Mercurial > repos > bgruening > sklearn_numeric_clustering

comparison main_macros.xml @ 6:4edccd1eaaf0 draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
planemo upload for repository https://github.com/bgruening/galaxytools/tools/sklearn commit 0e582cf1f3134c777cce3aa57d71b80ed95e6ba9
author bgruening
date Fri, 16 Feb 2018 09:13:42 -0500
parents 7dc70333811d
children 7094ca215c2d
comparison
equal deleted inserted replaced
5:7dc70333811d 6:4edccd1eaaf0
10 y = data.iloc[:,cols].values 10 y = data.iloc[:,cols].values
11 return y 11 return y
12 </token> 12 </token>
13 13
14 <xml name="python_requirements"> 14 <xml name="python_requirements">
15 <requirements> 15 <requirements>
16 <requirement type="package" version="0.2.1b">eden</requirement> 16 <requirement type="package" version="2.7">python</requirement>
17 <yield /> 17 <requirement type="package" version="0.19.1">scikit-learn</requirement>
18 </requirements> 18 <requirement type="package" version="0.22.0">pandas</requirement>
19 <yield />
20 </requirements>
19 </xml> 21 </xml>
20 22
21 <xml name="macro_stdio"> 23 <xml name="macro_stdio">
22 <stdio> 24 <stdio>
23 <exit_code range="1:" level="fatal" description="Error occurred. Please check Tool Standard Error"/> 25 <exit_code range="1:" level="fatal" description="Error occurred. Please check Tool Standard Error"/>
88 <yield /> 90 <yield />
89 </section> 91 </section>
90 </xml> 92 </xml>
91 93
92 94
95 <!--Generalized Linear Models-->
96 <xml name="loss" token_help=" " token_select="false">
97 <param argument="loss" type="select" label="Loss function" help="@HELP@">
98 <option value="squared_loss" selected="@SELECT@">squared loss</option>
99 <option value="huber">huber</option>
100 <option value="epsilon_insensitive">epsilon insensitive</option>
101 <option value="squared_epsilon_insensitive">squared epsilon insensitive</option>
102 <yield/>
103 </param>
104 </xml>
105
106 <xml name="penalty" token_help=" ">
107 <param argument="penalty" type="select" label="Penalty (regularization term)" help="@HELP@">
108 <option value="l2" selected="true">l2</option>
109 <option value="l1">l1</option>
110 <option value="elasticnet">elastic net</option>
111 <option value="none">none</option>
112 <yield/>
113 </param>
114 </xml>
115
116 <xml name="l1_ratio" token_default_value="0.15" token_help=" ">
117 <param argument="l1_ratio" type="float" value="@DEFAULT_VALUE@" label="Elastic Net mixing parameter" help="@HELP@"/>
118 </xml>
119
120 <xml name="epsilon" token_default_value="0.1" token_help="Used if loss is ‘huber’, ‘epsilon_insensitive’, or ‘squared_epsilon_insensitive’. ">
121 <param argument="epsilon" type="float" value="@DEFAULT_VALUE@" label="Epsilon (epsilon-sensitive loss functions only)" help="@HELP@"/>
122 </xml>
123
124 <xml name="learning_rate_s" token_help=" " token_selected1="false" token_selected2="false">
125 <param argument="learning_rate" type="select" optional="true" label="Learning rate schedule" help="@HELP@">
126 <option value="optimal" selected="@SELECTED1@">optimal</option>
127 <option value="constant">constant</option>
128 <option value="invscaling" selected="@SELECTED2@">inverse scaling</option>
129 <yield/>
130 </param>
131 </xml>
132
133 <xml name="eta0" token_default_value="0.0" token_help="Used with ‘constant’ or ‘invscaling’ schedules. ">
134 <param argument="eta0" type="float" value="@DEFAULT_VALUE@" label="Initial learning rate" help="@HELP@"/>
135 </xml>
136
137 <xml name="power_t" token_default_value="0.5" token_help=" ">
138 <param argument="power_t" type="float" value="@DEFAULT_VALUE@" label="Exponent for inverse scaling learning rate" help="@HELP@"/>
139 </xml>
140
141 <xml name="normalize" token_checked="false" token_help=" ">
142 <param argument="normalize" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolfalse" checked="@CHECKED@" label="Normalize samples before training" help=" "/>
143 </xml>
144
145 <xml name="copy_X" token_checked="true" token_help=" ">
146 <param argument="copy_X" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolfalse" checked="@CHECKED@" label="Use a copy of samples" help="If false, samples would be overwritten. "/>
147 </xml>
148
149 <xml name="ridge_params">
150 <expand macro="normalize"/>
151 <expand macro="alpha" default_value="1.0"/>
152 <expand macro="fit_intercept"/>
153 <expand macro="max_iter" default_value=""/>
154 <expand macro="tol" default_value="0.001" help_text="Precision of the solution. "/>
155 <!--class_weight-->
156 <expand macro="copy_X"/>
157 <param argument="solver" type="select" value="" label="Solver to use in the computational routines" help=" ">
158 <option value="auto" selected="true">auto</option>
