Mercurial > repos > bgruening > sklearn_clf_metrics

comparison main_macros.xml @ 0:8d7f8dc7c347 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 a9f28163f0d2e808e49c43a6df5a040706e79991
author bgruening
date Thu, 23 Jun 2016 15:26:39 -0400
parents
children 65bd390f50ae
comparison
equal deleted inserted replaced
-1:000000000000 0:8d7f8dc7c347
1 <macros>
2 <token name="@VERSION@">0.9</token>
3
4 <token name="@COLUMNS_FUNCTION@">
5 def columns(f,c):
6 data = pandas.read_csv(f, sep='\t', header=None, index_col=None, parse_dates=True, encoding=None, tupleize_cols=False)
7 cols = c.split (',')
8 cols = map(int, cols)
9 cols = list(map(lambda x: x - 1, cols))
10 y = data.iloc[:,cols].values
11 return y
12 </token>
13
14 <xml name="python_requirements">
15 <requirements>
16 <requirement type="package" version="0.2.1b">eden</requirement>
17 <yield />
18 </requirements>
19 </xml>
20
21 <xml name="macro_stdio">
22 <stdio>
23 <exit_code range="1:" level="fatal" description="Error occurred. Please check Tool Standard Error"/>
24 </stdio>
25 </xml>
26
27
28 <!--Generic interface-->
29 <xml name="train_loadConditional" token_train="tabular" token_data="tabular" token_model="txt">
30 <conditional name="selected_tasks">
31 <param name="selected_task" type="select" label="Select a Classification Task">
32 <option value="train" selected="true">Train a model</option>
33 <option value="load">Load a model and predict</option>
34 </param>
35 <when value="load">
36 <param name="infile_model" type="data" format="@MODEL@" label="Models" help="Select a model file."/>
37 <param name="infile_data" type="data" format="@DATA@" label="Data (tabular)" help="Select the dataset you want to classify."/>
38 <conditional name="prediction_options">
39 <param name="prediction_option" type="select" label="Select the type of prediction">
40 <option value="predict">Predict class labels</option>
41 <option value="advanced">Include advanced options</option>
42 </param>
43 <when value="predict">
44 </when>
45 <when value="advanced">
46 </when>
47 </conditional>
48 </when>
49 <when value="train">
50 <param name="infile_train" type="data" format="@TRAIN@" label="Training samples (tabular)"/>
51 <conditional name="selected_algorithms">
52 <yield />
53 </conditional>
54 </when>
55 </conditional>
56 </xml>
57
58 <xml name="sl_Conditional" token_train="tabular" token_data="tabular" token_model="txt">
59 <conditional name="selected_tasks">
60 <param name="selected_task" type="select" label="Select a Classification Task">
61 <option value="train" selected="true">Train a model</option>
62 <option value="load">Load a model and predict</option>
63 </param>
64 <when value="load">
65 <param name="infile_model" type="data" format="@MODEL@" label="Models" help="Select a model file."/>
66 <param name="infile_data" type="data" format="@DATA@" label="Data (tabular)" help="Select the dataset you want to classify."/>
67 <conditional name="prediction_options">
68 <param name="prediction_option" type="select" label="Select the type of prediction">
69 <option value="predict">Predict class labels</option>
70 <option value="advanced">Include advanced options</option>
71 </param>
72 <when value="predict">
73 </when>
74 <when value="advanced">
75 </when>
76 </conditional>
77 </when>
78 <when value="train">
79 <conditional name="selected_algorithms">
80 <yield />
81 </conditional>
82 </when>
83 </conditional>
84 </xml>
85
86 <xml name="advanced_section">
87 <section name="options" title="Advanced Options" expanded="False">
88 <yield />
89 </section>
90 </xml>
91
92
93 <!--Ensemble methods-->
94 <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@"/>
96 </xml>
97
98 <xml name="max_depth" token_default_value="" token_help=" ">
99 <param argument="max_depth" type="integer" optional="true" value="@DEFAULT_VALUE@" label="Maximum depth of the tree" help="@HELP@"/>
100 </xml>
101
102 <xml name="min_samples_split" token_default_value="2" token_help=" ">
103 <param argument="min_samples_split" type="integer" optional="true" value="@DEFAULT_VALUE@" label="Maximum depth of the tree" help="@HELP@"/>
104 </xml>
105
106 <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@"/>
108 </xml>
109
110 <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@"/>
112 </xml>
113
114 <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@"/>
116 </xml>
117
