" label="Number of runs with different centroid seeds" help=" "/>
292 </xml>
293
294 <xml name="init">
295 <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.">
296 <option value="k-means++">k-means++</option>
297 <option value="random">random</option>
298 </param>
299 </xml>
300
301 <xml name="gamma" token_default_value="1.0" token_label="Scaling parameter" token_help_text=" ">
302 <param argument="gamma" type="float" optional="true" value="@DEFAULT_VALUE@" label="@LABEL@" help="@HELP_TEXT@"/>
303 </xml>
304
305 <xml name="degree" token_default_value="3" token_label="Degree of the polynomial" token_help_text=" ">
306 <param argument="degree" type="integer" optional="true" value="@DEFAULT_VALUE@" label="@LABEL@" help="@HELP_TEXT@"/>
307 </xml>
308
309 <xml name="coef0" token_default_value="1" token_label="Zero coefficient" token_help_text=" ">
310 <param argument="coef0" type="integer" optional="true" value="@DEFAULT_VALUE@" label="@LABEL@" help="@HELP_TEXT@"/>
311 </xml>
312
313 <xml name="pos_label" token_default_value="">
314 <param argument="pos_label" type="integer" optional="true" value="@DEFAULT_VALUE@" label="Label of the positive class" help=" "/>
315 </xml>
316
317 <xml name="average">
318 <param argument="average" type="select" optional="true" label="Averaging type" help=" ">
319 <option value="micro">Calculate metrics globally by counting the total true positives, false negatives and false positives. (micro)</option>
320 <option value="samples">Calculate metrics for each instance, and find their average. Only meaningful for multilabel. (samples)</option>
321 <option value="macro">Calculate metrics for each label, and find their unweighted mean. This does not take label imbalance into account. (macro)</option>
322 <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>
323 <option value="None">None</option>
324 <yield/>
325 </param>
326 </xml>
327
328 <xml name="beta">
329 <param argument="beta" type="float" value="1.0" label="The strength of recall versus precision in the F-score" help=" "/>
330 </xml>
331
332
333 <!--Data interface-->
334
335 <xml name="samples_tabular" token_multiple1="false" token_multiple2="false">
336 <param name="infile1" type="data" format="tabular" label="Training samples dataset:"/>
337 <param name="header1" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolfalse" checked="False" label="Does the dataset contain header:" />
338 <conditional name="column_selector_options_1">
339 <expand macro="samples_column_selector_options" multiple="@MULTIPLE1@"/>
340 </conditional>
341 <param name="infile2" type="data" format="tabular" label="Dataset containing class labels or target values:"/>
342 <param name="header2" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolfalse" checked="False" label="Does the dataset contain header:" />
343 <conditional name="column_selector_options_2">
344 <expand macro="samples_column_selector_options" column_option="selected_column_selector_option2" col_name="col2" multiple="@MULTIPLE2@" infile="infile2"/>
345 </conditional>
346 <yield/>
347 </xml>
348
349 <xml name="samples_column_selector_options" token_column_option="selected_column_selector_option" token_col_name="col1" token_multiple="False" token_infile="infile1">
350 <param name="@COLUMN_OPTION@" type="select" label="Choose how to select data by column:">
351 <option value="by_index_number" selected="true">Select columns by column index number(s)</option>
352 <option value="all_but_by_index_number">All columns BUT by column index number(s)</option>
353 <option value="by_header_name">Select columns by column header name(s)</option>
354 <option value="all_but_by_header_name">All columns BUT by column header name(s)</option>
355 <option value="all_columns">All columns</option>
356 </param>
357 <when value="by_index_number">
358 <param name="@COL_NAME@" multiple="@MULTIPLE@" type="data_column" use_header_names="true" data_ref="@INFILE@" label="Select target column(s):"/>
359 </when>
360 <when value="all_but_by_index_number">
361 <param name="@COL_NAME@" multiple="@MULTIPLE@" type="data_column" use_header_names="true" data_ref="@INFILE@" label="Select target column(s):"/>
362 </when>
363 <when value="by_header_name">
364 <param name="@COL_NAME@" type="text" value="" label="Type header name(s):" help="Comma-separated string. For example: target1,target2"/>
365 </when>
366 <when value="all_but_by_header_name">
367 <param name="@COL_NAME@" type="text" value="" label="Type header name(s):" help="Comma-separated string. For example: target1,target2"/>
368 </when>
369 <when value="all_columns">
370 </when>
371 </xml>
372
373 <xml name="clf_inputs_extended" token_label1=" " token_label2=" " token_multiple="False">
374 <conditional name="true_columns">
375 <param name="selected_input1" type="select" label="Select the input type of true labels dataset:">
376 <option value="tabular" selected="true">Tabular</option>
377 <option value="sparse">Sparse</option>
378 </param>
379 <when value="tabular">
380 <param name="infile1" type="data" label="@LABEL1@"/>
381 <param name="col1" type="data_column" data_ref="infile1" label="Select the target column:"/>
382 </when>
383 <when value="sparse">
384 <param name="infile1" type="data" format="txt" label="@LABEL1@"/>
385 </when>
386 </conditional>
387 <conditional name="predicted_columns">
388 <param name="selected_input2" type="select" label="Select the input type of predicted labels dataset:">
389 <option value="tabular" selected="true">Tabular</option>
390 <option value="sparse">Sparse</option>
391 </param>
392 <when value="tabular">
393 <param name="infile2" type="data" label="@LABEL2@"/>
394 <param name="col2" multiple="@MULTIPLE@" type="data_column" data_ref="infile2" label="Select target column(s):"/>
395 </when>
396 <when value="sparse">
397 <param name="infile2" type="data" format="txt" label="@LABEL1@"/>
398 </when>
399 </conditional>
400 </xml>
401
402 <xml name="clf_inputs" token_label1="Dataset containing true labels (tabular):" token_label2="Dataset containing predicted values (tabular):" token_multiple1="False" token_multiple="False">
403 <param name="infile1" type="data" format="tabular" label="@LABEL1@"/>
404 <param name="header1" type="boolean" optional="True" truevalue="booltrue" falsevalue="boolfalse" checked="False" label="Does the dataset contain header:" />
405 <conditional name="column_selector_options_1">
406 <expand macro="samples_column_selector_options" multiple="@MULTIPLE1@"/>
407 </conditional>
408 <param name="infile2" type="data" format="tabular" label="@LABEL2@"/>
409 <param name="header2" type="boolean" optional="True" truevalue="booltrue" falsevalue="boolfalse" checked="False" label="Does the dataset contain header:" />
410 <conditional name="column_selector_options_2">
411 <expand macro="samples_column_selector_options" column_option="selected_column_selector_option2" col_name="col2" multiple="@MULTIPLE@" infile="infile2"/>
412 </conditional>
413 </xml>
414
415 <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.">
416 <repeat name="@NAME@" min="1" max="@MAX_NUM@" title="Select input file(s):">
417 <param name="input" type="data" format="@FORMAT@" label="@LABEL@" help="@HELP_TEXT@"/>
418 </repeat>
419 </xml>
420
421 <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="">
422 <param name="infile1" type="data" format="@FORMAT1@" label="@LABEL1@" help="@HELP1@"/>
423 <param name="infile2" type="data" format="@FORMAT2@" label="@LABEL2@" help="@HELP2@"/>
424 <param name="col2" multiple="@MULTIPLE@" type="data_column" data_ref="infile2" label="Select target column(s):"/>
425 </xml>
426
427 <xml name="sl_mixed_input">
428 <conditional name="input_options">
429 <param name="selected_input" type="select" label="Select input type:">
430 <option value="tabular" selected="true">tabular data</option>
431 <option value="sparse">sparse matrix</option>
432 </param>
433 <when value="tabular">
434 <expand macro="samples_tabular" multiple1="true" multiple2="false"/>
435 </when>
436 <when value="sparse">
437 <expand macro="sparse_target"/>
438 </when>
439 </conditional>
440 </xml>
441
442 <!--Advanced options-->
443 <xml name="nn_advanced_options">
444 <section name="options" title="Advanced Options" expanded="False">
445 <yield/>
446 <param argument="weights" type="select" label="Weight function" help="Used in prediction.">
447 <option value="uniform" selected="true">Uniform weights. All points in each neighborhood are weighted equally. (Uniform)</option>
448 <option value="distance">Weight points by the inverse of their distance. (Distance)</option>
449 </param>
450 <param argument="algorithm" type="select" label="Neighbor selection algorithm" help=" ">
451 <option value="auto" selected="true">Auto</option>
452 <option value="ball_tree">BallTree</option>
453 <option value="kd_tree">KDTree</option>
454 <option value="brute">Brute-force</option>
455 </param>
456 <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."/>
457 <!--param name="metric"-->
458 <!--param name="p"-->
459 <!--param name="metric_params"-->
460 </section>
461 </xml>
462
463 <xml name="svc_advanced_options">
464 <section name="options" title="Advanced Options" expanded="False">
465 <yield/>
466 <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.">
467 <option value="rbf" selected="true">rbf</option>
468 <option value="linear">linear</option>
469 <option value="poly">poly</option>
470 <option value="sigmoid">sigmoid</option>
471 <option value="precomputed">precomputed</option>
472 </param>
473 <param argument="degree" type="integer" optional="true" value="3" label="Degree of the polynomial (polynomial kernel only)" help="Ignored by other kernels. dafault : 3 "/>
474 <!--TODO: param argument="gamma" float, optional (default=’auto’) -->
475 <param argument="coef0" type="float" optional="true" value="0.0" label="Zero coefficient (polynomial and sigmoid kernels only)"
476 help="Independent term in kernel function. dafault: 0.0 "/>
477 <param argument="shrinking" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolfalse" checked="true"
478 label="Use the shrinking heuristic" help=" "/>
479 <param argument="probability" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolfalse" checked="false"
480 label="Enable probability estimates. " help="This must be enabled prior to calling fit, and will slow down that method."/>
481 <!-- param argument="cache_size"-->
482 <!--expand macro="class_weight"/-->
483 <expand macro="tol" default_value="0.001" help_text="Tolerance for stopping criterion. "/>
484 <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."/>
485 <!--param argument="decision_function_shape"-->
486 <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."/>
487 </section>
488 </xml>
489
490 <xml name="spectral_clustering_advanced_options">
491 <section name="options" title="Advanced Options" expanded="False">
492 <expand macro="n_clusters"/>
493 <param argument="eigen_solver" type="select" value="" label="Eigen solver" help="The eigenvalue decomposition strategy to use.">
494 <option value="arpack" selected="true">arpack</option>
495 <option value="lobpcg">lobpcg</option>
496 <option value="amg">amg</option>
497 <!--None-->
498 </param>
499 <expand macro="random_state"/>
500 <expand macro="n_init"/>
501 <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''."/>
502 <param argument="affinity" type="select" label="Affinity" help="Affinity kernel to use. ">
503 <option value="rbf" selected="true">RBF</option>
504 <option value="precomputed">precomputed</option>
505 <option value="nearest_neighbors">Nearset neighbors</option>
506 </param>
507 <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''"/>
508 <!--param argument="eigen_tol"-->
509 <param argument="assign_labels" type="select" label="Assign labels" help="The strategy to use to assign labels in the embedding space.">
510 <option value="kmeans" selected="true">kmeans</option>
511 <option value="discretize">discretize</option>
512 </param>
513 <param argument="degree" type="integer" optional="true" value="3"
514 label="Degree of the polynomial (polynomial kernel only)" help="Ignored by other kernels. dafault : 3 "/>
515 <param argument="coef0" type="integer" optional="true" value="1"
516 label="Zero coefficient (polynomial and sigmoid kernels only)" help="Ignored by other kernels. dafault : 1 "/>
517 <!--param argument="kernel_params"-->
518 </section>
519 </xml>
520
521 <xml name="minibatch_kmeans_advanced_options">
522 <section name="options" title="Advanced Options" expanded="False">
523 <expand macro="n_clusters"/>
524 <expand macro="init"/>
525 <expand macro="n_init" default_value="3"/>
526 <expand macro="max_iter" default_value="100"/>
527 <expand macro="tol" help_text="Early stopping heuristics based on normalized center change. To disable set to 0.0 ."/>
528 <expand macro="random_state"/>
529 <param argument="batch_size" type="integer" optional="true" value="100" label="Batch size" help="Size of the mini batches."/>
530 <!--param argument="compute_labels"-->
531 <param argument="max_no_improvement" type="integer" optional="true" value="10" label="Maximum number of improvement attempts" help="
532 Convergence detection based on inertia (the consecutive number of mini batches that doe not yield an improvement on the smoothed inertia).
