annotate freq.xml @ 0:a288e0146c2e draft default tip

"planemo upload for repository https://github.com/shenwei356/csvtk commit 3a97e1b79bf0c6cdd37d5c8fb497b85531a563ab"

<tool id="csvtk_freq" name="csvtk-freq" version="@VERSION@+@GALAXY_VERSION@">
    <description>of value in column(s)</description>
    <macros>
        <import>macros.xml</import>
    </macros>
    <expand macro="requirements" />
    <expand macro="version_cmd" />
    <command detect_errors="exit_code"><![CDATA[

###################
## Start Command ##
###################

csvtk freq --num-cpus "\${GALAXY_SLOTS:-1}"

    ## Add additional flags as specified ##
    #######################################
    $ignore_case
    $global_param.illegal_rows
    $global_param.empty_rows
    $global_param.header
    $global_param.lazy_quotes

    ## Set Tabular input/output flag if input is tabular ##
    #######################################################
    #if $in_1.is_of_type("tabular"):
        -t -T
    #end if

    ## Set Input ##
    ###############
    '$in_1'

    ## Specify fields for freq ##
    #############################
    -F -f '$column_text.in_text'

    ## Sorting? ##
    ##############
    #if $sorting.want_sort == 'yes_sort'

        #if $sorting.how_sort == 'frequency'
            -n
        #elif $sorting.how_sort == 'alphabetical'
            -k
        #end if

        #if $sorting.reverse_sort == 'yes_reverse'
            -r
        #end if
    #end if

    ## To output ##
    ###############
    > freq

    ]]></command>
    <inputs>
        <expand macro="singular_input" />
        <expand macro="fields_input" />
        <expand macro="ignore_case" />
        <expand macro="global_parameters" />
        <conditional name="sorting" >
            <param type="select" name="want_sort"
                label="Sort Output Columns?"
                help="Change the order of output column(s)">
                <option value="no_sort">No</option>
                <option value="yes_sort">Yes</option>
            </param>
            <when value="no_sort" />
            <when value="yes_sort">
                <param type="select" name="how_sort" label="How to Sort Output">
                    <option value="frequency">Frequency (Low -> High)</option>
                    <option value="alphabetical">Alphabetical</option>
                </param>
                <param type="select" name="reverse_sort" label="Reverse Sort" help="Sort in reverse order. IE. highest to lowest or reverse alphabetical" >
                    <option value="no_reverse">No</option>
                    <option value="yes_reverse">Yes</option>
                </param>
            </when>
        </conditional>
    </inputs>
    <outputs>
        <data format_source="in_1" name="freq" from_work_dir="freq" label="${in_1.name} frequency of column(s) ${column_text.in_text}" />
    </outputs>
    <tests>
        <test>
            <param name="in_1" value="blood_type.tsv" />
            <conditional name="column_text">
                <param name="select" value="string" />
                <param name="in_text" value="2,3" />
            </conditional>
            <conditional name="sorting" >
                <param name="want_sort" value="no_sort" />
            </conditional>
            <output name="freq" file="frequency.tsv" ftype="tabular" />
        </test>
    </tests>
    <help><![CDATA[
    
Csvtk - Freq Help
-----------------

Info
####
Find the frequency of the data based on the selected column(s).

If one column is selected, the frequency will be the number of times each value is found in the column. These can further be sorted if so desired.

Examples can be found in the usage section below!

.. class:: warningmark

    Single quotes are not allowed in text inputs!

@HELP_INPUT_DATA@


Usage
#####

To run csvtk-freq, all you need is a valid (as defined above) CSV or TSV and the column(s) that you want the frequency of.

**Ex. of frequency with one column:**

+------------+-----------+
| Blood Type | Frequency |
+============+===========+
| A          | 31        |
+------------+-----------+
| B          | 103       |
+------------+-----------+
| etc.       | etc.      |
+------------+-----------+

----

**Ex. of frequency with more than one column for frequency:**

+---------+------------+-----------+
| Name    | Blood Type | Frequency |
+=========+============+===========+
| Bob     | A          | 4         |
+---------+------------+-----------+
| Jacob   | B          | 5         |
+---------+------------+-----------+
| Matthew | O          | 12        |
+---------+------------+-----------+
| Darian  | AB         | 1         |
+---------+------------+-----------+

With multiple columns, you end up getting the frequency of how many times the values from each column
are found together. In this example from an input dataset of names and bloodtypes, we can find the frequency that
each name in our database is a certain bloodtype. 

Here, we can note that there are 4 people named bob with blood type A.

----

@HELP_COLUMNS@


@HELP_END_STATEMENT@


    ]]></help>
    <expand macro="citations" />
</tool>