118 <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@"/>
120 </xml>
121
122 <xml name="criterion" token_help=" ">
123 <param argument="criterion" type="select" label="Function to measure the quality of a split" help=" ">
124 <option value="gini" selected="true">Gini impurity</option>
125 <option value="entropy">Information gain</option>
126 <yield/>
127 </param>
128 </xml>
129
130 <xml name="oob_score" token_checked="flase" 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@"/>
132 </xml>
133
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. ">
135 <param argument="max_features" type="text" optional="true" value="@DEFAULT_VALUE@" label="Number of features for finding the best split" help="@HELP@"/>
136 </xml>
137
138 <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@"/>
140 </xml>
141
142
143 <!--Parameters-->
144 <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.">
145 <param argument="tol" type="float" optional="true" value="@DEFAULT_VALUE@" label="Tolerance" help="@HELP_TEXT@"/>
146 </xml>
147
148 <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=" "/>
150 </xml>
151
152 <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."/>
154 </xml>
155
156 <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@"/>
158 </xml>
159
160 <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@"/>
162 </xml>
163
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.">
165 <param argument="random_state" type="integer" optional="true" value="@DEFAULT_VALUE@" label="Random seed number" help="@HELP_TEXT@"/>
166 </xml>
167
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.">
169 <param argument="warm_start" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolflase" checked="@CHECKED@" label="Perform warm start" help="@HELP_TEXT@"/>
170 </xml>
171
172 <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@"/>
174 </xml>
175
176 <!--xml name="class_weight" token_default_value="" token_help_text="">
177 <param argument="class_weight" type="" optional="true" value="@DEFAULT_VALUE@" label="" help="@HELP_TEXT@"/>
178 </xml-->
179
180 <xml name="alpha" token_default_value="0.0001" token_help_text="Constant that multiplies the regularization term if regularization is used. ">
181 <param argument="alpha" type="float" optional="true" value="@DEFAULT_VALUE@" label="Regularization coefficient" help="@HELP_TEXT@"/>
182 </xml>
183
184 <xml name="n_samples" token_default_value="100" token_help_text="The total number of points equally divided among clusters.">
185 <param argument="n_samples" type="integer" optional="true" value="@DEFAULT_VALUE@" label="Number of samples" help="@HELP_TEXT@"/>
186 </xml>
187
188 <xml name="n_features" token_default_value="2" token_help_text="Number of different numerical properties produced for each sample.">
189 <param argument="n_features" type="integer" optional="true" value="@DEFAULT_VALUE@" label="Number of features" help="@HELP_TEXT@"/>
190 </xml>
191
192 <xml name="noise" token_default_value="0.0" token_help_text="Floating point number. ">
193 <param argument="noise" type="float" optional="true" value="@DEFAULT_VALUE@" label="Standard deviation of the Gaussian noise added to the data" help="@HELP_TEXT@"/>
194 </xml>
195
196 <xml name="C" token_default_value="1.0" token_help_text="Penalty parameter C of the error term. ">
197 <param argument="C" type="float" optional="true" value="@DEFAULT_VALUE@" label="Penalty parameter" help="@HELP_TEXT@"/>
198 </xml>
199
200 <xml name="max_iter" token_default_value="300" token_label="Maximum number of iterations per single run" token_help_text=" ">
201 <param argument="max_iter" type="integer" optional="true" value="@DEFAULT_VALUE@" label="@LABEL@" help="@HELP_TEXT@"/>
202 </xml>
203
204 <xml name="n_init" token_default_value="10" >
205 <param argument="n_init" type="integer" optional="true" value="@DEFAULT_VALUE@" label="Number of runs with different centroid seeds" help=" "/>
206 </xml>
207
208 <xml name="init">
209 <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.">
210 <option value="k-means++">k-means++</option>
211 <option value="random">random</option>
212 </param>
213 </xml>
214
215 <xml name="gamma" token_default_value="1.0" token_label="Scaling parameter" token_help_text=" ">
216 <param argument="gamma" type="float" optional="true" value="@DEFAULT_VALUE@" label="@LABEL@" help="@HELP_TEXT@"/>