533 To disable, set max_no_improvement to None. "/>
534 <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 )"/>
535 <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."/>
536 </section>
537 </xml>
538
539 <xml name="kmeans_advanced_options">
540 <section name="options" title="Advanced Options" expanded="False">
541 <expand macro="n_clusters"/>
542 <expand macro="init"/>
543 <expand macro="n_init"/>
544 <expand macro="max_iter"/>
545 <expand macro="tol" default_value="0.0001" help_text="Relative tolerance with regards to inertia to declare convergence."/>
546 <!--param argument="precompute_distances"/-->
547 <expand macro="random_state"/>
548 <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."/>
549 <expand macro="kmeans_algorithm"/>
550 </section>
551 </xml>
552
553 <xml name="kmeans_algorithm">
554 <param argument="algorithm" type="select" label="K-means algorithm to use:">
555 <option value="auto" selected="true">auto</option>
556 <option value="full">full</option>
557 <option value="elkan">elkan</option>
558 </param>
559 </xml>
560
561 <xml name="birch_advanced_options">
562 <section name="options" title="Advanced Options" expanded="False">
563 <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."/>
564 <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."/>
565 <expand macro="n_clusters" default_value="3"/>
566 <!--param argument="compute_labels"/-->
567 </section>
568 </xml>
569
570 <xml name="dbscan_advanced_options">
571 <section name="options" title="Advanced Options" expanded="False">
572 <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."/>
573 <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."/>
574 <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."/>
575 <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.">
576 <option value="auto" selected="true">auto</option>
577 <option value="ball_tree">ball_tree</option>
578 <option value="kd_tree">kd_tree</option>
579 <option value="brute">brute</option>
580 </param>
581 <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."/>
582 </section>
583 </xml>
584
585 <xml name="clustering_algorithms_options">
586 <conditional name="algorithm_options">
587 <param name="selected_algorithm" type="select" label="Clustering Algorithm">
588 <option value="KMeans" selected="true">KMeans</option>
589 <option value="SpectralClustering">Spectral Clustering</option>
590 <option value="MiniBatchKMeans">Mini Batch KMeans</option>
591 <option value="DBSCAN">DBSCAN</option>
592 <option value="Birch">Birch</option>
593 </param>
594 <when value="KMeans">
595 <expand macro="kmeans_advanced_options"/>
596 </when>
597 <when value="DBSCAN">
598 <expand macro="dbscan_advanced_options"/>
599 </when>
600 <when value="Birch">
601 <expand macro="birch_advanced_options"/>
602 </when>
603 <when value="SpectralClustering">
604 <expand macro="spectral_clustering_advanced_options"/>
605 </when>
606 <when value="MiniBatchKMeans">
607 <expand macro="minibatch_kmeans_advanced_options"/>
608 </when>
609 </conditional>
610 </xml>
611
612 <xml name="distance_metrics">
613 <param argument="metric" type="select" label="Distance metric" help=" ">
614 <option value="euclidean" selected="true">euclidean</option>
615 <option value="cityblock">cityblock</option>
616 <option value="cosine">cosine</option>
617 <option value="l1">l1</option>
618 <option value="l2">l2</option>
619 <option value="manhattan">manhattan</option>
620 <yield/>
621 </param>
622 </xml>
623
624 <xml name="distance_nonsparse_metrics">
625 <option value="braycurtis">braycurtis</option>
626 <option value="canberra">canberra</option>
627 <option value="chebyshev">chebyshev</option>
628 <option value="correlation">correlation</option>
629 <option value="dice">dice</option>
630 <option value="hamming">hamming</option>
631 <option value="jaccard">jaccard</option>
632 <option value="kulsinski">kulsinski</option>
633 <option value="mahalanobis">mahalanobis</option>
634 <option value="matching">matching</option>
635 <option value="minkowski">minkowski</option>
636 <option value="rogerstanimoto">rogerstanimoto</option>
637 <option value="russellrao">russellrao</option>
638 <option value="seuclidean">seuclidean</option>
639 <option value="sokalmichener">sokalmichener</option>
640 <option value="sokalsneath">sokalsneath</option>
641 <option value="sqeuclidean">sqeuclidean</option>
642 <option value="yule">yule</option>
643 </xml>
644
645 <xml name="pairwise_kernel_metrics">
646 <param argument="metric" type="select" label="Pirwise Kernel metric" help=" ">
647 <option value="rbf" selected="true">rbf</option>
648 <option value="sigmoid">sigmoid</option>
649 <option value="polynomial">polynomial</option>
650 <option value="linear" selected="true">linear</option>
651 <option value="chi2">chi2</option>
652 <option value="additive_chi2">additive_chi2</option>
653 </param>
654 </xml>
655
656 <xml name="sparse_pairwise_metric_functions">
657 <param name="selected_metric_function" type="select" label="Select the pairwise metric you want to compute:">
658 <option value="euclidean_distances" selected="true">Euclidean distance matrix</option>
659 <option value="pairwise_distances">Distance matrix</option>
660 <option value="pairwise_distances_argmin">Minimum distances between one point and a set of points</option>
661 <yield/>
662 </param>
663 </xml>
664
665 <xml name="pairwise_metric_functions">
666 <option value="additive_chi2_kernel" >Additive chi-squared kernel</option>
667 <option value="chi2_kernel">Exponential chi-squared kernel</option>
668 <option value="linear_kernel">Linear kernel</option>
669 <option value="manhattan_distances">L1 distances</option>
670 <option value="pairwise_kernels">Kernel</option>
671 <option value="polynomial_kernel">Polynomial kernel</option>
672 <option value="rbf_kernel">Gaussian (rbf) kernel</option>
673 <option value="laplacian_kernel">Laplacian kernel</option>
674 </xml>
675
676 <xml name="sparse_pairwise_condition">
677 <when value="pairwise_distances">
678 <section name="options" title="Advanced Options" expanded="False">
679 <expand macro="distance_metrics">
680 <yield/>
681 </expand>
682 </section>
683 </when>
684 <when value="euclidean_distances">
685 <section name="options" title="Advanced Options" expanded="False">
686 <param argument="squared" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolfalse" checked="false"
687 label="Return squared Euclidean distances" help=" "/>
688 </section>
689 </when>
690 </xml>
691
692 <xml name="argmin_distance_condition">
693 <when value="pairwise_distances_argmin">
694 <section name="options" title="Advanced Options" expanded="False">
695 <param argument="axis" type="integer" optional="true" value="1" label="Axis" help="Axis along which the argmin and distances are to be computed."/>
696 <expand macro="distance_metrics">
697 <yield/>
698 </expand>
699 <param argument="batch_size" type="integer" optional="true" value="500" label="Batch size" help="Number of rows to be processed in each batch run."/>
700 </section>
701 </when>
702 </xml>
703
704 <xml name="sparse_preprocessors">
705 <param name="selected_pre_processor" type="select" label="Select a preprocessor:">
706 <option value="StandardScaler" selected="true">Standard Scaler (Standardizes features by removing the mean and scaling to unit variance)</option>
707 <option value="Binarizer">Binarizer (Binarizes data)</option>
708 <option value="Imputer">Imputer (Completes missing values)</option>
709 <option value="MaxAbsScaler">Max Abs Scaler (Scales features by their maximum absolute value)</option>
710 <option value="Normalizer">Normalizer (Normalizes samples individually to unit norm)</option>
711 <yield/>
712 </param>
713 </xml>
714
715 <xml name="sparse_preprocessors_ext">
716 <expand macro="sparse_preprocessors">
717 <option value="KernelCenterer">Kernel Centerer (Centers a kernel matrix)</option>
718 <option value="MinMaxScaler">Minmax Scaler (Scales features to a range)</option>
719 <option value="PolynomialFeatures">Polynomial Features (Generates polynomial and interaction features)</option>
720 <option value="RobustScaler">Robust Scaler (Scales features using outlier-invariance statistics)</option>
721 </expand>
722 </xml>
723
724 <xml name="sparse_preprocessor_options">
725 <when value="Binarizer">
726 <section name="options" title="Advanced Options" expanded="False">
727 <param argument="copy" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolfalse" checked="true"
728 label="Use a copy of data for precomputing binarization" help=" "/>
729 <param argument="threshold" type="float" optional="true" value="0.0"
730 label="Threshold"
731 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. "/>
732 </section>
733 </when>
734 <when value="Imputer">
735 <section name="options" title="Advanced Options" expanded="False">
736 <param argument="copy" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolfalse" checked="true"
737 label="Use a copy of data for precomputing imputation" help=" "/>
738 <param argument="strategy" type="select" optional="true" label="Imputation strategy" help=" ">
739 <option value="mean" selected="true">Replace missing values using the mean along the axis</option>
740 <option value="median">Replace missing values using the median along the axis</option>