159 <option value="svd">svd</option>
160 <option value="cholesky">cholesky</option>
161 <option value="lsqr">lsqr</option>
162 <option value="sparse_cg">sparse_cg</option>
163 <option value="sag">sag</option>
164 </param>
165 <expand macro="random_state"/>
166 </xml>
167
93 <!--Ensemble methods--> 168 <!--Ensemble methods-->
94 <xml name="n_estimators" token_default_value="10" token_help=" "> 169 <xml name="n_estimators" token_default_value="10" token_help=" ">
95 <param argument="n_estimators" type="integer" optional="true" value="@DEFAULT_VALUE@" label="Number of trees in the forest" help="@HELP@"/> 170 <param argument="n_estimators" type="integer" optional="true" value="@DEFAULT_VALUE@" label="Number of trees in the forest" help="@HELP@"/>
96 </xml> 171 </xml>
97 172
104 </xml> 179 </xml>
105 180
106 <xml name="min_samples_leaf" token_default_value="1" token_help=" "> 181 <xml name="min_samples_leaf" token_default_value="1" token_help=" ">
107 <param argument="min_samples_leaf" type="integer" optional="true" value="@DEFAULT_VALUE@" label="Minimum number of samples in newly created leaves" help="@HELP@"/> 182 <param argument="min_samples_leaf" type="integer" optional="true" value="@DEFAULT_VALUE@" label="Minimum number of samples in newly created leaves" help="@HELP@"/>
108 </xml> 183 </xml>
109 184
110 <xml name="min_weight_fraction_leaf" token_default_value="0.0" token_help=" "> 185 <xml name="min_weight_fraction_leaf" token_default_value="0.0" token_help=" ">
111 <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@"/> 186 <param argument="min_weight_fraction_leaf" type="float" optional="true" value="@DEFAULT_VALUE@" label="Minimum weighted fraction of the input samples required to be at a leaf node" help="@HELP@"/>
112 </xml> 187 </xml>
113 188
114 <xml name="max_leaf_nodes" token_default_value="" token_help=" "> 189 <xml name="max_leaf_nodes" token_default_value="" token_help=" ">
115 <param argument="max_leaf_nodes" type="integer" optional="true" value="@DEFAULT_VALUE@" label="Maximum number of leaf nodes in best-first method" help="@HELP@"/> 190 <param argument="max_leaf_nodes" type="integer" optional="true" value="@DEFAULT_VALUE@" label="Maximum number of leaf nodes in best-first method" help="@HELP@"/>
116 </xml> 191 </xml>
117 192
118 <xml name="bootstrap" token_checked="true" token_help=" "> 193 <xml name="bootstrap" token_checked="true" token_help=" ">
119 <param argument="bootstrap" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolflase" checked="@CHECKED@" label="Use bootstrap samples for building trees." help="@HELP@"/> 194 <param argument="bootstrap" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolflase" checked="@CHECKED@" label="Use bootstrap samples for building trees." help="@HELP@"/>
120 </xml> 195 </xml>
121 196
122 <xml name="criterion" token_help=" "> 197 <xml name="criterion" token_help=" ">
123 <param argument="criterion" type="select" label="Function to measure the quality of a split" help=" "> 198 <param argument="criterion" type="select" label="Function to measure the quality of a split" help=" ">
124 <option value="gini" selected="true">Gini impurity</option> 199 <option value="gini" selected="true">Gini impurity</option>
125 <option value="entropy">Information gain</option> 200 <option value="entropy">Information gain</option>
126 <yield/> 201 <yield/>
127 </param> 202 </param>
128 </xml> 203 </xml>
129 204
130 <xml name="oob_score" token_checked="flase" token_help=" "> 205 <xml name="oob_score" token_checked="false" token_help=" ">
131 <param argument="oob_score" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolflase" checked="@CHECKED@" label="Use out-of-bag samples to estimate the generalization error" help="@HELP@"/> 206 <param argument="oob_score" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolfalse" checked="@CHECKED@" label="Use out-of-bag samples to estimate the generalization error" help="@HELP@"/>
132 </xml> 207 </xml>
133 208
134 <xml name="max_features" token_default_value="auto" token_help="This could be an integer, float, string, or None. For more information please refer to help. "> 209 <xml name="max_features" token_default_value="auto" token_help="This could be an integer, float, string, or None. For more information please refer to help. ">
135 <param argument="max_features" type="text" optional="true" value="@DEFAULT_VALUE@" label="Number of features for finding the best split" help="@HELP@"/> 210 <param argument="max_features" type="text" optional="true" value="@DEFAULT_VALUE@" label="Number of features for finding the best split" help="@HELP@"/>
136 </xml> 211 </xml>
