view join_files_on_column_fuzzy.xml @ 0:64469e7ecf9f draft

planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/text_processing/join_files_on_column_fuzzy commit fd2bc86108994c9eda731b305ca6a8c71554cfaa
author bgruening
date Sun, 26 Nov 2017 16:13:51 -0500
parents
children 8750c3125ec5
line wrap: on
line source

<tool id="join_files_on_column_fuzzy" name="Join two files" version="1.0.0">
    <description>
        on column allowing a small difference
    </description>
    <requirements>
        <requirement type="package" version="3.6">python</requirement> 
    </requirements>
    <command>
    <![CDATA[
python '$__tool_directory__/join_files_on_column_fuzzy.py'
--f1 '$f1'
--f2 '$f2'
--c1 $c1
--c2 $c2
--outfile '$merged_file'
$header
$add_distance
#if $merge_mode.merge_mode_select == 'closest':
    --closest
#else:
    --distance $merge_mode.distance
    --unit $merge_mode.units
#end if
    ]]>
    </command>
    <inputs>
        <param argument="--f1" type="data" optional="true" format="tabular" label="1st file"
            help=""/>
        <param argument="--c1" type="data_column" data_ref="f1" label="Column to use from 1st file" help="The file needs to be sorted by this column, ascending."/>
        <param argument="--f2" type="data" optional="true" format="tabular" label="2nd file"
            help=""/>
        <param argument="--c2" type="data_column" data_ref="f2" label="Column to use from 2nd file" help="The file needs to be sorted by this column, ascending."/>

        <param argument="--header" type="boolean" checked="false" truevalue="--header" falsevalue="" label="Does the input files contain a header line" />
        <param argument="--add_distance" type="boolean" checked="false" truevalue="--add_distance" falsevalue="" label="Add an addional column with the calculated distance." />

        <conditional name="merge_mode">
            <param name="merge_mode_select" type="select" label="Choose the mode of merging.">
                <option value="closest" selected="True">Best match (in case of multiple best matches, only the first one is reported)</option>
                <option value="distance">Matching with a defined distance</option>
            </param>
            <when value="closest"/>
            <when value="distance">
                <param name="units" display="radio" type="select" value="ppm_value" label="Choose the metrics of your distance"
                    help="ppm is useful for very small differences">
                        <option value="absolute" selected="True">Absolute distance</option>
                        <option value="ppm" >Distance in ppm</option>
                </param>
                <param name="distance" value="0.2" type="float" label="Allowed distance between the two values that will trigger a merge" help=""/>
            </when>
        </conditional>
    </inputs>
    <outputs>
        <data name="merged_file" format="tabular" />
    </outputs>

    <tests>
        <test>
            <param name="f1" value="file1.tab" ftype="tabular"/>
            <param name="f2" value="file2.tab" ftype="tabular"/>
            <param name="c1" value="1"/>
            <param name="c2" value="1"/>
            <param name="merge_mode_select" value="distance"/>
            <param name="distance" value="0.1"/>
            <param name="units" value="absolute"/>
            <output name="merged_file" file="no_header_result1.tab" />
        </test>
        <test>
            <param name="f1" value="file1_header.tab" ftype="tabular"/>
            <param name="f2" value="file2_header.tab" ftype="tabular"/>
            <param name="c1" value="1"/>
            <param name="c2" value="1"/>
            <param name="merge_mode_select" value="distance"/>
            <param name="distance" value="0.2"/>
            <param name="units" value="absolute"/>
            <param name="header" value="true"/>
            <output name="merged_file" file="header_result2.tab" />
        </test>
        <test>
            <param name="f1" value="file1_header.tab" ftype="tabular"/>
            <param name="f2" value="file2_header.tab" ftype="tabular"/>
            <param name="c1" value="1"/>
            <param name="c2" value="1"/>
            <param name="header" value="true"/>
            <param name="closest" value="true"/>
            <output name="merged_file" file="header_closest_result3.tab" />
        </test>
        <test>
            <param name="f1" value="file1_ppm.tab" ftype="tabular"/>
            <param name="f2" value="file2_ppm.tab" ftype="tabular"/>
            <param name="c1" value="1"/>
            <param name="c2" value="1"/>
            <param name="header" value="false"/>
            <param name="merge_mode_select" value="distance"/>
            <param name="distance" value="100"/>
            <param name="units" value="ppm"/>
            <output name="merged_file" file="no_header_ppm_result4.tab" />
        </test>
        <test>
            <param name="f1" value="file1_header.tab" ftype="tabular"/>
            <param name="f2" value="file2_header.tab" ftype="tabular"/>
            <param name="c1" value="1"/>
            <param name="c2" value="1"/>
            <param name="header" value="true"/>
            <param name="closest" value="true"/>
            <param name="add_distance" value="true"/>
            <output name="merged_file" file="header_closest_result5.tab" />
        </test>
        <test>
            <param name="f1" value="file1_ppm.tab" ftype="tabular"/>
            <param name="f2" value="file2_ppm.tab" ftype="tabular"/>
            <param name="c1" value="1"/>
            <param name="c2" value="1"/>
            <param name="header" value="false"/>
            <param name="merge_mode_select" value="distance"/>
            <param name="distance" value="100"/>
            <param name="units" value="ppm"/>
            <param name="add_distance" value="true"/>
            <output name="merged_file" file="no_header_ppm_result6.tab" />
        </test>
    </tests>
    <help>
<![CDATA[

Join two files on a common column. It is possible to provide an allowed difference between both values (currently only numbers)
as the absolute differece or as PPM. 

Two modes are available: 

1. In the **best match** mode only the rows are merged for the most similar (or identical) values. In case of multiple best matches, only the first one is reported.

1. The **Matching with a defined distance** option will offer you the possibility
to provide a distance between the two values of the columns. Is the calculates distance smaller or equal than the given distance the columns will be joined. You can specify the allowed distance as an absolute distance or as PPM.


]]>
    </help>
    <citations>
    </citations>
</tool>