741 <option value="most_frequent">Replace missing using the most frequent value along the axis</option>
742 </param>
743 <param argument="missing_values" type="text" optional="true" value="NaN"
744 label="Placeholder for missing values" help="For missing values encoded as numpy.nan, use the string value “NaN”"/>
745 <!--param argument="axis" type="boolean" optional="true" truevalue="1" falsevalue="0"
746 label="Impute along axis = 1" help="If fasle, axis = 0 is selected for imputation. "/> -->
747 <!--param argument="axis" type="select" optional="true" label="The axis along which to impute" help=" ">
748 <option value="0" selected="true">Impute along columns</option>
749 <option value="1">Impute along rows</option>
750 </param-->
751 </section>
752 </when>
753 <when value="StandardScaler">
754 <section name="options" title="Advanced Options" expanded="False">
755 <param argument="copy" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolfalse" checked="true"
756 label="Use a copy of data for performing inplace scaling" help=" "/>
757 <param argument="with_mean" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolfalse" checked="true"
758 label="Center the data before scaling" help=" "/>
759 <param argument="with_std" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolfalse" checked="true"
760 label="Scale the data to unit variance (or unit standard deviation)" help=" "/>
761 </section>
762 </when>
763 <when value="MaxAbsScaler">
764 <section name="options" title="Advanced Options" expanded="False">
765 <param argument="copy" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolfalse" checked="true"
766 label="Use a copy of data for precomputing scaling" help=" "/>
767 </section>
768 </when>
769 <when value="Normalizer">
770 <section name="options" title="Advanced Options" expanded="False">
771 <param argument="norm" type="select" optional="true" label="The norm to use to normalize non zero samples" help=" ">
772 <option value="l1" selected="true">l1</option>
773 <option value="l2">l2</option>
774 <option value="max">max</option>
775 </param>
776 <param argument="copy" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolfalse" checked="true"
777 label="Use a copy of data for precomputing row normalization" help=" "/>
778 </section>
779 </when>
780 <yield/>
781 </xml>
782
783 <xml name="sparse_preprocessor_options_ext">
784 <expand macro="sparse_preprocessor_options">
785 <when value="KernelCenterer">
786 <section name="options" title="Advanced Options" expanded="False">
787 </section>
788 </when>
789 <when value="MinMaxScaler">
790 <section name="options" title="Advanced Options" expanded="False">
791 <!--feature_range-->
792 <param argument="copy" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolflase" checked="true"
793 label="Use a copy of data for precomputing normalization" help=" "/>
794 </section>
795 </when>
796 <when value="PolynomialFeatures">
797 <section name="options" title="Advanced Options" expanded="False">
798 <param argument="degree" type="integer" optional="true" value="2" label="The degree of the polynomial features " help=""/>
799 <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) "/>
800 <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 "/>
801 </section>
802 </when>
803 <when value="RobustScaler">
804 <section name="options" title="Advanced Options" expanded="False">
805 <!--=True, =True, copy=True-->
806 <param argument="with_centering" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolflase" checked="true"
807 label="Center the data before scaling" help=" "/>
808 <param argument="with_scaling" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolflase" checked="true"
809 label="Scale the data to interquartile range" help=" "/>
810 <param argument="copy" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolflase" checked="true"
811 label="Use a copy of data for inplace scaling" help=" "/>
812 </section>
813 </when>
814 </expand>
815 </xml>
816
817 <xml name="cv_splitter">
818 <option value="default" selected="true">default splitter</option>
819 <option value="KFold">KFold</option>
820 <option value="StratifiedKFold">StratifiedKFold</option>
821 <option value="LeaveOneOut">LeaveOneOut</option>
822 <option value="LeavePOut">LeavePOut</option>
823 <option value="RepeatedKFold">RepeatedKFold</option>
824 <option value="RepeatedStratifiedKFold">RepeatedStratifiedKFold</option>
825 <option value="ShuffleSplit">ShuffleSplit</option>
826 <option value="StratifiedShuffleSplit">StratifiedShuffleSplit</option>
827 <option value="TimeSeriesSplit">TimeSeriesSplit</option>
828 <option value="PredefinedSplit">PredefinedSplit</option>
829 <option value="OrderedKFold">OrderedKFold</option>
830 <option value="RepeatedOrderedKFold">RepeatedOrderedKFold</option>
831 <yield/>
832 </xml>
833
834 <xml name="cv_splitter_options">
835 <when value="default">
836 <expand macro="cv_n_splits"/>
837 </when>
838 <when value="KFold">
839 <expand macro="cv_n_splits"/>
840 <expand macro="cv_shuffle"/>
841 <expand macro="random_state"/>
842 </when>
843 <when value="StratifiedKFold">
844 <expand macro="cv_n_splits"/>
845 <expand macro="cv_shuffle"/>
846 <expand macro="random_state"/>
847 </when>
848 <when value="LeaveOneOut">
849 </when>
850 <when value="LeavePOut">
851 <param argument="p" type="integer" value="" label="p" help="Integer. Size of the test sets."/>
852 </when>
853 <when value="RepeatedKFold">
854 <expand macro="cv_n_splits" value="5"/>
855 <param argument="n_repeats" type="integer" value="10" label="n_repeats" help="Number of times cross-validator needs to be repeated." />
856 <expand macro="random_state" />
857 </when>
858 <when value="RepeatedStratifiedKFold">
859 <expand macro="cv_n_splits" value="5"/>
860 <param argument="n_repeats" type="integer" value="10" label="n_repeats" help="Number of times cross-validator needs to be repeated." />
861 <expand macro="random_state" />
862 </when>
863 <when value="ShuffleSplit">
864 <expand macro="cv_n_splits" value="10" help="Number of re-shuffling and splitting iterations."/>
865 <expand macro="cv_test_size" value="0.1" />
866 <expand macro="random_state"/>
867 </when>
868 <when value="StratifiedShuffleSplit">
869 <expand macro="cv_n_splits" value="10" help="Number of re-shuffling and splitting iterations."/>
870 <expand macro="cv_test_size" value="0.1" />
871 <expand macro="random_state"/>
872 </when>
873 <when value="TimeSeriesSplit">
874 <expand macro="cv_n_splits"/>
875 <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." />
876 </when>
877 <when value="PredefinedSplit">
878 <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'."/>
879 </when>
880 <when value="OrderedKFold">
881 <expand macro="cv_n_splits"/>
882 <expand macro="cv_shuffle"/>
883 <expand macro="random_state"/>
884 </when>
885 <when value="RepeatedOrderedKFold">
886 <expand macro="cv_n_splits"/>
887 <param argument="n_repeats" type="integer" value="5"/>
888 <expand macro="random_state"/>
889 </when>
890 <yield/>
891 </xml>
892
893 <xml name="cv">
894 <conditional name="cv_selector">
895 <param name="selected_cv" type="select" label="Select the cv splitter:">
896 <expand macro="cv_splitter">
897 <option value="GroupKFold">GroupKFold</option>
898 <option value="GroupShuffleSplit">GroupShuffleSplit</option>
899 <option value="LeaveOneGroupOut">LeaveOneGroupOut</option>
900 <option value="LeavePGroupsOut">LeavePGroupsOut</option>
901 </expand>
902 </param>
903 <expand macro="cv_splitter_options">
904 <when value="GroupKFold">
905 <expand macro="cv_n_splits"/>
906 <expand macro="cv_groups" />
907 </when>
908 <when value="GroupShuffleSplit">
909 <expand macro="cv_n_splits" value="5"/>
910 <expand macro="cv_test_size"/>
911 <expand macro="random_state"/>
912 <expand macro="cv_groups"/>
913 </when>
914 <when value="LeaveOneGroupOut">
915 <expand macro="cv_groups"/>
916 </when>
917 <when value="LeavePGroupsOut">
918 <param argument="n_groups" type="integer" value="" label="n_groups" help="Number of groups (p) to leave out in the test split." />
919 <expand macro="cv_groups"/>
920 </when>
921 </expand>
922 </conditional>
923 </xml>
924
925 <xml name="cv_reduced">
926 <conditional name="cv_selector">
927 <param name="selected_cv" type="select" label="Select the cv splitter:">
928 <expand macro="cv_splitter"/>
929 </param>
930 <expand macro="cv_splitter_options"/>
931 </conditional>
932 </xml>
933
934 <xml name="cv_n_splits" token_value="3" token_help="Number of folds. Must be at least 2.">
935 <param argument="n_splits" type="integer" value="@VALUE@" min="2" label="n_splits" help="@HELP@"/>
936 </xml>
937
938 <xml name="cv_shuffle">
939 <param argument="shuffle" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolfalse" checked="false" label="Whether to shuffle data before splitting" />
940 </xml>
941
942 <xml name="cv_test_size" token_value="0.2">
943 <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 "/>
944 </xml>
945
946 <xml name="cv_groups" >
947 <section name="groups_selector" title="Groups column selector" expanded="true">
948 <param name="infile_g" type="data" format="tabular" label="Choose dataset containing groups info:"/>
949 <param name="header_g" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolfalse" checked="False" label="Does the dataset contain header:" />
950 <conditional name="column_selector_options_g">