217 </xml>
218
219 <xml name="degree" token_default_value="3" token_label="Degree of the polynomial" token_help_text=" ">
220 <param argument="degree" type="integer" optional="true" value="@DEFAULT_VALUE@" label="@LABEL@" help="@HELP_TEXT@"/>
221 </xml>
222
223 <xml name="coef0" token_default_value="1" token_label="Zero coefficient" token_help_text=" ">
224 <param argument="coef0" type="integer" optional="true" value="@DEFAULT_VALUE@" label="@LABEL@" help="@HELP_TEXT@"/>
225 </xml>
226
227 <xml name="pos_label" token_default_value="">
228 <param argument="pos_label" type="integer" optional="true" value="@DEFAULT_VALUE@" label="Label of the positive class" help=" "/>
229 </xml>
230
231 <xml name="average">
232 <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>
234 <option value="samples" help="Calculate metrics for each instance, and find their average (only meaningful for multilabel).">samples</option>
235 <!--option value="macro" help=""></option-->
236 <!--option value="weighted" help=""></option-->
237 <yield/>
238 </param>
239 </xml>
240
241 <xml name="beta">
242 <param argument="beta" type="float" value="1.0" label="The strength of recall versus precision in the F-score" help=" "/>
243 </xml>
244
245
246 <!--Data interface-->
247 <xml name="tabular_input">
248 <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:" />
250 <param name="end_column" type="data_column" data_ref="infile" optional="True" label="End column:" />
251 </xml>
252
253 <xml name="sample_cols" token_label1="File containing true class labels:" token_label2="File containing predicted class labels:" token_multiple1="False" token_multiple2="False" token_format1="tabular" token_format2="tabular" token_help1="" token_help2="">
254 <param name="infile1" type="data" format="@FORMAT1@" label="@LABEL1@" help="@HELP1@"/>
255 <param name="col1" multiple="@MULTIPLE1@" type="data_column" data_ref="infile1" label="Select target column(s):"/>
256 <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):"/>
258 <yield/>
259 </xml>
260
261
262 <xml name="clf_inputs_extended" token_label1=" " token_label2=" " token_multiple="False">
263 <conditional name="true_columns">
264 <param name="selected_input1" type="select" label="Select the input type of true labels dataset:">
265 <option value="tabular" selected="true">Tabular</option>
266 <option value="sparse">Sparse</option>
267 </param>
268 <when value="tabular">
269 <param name="infile1" type="data" label="@LABEL1@"/>
270 <param name="col1" type="data_column" data_ref="infile1" label="Select the target column:"/>
271 </when>
272 <when value="sparse">
273 <param name="infile1" type="data" format="txt" label="@LABEL1@"/>
274 </when>
275 </conditional>
276 <conditional name="predicted_columns">
277 <param name="selected_input2" type="select" label="Select the input type of predicted labels dataset:">
278 <option value="tabular" selected="true">Tabular</option>
279 <option value="sparse">Sparse</option>
280 </param>
281 <when value="tabular">
282 <param name="infile2" type="data" label="@LABEL2@"/>
283 <param name="col2" multiple="@MULTIPLE@" type="data_column" data_ref="infile2" label="Select target column(s):"/>
284 </when>
285 <when value="sparse">
286 <param name="infile2" type="data" format="txt" label="@LABEL1@"/>
287 </when>
288 </conditional>
289 </xml>
290
291 <xml name="clf_inputs" token_label1="Dataset containing true labels (tabular):" token_label2="Dataset containing predicted values (tabular):" token_multiple1="False" token_multiple="False">
292 <param name="infile1" type="data" format="tabular" label="@LABEL1@"/>
293 <param name="col1" multiple="@MULTIPLE1@" type="data_column" data_ref="infile1" label="Select the target column:"/>
294 <param name="infile2" type="data" format="tabular" label="@LABEL2@"/>
295 <param name="col2" multiple="@MULTIPLE@" type="data_column" data_ref="infile2" label="Select target column(s):"/>
296 </xml>
297
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.">
299 <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@"/>
301 </repeat>
302 </xml>
303
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="">
305 <param name="infile1" type="data" format="@FORMAT1@" label="@LABEL1@" help="@HELP1@"/>
306 <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):"/>
308 </xml>
309
310 <xml name="sl_mixed_input">
