Mercurial > repos > bgruening > sklearn_numeric_clustering

comparison main_macros.xml @ 2:fe2d62fbf47b 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 6c002ea2995c85f5f16adb2ef1c6be82dfbc5417
author bgruening
date Tue, 31 May 2016 16:52:04 -0400
parents d938b80a954f
children a8951d76b7d2
comparison
equal deleted inserted replaced
1:d938b80a954f 2:fe2d62fbf47b
12 <stdio> 12 <stdio>
13 <exit_code range="1:" level="fatal" description="Error occurred. Please check Tool Standard Error" /> 13 <exit_code range="1:" level="fatal" description="Error occurred. Please check Tool Standard Error" />
14 </stdio> 14 </stdio>
15 </xml> 15 </xml>
16 16
17
18 <!--Generic interface-->
17 <xml name="train_loadConditional" token_train="tabular" token_data="tabular" token_model="txt"> 19 <xml name="train_loadConditional" token_train="tabular" token_data="tabular" token_model="txt">
18 <conditional name="selected_tasks"> 20 <conditional name="selected_tasks">
19 <param name="selected_task" type="select" label="Select a Classification Task"> 21 <param name="selected_task" type="select" label="Select a Classification Task">
22 <option value="train" selected="true">Train a model</option>
20 <option value="load">Load a model and predict</option> 23 <option value="load">Load a model and predict</option>
21 <option value="train" selected="true">Train a model</option>
22 </param> 24 </param>
23 <when value="load"> 25 <when value="load">
24 <param name="infile_model" type="data" format="@MODEL@" label="Models" help="Select a model file." /> 26 <param name="infile_model" type="data" format="@MODEL@" label="Models" help="Select a model file." />
25 <param name="infile_data" type="data" format="@DATA@" label="Data (tabular)" help="Select the dataset you want to classify."/> 27 <param name="infile_data" type="data" format="@DATA@" label="Data (tabular)" help="Select the dataset you want to classify."/>
26 <conditional name="prediction_options"> 28 <conditional name="prediction_options">
41 </conditional> 43 </conditional>
42 </when> 44 </when>
43 </conditional> 45 </conditional>
44 </xml> 46 </xml>
45 47
48 <xml name="sl_Conditional" token_train="tabular" token_data="tabular" token_model="txt">
49 <conditional name="selected_tasks">
50 <param name="selected_task" type="select" label="Select a Classification Task">
51 <option value="train" selected="true">Train a model</option>
52 <option value="load">Load a model and predict</option>
53 </param>
54 <when value="load">
55 <param name="infile_model" type="data" format="@MODEL@" label="Models" help="Select a model file." />
56 <param name="infile_data" type="data" format="@DATA@" label="Data (tabular)" help="Select the dataset you want to classify."/>
57 <conditional name="prediction_options">
58 <param name="prediction_option" type="select" label="Select the type of prediction">
59 <option value="predict">Predict class labels</option>
60 <option value="advanced">Include advanced options</option>
61 </param>
62 <when value="predict">
63 </when>
64 <when value="advanced">
65 </when>
66 </conditional>
67 </when>
68 <when value="train">
69 <conditional name="selected_algorithms">
70 <yield />
71 </conditional>
72 </when>
73 </conditional>
74 </xml>
75
46 <xml name="advanced_section"> 76 <xml name="advanced_section">
47 <section name="options" title="Advanced Options" expanded="False"> 77 <section name="options" title="Advanced Options" expanded="False">
48 <yield /> 78 <yield />
49 </section> 79 </section>
50 </xml> 80 </xml>
51 81
52 <xml name="tabular_input"> 82
53 <param name="infile" type="data" format="tabular" label="Data file with numeric values"/> 83 <!--Ensemble methods-->
54 <param name="start_column" type="data_column" data_ref="infile" optional="True" label="Select a subset of data. Start column:" /> 84 <xml name="n_estimators" token_default_value="10" token_help=" ">
55 <param name="end_column" type="data_column" data_ref="infile" optional="True" label="End column:" /> 85 <param argument="n_estimators" type="integer" optional="true" value="@DEFAULT_VALUE@" label="Number of trees in the forest" help="@HELP@"/>
56 </xml> 86 </xml>
57 87
88 <xml name="max_depth" token_default_value="" token_help=" ">
89 <param argument="max_depth" type="integer" optional="true" value="@DEFAULT_VALUE@" label="Maximum depth of the tree" help="@HELP@"/>
90 </xml>
91
92 <xml name="min_samples_split" token_default_value="2" token_help=" ">
93 <param argument="min_samples_split" type="integer" optional="true" value="@DEFAULT_VALUE@" label="Maximum depth of the tree" help="@HELP@"/>
94 </xml>
95
96 <xml name="min_samples_leaf" token_default_value="1" token_help=" ">
