annotate sample.xml @ 0:447272175720 draft default tip

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

<tool id="csvtk_sample" name="csvtk-sample" version="@VERSION@+@GALAXY_VERSION@">
    <description> random proportion of dataset</description>
    <macros>
        <import>macros.xml</import>
    </macros>
    <expand macro="requirements" />
    <expand macro="version_cmd" />
    <command detect_errors="exit_code"><![CDATA[

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

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

    ## Add additional flags as specified ##
    #######################################
    $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'

    ## other ##
    ###########
    -p '$proportion'
    -s '$seed'
    $line_number

    ## To output ##
    ###############
    &> sampled

    ]]></command>
    <inputs>
        <expand macro="singular_input" />
        <param name="proportion" type="float" argument="-p" value="0.5"
            min="0"
            max="1"
            label="Proportion of Data to Sample"
        />
        <param name="seed" type="integer" argument="-s" value="1900"
            label="Random Seed"
            help="Specify a seed number to sample data with"
        />
        <param name="line_number" type="boolean" checked="false" argument="-n"
            truevalue="-n"
            falsevalue=""
            label="Create column with original line numbers of sampled data"
        />
        <expand macro="global_parameters" />
    </inputs>
    <outputs>
        <data format_source="in_1" name="sampled" from_work_dir="sampled" label="${proportion} of ${in_1.name} sampled" />
    </outputs>
    <tests>
        <test>
            <param name="in_1" value="plot.csv" />
            <param name="proportion" value="0.5" />
            <param name="seed" value="11" />
            <output name="sampled" value="sampled_1.csv" />
        </test>
        <test>
            <param name="in_1" value="plot.csv" />
            <param name="proportion" value="0.7" />
            <param name="seed" value="11" />
            <param name="line_number" value="true" />
            <output name="sampled" value="sampled_2.csv" />
        </test>
    </tests>
    <help><![CDATA[
    
Csvtk - Sample Help
-------------------

Info
####

Csvtk-sample samples a random (as defined by the seed) proportion of a dataset that can be used further.  

.. class:: warningmark

    Single quotes are not allowed in text inputs!

@HELP_INPUT_DATA@


Usage
#####

To run csvtk-sample, all you need is a valid (as defined above) CSV or TSV file.

**Example**

Input table:

+-------+--------+
| Group | Length | 
+=======+========+
| 1     | 1500   |
+-------+--------+
| 2     | 1000   |
+-------+--------+
| 1     | 1500   |
+-------+--------+
| 3     | 2000   |
+-------+--------+

To get a 0.5 proportion (50% sample) of the population, our input would be 0.5 for the proportion (-p) and then some random seed.

Our output could then look as such:

+-------+--------+
| Group | Length |
+=======+========+
| 1     | 1500   |
+-------+--------+
| 3     | 2000   |
+-------+--------+

If we used the same seed, input, and proportion with the "Create column with original line numbers of sampled data"
set to yes, we would get the following table:

+---+-------+--------+
| n | Group | Length |
+===+=======+========+
| 1 | 1     | 1500   |
+---+-------+--------+
| 4 | 3     | 2000   |
+---+-------+--------+

--------


@HELP_COLUMNS@


@HELP_END_STATEMENT@


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