311 <conditional name="input_options">
312 <param name="selected_input" type="select" label="Select input type:">
313 <option value="tabular" selected="true">tabular data</option>
314 <option value="sparse">sparse matrix</option>
315 </param>
316 <when value="tabular">
317 <expand macro="sample_cols" multiple1="true"/>
318 </when>
319 <when value="sparse">
320 <expand macro="sparse_target"/>
321 </when>
322 </conditional>
323 </xml>
324
325 <xml name="multitype_input" token_format="tabular" token_help="All datasets with tabular format are supporetd.">
326 <param name="infile_transform" type="data" format="@FORMAT@" label="Select a dataset to transform:" help="@HELP@"/>
327 </xml>
328
329
330 <!--Advanced options-->
331 <xml name="nn_advanced_options">
332 <section name="options" title="Advanced Options" expanded="False">
333 <yield/>
334 <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>
336 <option value="distance" help="Weight points by the inverse of their distance.">Distance</option>
337 </param>
338 <param argument="algorithm" type="select" label="Neighbor selection algorithm" help=" ">
339 <option value="auto" selected="true">Auto</option>
340 <option value="ball_tree">BallTree</option>
341 <option value="kd_tree">KDTree</option>
342 <option value="brute">Brute-force</option>
343 </param>
344 <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."/>
345 <!--param name="metric"-->
346 <!--param name="p"-->
347 <!--param name="metric_params"-->
348 </section>
349 </xml>
350
351 <xml name="svc_advanced_options">
352 <section name="options" title="Advanced Options" expanded="False">
353 <yield/>
354 <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.">
355 <option value="rbf" selected="true">rbf</option>
356 <option value="linear">linear</option>
357 <option value="poly">poly</option>
358 <option value="sigmoid">sigmoid</option>
359 <option value="precomputed">precomputed</option>
360 </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 "/>
362 <!--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 "/>
364 <param argument="shrinking" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolflase" checked="true" label="Use the shrinking heuristic" help=" "/>
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."/>
366 <!-- param argument="cache_size"-->
367 <!--expand macro="class_weight"/-->
368 <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."/>
370 <!--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."/>
372 </section>
373 </xml>
374
375 <xml name="spectral_clustering_advanced_options">
376 <section name="options" title="Advanced Options" expanded="False">
377 <expand macro="n_clusters"/>
378 <param argument="eigen_solver" type="select" value="" label="Eigen solver" help="The eigenvalue decomposition strategy to use.">
379 <option value="arpack" selected="true">arpack</option>
380 <option value="lobpcg">lobpcg</option>
381 <option value="amg">amg</option>
382 <!--None-->
383 </param>
384 <expand macro="random_state"/>
385 <expand macro="n_init"/>
386 <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''."/>
387 <param argument="affinity" type="select" label="Affinity" help="Affinity kernel to use. ">
388 <option value="rbf" selected="true">RBF</option>
389 <option value="precomputed">precomputed</option>
390 <option value="nearest_neighbors">Nearset neighbors</option>
391 </param>
392 <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''"/>
393 <!--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.">
395 <option value="kmeans" selected="true">kmeans</option>
396 <option value="discretize">discretize</option>
397 </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 "/>
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 "/>
400 <!--param argument="kernel_params"-->
401 </section>
402 </xml>
403
404 <xml name="minibatch_kmeans_advanced_options">
405 <section name="options" title="Advanced Options" expanded="False">
406 <expand macro="n_clusters"/>
407 <expand macro="init"/>
408 <expand macro="n_init" default_value="3"/>
409 <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 ."/>
411 <expand macro="random_state"/>
412 <param argument="batch_size" type="integer" optional="true" value="100" label="Batch size" help="Size of the mini batches."/>
413 <!--param argument="compute_labels"-->
414 <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).