951 <expand macro="samples_column_selector_options" column_option="selected_column_selector_option_g" col_name="col_g" multiple="False" infile="infile_g"/>
952 </conditional>
953 </section>
954 </xml>
955
956 <xml name="feature_selection_algorithms">
957 <option value="SelectKBest" selected="true">SelectKBest - Select features according to the k highest scores</option>
958 <option value="GenericUnivariateSelect">GenericUnivariateSelect - Univariate feature selector with configurable strategy</option>
959 <option value="SelectPercentile">SelectPercentile - Select features according to a percentile of the highest scores</option>
960 <option value="SelectFpr">SelectFpr - Filter: Select the p-values below alpha based on a FPR test</option>
961 <option value="SelectFdr">SelectFdr - Filter: Select the p-values for an estimated false discovery rate</option>
962 <option value="SelectFwe">SelectFwe - Filter: Select the p-values corresponding to Family-wise error rate</option>
963 <option value="VarianceThreshold">VarianceThreshold - Feature selector that removes all low-variance features</option>
964 <option value="SelectFromModel">SelectFromModel - Meta-transformer for selecting features based on importance weights</option>
965 <option value="RFE">RFE - Feature ranking with recursive feature elimination</option>
966 <option value="RFECV">RFECV - Feature ranking with recursive feature elimination and cross-validated selection of the best number of features</option>
967 <yield/>
968 </xml>
969
970 <xml name="feature_selection_algorithm_details">
971 <when value="GenericUnivariateSelect">
972 <expand macro="feature_selection_score_function" />
973 <section name="options" title="Advanced Options" expanded="False">
974 <param argument="mode" type="select" label="Feature selection mode">
975 <option value="percentile">percentile</option>
976 <option value="k_best">k_best</option>
977 <option value="fpr">fpr</option>
978 <option value="fdr">fdr</option>
979 <option value="fwe">fwe</option>
980 </param>
981 <param argument="param" type="float" value="" optional="true" label="Parameter of the corresponding mode" help="float or int depending on the feature selection mode" />
982 </section>
983 </when>
984 <when value="SelectPercentile">
985 <expand macro="feature_selection_score_function" />
986 <section name="options" title="Advanced Options" expanded="False">
987 <param argument="percentile" type="integer" value="10" optional="True" label="Percent of features to keep" />
988 </section>
989 </when>
990 <when value="SelectKBest">
991 <expand macro="feature_selection_score_function" />
992 <section name="options" title="Advanced Options" expanded="False">
993 <param argument="k" type="integer" value="10" optional="True" label="Number of top features to select" help="No 'all' option is supported." />
994 </section>
995 </when>
996 <when value="SelectFpr">
997 <expand macro="feature_selection_score_function" />
998 <section name="options" title="Advanced Options" expanded="False">
999 <param argument="alpha" type="float" value="" optional="True" label="Alpha" help="The highest p-value for features to be kept."/>
1000 </section>
1001 </when>
1002 <when value="SelectFdr">
1003 <expand macro="feature_selection_score_function" />
1004 <section name="options" title="Advanced Options" expanded="False">
1005 <param argument="alpha" type="float" value="" optional="True" label="Alpha" help="The highest uncorrected p-value for features to keep."/>
1006 </section>
1007 </when>
1008 <when value="SelectFwe">
1009 <expand macro="feature_selection_score_function" />
1010 <section name="options" title="Advanced Options" expanded="False">
1011 <param argument="alpha" type="float" value="" optional="True" label="Alpha" help="The highest uncorrected p-value for features to keep."/>
1012 </section>
1013 </when>
1014 <when value="VarianceThreshold">
1015 <section name="options" title="Options" expanded="False">
1016 <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."/>
1017 </section>
1018 </when>
1019 </xml>
1020
1021 <xml name="feature_selection_SelectFromModel">
1022 <when value="SelectFromModel">
1023 <conditional name="model_inputter">
1024 <param name="input_mode" type="select" label="Construct a new estimator from a selection list?" >
1025 <option value="new" selected="true">Yes</option>
1026 <option value="prefitted">No. Load a prefitted estimator</option>
1027 </param>
1028 <when value="new">
1029 <expand macro="estimator_selector_fs"/>
1030 </when>
1031 <when value="prefitted">
1032 <param name="fitted_estimator" type="data" format='zip' label="Load a prefitted estimator" />
1033 </when>
1034 </conditional>
1035 <expand macro="feature_selection_SelectFromModel_options"/>
1036 </when>
1037 </xml>
1038
1039 <xml name="feature_selection_SelectFromModel_no_prefitted">
1040 <when value="SelectFromModel">
1041 <conditional name="model_inputter">
1042 <param name="input_mode" type="select" label="Construct a new estimator from a selection list?" >
1043 <option value="new" selected="true">Yes</option>
1044 </param>
1045 <when value="new">
1046 <expand macro="estimator_selector_all"/>
1047 </when>
1048 </conditional>
1049 <expand macro="feature_selection_SelectFromModel_options"/>
1050 </when>
1051 </xml>
1052
1053 <xml name="feature_selection_SelectFromModel_options">
1054 <section name="options" title="Advanced Options" expanded="False">
1055 <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'." />
1056 <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. " />
1057 <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."/>
1058 </section>
1059 </xml>
1060
1061 <xml name="feature_selection_RFE">
1062 <when value="RFE">
1063 <yield/>
1064 <section name="options" title="Advanced Options" expanded="False">
1065 <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." />
1066 <param argument="step" type="float" value="1" label="step" optional="true" help="Default = 1. " />
1067 <param argument="verbose" type="integer" value="0" label="verbose" help="Controls verbosity of output." />
1068 </section>
1069 </when>
1070 </xml>
1071
1072 <xml name="feature_selection_RFECV_fs">
1073 <when value="RFECV">
1074 <yield/>
1075 <section name="options" title="Advanced Options" expanded="False">
1076 <param argument="step" type="float" value="1" label="step" optional="true" help="Default = 1. " />
1077 <param argument="min_features_to_select" type="integer" value="1" optional="true" label="The minimum number of features to be selected"/>
1078 <expand macro="cv"/>
1079 <expand macro="scoring_selection"/>
1080 <param argument="verbose" type="integer" value="0" label="verbose" help="Controls verbosity of output." />
1081 </section>
1082 </when>
1083 </xml>
1084
1085 <xml name="feature_selection_RFECV_pipeline">
1086 <when value="RFECV">
1087 <yield/>
1088 <section name="options" title="Advanced Options" expanded="False">
1089 <param argument="step" type="float" value="1" label="step" optional="true" help="Default = 1. " />
1090 <param argument="min_features_to_select" type="integer" value="1" optional="true" label="The minimum number of features to be selected"/>
1091 <expand macro="cv_reduced"/>
1092 <!-- TODO: group splitter support-->
1093 <expand macro="scoring_selection"/>
1094 <param argument="verbose" type="integer" value="0" label="verbose" help="Controls verbosity of output." />
1095 </section>
1096 </when>
1097 </xml>
1098
1099 <xml name="feature_selection_DyRFECV_fs">
1100 <when value="DyRFECV">
1101 <yield/>
1102 <section name="options" title="Advanced Options" expanded="False">
1103 <param argument="step" type="text" size="30" value="1" label="step" optional="true" help="Default = 1. Support float, int and list." >
1104 <sanitizer>
1105 <valid initial="default">
1106 <add value="["/>
1107 <add value="]"/>
1108 </valid>
1109 </sanitizer>
1110 </param>
1111 <param argument="min_features_to_select" type="integer" value="1" optional="true" label="The minimum number of features to be selected"/>
1112 <expand macro="cv"/>
1113 <expand macro="scoring_selection"/>
1114 <param argument="verbose" type="integer" value="0" label="verbose" help="Controls verbosity of output." />
1115 </section>
1116 </when>
1117 </xml>
1118
1119 <xml name="feature_selection_pipeline">
1120 <!--compare to `feature_selection_fs`, no fitted estimator for SelectFromModel and no custom estimator for RFE and RFECV-->
1121 <conditional name="fs_algorithm_selector">
1122 <param name="selected_algorithm" type="select" label="Select a feature selection algorithm">
1123 <expand macro="feature_selection_algorithms"/>
1124 </param>
1125 <expand macro="feature_selection_algorithm_details"/>
1126 <expand macro="feature_selection_SelectFromModel_no_prefitted"/>
1127 <expand macro="feature_selection_RFE">
1128 <expand macro="estimator_selector_all"/>
1129 </expand>
1130 <expand macro="feature_selection_RFECV_pipeline">
1131 <expand macro="estimator_selector_all"/>
1132 </expand>
1133 <!-- TODO: add DyRFECV to pipeline-->
1134 </conditional>
1135 </xml>
1136
1137 <xml name="feature_selection_fs">
1138 <conditional name="fs_algorithm_selector">
1139 <param name="selected_algorithm" type="select" label="Select a feature selection algorithm">
1140 <expand macro="feature_selection_algorithms">