137 212
138 <xml name="learning_rate" token_default_value="1.0" token_help=" "> 213 <xml name="learning_rate" token_default_value="1.0" token_help=" ">
139 <param argument="learning_rate" type="float" optional="true" value="@DEFAULT_VALUE@" label="Learning rate" help="@HELP@"/> 214 <param argument="learning_rate" type="float" optional="true" value="@DEFAULT_VALUE@" label="Learning rate" help="@HELP@"/>
140 </xml> 215 </xml>
141 216
148 <xml name="n_clusters" token_default_value="8"> 223 <xml name="n_clusters" token_default_value="8">
149 <param argument="n_clusters" type="integer" optional="true" value="@DEFAULT_VALUE@" label="Number of clusters" help=" "/> 224 <param argument="n_clusters" type="integer" optional="true" value="@DEFAULT_VALUE@" label="Number of clusters" help=" "/>
150 </xml> 225 </xml>
151 226
152 <xml name="fit_intercept" token_checked="true"> 227 <xml name="fit_intercept" token_checked="true">
153 <param argument="fit_intercept" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolflase" checked="@CHECKED@" label="Estimate the intercept" help="If false, the data is assumed to be already centered."/> 228 <param argument="fit_intercept" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolfalse" checked="@CHECKED@" label="Estimate the intercept" help="If false, the data is assumed to be already centered."/>
154 </xml> 229 </xml>
155 230
156 <xml name="n_iter" token_default_value="5" token_help_text="The number of passes over the training data (aka epochs). "> 231 <xml name="n_iter" token_default_value="5" token_help_text="The number of passes over the training data (aka epochs). ">
157 <param argument="n_iter" type="integer" optional="true" value="@DEFAULT_VALUE@" label="Number of iterations" help="@HELP_TEXT@"/> 232 <param argument="n_iter" type="integer" optional="true" value="@DEFAULT_VALUE@" label="Number of iterations" help="@HELP_TEXT@"/>
158 </xml> 233 </xml>
159 234
160 <xml name="shuffle" token_checked="true" token_help_text=" " token_label="Shuffle data after each iteration"> 235 <xml name="shuffle" token_checked="true" token_help_text=" " token_label="Shuffle data after each iteration">
161 <param argument="shuffle" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolflase" checked="@CHECKED@" label="@LABEL@" help="@HELP_TEXT@"/> 236 <param argument="shuffle" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolfalse" checked="@CHECKED@" label="@LABEL@" help="@HELP_TEXT@"/>
162 </xml> 237 </xml>
163 238
164 <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."> 239 <xml name="random_state" token_default_value="" token_help_text="Integer number. The seed of the pseudo random number generator to use when shuffling the data. A fixed seed allows reproducible results.">
165 <param argument="random_state" type="integer" optional="true" value="@DEFAULT_VALUE@" label="Random seed number" help="@HELP_TEXT@"/> 240 <param argument="random_state" type="integer" optional="true" value="@DEFAULT_VALUE@" label="Random seed number" help="@HELP_TEXT@"/>
166 </xml> 241 </xml>
167 242
168 <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."> 243 <xml name="warm_start" token_checked="true" token_help_text="When set to True, reuse the solution of the previous call to fit as initialization,otherwise, just erase the previous solution.">
169 <param argument="warm_start" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolflase" checked="@CHECKED@" label="Perform warm start" help="@HELP_TEXT@"/> 244 <param argument="warm_start" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolfalse" checked="@CHECKED@" label="Perform warm start" help="@HELP_TEXT@"/>
170 </xml> 245 </xml>
171 246
172 <xml name="C" token_default_value="1.0" token_help_text="Penalty parameter C of the error term."> 247 <xml name="C" token_default_value="1.0" token_help_text="Penalty parameter C of the error term.">
173 <param argument="C" type="float" optional="true" value="@DEFAULT_VALUE@" label="Penalty parameter" help="@HELP_TEXT@"/> 248 <param argument="C" type="float" optional="true" value="@DEFAULT_VALUE@" label="Penalty parameter" help="@HELP_TEXT@"/>
174 </xml> 249 </xml>
228 <param argument="pos_label" type="integer" optional="true" value="@DEFAULT_VALUE@" label="Label of the positive class" help=" "/> 303 <param argument="pos_label" type="integer" optional="true" value="@DEFAULT_VALUE@" label="Label of the positive class" help=" "/>
229 </xml> 304 </xml>
230 305
231 <xml name="average"> 306 <xml name="average">
232 <param argument="average" type="select" optional="true" label="Averaging type" help=" "> 307 <param argument="average" type="select" optional="true" label="Averaging type" help=" ">