416 To disable, set max_no_improvement to None. "/>
417 <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 )"/>
418 <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."/>
419 </section>
420 </xml>
421
422 <xml name="kmeans_advanced_options">
423 <section name="options" title="Advanced Options" expanded="False">
424 <expand macro="n_clusters"/>
425 <expand macro="init"/>
426 <expand macro="n_init"/>
427 <expand macro="max_iter"/>
428 <expand macro="tol" default_value="0.0001" help_text="Relative tolerance with regards to inertia to declare convergence."/>
429 <!--param argument="precompute_distances"/-->
430 <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."/>
432 </section>
433 </xml>
434
435 <xml name="birch_advanced_options">
436 <section name="options" title="Advanced Options" expanded="False">
437 <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."/>
438 <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."/>
439 <expand macro="n_clusters" default_value="3"/>
440 <!--param argument="compute_labels"/-->
441 </section>
442 </xml>
443
444 <xml name="dbscan_advanced_options">
445 <section name="options" title="Advanced Options" expanded="False">
446 <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."/>
447 <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."/>
448 <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."/>
449 <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.">
450 <option value="auto" selected="true">auto</option>
451 <option value="ball_tree">ball_tree</option>
452 <option value="kd_tree">kd_tree</option>
453 <option value="brute">brute</option>
454 </param>
455 <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."/>
456 </section>
457 </xml>
458
459 <xml name="clustering_algorithms_options">
460 <conditional name="algorithm_options">
461 <param name="selected_algorithm" type="select" label="Clustering Algorithm">
462 <option value="KMeans" selected="true">KMeans</option>
463 <option value="SpectralClustering">Spectral Clustering</option>
464 <option value="MiniBatchKMeans">Mini Batch KMeans</option>
465 <option value="DBSCAN">DBSCAN</option>
466 <option value="Birch">Birch</option>
467 </param>
468 <when value="KMeans">
469 <expand macro="kmeans_advanced_options"/>
470 </when>
471 <when value="DBSCAN">
472 <expand macro="dbscan_advanced_options"/>
473 </when>
474 <when value="Birch">
475 <expand macro="birch_advanced_options"/>
476 </when>
477 <when value="SpectralClustering">
478 <expand macro="spectral_clustering_advanced_options"/>
479 </when>
480 <when value="MiniBatchKMeans">
481 <expand macro="minibatch_kmeans_advanced_options"/>
482 </when>
483 </conditional>
484 </xml>
485
486 <xml name="distance_metrics">
487 <param argument="metric" type="select" label="Distance metric" help=" ">
488 <option value="euclidean" selected="true">euclidean</option>
489 <option value="cityblock">cityblock</option>
490 <option value="cosine">cosine</option>
491 <option value="l1">l1</option>
492 <option value="l2">l2</option>
493 <option value="manhattan">manhattan</option>
494 <yield/>
495 </param>
496 </xml>
497
498 <xml name="distance_nonsparse_metrics">
499 <option value="braycurtis">braycurtis</option>
500 <option value="canberra">canberra</option>
501 <option value="chebyshev">chebyshev</option>
502 <option value="correlation">correlation</option>
503 <option value="dice">dice</option>
504 <option value="hamming">hamming</option>
505 <option value="jaccard">jaccard</option>
506 <option value="kulsinski">kulsinski</option>
507 <option value="mahalanobis">mahalanobis</option>
508 <option value="matching">matching</option>
509 <option value="minkowski">minkowski</option>
510 <option value="rogerstanimoto">rogerstanimoto</option>
511 <option value="russellrao">russellrao</option>
512 <option value="seuclidean">seuclidean</option>
513 <option value="sokalmichener">sokalmichener</option>
514 <option value="sokalsneath">sokalsneath</option>
515 <option value="sqeuclidean">sqeuclidean</option>
516 <option value="yule">yule</option>
517 </xml>
518
519 <xml name="pairwise_kernel_metrics">
520 <param argument="metric" type="select" label="Pirwise Kernel metric" help=" ">
521 <option value="rbf" selected="true">rbf</option>
522 <option value="sigmoid">sigmoid</option>
523 <option value="polynomial">polynomial</option>
524 <option value="linear" selected="true">linear</option>
525 <option value="chi2">chi2</option>
526 <option value="additive_chi2">additive_chi2</option>
527 </param>
528 </xml>
529
530 <xml name="sparse_pairwise_metric_functions">
531 <param name="selected_metric_function" type="select" label="Select the pairwise metric you want to compute:">
532 <option value="euclidean_distances" selected="true">Euclidean distance matrix</option>
533 <option value="pairwise_distances">Distance matrix</option>
534 <option value="pairwise_distances_argmin">Minimum distances between one point and a set of points</option>
535 <yield/>
536 </param>
537 </xml>
538
539 <xml name="pairwise_metric_functions">
540 <option value="additive_chi2_kernel" >Additive chi-squared kernel</option>
541 <option value="chi2_kernel">Exponential chi-squared kernel</option>
542 <option value="linear_kernel">Linear kernel</option>
543 <option value="manhattan_distances">L1 distances</option>