1141 <option value="DyRFECV">DyRFECV - Extended RFECV with changeable steps</option>
1142 </expand>
1143 </param>
1144 <expand macro="feature_selection_algorithm_details"/>
1145 <expand macro="feature_selection_SelectFromModel"/>
1146 <expand macro="feature_selection_RFE">
1147 <expand macro="estimator_selector_fs"/>
1148 </expand>
1149 <expand macro="feature_selection_RFECV_fs">
1150 <expand macro="estimator_selector_fs"/>
1151 </expand>
1152 <expand macro="feature_selection_DyRFECV_fs">
1153 <expand macro="estimator_selector_fs"/>
1154 </expand>
1155 </conditional>
1156 </xml>
1157
1158 <xml name="feature_selection_score_function">
1159 <param argument="score_func" type="select" label="Select a score function">
1160 <option value="chi2">chi2 - Compute chi-squared stats between each non-negative feature and class</option>
1161 <option value="f_classif">f_classif - Compute the ANOVA F-value for the provided sample</option>
1162 <option value="f_regression">f_regression - Univariate linear regression tests</option>
1163 <option value="mutual_info_classif">mutual_info_classif - Estimate mutual information for a discrete target variable</option>
1164 <option value="mutual_info_regression">mutual_info_regression - Estimate mutual information for a continuous target variable</option>
1165 </param>
1166 </xml>
1167
1168 <xml name="model_validation_common_options">
1169 <expand macro="cv"/>
1170 <!-- expand macro="verbose"/> -->
1171 <yield/>
1172 </xml>
1173
1174 <xml name="scoring_selection">
1175 <conditional name="scoring">
1176 <param name="primary_scoring" type="select" multiple="false" label="Select the primary metric (scoring):" help="Metric to refit the best estimator.">
1177 <option value="default" selected="true">default with estimator</option>
1178 <option value="accuracy">Classification -- 'accuracy'</option>
1179 <option value="balanced_accuracy">Classification -- 'balanced_accuracy'</option>
1180 <option value="average_precision">Classification -- 'average_precision'</option>
1181 <option value="f1">Classification -- 'f1'</option>
1182 <option value="f1_micro">Classification -- 'f1_micro'</option>
1183 <option value="f1_macro">Classification -- 'f1_macro'</option>
1184 <option value="f1_weighted">Classification -- 'f1_weighted'</option>
1185 <option value="f1_samples">Classification -- 'f1_samples'</option>
1186 <option value="neg_log_loss">Classification -- 'neg_log_loss'</option>
1187 <option value="precision">Classification -- 'precision'</option>
1188 <option value="precision_micro">Classification -- 'precision_micro'</option>
1189 <option value="precision_macro">Classification -- 'precision_macro'</option>
1190 <option value="precision_wighted">Classification -- 'precision_wighted'</option>
1191 <option value="precision_samples">Classification -- 'precision_samples'</option>
1192 <option value="recall">Classification -- 'recall'</option>
1193 <option value="recall_micro">Classification -- 'recall_micro'</option>
1194 <option value="recall_macro">Classification -- 'recall_macro'</option>
1195 <option value="recall_wighted">Classification -- 'recall_wighted'</option>
1196 <option value="recall_samples">Classification -- 'recall_samples'</option>
1197 <option value="roc_auc">Classification -- 'roc_auc'</option>
1198 <option value="explained_variance">Regression -- 'explained_variance'</option>
1199 <option value="neg_mean_absolute_error">Regression -- 'neg_mean_absolute_error'</option>
1200 <option value="neg_mean_squared_error">Regression -- 'neg_mean_squared_error'</option>
1201 <option value="neg_mean_squared_log_error">Regression -- 'neg_mean_squared_log_error'</option>
1202 <option value="neg_median_absolute_error">Regression -- 'neg_median_absolute_error'</option>
1203 <option value="r2">Regression -- 'r2'</option>
1204 <option value="binarize_auc_scorer">anomaly detection -- binarize_auc_scorer</option>
1205 <option value="binarize_average_precision_scorer">anomaly detection -- binarize_average_precision_scorer</option>
1206 </param>
1207 <when value="default"/>
1208 <when value="accuracy"><expand macro="secondary_scoring_selection_classification"/></when>
1209 <when value="balanced_accuracy"><expand macro="secondary_scoring_selection_classification"/></when>
1210 <when value="average_precision"><expand macro="secondary_scoring_selection_classification"/></when>
1211 <when value="f1"><expand macro="secondary_scoring_selection_classification"/></when>
1212 <when value="f1_micro"><expand macro="secondary_scoring_selection_classification"/></when>
1213 <when value="f1_macro"><expand macro="secondary_scoring_selection_classification"/></when>
1214 <when value="f1_weighted"><expand macro="secondary_scoring_selection_classification"/></when>
1215 <when value="f1_samples"><expand macro="secondary_scoring_selection_classification"/></when>
1216 <when value="neg_log_loss"><expand macro="secondary_scoring_selection_classification"/></when>
1217 <when value="precision"><expand macro="secondary_scoring_selection_classification"/></when>
1218 <when value="precision_micro"><expand macro="secondary_scoring_selection_classification"/></when>
1219 <when value="precision_macro"><expand macro="secondary_scoring_selection_classification"/></when>
1220 <when value="precision_wighted"><expand macro="secondary_scoring_selection_classification"/></when>
1221 <when value="precision_samples"><expand macro="secondary_scoring_selection_classification"/></when>
1222 <when value="recall"><expand macro="secondary_scoring_selection_classification"/></when>
1223 <when value="recall_micro"><expand macro="secondary_scoring_selection_classification"/></when>
1224 <when value="recall_macro"><expand macro="secondary_scoring_selection_classification"/></when>
1225 <when value="recall_wighted"><expand macro="secondary_scoring_selection_classification"/></when>
1226 <when value="recall_samples"><expand macro="secondary_scoring_selection_classification"/></when>
1227 <when value="roc_auc"><expand macro="secondary_scoring_selection_classification"/></when>
1228 <when value="explained_variance"><expand macro="secondary_scoring_selection_regression"/></when>
1229 <when value="neg_mean_absolute_error"><expand macro="secondary_scoring_selection_regression"/></when>
1230 <when value="neg_mean_squared_error"><expand macro="secondary_scoring_selection_regression"/></when>
1231 <when value="neg_mean_squared_log_error"><expand macro="secondary_scoring_selection_regression"/></when>
1232 <when value="neg_median_absolute_error"><expand macro="secondary_scoring_selection_regression"/></when>
1233 <when value="r2"><expand macro="secondary_scoring_selection_regression"/></when>
1234 <when value="binarize_auc_scorer"><expand macro="secondary_scoring_selection_anormaly"/></when>
1235 <when value="binarize_average_precision_scorer"><expand macro="secondary_scoring_selection_anormaly"/></when>
1236 </conditional>
1237 </xml>
1238
1239 <xml name="secondary_scoring_selection_classification">
1240 <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.">
1241 <option value="accuracy">Classification -- 'accuracy'</option>
1242 <option value="balanced_accuracy">Classification -- 'balanced_accuracy'</option>
1243 <option value="average_precision">Classification -- 'average_precision'</option>
1244 <option value="f1">Classification -- 'f1'</option>
1245 <option value="f1_micro">Classification -- 'f1_micro'</option>
1246 <option value="f1_macro">Classification -- 'f1_macro'</option>
1247 <option value="f1_weighted">Classification -- 'f1_weighted'</option>
1248 <option value="f1_samples">Classification -- 'f1_samples'</option>
1249 <option value="neg_log_loss">Classification -- 'neg_log_loss'</option>
1250 <option value="precision">Classification -- 'precision'</option>
1251 <option value="precision_micro">Classification -- 'precision_micro'</option>
1252 <option value="precision_macro">Classification -- 'precision_macro'</option>
1253 <option value="precision_wighted">Classification -- 'precision_wighted'</option>
1254 <option value="precision_samples">Classification -- 'precision_samples'</option>
1255 <option value="recall">Classification -- 'recall'</option>
1256 <option value="recall_micro">Classification -- 'recall_micro'</option>
1257 <option value="recall_macro">Classification -- 'recall_macro'</option>
1258 <option value="recall_wighted">Classification -- 'recall_wighted'</option>
1259 <option value="recall_samples">Classification -- 'recall_samples'</option>
1260 <option value="roc_auc">Classification -- 'roc_auc'</option>
1261 </param>
1262 </xml>
1263
1264 <xml name="secondary_scoring_selection_regression">
1265 <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.">
1266 <option value="explained_variance">Regression -- 'explained_variance'</option>
1267 <option value="neg_mean_absolute_error">Regression -- 'neg_mean_absolute_error'</option>
1268 <option value="neg_mean_squared_error">Regression -- 'neg_mean_squared_error'</option>
1269 <option value="neg_mean_squared_log_error">Regression -- 'neg_mean_squared_log_error'</option>
1270 <option value="neg_median_absolute_error">Regression -- 'neg_median_absolute_error'</option>
1271 <option value="r2">Regression -- 'r2'</option>
1272 </param>
1273 </xml>
1274
1275 <xml name="secondary_scoring_selection_anormaly">