97 <param argument="min_samples_leaf" type="integer" optional="true" value="@DEFAULT_VALUE@" label="Minimum number of samples in newly created leaves" help="@HELP@"/>
98 </xml>
99
100 <xml name="min_weight_fraction_leaf" token_default_value="0.0" token_help=" ">
101 <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@"/>
102 </xml>
103
104 <xml name="max_leaf_nodes" token_default_value="" token_help=" ">
105 <param argument="max_leaf_nodes" type="integer" optional="true" value="@DEFAULT_VALUE@" label="Maximum number of leaf nodes in best-first method" help="@HELP@"/>
106 </xml>
107
108 <xml name="bootstrap" token_checked="true" token_help=" ">
109 <param argument="bootstrap" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolflase" checked="@CHECKED@" label="Use bootstrap samples for building trees." help="@HELP@"/>
110 </xml>
111
112 <xml name="criterion" token_help=" ">
113 <param argument="criterion" type="select" label="Function to measure the quality of a split" help=" ">
114 <option value="gini" selected="true">Gini impurity</option>
115 <option value="entropy">Information gain</option>
116 <yield/>
117 </param>
118 </xml>
119
120 <xml name="oob_score" token_checked="flase" token_help=" ">
121 <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@"/>
122 </xml>
123
124 <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. ">
125 <param argument="max_features" type="text" optional="true" value="@DEFAULT_VALUE@" label="Number of features for finding the best split" help="@HELP@"/>
126 </xml>
127
128 <xml name="learning_rate" token_default_value="1.0" token_help=" ">
129 <param argument="learning_rate" type="float" optional="true" value="@DEFAULT_VALUE@" label="Learning rate" help="@HELP@"/>
130 </xml>
131
132
133 <!--Parameters-->
58 <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."> 134 <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.">
59 <param argument="tol" type="float" optional="true" value="@DEFAULT_VALUE@" label="Tolerance" help="@HELP_TEXT@"/> 135 <param argument="tol" type="float" optional="true" value="@DEFAULT_VALUE@" label="Tolerance" help="@HELP_TEXT@"/>
60 </xml> 136 </xml>
61 137
62 <xml name="n_clusters" token_default_value="8"> 138 <xml name="n_clusters" token_default_value="8">
134 <param argument="degree" type="integer" optional="true" value="@DEFAULT_VALUE@" label="@LABEL@" help="@HELP_TEXT@"/> 210 <param argument="degree" type="integer" optional="true" value="@DEFAULT_VALUE@" label="@LABEL@" help="@HELP_TEXT@"/>
135 </xml> 211 </xml>
136 212
137 <xml name="coef0" token_default_value="1" token_label="Zero coefficient" token_help_text=" "> 213 <xml name="coef0" token_default_value="1" token_label="Zero coefficient" token_help_text=" ">
138 <param argument="coef0" type="integer" optional="true" value="@DEFAULT_VALUE@" label="@LABEL@" help="@HELP_TEXT@"/> 214 <param argument="coef0" type="integer" optional="true" value="@DEFAULT_VALUE@" label="@LABEL@" help="@HELP_TEXT@"/>
139 </xml> 215 </xml>
216
217 <xml name="pos_label" token_default_value="">
218 <param argument="pos_label" type="integer" optional="true" value="@DEFAULT_VALUE@" label="Label of the positive class" help=" "/>
219 </xml>
220
221 <xml name="average">
222 <param argument="average" type="select" optional="True" label="Averaging type" help=" ">
223 <option value="binary" selected="true" help="Only report results for the class specified by pos_label. Applicable only on binary classification.">binary</option>
224 <option value="micro" help="Calculate metrics globally by counting the total true positives, false negatives and false positives.">micro</option>
225 <option value="samples" help="Calculate metrics for each instance, and find their average (only meaningful for multilabel).">samples</option>
226 <!--option value="macro" help=""></option-->
227 <!--option value="weighted" help=""></option-->
228 </param>
229 </xml>
230
231 <xml name="beta">
232 <param argument="beta" type="float" value="1.0" label="The strength of recall versus precision in the F-score" help=" "/>
233 </xml>
234
235
236 <!--Data interface-->
237 <xml name="tabular_input">
238 <param name="infile" type="data" format="tabular" label="Data file with numeric values"/>
239 <param name="start_column" type="data_column" data_ref="infile" optional="True" label="Select a subset of data. Start column:" />
240 <param name="end_column" type="data_column" data_ref="infile" optional="True" label="End column:" />
241 </xml>
242
243 <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="">
244 <param name="infile1" type="data" format="@FORMAT1@" label="@LABEL1@" help="@HELP1@"/>