233 <option value="micro" help="Calculate metrics globally by counting the total true positives, false negatives and false positives.">micro</option> 308 <option value="micro">Calculate metrics globally by counting the total true positives, false negatives and false positives. (micro)</option>
234 <option value="samples" help="Calculate metrics for each instance, and find their average (only meaningful for multilabel).">samples</option> 309 <option value="samples">Calculate metrics for each instance, and find their average. Only meaningful for multilabel. (samples)</option>
235 <!--option value="macro" help=""></option--> 310 <option value="macro">Calculate metrics for each label, and find their unweighted mean. This does not take label imbalance into account. (macro)</option>
236 <!--option value="weighted" help=""></option--> 311 <option value="weighted">Calculate metrics for each label, and find their average, weighted by support (the number of true instances for each label). This alters ‘macro’ to account for label imbalance; it can result in an F-score that is not between precision and recall. (weighted)</option>
312 <option value="None">None</option>
237 <yield/> 313 <yield/>
238 </param> 314 </param>
239 </xml> 315 </xml>
240 316
241 <xml name="beta"> 317 <xml name="beta">
242 <param argument="beta" type="float" value="1.0" label="The strength of recall versus precision in the F-score" help=" "/> 318 <param argument="beta" type="float" value="1.0" label="The strength of recall versus precision in the F-score" help=" "/>
243 </xml> 319 </xml>
244 320
245 321
246 <!--Data interface--> 322 <!--Data interface-->
247 <xml name="tabular_input"> 323 <xml name="tabular_input">
248 <param name="infile" type="data" format="tabular" label="Data file with numeric values"/> 324 <param name="infile" type="data" format="tabular" label="Data file with numeric values"/>
249 <param name="start_column" type="data_column" data_ref="infile" optional="True" label="Select a subset of data. Start column:" /> 325 <param name="start_column" type="data_column" data_ref="infile" optional="True" label="Select a subset of data. Start column:" />
250 <param name="end_column" type="data_column" data_ref="infile" optional="True" label="End column:" /> 326 <param name="end_column" type="data_column" data_ref="infile" optional="True" label="End column:" />
256 <param name="infile2" type="data" format="@FORMAT2@" label="@LABEL2@" help="@HELP2@"/> 332 <param name="infile2" type="data" format="@FORMAT2@" label="@LABEL2@" help="@HELP2@"/>
257 <param name="col2" multiple="@MULTIPLE2@" type="data_column" data_ref="infile2" label="Select target column(s):"/> 333 <param name="col2" multiple="@MULTIPLE2@" type="data_column" data_ref="infile2" label="Select target column(s):"/>
258 <yield/> 334 <yield/>
259 </xml> 335 </xml>
260 336
337 <xml name="samples_tabular" token_multiple1="False" token_multiple2="False">
338 <param name="infile1" type="data" format="tabular" label="Training samples dataset:"/>
339 <param name="col1" multiple="@MULTIPLE1@" type="data_column" data_ref="infile1" label="Select target column(s):"/>
340 <param name="infile2" type="data" format="tabular" label="Dataset containing class labels:"/>
341 <param name="col2" multiple="@MULTIPLE2@" type="data_column" data_ref="infile2" label="Select target column(s):"/>
342 <yield/>
343 </xml>
261 344
262 <xml name="clf_inputs_extended" token_label1=" " token_label2=" " token_multiple="False"> 345 <xml name="clf_inputs_extended" token_label1=" " token_label2=" " token_multiple="False">
263 <conditional name="true_columns"> 346 <conditional name="true_columns">
264 <param name="selected_input1" type="select" label="Select the input type of true labels dataset:"> 347 <param name="selected_input1" type="select" label="Select the input type of true labels dataset:">
265 <option value="tabular" selected="true">Tabular</option> 348 <option value="tabular" selected="true">Tabular</option>
297 380
298 <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."> 381 <xml name="multiple_input" token_name="input_files" token_max_num="10" token_format="txt" token_label="Sparse matrix file (.mtx, .txt)" token_help_text="Specify a sparse matrix file in .txt format.">
299 <repeat name="@NAME@" min="1" max="@MAX_NUM@" title="Select input file(s):"> 382 <repeat name="@NAME@" min="1" max="@MAX_NUM@" title="Select input file(s):">
300 <param name="input" type="data" format="@FORMAT@" label="@LABEL@" help="@HELP_TEXT@"/> 383 <param name="input" type="data" format="@FORMAT@" label="@LABEL@" help="@HELP_TEXT@"/>
301 </repeat> 384 </repeat>