1276 <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.">
1277 <option value="binarize_auc_scorer">anomaly detection -- binarize_auc_scorer</option>
1278 <option value="binarize_average_precision_scorer">anomaly detection -- binarize_average_precision_scorer</option>
1279 </param>
1280 </xml>
1281
1282 <xml name="pre_dispatch" token_type="hidden" token_default_value="all" token_help="Number of predispatched jobs for parallel execution">
1283 <param argument="pre_dispatch" type="@TYPE@" value="@DEFAULT_VALUE@" optional="true" label="pre_dispatch" help="@HELP@"/>
1284 </xml>
1285
1286 <xml name="search_cv_estimator">
1287 <param name="infile_estimator" type="data" format="zip" label="Choose the dataset containing pipeline/estimator object"/>
1288 <section name="search_params_builder" title="Search parameters Builder" expanded="true">
1289 <param name="infile_params" type="data" format="tabular" label="Choose the dataset containing parameter names"/>
1290 <repeat name="param_set" min="1" max="30" title="Parameter settings for search:">
1291 <param name="sp_name" type="select" label="Choose a parameter name (with current value)">
1292 <options from_dataset="infile_params" startswith="@">
1293 <column name="name" index="2"/>
1294 <column name="value" index="1"/>
1295 <filter type="unique_value" name="unique_param" column="1"/>
1296 <filter type="sort_by" name="sorted_param" column="2"/>
1297 </options>
1298 </param>
1299 <param name="sp_list" type="text" value="" optional="true" label="Search list" help="list or array-like, for example: [1, 10, 100, 1000], [True, False] and ['auto', 'sqrt', None]. See `help` section for more examples">
1300 <sanitizer>
1301 <valid initial="default">
1302 <add value="&apos;"/>
1303 <add value="&quot;"/>
1304 <add value="["/>
1305 <add value="]"/>
1306 </valid>
1307 </sanitizer>
1308 </param>
1309 </repeat>
1310 </section>
1311 </xml>
1312
1313 <xml name="search_cv_options">
1314 <expand macro="scoring_selection"/>
1315 <expand macro="model_validation_common_options"/>
1316 <!--expand macro="pre_dispatch" default_value="2*n_jobs" help="Controls the number of jobs that get dispatched during parallel execution"/-->
1317 <param argument="iid" type="boolean" truevalue="booltrue" falsevalue="boolfalse" checked="true" label="iid" help="If True, data is identically distributed across the folds"/>
1318 <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."/>
1319 <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."/>
1320 <param argument="return_train_score" type="boolean" truevalue="booltrue" falsevalue="boolfalse" checked="false" label="return_train_score" help=""/>
1321 </xml>
1322
1323 <xml name="estimator_module_options">
1324 <option value="svm" selected="true">sklearn.svm</option>
1325 <option value="linear_model">sklearn.linear_model</option>
1326 <option value="ensemble">sklearn.ensemble</option>
1327 <option value="naive_bayes">sklearn.naive_bayes</option>
1328 <option value="tree">sklearn.tree</option>
1329 <option value="neighbors">sklearn.neighbors</option>
1330 <option value="xgboost">xgboost</option>
1331 <yield/>
1332 </xml>
1333
1334 <xml name="estimator_suboptions">
1335 <when value="svm">
1336 <param name="selected_estimator" type="select" label="Choose estimator class:">
1337 <option value="LinearSVC" selected="true">LinearSVC</option>
1338 <option value="LinearSVR">LinearSVR</option>
1339 <option value="NuSVC">NuSVC</option>
1340 <option value="NuSVR">NuSVR</option>
1341 <option value="OneClassSVM">OneClassSVM</option>
1342 <option value="SVC">SVC</option>
1343 <option value="SVR">SVR</option>
1344 </param>
1345 <expand macro="estimator_params_text"/>
1346 </when>
1347 <when value="linear_model">
1348 <param name="selected_estimator" type="select" label="Choose estimator class:">
1349 <option value="ARDRegression" selected="true">ARDRegression</option>
1350 <option value="BayesianRidge">BayesianRidge</option>
1351 <option value="ElasticNet">ElasticNet</option>
1352 <option value="ElasticNetCV">ElasticNetCV</option>
1353 <option value="HuberRegressor">HuberRegressor</option>
1354 <option value="Lars">Lars</option>
1355 <option value="LarsCV">LarsCV</option>
1356 <option value="Lasso">Lasso</option>
1357 <option value="LassoCV">LassoCV</option>
1358 <option value="LassoLars">LassoLars</option>
1359 <option value="LassoLarsCV">LassoLarsCV</option>
1360 <option value="LassoLarsIC">LassoLarsIC</option>
1361 <option value="LinearRegression">LinearRegression</option>
1362 <option value="LogisticRegression">LogisticRegression</option>
1363 <option value="LogisticRegressionCV">LogisticRegressionCV</option>
1364 <option value="MultiTaskLasso">MultiTaskLasso</option>
1365 <option value="MultiTaskElasticNet">MultiTaskElasticNet</option>
1366 <option value="MultiTaskLassoCV">MultiTaskLassoCV</option>
1367 <option value="MultiTaskElasticNetCV">MultiTaskElasticNetCV</option>
1368 <option value="OrthogonalMatchingPursuit">OrthogonalMatchingPursuit</option>
1369 <option value="OrthogonalMatchingPursuitCV">OrthogonalMatchingPursuitCV</option>
1370 <option value="PassiveAggressiveClassifier">PassiveAggressiveClassifier</option>
1371 <option value="PassiveAggressiveRegressor">PassiveAggressiveRegressor</option>
1372 <option value="Perceptron">Perceptron</option>
1373 <option value="RANSACRegressor">RANSACRegressor</option>
1374 <option value="Ridge">Ridge</option>
1375 <option value="RidgeClassifier">RidgeClassifier</option>
1376 <option value="RidgeClassifierCV">RidgeClassifierCV</option>
1377 <option value="RidgeCV">RidgeCV</option>
1378 <option value="SGDClassifier">SGDClassifier</option>
1379 <option value="SGDRegressor">SGDRegressor</option>
1380 <option value="TheilSenRegressor">TheilSenRegressor</option>
1381 </param>
1382 <expand macro="estimator_params_text"/>
1383 </when>
1384 <when value="ensemble">
1385 <param name="selected_estimator" type="select" label="Choose estimator class:">
1386 <option value="AdaBoostClassifier" selected="true">AdaBoostClassifier</option>
1387 <option value="AdaBoostRegressor">AdaBoostRegressor</option>
1388 <option value="BaggingClassifier">BaggingClassifier</option>
1389 <option value="BaggingRegressor">BaggingRegressor</option>
1390 <option value="ExtraTreesClassifier">ExtraTreesClassifier</option>
1391 <option value="ExtraTreesRegressor">ExtraTreesRegressor</option>
1392 <option value="GradientBoostingClassifier">GradientBoostingClassifier</option>
1393 <option value="GradientBoostingRegressor">GradientBoostingRegressor</option>
1394 <option value="IsolationForest">IsolationForest</option>
1395 <option value="RandomForestClassifier">RandomForestClassifier</option>
1396 <option value="RandomForestRegressor">RandomForestRegressor</option>
1397 <option value="RandomTreesEmbedding">RandomTreesEmbedding</option>
1398 <!--option value="VotingClassifier">VotingClassifier</option-->
1399 </param>
1400 <expand macro="estimator_params_text"/>
1401 </when>
1402 <when value="naive_bayes">
1403 <param name="selected_estimator" type="select" label="Choose estimator class:">
1404 <option value="BernoulliNB" selected="true">BernoulliNB</option>
1405 <option value="GaussianNB">GaussianNB</option>
1406 <option value="MultinomialNB">MultinomialNB</option>
1407 </param>
1408 <expand macro="estimator_params_text"/>
1409 </when>
1410 <when value="tree">
1411 <param name="selected_estimator" type="select" label="Choose estimator class:">
1412 <option value="DecisionTreeClassifier" selected="true">DecisionTreeClassifier</option>
1413 <option value="DecisionTreeRegressor">DecisionTreeRegressor</option>
1414 <option value="ExtraTreeClassifier">ExtraTreeClassifier</option>
1415 <option value="ExtraTreeRegressor">ExtraTreeRegressor</option>
1416 </param>
1417 <expand macro="estimator_params_text"/>
1418 </when>
1419 <when value="neighbors">
1420 <param name="selected_estimator" type="select" label="Choose estimator class:">
1421 <option value="KNeighborsClassifier" selected="true">KNeighborsClassifier</option>
1422 <option value="KNeighborsRegressor">KNeighborsRegressor</option>
1423 <!--option value="BallTree">BallTree</option-->
1424 <!--option value="KDTree">KDTree</option-->
1425 <option value="KernelDensity">KernelDensity</option>
1426 <option value="LocalOutlierFactor">LocalOutlierFactor</option>
1427 <option value="RadiusNeighborsClassifier">RadiusNeighborsClassifier</option>
1428 <option value="RadiusNeighborsRegressor">RadiusNeighborsRegressor</option>
1429 <option value="NearestCentroid">NearestCentroid</option>
1430 <option value="NearestNeighbors">NearestNeighbors</option>
1431 </param>
1432 <expand macro="estimator_params_text"/>
1433 </when>
1434 <when value="xgboost">
1435 <param name="selected_estimator" type="select" label="Choose estimator class:">
1436 <option value="XGBRegressor" selected="true">XGBRegressor</option>
1437 <option value="XGBClassifier">XGBClassifier</option>
1438 </param>
1439 <expand macro="estimator_params_text"/>
1440 </when>
1441 <yield/>
1442 </xml>
1443
1444 <xml name="estimator_selector_all">
1445 <conditional name="estimator_selector">
1446 <param name="selected_module" type="select" label="Choose the module that contains target estimator:" >
1447 <expand macro="estimator_module_options"/>
1448 </param>
1449 <expand macro="estimator_suboptions"/>