245 <param name="col1" multiple="@MULTIPLE1@" type="data_column" data_ref="infile1" label="Select target column(s):"/>
246 <param name="infile2" type="data" format="@FORMAT2@" label="@LABEL2@" help="@HELP2@"/>
247 <param name="col2" multiple="@MULTIPLE2@" type="data_column" data_ref="infile2" label="Select target column(s):"/>
248 <yield/>
249 </xml>
140 250
141 <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."> 251 <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.">
142 <repeat name="@NAME@" min="1" max="@MAX_NUM@" title="Select input file(s):"> 252 <repeat name="@NAME@" min="1" max="@MAX_NUM@" title="Select input file(s):">
143 <param name="input" type="data" format="@FORMAT@" label="@LABEL@" help="@HELP_TEXT@"/> 253 <param name="input" type="data" format="@FORMAT@" label="@LABEL@" help="@HELP_TEXT@"/>
144 </repeat> 254 </repeat>
145 </xml> 255 </xml>
146 256
147 <xml name="eden_citation"> 257 <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="">
148 <citations> 258 <param name="infile1" type="data" format="@FORMAT1@" label="@LABEL1@" help="@HELP1@"/>
149 <citation type="bibtex"> 259 <param name="infile2" type="data" format="@FORMAT2@" label="@LABEL2@" help="@HELP2@"/>
150 @misc{fabrizio_costa_2015_15094, 260 <param name="col2" multiple="@MULTIPLE@" type="data_column" data_ref="infile2" label="Select target column(s):"/>
151 author = {Fabrizio Costa and 261 </xml>
152 Björn Grüning and 262
153 gigolo}, 263 <xml name="sl_mixed_input">
154 title = {EDeN: EDeN - Graph Vectorizer}, 264 <conditional name="input_options">
155 month = feb, 265 <param name="selected_input" type="select" label="Select input type:">
156 year = 2015, 266 <option value="tabular" selected="true">tabular data</option>
157 doi = {10.5281/zenodo.15094}, 267 <option value="sparse">sparse matrix</option>
158 url = {http://dx.doi.org/10.5281/zenodo.15094} 268 </param>
159 } 269 <when value="tabular">
160 } 270 <expand macro="sample_cols" multiple1="true"/>
161 </citation> 271 </when>
162 </citations> 272 <when value="sparse">
163 </xml> 273 <expand macro="sparse_target"/>
164 274 </when>
165 <xml name="sklearn_citation"> 275 </conditional>
166 <citations> 276 </xml>
167 <citation type="bibtex"> 277
168 @article{scikit-learn, 278
169 title={Scikit-learn: Machine Learning in {P}ython}, 279 <!--Advanced options-->
170 author={Pedregosa, F. and Varoquaux, G. and Gramfort, A. and Michel, V.
171 and Thirion, B. and Grisel, O. and Blondel, M. and Prettenhofer, P.
172 and Weiss, R. and Dubourg, V. and Vanderplas, J. and Passos, A. and
173 Cournapeau, D. and Brucher, M. and Perrot, M. and Duchesnay, E.},
174 journal={Journal of Machine Learning Research},
175 volume={12},
176 pages={2825--2830},
177 year={2011}
178 url = {https://github.com/scikit-learn/scikit-learn}
179 }
180 </citation>
181 </citations>
182 </xml>
183
184 <xml name="scipy_citation">
185 <citations>
186 <citation type="bibtex">
187 @Misc{,
188 author = {Eric Jones and Travis Oliphant and Pearu Peterson and others},
189 title = {{SciPy}: Open source scientific tools for {Python}},
190 year = {2001--},
191 url = "http://www.scipy.org/",
192 note = {[Online; accessed 2016-04-09]}
193 }
194 </citation>
195 </citations>
196 </xml>
197
198
199 <xml name="nn_advanced_options"> 280 <xml name="nn_advanced_options">
200 <section name="options" title="Advanced Options" expanded="False"> 281 <section name="options" title="Advanced Options" expanded="False">
201 <yield/> 282 <yield/>
202 <param argument="weights" type="select" label="Weight function" help="Used in prediction."> 283 <param argument="weights" type="select" label="Weight function" help="Used in prediction.">
203 <option value="uniform" selected="true" help="Uniform weights. All points in each neighborhood are weighted equally.">Uniform</option> 284 <option value="uniform" selected="true" help="Uniform weights. All points in each neighborhood are weighted equally.">Uniform</option>
440 <param argument="batch_size" type="integer" optional="true" value="500" label="Batch size" help="Number of rows to be processed in each batch run."/> 521 <param argument="batch_size" type="integer" optional="true" value="500" label="Batch size" help="Number of rows to be processed in each batch run."/>
441 </section> 522 </section>
442 </when> 523 </when>
443 </xml> 524 </xml>
444 525
526 <xml name="sparse_preprocessors">
527 <param name="selected_pre_processor" type="select" label="Select a preprocessor:">
528 <option value="StandardScaler" selected="true">Standardize features by removing the mean and scaling to unit variance</option>
529 <option value="Binarizer">Binarize data</option>