302 </xml> 385 </xml>
303 386
304 <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=""> 387 <xml name="sparse_target" token_label1="Select a sparse matrix:" token_label2="Select the tabular containing true labels:" token_multiple="False" token_format1="txt" token_format2="tabular" token_help1="" token_help2="">
305 <param name="infile1" type="data" format="@FORMAT1@" label="@LABEL1@" help="@HELP1@"/> 388 <param name="infile1" type="data" format="@FORMAT1@" label="@LABEL1@" help="@HELP1@"/>
306 <param name="infile2" type="data" format="@FORMAT2@" label="@LABEL2@" help="@HELP2@"/> 389 <param name="infile2" type="data" format="@FORMAT2@" label="@LABEL2@" help="@HELP2@"/>
307 <param name="col2" multiple="@MULTIPLE@" type="data_column" data_ref="infile2" label="Select target column(s):"/> 390 <param name="col2" multiple="@MULTIPLE@" type="data_column" data_ref="infile2" label="Select target column(s):"/>
312 <param name="selected_input" type="select" label="Select input type:"> 395 <param name="selected_input" type="select" label="Select input type:">
313 <option value="tabular" selected="true">tabular data</option> 396 <option value="tabular" selected="true">tabular data</option>
314 <option value="sparse">sparse matrix</option> 397 <option value="sparse">sparse matrix</option>
315 </param> 398 </param>
316 <when value="tabular"> 399 <when value="tabular">
317 <expand macro="sample_cols" multiple1="true"/> 400 <expand macro="samples_tabular" multiple1="true"/>
318 </when> 401 </when>
319 <when value="sparse"> 402 <when value="sparse">
320 <expand macro="sparse_target"/> 403 <expand macro="sparse_target"/>
321 </when> 404 </when>
322 </conditional> 405 </conditional>
330 <!--Advanced options--> 413 <!--Advanced options-->
331 <xml name="nn_advanced_options"> 414 <xml name="nn_advanced_options">
332 <section name="options" title="Advanced Options" expanded="False"> 415 <section name="options" title="Advanced Options" expanded="False">
333 <yield/> 416 <yield/>
334 <param argument="weights" type="select" label="Weight function" help="Used in prediction."> 417 <param argument="weights" type="select" label="Weight function" help="Used in prediction.">
335 <option value="uniform" selected="true" help="Uniform weights. All points in each neighborhood are weighted equally.">Uniform</option> 418 <option value="uniform" selected="true">Uniform weights. All points in each neighborhood are weighted equally. (Uniform)</option>
336 <option value="distance" help="Weight points by the inverse of their distance.">Distance</option> 419 <option value="distance">Weight points by the inverse of their distance. (Distance)</option>
337 </param> 420 </param>
338 <param argument="algorithm" type="select" label="Neighbor selection algorithm" help=" "> 421 <param argument="algorithm" type="select" label="Neighbor selection algorithm" help=" ">
339 <option value="auto" selected="true">Auto</option> 422 <option value="auto" selected="true">Auto</option>
340 <option value="ball_tree">BallTree</option> 423 <option value="ball_tree">BallTree</option>
341 <option value="kd_tree">KDTree</option> 424 <option value="kd_tree">KDTree</option>
358 <option value="sigmoid">sigmoid</option> 441 <option value="sigmoid">sigmoid</option>
359 <option value="precomputed">precomputed</option> 442 <option value="precomputed">precomputed</option>
360 </param> 443 </param>
361 <param argument="degree" type="integer" optional="true" value="3" label="Degree of the polynomial (polynomial kernel only)" help="Ignored by other kernels. dafault : 3 "/> 444 <param argument="degree" type="integer" optional="true" value="3" label="Degree of the polynomial (polynomial kernel only)" help="Ignored by other kernels. dafault : 3 "/>
362 <!--TODO: param argument="gamma" float, optional (default=’auto’) --> 445 <!--TODO: param argument="gamma" float, optional (default=’auto’) -->
363 <param argument="coef0" type="float" optional="true" value="0.0" label="Zero coefficient (polynomial and sigmoid kernels only)" help="Independent term in kernel function. dafault: 0.0 "/> 446 <param argument="coef0" type="float" optional="true" value="0.0" label="Zero coefficient (polynomial and sigmoid kernels only)"
364 <param argument="shrinking" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolflase" checked="true" label="Use the shrinking heuristic" help=" "/> 447 help="Independent term in kernel function. dafault: 0.0 "/>
365 <param argument="probability" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolflase" checked="false" label="Enable probability estimates. " help="This must be enabled prior to calling fit, and will slow down that method."/> 448 <param argument="shrinking" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolfalse" checked="true"