544 <option value="pairwise_kernels">Kernel</option>
545 <option value="polynomial_kernel">Polynomial kernel</option>
546 <option value="rbf_kernel">Gaussian (rbf) kernel</option>
547 <option value="laplacian_kernel">Laplacian kernel</option>
548 </xml>
549
550 <xml name="sparse_pairwise_condition">
551 <when value="pairwise_distances">
552 <section name="options" title="Advanced Options" expanded="False">
553 <expand macro="distance_metrics">
554 <yield/>
555 </expand>
556 </section>
557 </when>
558 <when value="euclidean_distances">
559 <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=" "/>
561 </section>
562 </when>
563 </xml>
564
565 <xml name="argmin_distance_condition">
566 <when value="pairwise_distances_argmin">
567 <section name="options" title="Advanced Options" expanded="False">
568 <param argument="axis" type="integer" optional="true" value="1" label="Axis" help="Axis along which the argmin and distances are to be computed."/>
569 <expand macro="distance_metrics">
570 <yield/>
571 </expand>
572 <param argument="batch_size" type="integer" optional="true" value="500" label="Batch size" help="Number of rows to be processed in each batch run."/>
573 </section>
574 </when>
575 </xml>
576
577 <xml name="sparse_preprocessors">
578 <param name="selected_pre_processor" type="select" label="Select a preprocessor:">
579 <option value="StandardScaler" selected="true">Standard Scaler (Standardizes features by removing the mean and scaling to unit variance)</option>
580 <option value="Binarizer">Binarizer (Binarizes data)</option>
581 <option value="Imputer">Imputer (Completes missing values)</option>
582 <option value="MaxAbsScaler">Max Abs Scaler (Scales features by their maximum absolute value)</option>
583 <option value="Normalizer">Normalizer (Normalizes samples individually to unit norm)</option>
584 <yield/>
585 </param>
586 </xml>
587
588 <xml name="sparse_preprocessor_options">
589 <when value="Binarizer">
590 <expand macro="multitype_input" format="tabular,txt" help="Tabular and sparse datasets are supporetd."/>
591 <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=" "/>
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. "/>
594 </section>
595 </when>
596 <when value="Imputer">
597 <expand macro="multitype_input" format="tabular,txt" help="Tabular and sparse datasets are supporetd."/>
598 <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=" "/>
600 <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>
602 <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>
604 </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”"/>
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. "/>
607 <!--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>
609 <option value="1">Impute along rows</option>
610 </param-->
611 </section>
612 </when>
613 <when value="StandardScaler">
614 <expand macro="multitype_input"/>
615 <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=" "/>
617 <param argument="with_mean" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolflase" checked="true" label="Center the data before 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=" "/>
619 </section>
620 </when>
621 <when value="MaxAbsScaler">
622 <expand macro="multitype_input" format="tabular,txt" help="Tabular and sparse datasets are supporetd."/>
623 <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=" "/>
625 </section>
626 </when>
627 <when value="Normalizer">
628 <expand macro="multitype_input" format="tabular,txt" help="Tabular and sparse datasets are supporetd."/>
629 <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=" ">
631 <option value="l1" selected="true">l1</option>
632 <option value="l2">l2</option>
633 <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>
636 </section>
637 </when>
638 <yield/>
639 </xml>
640
641
642 <!--Citations-->
643 <xml name="eden_citation">
644 <citations>
645 <citation type="bibtex">
646 @misc{fabrizio_costa_2015_15094,
647 author = {Fabrizio Costa and
648 Björn Grüning and
649 gigolo},
650 title = {EDeN: EDeN - Graph Vectorizer},
651 month = feb,
652 year = 2015,
653 doi = {10.5281/zenodo.15094},
654 url = {http://dx.doi.org/10.5281/zenodo.15094}
655 }
656 }
657 </citation>
658 </citations>
659 </xml>
660
661 <xml name="sklearn_citation">
662 <citations>
663 <citation type="bibtex">
664 @article{scikit-learn,
665 title={Scikit-learn: Machine Learning in {P}ython},
666 author={Pedregosa, F. and Varoquaux, G. and Gramfort, A. and Michel, V.
667 and Thirion, B. and Grisel, O. and Blondel, M. and Prettenhofer, P.
668 and Weiss, R. and Dubourg, V. and Vanderplas, J. and Passos, A. and
669 Cournapeau, D. and Brucher, M. and Perrot, M. and Duchesnay, E.},
670 journal={Journal of Machine Learning Research},
671 volume={12},
672 pages={2825--2830},
673 year={2011}
674 url = {https://github.com/scikit-learn/scikit-learn}
675 }
676 </citation>
677 </citations>
678 </xml>
679
680 <xml name="scipy_citation">
681 <citations>
682 <citation type="bibtex">
683 @Misc{,
684 author = {Eric Jones and Travis Oliphant and Pearu Peterson and others},
685 title = {{SciPy}: Open source scientific tools for {Python}},
686 year = {2001--},
687 url = "http://www.scipy.org/",
688 note = {[Online; accessed 2016-04-09]}
689 }
690 </citation>
691 </citations>
692 </xml>
693
694 </macros>