1450 </conditional>
1451 </xml>
1452
1453 <xml name="estimator_selector_fs">
1454 <conditional name="estimator_selector">
1455 <param name="selected_module" type="select" label="Choose the module that contains target estimator:" >
1456 <expand macro="estimator_module_options">
1457 <option value="custom_estimator">Load a custom estimator</option>
1458 </expand>
1459 </param>
1460 <expand macro="estimator_suboptions">
1461 <when value="custom_estimator">
1462 <param name="c_estimator" type="data" format="zip" label="Choose the dataset containing the custom estimator or pipeline:"/>
1463 </when>
1464 </expand>
1465 </conditional>
1466 </xml>
1467
1468 <xml name="estimator_params_text" token_label="Type in parameter settings if different from default:" token_default_value=''
1469 token_help="Dictionary-capable, e.g., C=1, kernel='linear'. No double quotes. Leave this box blank for default estimator.">
1470 <param name="text_params" type="text" value="@DEFAULT_VALUE@" optional="true" label="@LABEL@" help="@HELP@">
1471 <sanitizer>
1472 <valid initial="default">
1473 <add value="&apos;"/>
1474 </valid>
1475 </sanitizer>
1476 </param>
1477 </xml>
1478
1479 <xml name="kernel_approximation_all">
1480 <conditional name="kernel_approximation_selector">
1481 <param name="select_algorithm" type="select" label="Choose a kernel approximation algorithm:">
1482 <option value="Nystroem" selected="true">Nystroem</option>
1483 <option value="RBFSampler">RBFSampler</option>
1484 <option value="AdditiveChi2Sampler">AdditiveChi2Sampler</option>
1485 <option value="SkewedChi2Sampler">SkewedChi2Sampler</option>
1486 </param>
1487 <when value="Nystroem">
1488 <expand macro="estimator_params_text"
1489 help="Default(=blank): coef0=None, degree=None, gamma=None, kernel='rbf', kernel_params=None, n_components=100, random_state=None. No double quotes"/>
1490 </when>
1491 <when value="RBFSampler">
1492 <expand macro="estimator_params_text"
1493 help="Default(=blank): gamma=1.0, n_components=100, random_state=None."/>
1494 </when>
1495 <when value="AdditiveChi2Sampler">
1496 <expand macro="estimator_params_text"
1497 help="Default(=blank): sample_interval=None, sample_steps=2."/>
1498 </when>
1499 <when value="SkewedChi2Sampler">
1500 <expand macro="estimator_params_text"
1501 help="Default(=blank): n_components=100, random_state=None, skewedness=1.0."/>
1502 </when>
1503 </conditional>
1504 </xml>
1505
1506 <xml name="matrix_decomposition_all">
1507 <conditional name="matrix_decomposition_selector">
1508 <param name="select_algorithm" type="select" label="Choose a matrix decomposition algorithm:">
1509 <option value="DictionaryLearning" selected="true">DictionaryLearning</option>
1510 <option value="FactorAnalysis">FactorAnalysis</option>
1511 <option value="FastICA">FastICA</option>
1512 <option value="IncrementalPCA">IncrementalPCA</option>
1513 <option value="KernelPCA">KernelPCA</option>
1514 <option value="LatentDirichletAllocation">LatentDirichletAllocation</option>
1515 <option value="MiniBatchDictionaryLearning">MiniBatchDictionaryLearning</option>
1516 <option value="MiniBatchSparsePCA">MiniBatchSparsePCA</option>
1517 <option value="NMF">NMF</option>
1518 <option value="PCA">PCA</option>
1519 <option value="SparsePCA">SparsePCA</option>
1520 <!--option value="SparseCoder">SparseCoder</option-->
1521 <option value="TruncatedSVD">TruncatedSVD</option>
1522 </param>
1523 <when value="DictionaryLearning">
1524 <expand macro="estimator_params_text"
1525 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."/>
1526 </when>
1527 <when value="FactorAnalysis">
1528 <expand macro="estimator_params_text"
1529 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."/>
1530 </when>
1531 <when value="FastICA">
1532 <expand macro="estimator_params_text"
1533 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."/>
1534 </when>
1535 <when value="IncrementalPCA">
1536 <expand macro="estimator_params_text"
1537 help="Default(=blank): batch_size=None, copy=True, n_components=None, whiten=False."/>
1538 </when>
1539 <when value="KernelPCA">
1540 <expand macro="estimator_params_text"
1541 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."/>
1542 </when>
1543 <when value="LatentDirichletAllocation">
1544 <expand macro="estimator_params_text"
1545 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."/>
1546 </when>
1547 <when value="MiniBatchDictionaryLearning">
1548 <expand macro="estimator_params_text"
1549 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."/>
1550 </when>
1551 <when value="MiniBatchSparsePCA">
1552 <expand macro="estimator_params_text"
1553 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."/>
1554 </when>
1555 <when value="NMF">
1556 <expand macro="estimator_params_text"
1557 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."/>
1558 </when>
1559 <when value="PCA">
1560 <expand macro="estimator_params_text"
1561 help="Default(=blank): copy=True, iterated_power='auto', n_components=None, random_state=None, svd_solver='auto', tol=0.0, whiten=False."/>
1562 </when>
1563 <when value="SparsePCA">
1564 <expand macro="estimator_params_text"
1565 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."/>
1566 </when>
1567 <when value="TruncatedSVD">
1568 <expand macro="estimator_params_text"
1569 help="Default(=blank): algorithm='randomized', n_components=2, n_iter=5, random_state=None, tol=0.0."/>
1570 </when>
1571 </conditional>
1572 </xml>
1573
1574 <xml name="FeatureAgglomeration">
1575 <conditional name="FeatureAgglomeration_selector">
1576 <param name="select_algorithm" type="select" label="Choose the algorithm:">
1577 <option value="FeatureAgglomeration" selected="true">FeatureAgglomeration</option>
1578 </param>
1579 <when value="FeatureAgglomeration">
1580 <expand macro="estimator_params_text"
1581 help="Default(=blank): affinity='euclidean', compute_full_tree='auto', connectivity=None, linkage='ward', memory=None, n_clusters=2, pooling_func=np.mean."/>
1582 </when>
1583 </conditional>
1584 </xml>
1585
1586 <xml name="skrebate">
1587 <conditional name="skrebate_selector">
1588 <param name="select_algorithm" type="select" label="Choose the algorithm:">
1589 <option value="ReliefF">ReliefF</option>
1590 <option value="SURF">SURF</option>
1591 <option value="SURFstar">SURFstar</option>
1592 <option value="MultiSURF">MultiSURF</option>
1593 <option value="MultiSURFstar">MultiSURFstar</option>
1594 <!--option value="TuRF">TuRF</option> -->
1595 </param>
1596 <when value="ReliefF">
1597 <expand macro="estimator_params_text"
1598 help="Default(=blank): discrete_threshold=10, n_features_to_select=10, n_neighbors=100, verbose=False."/>
1599 </when>
1600 <when value="SURF">
1601 <expand macro="estimator_params_text"
1602 help="Default(=blank): discrete_threshold=10, n_features_to_select=10, verbose=False."/>
1603 </when>
1604 <when value="SURFstar">
1605 <expand macro="estimator_params_text"
1606 help="Default(=blank): discrete_threshold=10, n_features_to_select=10, verbose=False."/>
1607 </when>
1608 <when value="MultiSURF">
1609 <expand macro="estimator_params_text"
1610 help="Default(=blank): discrete_threshold=10, n_features_to_select=10, verbose=False."/>
1611 </when>
1612 <when value="MultiSURFstar">
1613 <expand macro="estimator_params_text"
1614 help="Default(=blank): discrete_threshold=10, n_features_to_select=10, verbose=False."/>
1615 </when>
1616 <!--when value="TuRF">
1617 <expand macro="estimator_params_text"
1618 help="Default(=blank): core_algorithm='ReliefF', discrete_threshold=10, n_features_to_select=10, n_neighbors=100, pct=0.5, verbose=False."/>
1619 </when> -->
1620 </conditional>
1621 </xml>
1622
1623 <xml name="imbalanced_learn_sampling">
1624 <conditional name="imblearn_selector">
1625 <param name="select_algorithm" type="select" label="Choose the algorithm:">
1626 <option value="under_sampling.ClusterCentroids" selected="true">under_sampling.ClusterCentroids</option>
1627 <option value="under_sampling.CondensedNearestNeighbour">under_sampling.CondensedNearestNeighbour</option>
1628 <option value="under_sampling.EditedNearestNeighbours">under_sampling.EditedNearestNeighbours</option>
1629 <option value="under_sampling.RepeatedEditedNearestNeighbours">under_sampling.RepeatedEditedNearestNeighbours</option>
1630 <option value="under_sampling.AllKNN">under_sampling.AllKNN</option>
1631 <option value="under_sampling.InstanceHardnessThreshold">under_sampling.InstanceHardnessThreshold</option>
1632 <option value="under_sampling.NearMiss">under_sampling.NearMiss</option>
1633 <option value="under_sampling.NeighbourhoodCleaningRule">under_sampling.NeighbourhoodCleaningRule</option>
1634 <option value="under_sampling.OneSidedSelection">under_sampling.OneSidedSelection</option>
1635 <option value="under_sampling.RandomUnderSampler">under_sampling.RandomUnderSampler</option>
1636 <option value="under_sampling.TomekLinks">under_sampling.TomekLinks</option>
1637 <option value="over_sampling.ADASYN">over_sampling.ADASYN</option>
1638 <option value="over_sampling.RandomOverSampler">over_sampling.RandomOverSampler</option>
1639 <option value="over_sampling.SMOTE">over_sampling.SMOTE</option>
1640 <option value="over_sampling.SVMSMOTE">over_sampling.SVMSMOTE</option>
1641 <option value="over_sampling.BorderlineSMOTE">over_sampling.BorderlineSMOTE</option>