449 label="Use the shrinking heuristic" help=" "/>
450 <param argument="probability" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolfalse" checked="false"
451 label="Enable probability estimates. " help="This must be enabled prior to calling fit, and will slow down that method."/>
366 <!-- param argument="cache_size"--> 452 <!-- param argument="cache_size"-->
367 <!--expand macro="class_weight"/--> 453 <!--expand macro="class_weight"/-->
368 <expand macro="tol" default_value="0.001" help_text="Tolerance for stopping criterion. "/> 454 <expand macro="tol" default_value="0.001" help_text="Tolerance for stopping criterion. "/>
369 <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."/> 455 <expand macro="max_iter" default_value="-1" label="Solver maximum number of iterations" help_text="Hard limit on iterations within solver, or -1 for no limit."/>
370 <!--param argument="decision_function_shape"--> 456 <!--param argument="decision_function_shape"-->
371 <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."/> 457 <expand macro="random_state" help_text="Integer number. The seed of the pseudo random number generator to use when shuffling the data for probability estimation. A fixed seed allows reproducible results."/>
372 </section> 458 </section>
373 </xml> 459 </xml>
393 <!--param argument="eigen_tol"--> 479 <!--param argument="eigen_tol"-->
394 <param argument="assign_labels" type="select" label="Assign labels" help="The strategy to use to assign labels in the embedding space."> 480 <param argument="assign_labels" type="select" label="Assign labels" help="The strategy to use to assign labels in the embedding space.">
395 <option value="kmeans" selected="true">kmeans</option> 481 <option value="kmeans" selected="true">kmeans</option>
396 <option value="discretize">discretize</option> 482 <option value="discretize">discretize</option>
397 </param> 483 </param>
398 <param argument="degree" type="integer" optional="true" value="3" label="Degree of the polynomial (polynomial kernel only)" help="Ignored by other kernels. dafault : 3 "/> 484 <param argument="degree" type="integer" optional="true" value="3"
399 <param argument="coef0" type="integer" optional="true" value="1" label="Zero coefficient (polynomial and sigmoid kernels only)" help="Ignored by other kernels. dafault : 1 "/> 485 label="Degree of the polynomial (polynomial kernel only)" help="Ignored by other kernels. dafault : 3 "/>
486 <param argument="coef0" type="integer" optional="true" value="1"
487 label="Zero coefficient (polynomial and sigmoid kernels only)" help="Ignored by other kernels. dafault : 1 "/>
400 <!--param argument="kernel_params"--> 488 <!--param argument="kernel_params"-->
401 </section> 489 </section>
402 </xml> 490 </xml>
403 491
404 <xml name="minibatch_kmeans_advanced_options"> 492 <xml name="minibatch_kmeans_advanced_options">
405 <section name="options" title="Advanced Options" expanded="False"> 493 <section name="options" title="Advanced Options" expanded="False">
406 <expand macro="n_clusters"/> 494 <expand macro="n_clusters"/>
407 <expand macro="init"/> 495 <expand macro="init"/>
408 <expand macro="n_init" default_value="3"/> 496 <expand macro="n_init" default_value="3"/>
409 <expand macro="max_iter" default_value="100"/> 497 <expand macro="max_iter" default_value="100"/>
410 <expand macro="tol" help_text="Early stopping heuristics based on normalized center change. To disable set to 0.0 ."/> 498 <expand macro="tol" help_text="Early stopping heuristics based on normalized center change. To disable set to 0.0 ."/>
411 <expand macro="random_state"/> 499 <expand macro="random_state"/>
412 <param argument="batch_size" type="integer" optional="true" value="100" label="Batch size" help="Size of the mini batches."/> 500 <param argument="batch_size" type="integer" optional="true" value="100" label="Batch size" help="Size of the mini batches."/>
413 <!--param argument="compute_labels"--> 501 <!--param argument="compute_labels"-->
414 <param argument="max_no_improvement" type="integer" optional="true" value="10" label="Maximum number of improvement attempts" help=" 502 <param argument="max_no_improvement" type="integer" optional="true" value="10" label="Maximum number of improvement attempts" help="
415 Convergence detection based on inertia (the consecutive number of mini batches that doe not yield an improvement on the smoothed inertia). 503 Convergence detection based on inertia (the consecutive number of mini batches that doe not yield an improvement on the smoothed inertia).
