view g_collocation.xml @ 1:fb617586f4b2 draft

planemo upload commit a81826fe44f09a3710a35c183aa88b745aeec064-dirty

<tool id="Collocation" name="Collocation" version="1.0">
    <description>Generates a list of the most frequent collocations from an input sequence</description>
    <requirements>
        <requirement type="package" version="3.2.1">nltk</requirement>
    </requirements>

    <command interpreter="python">
        g_collocation.py --input $input1 --output $tab_file --freq_filter $freq_filter --results $results --coll_type $collocation_type --pos $pos
    </command>

    <inputs>
        <param name="input1" type="data" format="txt" label="Select a suitable input file from your history"/>
        <param name="job_name" type="text" size="25"
               label="Supply a name for the outputs to remind you what they contain" value="Collocation"/>
        <param name="freq_filter" type="integer" label="The minimum number of required occurrences in the corpus"
               value="0"/>
        <param name="results" type="integer" label="The maximum number of collocations to show in the results"
               value="10"/>
        <param name="collocation_type" type="select" label="" display="radio">
            <option value="bigram">Bigram Collocations</option>
            <option value="trigram">Trigram Collocations</option>
        </param>
        <param name="pos" type="boolean" label="Data input is a set of POS tags"/>
    </inputs>
    <outputs>
        <data format="tabular" name="tab_file" label="${job_name}"/>

    </outputs>
    <options refresh="True"/>
    <help>
        <![CDATA[

Input is a text, optionally with POS tags. Output is a list of the top N collocations ordered by frequency.

]]>

    </help>
</tool>