1642 <option value="over_sampling.SMOTENC">over_sampling.SMOTENC</option>
1643 <option value="combine.SMOTEENN">combine.SMOTEENN</option>
1644 <option value="combine.SMOTETomek">combine.SMOTETomek</option>
1645 <option value="Z_RandomOverSampler">Z_RandomOverSampler - for regression</option>
1646 </param>
1647 <when value="under_sampling.ClusterCentroids">
1648 <expand macro="estimator_params_text"
1649 help="Default(=blank): sampling_strategy='auto', random_state=None, estimator=None, voting='auto'."/>
1650 </when>
1651 <when value="under_sampling.CondensedNearestNeighbour">
1652 <expand macro="estimator_params_text"
1653 help="Default(=blank): sampling_strategy='auto', random_state=None, n_neighbors=None, n_seeds_S=1."/>
1654 </when>
1655 <when value="under_sampling.EditedNearestNeighbours">
1656 <expand macro="estimator_params_text"
1657 help="Default(=blank): sampling_strategy='auto', random_state=None, n_neighbors=3, max_iter=100, kind_sel='all'."/>
1658 </when>
1659 <when value="under_sampling.RepeatedEditedNearestNeighbours">
1660 <expand macro="estimator_params_text"
1661 help="Default(=blank): sampling_strategy='auto', random_state=None, n_neighbors=3, max_iter=100, kind_sel='all'."/>
1662 </when>
1663 <when value="under_sampling.AllKNN">
1664 <expand macro="estimator_params_text"
1665 help="Default(=blank): sampling_strategy='auto', random_state=None, n_neighbors=3, kind_sel='all', allow_minority=False."/>
1666 </when>
1667 <when value="under_sampling.InstanceHardnessThreshold">
1668 <expand macro="estimator_params_text"
1669 help="Default(=blank): estimator=None, sampling_strategy='auto', random_state=None, cv=5."/>
1670 </when>
1671 <when value="under_sampling.NearMiss">
1672 <expand macro="estimator_params_text"
1673 help="Default(=blank): sampling_strategy='auto', random_state=None, version=1, n_neighbors=3, n_neighbors_ver3=3."/>
1674 </when>
1675 <when value="under_sampling.NeighbourhoodCleaningRule">
1676 <expand macro="estimator_params_text"
1677 help="Default(=blank): sampling_strategy='auto', random_state=None, n_neighbors=3, kind_sel='all', threshold_cleaning=0.5."/>
1678 </when>
1679 <when value="under_sampling.OneSidedSelection">
1680 <expand macro="estimator_params_text"
1681 help="Default(=blank): sampling_strategy='auto', random_state=None, n_neighbors=None, n_seeds_S=1."/>
1682 </when>
1683 <when value="under_sampling.RandomUnderSampler">
1684 <expand macro="estimator_params_text"
1685 help="Default(=blank): sampling_strategy='auto', random_state=None, replacement=False."/>
1686 </when>
1687 <when value="under_sampling.TomekLinks">
1688 <expand macro="estimator_params_text"
1689 help="Default(=blank): sampling_strategy='auto', random_state=None."/>
1690 </when>
1691 <when value="over_sampling.ADASYN">
1692 <expand macro="estimator_params_text"
1693 help="Default(=blank): sampling_strategy='auto', random_state=None, n_neighbors=5."/>
1694 </when>
1695 <when value="over_sampling.RandomOverSampler">
1696 <expand macro="estimator_params_text"
1697 help="Default(=blank): sampling_strategy='auto', random_state=None."/>
1698 </when>
1699 <when value="over_sampling.SMOTE">
1700 <expand macro="estimator_params_text"
1701 help="Default(=blank): sampling_strategy='auto', random_state=None, k_neighbors=5."/>
1702 </when>
1703 <when value="over_sampling.SVMSMOTE">
1704 <expand macro="estimator_params_text"
1705 help="Default(=blank): sampling_strategy='auto', k_neighbors=5, m_neighbors=10, out_step=0.5, random_state=None, svm_estimator=None."/>
1706 </when>
1707 <when value="over_sampling.BorderlineSMOTE">
1708 <expand macro="estimator_params_text"
1709 help="Default(=blank): sampling_strategy='auto', k_neighbors=5, kind='borderline-1', m_neighbors=10, random_state=None."/>
1710 </when>
1711 <when value="over_sampling.SMOTENC">
1712 <expand macro="estimator_params_text"
1713 help="Default: categorical_features=[], sampling_strategy='auto', random_state=None, k_neighbors=5."/>
1714 </when>
1715 <when value="combine.SMOTEENN">
1716 <expand macro="estimator_params_text"
1717 help="Default(=blank): sampling_strategy='auto', random_state=None, smote=None, enn=None."/>
1718 </when>
1719 <when value="combine.SMOTETomek">
1720 <expand macro="estimator_params_text"
1721 help="Default(=blank): sampling_strategy='auto', random_state=None, smote=None, tomek=None."/>
1722 </when>
1723 <when value="Z_RandomOverSampler">
1724 <expand macro="estimator_params_text"
1725 help="Default(=blank): sampling_strategy='auto', random_state=None, negative_thres=0, positive_thres=-1."/>
1726 </when>
1727 </conditional>
1728 </xml>
1729
1730 <xml name="stacking_ensemble_inputs">
1731 <section name="options" title="Advanced Options" expanded="false">
1732 <yield/>
1733 <param argument="use_features_in_secondary" type="boolean" truevalue="booltrue" falsevalue="boolfalse" checked="false"/>
1734 <param argument="store_train_meta_features" type="boolean" truevalue="booltrue" falsevalue="boolfalse" checked="false"/>
1735 </section>
1736 </xml>
1737
1738 <xml name="stacking_base_estimator">
1739 <conditional name="estimator_selector">
1740 <param name="selected_module" type="select" label="Choose the module that contains target estimator:" >
1741 <expand macro="estimator_module_options">
1742 <option value="custom_estimator">Load a custom estimator</option>
1743 </expand>
1744 </param>
1745 <expand macro="estimator_suboptions">
1746 <when value="custom_estimator">
1747 <param name="c_estimator" type="data" format="zip" label="Choose the dataset containing the custom estimator or pipeline"/>
1748 </when>
1749 </expand>
1750 </conditional>
1751 </xml>
1752
1753 <!-- Outputs -->
1754
1755 <xml name="output">
1756 <outputs>
1757 <data format="tabular" name="outfile_predict">
1758 <filter>selected_tasks['selected_task'] == 'load'</filter>
1759 </data>
1760 <data format="zip" name="outfile_fit" label="${tool.name}.${selected_tasks.selected_algorithms.selected_algorithm}">
1761 <filter>selected_tasks['selected_task'] == 'train'</filter>
1762 </data>
1763 </outputs>
1764 </xml>
1765
1766 <!--Citations-->
1767 <xml name="eden_citation">
1768 <citations>
1769 <citation type="doi">10.5281/zenodo.15094</citation>
1770 </citations>
1771 </xml>
1772
1773 <xml name="sklearn_citation">
1774 <citations>
1775 <citation type="bibtex">
1776 @article{scikit-learn,
1777 title={Scikit-learn: Machine Learning in {P}ython},
1778 author={Pedregosa, F. and Varoquaux, G. and Gramfort, A. and Michel, V.
1779 and Thirion, B. and Grisel, O. and Blondel, M. and Prettenhofer, P.
1780 and Weiss, R. and Dubourg, V. and Vanderplas, J. and Passos, A. and
1781 Cournapeau, D. and Brucher, M. and Perrot, M. and Duchesnay, E.},
1782 journal={Journal of Machine Learning Research},
1783 volume={12},
1784 pages={2825--2830},
1785 year={2011}
1786 }
1787 </citation>
1788 <yield/>
1789 </citations>
1790 </xml>
1791
1792 <xml name="scipy_citation">
1793 <citations>
1794 <citation type="bibtex">
1795 @Misc{,
1796 author = {Eric Jones and Travis Oliphant and Pearu Peterson and others},
1797 title = {{SciPy}: Open source scientific tools for {Python}},
1798 year = {2001--},
1799 url = "http://www.scipy.org/",
1800 note = {[Online; accessed 2016-04-09]}
1801 }
1802 </citation>
1803 </citations>
1804 </xml>
1805
1806 <xml name="skrebate_citation">
1807 <citation type="bibtex">
1808 @article{DBLP:journals/corr/abs-1711-08477,
1809 author = {Ryan J. Urbanowicz and
1810 Randal S. Olson and
1811 Peter Schmitt and
1812 Melissa Meeker and
1813 Jason H. Moore},
1814 title = {Benchmarking Relief-Based Feature Selection Methods},
1815 journal = {CoRR},
1816 volume = {abs/1711.08477},
1817 year = {2017},
1818 url = {http://arxiv.org/abs/1711.08477},
1819 archivePrefix = {arXiv},
1820 eprint = {1711.08477},
1821 timestamp = {Mon, 13 Aug 2018 16:46:04 +0200},
1822 biburl = {https://dblp.org/rec/bib/journals/corr/abs-1711-08477},
1823 bibsource = {dblp computer science bibliography, https://dblp.org}
1824 }
1825 </citation>
1826 </xml>
1827
1828 <xml name="xgboost_citation">
1829 <citation type="bibtex">
1830 @inproceedings{Chen:2016:XST:2939672.2939785,
1831 author = {Chen, Tianqi and Guestrin, Carlos},
1832 title = {{XGBoost}: A Scalable Tree Boosting System},
1833 booktitle = {Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining},
1834 series = {KDD '16},
1835 year = {2016},
1836 isbn = {978-1-4503-4232-2},
1837 location = {San Francisco, California, USA},
1838 pages = {785--794},
1839 numpages = {10},
1840 url = {http://doi.acm.org/10.1145/2939672.2939785},
1841 doi = {10.1145/2939672.2939785},
1842 acmid = {2939785},
1843 publisher = {ACM},
1844 address = {New York, NY, USA},
1845 keywords = {large-scale machine learning},
1846 }
1847 </citation>
1848 </xml>
1849
1850 <xml name="imblearn_citation">
1851 <citation type="bibtex">
1852 @article{JMLR:v18:16-365,
1853 author = {Guillaume Lema{{\^i}}tre and Fernando Nogueira and Christos K. Aridas},
1854 title = {Imbalanced-learn: A Python Toolbox to Tackle the Curse of Imbalanced Datasets in Machine Learning},
1855 journal = {Journal of Machine Learning Research},
1856 year = {2017},
1857 volume = {18},
1858 number = {17},
1859 pages = {1-5},
1860 url = {http://jmlr.org/papers/v18/16-365.html}
1861 }
1862 </citation>
1863 </xml>
1864
1865 </macros>