root/galaxy-central/tools/stats/grouping.xml

<tool id="Grouping1" name="Group" version="1.9.1">
  <description>data by a column and perform aggregate operation on other columns.</description>
  <command interpreter="python">
    grouping.py 
      $out_file1
      $input1
      $groupcol
      $ignorecase
      #for $op in $operations
       '${op.optype}
        ${op.opcol}
        ${op.opround}'
      #end for
  </command>
  <inputs>
    <param format="tabular" name="input1" type="data" label="Select data" help="Query missing? See TIP below."/>
    <param name="groupcol" label="Group by column" type="data_column" data_ref="input1" />
    <param name="ignorecase" type="boolean" truevalue="1" falsevalue="0">
      <label>Ignore case while grouping?</label>
    </param>
    <repeat name="operations" title="Operation">
      <param name="optype" type="select" label="Type">
        <option value="mean">Mean</option>
        <option value="median">Median</option>
        <option value="Mode">Mode</option>
        <option value="max">Maximum</option>
        <option value="min">Minimum</option>
        <option value="sum">Sum</option>
        <option value="length">Count</option>
        <option value="unique">Count Distinct</option>
        <option value="c">Concatenate</option>
        <option value="cuniq">Concatenate Distinct</option>
        <option value="random">Randomly pick</option>
      </param>
      <param name="opcol" label="On column" type="data_column" data_ref="input1" />
      <param name="opround" type="select" label="Round result to nearest integer?">
         <option value="no">NO</option>
         <option value="yes">YES</option>
       </param>
    </repeat>
  </inputs>
  <outputs>
    <data format="tabular" name="out_file1" />
  </outputs>
  <requirements>
    <requirement type="python-module">rpy</requirement>
  </requirements>
  <tests>
    <!-- Test valid data -->
    <test>
      <param name="input1" value="1.bed"/>
      <param name="groupcol" value="1"/>
      <param name="ignorecase" value="true"/>
      <param name="optype" value="mean"/>
      <param name="opcol" value="2"/>
      <param name="opround" value="no"/>
      <output name="out_file1" file="groupby_out1.dat"/>
    </test>
    
    <!-- Test data with an invalid value in a column -->
    <test>
      <param name="input1" value="1.tabular"/>
      <param name="groupcol" value="1"/>
      <param name="ignorecase" value="true"/>
      <param name="optype" value="mean"/>
      <param name="opcol" value="2"/>
      <param name="opround" value="no"/>
      <output name="out_file1" file="groupby_out2.dat"/>
    </test>
  </tests>
  <help>

.. class:: infomark

**TIP:** If your data is not TAB delimited, use *Text Manipulation-&gt;Convert*

-----

**Syntax**

This tool allows you to group the input dataset by a particular column and perform aggregate functions like Mean, Median, Mode, Sum, Max, Min, Count, Random draw and Concatenate on other columns. 

- All invalid, blank and comment lines are skipped when performing the aggregate functions.  The number of skipped lines is displayed in the resulting history item.

- If multiple modes are present, all are reported.

-----

**Example**

- For the following input::

   chr22  1000  1003  TTT
   chr22  2000  2003  aaa
   chr10  2200  2203  TTT
   chr10  1200  1203  ttt
   chr22  1600  1603  AAA

- **Grouping on column 4** while ignoring case, and performing operation **Count on column 1** will return::

   AAA    2
   TTT    3
   
- **Grouping on column 4** while not ignoring case, and performing operation **Count on column 1** will return::

   aaa    1
   AAA    1
   ttt    1
   TTT    2
  </help>
</tool>