mirror of
https://github.com/galaxyproject/galaxy.git
synced 2026-09-24 16:30:27 +08:00
71 lines
2.6 KiB
XML
71 lines
2.6 KiB
XML
<tool id="rcve1" name="Compute RCVE" version="1.0.0">
|
|
<description> </description>
|
|
<command interpreter="python">
|
|
rcve.py
|
|
$input1
|
|
$response_col
|
|
$predictor_cols
|
|
$out_file1
|
|
1>/dev/null
|
|
</command>
|
|
<inputs>
|
|
<param format="tabular" name="input1" type="data" label="Select data" help="Dataset missing? See TIP below."/>
|
|
<param name="response_col" label="Response column (Y)" type="data_column" data_ref="input1" />
|
|
<param name="predictor_cols" label="Predictor columns (X)" type="data_column" data_ref="input1" multiple="true">
|
|
<validator type="no_options" message="Please select at least one column."/>
|
|
</param>
|
|
</inputs>
|
|
<outputs>
|
|
<data format="input" name="out_file1" metadata_source="input1" />
|
|
</outputs>
|
|
<requirements>
|
|
<requirement type="python-module">rpy</requirement>
|
|
</requirements>
|
|
<tests>
|
|
<!-- Test data with vlid values -->
|
|
<test>
|
|
<param name="input1" value="reg_inp.tab"/>
|
|
<param name="response_col" value="1"/>
|
|
<param name="predictor_cols" value="2,3,4"/>
|
|
<output name="out_file1" file="rcve_out.dat"/>
|
|
</test>
|
|
|
|
</tests>
|
|
<help>
|
|
|
|
.. class:: infomark
|
|
|
|
**TIP:** If your data is not TAB delimited, use *Edit Datasets->Convert characters*
|
|
|
|
-----
|
|
|
|
.. class:: infomark
|
|
|
|
**What it does**
|
|
|
|
This tool computes the RCVE (Relative Contribution to Variance) for all possible variable subsets using the following formula:
|
|
|
|
**RCVE(i) = [R-sq (full: 1,2,..,i..,p-1) - R-sq(without i: 1,2,...,p-1)] / R-sq (full: 1,2,..,i..,p-1)**,
|
|
which denotes the case where the 'i'th predictor is dropped.
|
|
|
|
|
|
In general,
|
|
**RCVE(X+) = [R-sq (full: {X,X+}) - R-sq(reduced: {X})] / R-sq (full: {X,X+})**,
|
|
where,
|
|
|
|
- {X,X+} denotes the set of all predictors,
|
|
- X+ is the set of predictors for which we compute RCVE (and therefore drop from the full model to obtain a reduced one),
|
|
- {X} is the set of the predictors that are left in the reduced model after excluding {X+}
|
|
|
|
|
|
The 4 columns in the output are described below:
|
|
|
|
- Column 1 (Model): denotes the variables present in the model ({X})
|
|
- Column 2 (R-sq): denotes the R-squared value corresponding to the model in Column 1
|
|
- Column 3 (RCVE_Terms): denotes the variable/s for which RCVE is computed ({X+}). These are the variables that are absent in the reduced model in Column 1. A '-' in this column indicates that the model in Column 1 is the Full model.
|
|
- Column 4 (RCVE): denotes the RCVE value corresponding to the variable/s in Column 3. A '-' in this column indicates that the model in Column 1 is the Full model.
|
|
|
|
|
|
</help>
|
|
</tool>
|