|
9
|
1 <tool id="bg_eden_cross_validation" name="EDeN Crossvalidation" version="0.1">
|
|
|
2 <description></description>
|
|
|
3 <macros>
|
|
|
4 <import>eden_macros.xml</import>
|
|
|
5 </macros>
|
|
|
6 <expand macro="requirements" />
|
|
|
7 <command>
|
|
|
8 EDeN --action CROSS_VALIDATION
|
|
|
9
|
|
|
10 --input_data_file_name $sparse_vector_infile
|
|
|
11 --file_type "SPARSE_VECTOR"
|
|
|
12
|
|
|
13 ## target_file_name is a file with 1 or -1 one in each row, indicating the class
|
|
|
14 --target_file_name $target_infile
|
|
|
15 --binary_file_type
|
|
|
16
|
|
|
17 --num_cross_validation_folds ${num_cross_validation_folds}
|
|
|
18 ;
|
|
|
19 cat cv_predictions | tr ' ' \\t > $outfile;
|
|
|
20
|
|
|
21 </command>
|
|
|
22 <inputs>
|
|
|
23 <param format="eden_sparse_vector" name="sparse_vector_infile" type="data" label="Input File" help="(--input_data_file_name/-f)"/>
|
|
|
24 <param format="txt" name="target_infile" type="data" label="Target file" help="indicates with -1 and 1 the class"/>
|
|
|
25
|
|
|
26 <param name="num_cross_validation_folds" type="integer" value="10" label="Number of cross validations" help="--num_cross_validation_folds/-c">
|
|
|
27 <validator type="in_range" min="1" />
|
|
|
28 </param>
|
|
|
29 </inputs>
|
|
|
30 <outputs>
|
|
|
31 <data format="tabular" name="outfile" label="Crossvalidation of ${on_string}"/>
|
|
|
32 </outputs>
|
|
|
33 <tests>
|
|
|
34 <test>
|
|
|
35 </test>
|
|
|
36 </tests>
|
|
|
37 <help>
|
|
|
38
|
|
|
39 .. class:: infomark
|
|
|
40
|
|
|
41 **What it does**
|
|
|
42
|
|
|
43 The linear model is induced using the accelerated stochastic gradient descent technique by Léon Bottou and Yann LeCun.
|
|
|
44 When the target information is 0, a self-training algorithm is used to impute a positive or negative class to the unsupervised instances.
|
|
|
45 If the target information is imbalanced a minority class resampling technique is used to rebalance the training set.
|
|
|
46
|
|
|
47 @references@
|
|
|
48
|
|
|
49 </help>
|
|
|
50 </tool>
|
