|
0
|
1 <tool id="BestSubsetsRegression1" name="Perform Best-subsets Regression">
|
|
|
2 <description> </description>
|
|
|
3 <command interpreter="python">
|
|
|
4 best_regression_subsets.py
|
|
|
5 $input1
|
|
|
6 $response_col
|
|
|
7 $predictor_cols
|
|
|
8 $out_file1
|
|
|
9 $out_file2
|
|
|
10 1>/dev/null
|
|
|
11 2>/dev/null
|
|
|
12 </command>
|
|
|
13 <inputs>
|
|
|
14 <param format="tabular" name="input1" type="data" label="Select data" help="Dataset missing? See TIP below."/>
|
|
|
15 <param name="response_col" label="Response column (Y)" type="data_column" data_ref="input1" />
|
|
|
16 <param name="predictor_cols" label="Predictor columns (X)" type="data_column" data_ref="input1" multiple="true" >
|
|
|
17 <validator type="no_options" message="Please select at least one column."/>
|
|
|
18 </param>
|
|
|
19 </inputs>
|
|
|
20 <outputs>
|
|
|
21 <data format="input" name="out_file1" metadata_source="input1" />
|
|
|
22 <data format="pdf" name="out_file2" />
|
|
|
23 </outputs>
|
|
|
24 <requirements>
|
|
|
25 <requirement type="python-module">rpy</requirement>
|
|
|
26 </requirements>
|
|
|
27 <tests>
|
|
|
28 <!-- Testing this tool will not be possible because this tool produces a pdf output file.
|
|
|
29 -->
|
|
|
30 </tests>
|
|
|
31 <help>
|
|
|
32
|
|
|
33 .. class:: infomark
|
|
|
34
|
|
|
35 **TIP:** If your data is not TAB delimited, use *Edit Datasets->Convert characters*
|
|
|
36
|
|
|
37 -----
|
|
|
38
|
|
|
39 .. class:: infomark
|
|
|
40
|
|
|
41 **What it does**
|
|
|
42
|
|
|
43 This tool uses the 'regsubsets' function from R statistical package for regression subset selection. It outputs two files, one containing a table with the best subsets and the corresponding summary statistics, and the other containing the graphical representation of the results.
|
|
|
44
|
|
|
45 -----
|
|
|
46
|
|
|
47 .. class:: warningmark
|
|
|
48
|
|
|
49 **Note**
|
|
|
50
|
|
|
51 - This tool currently treats all predictor and response variables as continuous variables.
|
|
|
52
|
|
|
53 - Rows containing non-numeric (or missing) data in any of the chosen columns will be skipped from the analysis.
|
|
|
54
|
|
|
55 - The 6 columns in the output are described below:
|
|
|
56
|
|
|
57 - Column 1 (Vars): denotes the number of variables in the model
|
|
|
58 - Column 2 ([c2 c3 c4...]): represents a list of the user-selected predictor variables (full model). An asterix denotes the presence of the corresponding predictor variable in the selected model.
|
|
|
59 - Column 3 (R-sq): the fraction of variance explained by the model
|
|
|
60 - Column 4 (Adj. R-sq): the above R-squared statistic adjusted, penalizing for higher number of predictors (p)
|
|
|
61 - Column 5 (Cp): Mallow's Cp statistics
|
|
|
62 - Column 6 (bic): Bayesian Information Criterion.
|
|
|
63
|
|
|
64
|
|
|
65 </help>
|
|
|
66 </tool>
|