530 <option value="Imputer">Complete missing values</option>
531 <option value="MaxAbsScaler">Scale features by their maximum absolute value</option>
532 <option value="Normalizer">Normalize samples individually to unit norm</option>
533 <yield/>
534 </param>
535 </xml>
536
537 <xml name="sparse_preprocessor_options">
538 <when value="Binarizer">
539 <section name="options" title="Advanced Options" expanded="False">
540 <param argument="copy" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolflase" checked="true" label="Use a copy of data for precomputing binarization" help=" "/>
541 <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. "/>
542 </section>
543 </when>
544 <when value="Imputer">
545 <section name="options" title="Advanced Options" expanded="False">
546 <param argument="copy" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolflase" checked="true" label="Use a copy of data for precomputing imputation" help=" "/>
547 <param argument="strategy" type="select" optional="true" label="Imputation strategy" help=" ">
548 <option value="mean" selected="true">Replace missing values using the mean along the axis</option>
549 <option value="median">Replace missing values using the median along the axis</option>
550 <option value="most_frequent">Replace missing using the most frequent value along the axis</option>
551 </param>
552 <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”"/>
553 <param argument="axis" type="select" optional="true" label="The axis along which to impute" help=" ">
554 <option value="0" selected="true">Impute along columns</option>
555 <option value="1">Impute along rows</option>
556 </param>
557 </section>
558 </when>
559 <when value="StandardScaler">
560 <section name="options" title="Advanced Options" expanded="False">
561 <param argument="copy" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolflase" checked="true" label="Use a copy of data for performing inplace scaling" help=" "/>
562 <param argument="with_mean" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolflase" checked="true" label="Center the data before scaling" help=" "/>
563 <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=" "/>
564 </section>
565 </when>
566 <when value="MaxAbsScaler">
567 <section name="options" title="Advanced Options" expanded="False">
568 <param argument="copy" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolflase" checked="true" label="Use a copy of data for precomputing scaling" help=" "/>
569 </section>
570 </when>
571 <when value="Normalizer">
572 <section name="options" title="Advanced Options" expanded="False">
573 <param argument="norm" type="select" optional="true" label="The norm to use to normalize non zero samples" help=" ">
574 <option value="l1" selected="true">l1</option>
575 <option value="l2">l2</option>
576 <option value="max">max</option>
577 <param argument="copy" type="boolean" optional="true" truevalue="booltrue" falsevalue="boolflase" checked="true" label="Use a copy of data for precomputing row normalization" help=" "/>
578 </param>
579 </section>
580 </when>
581 <yield/>
582 </xml>
583
584
585 <!--Citations-->
586 <xml name="eden_citation">
587 <citations>
588 <citation type="bibtex">
589 @misc{fabrizio_costa_2015_15094,
590 author = {Fabrizio Costa and
591 Björn Grüning and
592 gigolo},
593 title = {EDeN: EDeN - Graph Vectorizer},
594 month = feb,
595 year = 2015,
596 doi = {10.5281/zenodo.15094},
597 url = {http://dx.doi.org/10.5281/zenodo.15094}
598 }
599 }
600 </citation>
601 </citations>
602 </xml>
603
604 <xml name="sklearn_citation">
605 <citations>
606 <citation type="bibtex">
607 @article{scikit-learn,
608 title={Scikit-learn: Machine Learning in {P}ython},
609 author={Pedregosa, F. and Varoquaux, G. and Gramfort, A. and Michel, V.
610 and Thirion, B. and Grisel, O. and Blondel, M. and Prettenhofer, P.
611 and Weiss, R. and Dubourg, V. and Vanderplas, J. and Passos, A. and
612 Cournapeau, D. and Brucher, M. and Perrot, M. and Duchesnay, E.},
613 journal={Journal of Machine Learning Research},
614 volume={12},
615 pages={2825--2830},
616 year={2011}
617 url = {https://github.com/scikit-learn/scikit-learn}
618 }
619 </citation>
620 </citations>
621 </xml>
622
623 <xml name="scipy_citation">
624 <citations>
625 <citation type="bibtex">
626 @Misc{,
627 author = {Eric Jones and Travis Oliphant and Pearu Peterson and others},
628 title = {{SciPy}: Open source scientific tools for {Python}},
629 year = {2001--},
630 url = "http://www.scipy.org/",
631 note = {[Online; accessed 2016-04-09]}
632 }
633 </citation>
634 </citations>
635 </xml>
636
445 </macros> 637 </macros>