426 <expand macro="n_init"/> 514 <expand macro="n_init"/>
427 <expand macro="max_iter"/> 515 <expand macro="max_iter"/>
428 <expand macro="tol" default_value="0.0001" help_text="Relative tolerance with regards to inertia to declare convergence."/> 516 <expand macro="tol" default_value="0.0001" help_text="Relative tolerance with regards to inertia to declare convergence."/>
429 <!--param argument="precompute_distances"/--> 517 <!--param argument="precompute_distances"/-->
430 <expand macro="random_state"/> 518 <expand macro="random_state"/>
431 <param argument="copy_x" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolflase" 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."/> 519 <param argument="copy_x" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolfalse" checked="true" label="Use a copy of data for precomputing distances" help="Mofifying the original data introduces small numerical differences caused by subtracting and then adding the data mean."/>
432 </section> 520 </section>
433 </xml> 521 </xml>
434 522
435 <xml name="birch_advanced_options"> 523 <xml name="birch_advanced_options">
436 <section name="options" title="Advanced Options" expanded="False"> 524 <section name="options" title="Advanced Options" expanded="False">
555 </expand> 643 </expand>
556 </section> 644 </section>
557 </when> 645 </when>
558 <when value="euclidean_distances"> 646 <when value="euclidean_distances">
559 <section name="options" title="Advanced Options" expanded="False"> 647 <section name="options" title="Advanced Options" expanded="False">
560 <param argument="squared" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolflase" checked="false" label="Return squared Euclidean distances" help=" "/> 648 <param argument="squared" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolfalse" checked="false"
649 label="Return squared Euclidean distances" help=" "/>
561 </section> 650 </section>
562 </when> 651 </when>
563 </xml> 652 </xml>
564 653
565 <xml name="argmin_distance_condition"> 654 <xml name="argmin_distance_condition">
587 676
588 <xml name="sparse_preprocessor_options"> 677 <xml name="sparse_preprocessor_options">
589 <when value="Binarizer"> 678 <when value="Binarizer">
590 <expand macro="multitype_input" format="tabular,txt" help="Tabular and sparse datasets are supporetd."/> 679 <expand macro="multitype_input" format="tabular,txt" help="Tabular and sparse datasets are supporetd."/>
591 <section name="options" title="Advanced Options" expanded="False"> 680 <section name="options" title="Advanced Options" expanded="False">
592 <param argument="copy" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolflase" checked="true" label="Use a copy of data for precomputing binarization" help=" "/> 681 <param argument="copy" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolfalse" checked="true"
593 <param argument="threshold" type="float" optional="true" value="0.0" label="Threshold" help="Feature values below or equal to this are replaced by 0, above it by 1. Threshold may not be less than 0 for operations on sparse matrices. "/> 682 label="Use a copy of data for precomputing binarization" help=" "/>
683 <param argument="threshold" type="float" optional="true" value="0.0"
684 label="Threshold"
685 help="Feature values below or equal to this are replaced by 0, above it by 1. Threshold may not be less than 0 for operations on sparse matrices. "/>
594 </section> 686 </section>
595 </when> 687 </when>
596 <when value="Imputer"> 688 <when value="Imputer">
597 <expand macro="multitype_input" format="tabular,txt" help="Tabular and sparse datasets are supporetd."/> 689 <expand macro="multitype_input" format="tabular,txt" help="Tabular and sparse datasets are supporetd."/>
598 <section name="options" title="Advanced Options" expanded="False"> 690 <section name="options" title="Advanced Options" expanded="False">
599 <param argument="copy" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolflase" checked="true" label="Use a copy of data for precomputing imputation" help=" "/> 691 <param argument="copy" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolfalse" checked="true"
692 label="Use a copy of data for precomputing imputation" help=" "/>
600 <param argument="strategy" type="select" optional="true" label="Imputation strategy" help=" "> 693 <param argument="strategy" type="select" optional="true" label="Imputation strategy" help=" ">
601 <option value="mean" selected="true">Replace missing values using the mean along the axis</option> 694 <option value="mean" selected="true">Replace missing values using the mean along the axis</option>
602 <option value="median">Replace missing values using the median along the axis</option> 695 <option value="median">Replace missing values using the median along the axis</option>
603 <option value="most_frequent">Replace missing using the most frequent value along the axis</option> 696 <option value="most_frequent">Replace missing using the most frequent value along the axis</option>
604 </param> 697 </param>
605 <param argument="missing_values" type="text" optional="true" value="NaN" label="Placeholder for missing values" help="For missing values encoded as numpy.nan, use the string value “NaN”"/> 698 <param argument="missing_values" type="text" optional="true" value="NaN"
606 <param argument="axis" type="boolean" optional="true" truevalue="1" falsevalue="0" label="Impute along axis = 1" help="If fasle, axis = 0 is selected for imputation. "/> 699 label="Placeholder for missing values" help="For missing values encoded as numpy.nan, use the string value “NaN”"/>
700 <param argument="axis" type="boolean" optional="true" truevalue="1" falsevalue="0"
701 label="Impute along axis = 1" help="If fasle, axis = 0 is selected for imputation. "/>
607 <!--param argument="axis" type="select" optional="true" label="The axis along which to impute" help=" "> 702 <!--param argument="axis" type="select" optional="true" label="The axis along which to impute" help=" ">
608 <option value="0" selected="true">Impute along columns</option> 703 <option value="0" selected="true">Impute along columns</option>
609 <option value="1">Impute along rows</option> 704 <option value="1">Impute along rows</option>
610 </param--> 705 </param-->
611 </section> 706 </section>
612 </when> 707 </when>
613 <when value="StandardScaler"> 708 <when value="StandardScaler">
614 <expand macro="multitype_input"/> 709 <expand macro="multitype_input"/>
615 <section name="options" title="Advanced Options" expanded="False"> 710 <section name="options" title="Advanced Options" expanded="False">
616 <param argument="copy" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolflase" checked="true" label="Use a copy of data for performing inplace scaling" help=" "/> 711 <param argument="copy" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolfalse" checked="true"
617 <param argument="with_mean" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolflase" checked="true" label="Center the data before scaling" help=" "/> 712 label="Use a copy of data for performing inplace scaling" help=" "/>
618 <param argument="with_std" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolflase" checked="true" label="Scale the data to unit variance (or unit standard deviation)" help=" "/> 713 <param argument="with_mean" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolfalse" checked="true"
714 label="Center the data before scaling" help=" "/>
715 <param argument="with_std" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolfalse" checked="true"
716 label="Scale the data to unit variance (or unit standard deviation)" help=" "/>
619 </section> 717 </section>
620 </when> 718 </when>
621 <when value="MaxAbsScaler"> 719 <when value="MaxAbsScaler">
622 <expand macro="multitype_input" format="tabular,txt" help="Tabular and sparse datasets are supporetd."/> 720 <expand macro="multitype_input" format="tabular,txt" help="Tabular and sparse datasets are supporetd."/>
623 <section name="options" title="Advanced Options" expanded="False"> 721 <section name="options" title="Advanced Options" expanded="False">
624 <param argument="copy" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolflase" checked="true" label="Use a copy of data for precomputing scaling" help=" "/> 722 <param argument="copy" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolfalse" checked="true"
723 label="Use a copy of data for precomputing scaling" help=" "/>
625 </section> 724 </section>
626 </when> 725 </when>
627 <when value="Normalizer"> 726 <when value="Normalizer">
628 <expand macro="multitype_input" format="tabular,txt" help="Tabular and sparse datasets are supporetd."/> 727 <expand macro="multitype_input" format="tabular,txt" help="Tabular and sparse datasets are supporetd."/>
629 <section name="options" title="Advanced Options" expanded="False"> 728 <section name="options" title="Advanced Options" expanded="False">
630 <param argument="norm" type="select" optional="true" label="The norm to use to normalize non zero samples" help=" "> 729 <param argument="norm" type="select" optional="true" label="The norm to use to normalize non zero samples" help=" ">
631 <option value="l1" selected="true">l1</option> 730 <option value="l1" selected="true">l1</option>
632 <option value="l2">l2</option> 731 <option value="l2">l2</option>
633 <option value="max">max</option> 732 <option value="max">max</option>
634 <param argument="copy" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolflase" checked="true" label="Use a copy of data for precomputing row normalization" help=" "/>
635 </param> 733 </param>
734 <param argument="copy" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolfalse" checked="true"
735 label="Use a copy of data for precomputing row normalization" help=" "/>
636 </section> 736 </section>
637 </when> 737 </when>
638 <yield/> 738 <yield/>
739 </xml>
740
741 <!-- Outputs -->
742
743 <xml name="output">
744 <outputs>
745 <data format="tabular" name="outfile_predict">
746 <filter>selected_tasks['selected_task'] == 'load'</filter>
747 </data>
748 <data format="zip" name="outfile_fit">
749 <filter>selected_tasks['selected_task'] == 'train'</filter>
750 </data>
751 </outputs>
639 </xml> 752 </xml>
640 753
641 754
642 <!--Citations--> 755 <!--Citations-->
643 <xml name="eden_citation"> 756 <xml name="eden_citation">