view ez_histograms.xml @ 1:fbedb212982d draft default tip

planemo upload for repository https://github.com/artbio/tools-artbio/tree/main/tools/ez_histograms commit 5e25392164eca5585239b62c82b7f6ba326cda6e

<tool id="ez_histograms" name="ez_histograms" version="@TOOL_VERSION@+galaxy@VERSION_SUFFIX@" profile="@PROFILE@">
    <macros>
        <token name="@TOOL_VERSION@">3.4.4</token>
        <token name="@VERSION_SUFFIX@">1</token>
        <token name="@PROFILE@">23.0</token>
    </macros>
    <requirements>
        <requirement type="package" version="3.4.4">r-ggplot2</requirement>
        <requirement type="package" version="1.4.4">r-reshape2</requirement>
        <requirement type="package" version="1.1.4">r-dplyr</requirement>
        <requirement type="package" version="1.3.0">r-scales</requirement>
        <requirement type="package" version="2.4.1">r-psych</requirement>
        <requirement type="package" version="1.7.4">r-optparse</requirement>
    </requirements>

    <stdio>
        <exit_code range="1:" level="fatal" />
    </stdio>
    
    <command detect_errors="exit_code"><![CDATA[
    Rscript $__tool_directory__/ez_histograms.R
        --file '$file'
        --profile '$plot_options.plot_options_selector'
        --xscale '$plot_options.xscale'
        #if str($plot_options.plot_options_selector) == "count":
            --yscale '$plot_options.yscale'
        #end if
        --pdf '$pdf'
        --summary '$summary'
    ]]></command>

    <inputs>
        <param name="file" type="data" format="tabular" label="Input tabular dataset"
               help="Only numeric columns will be plotted"/>
        <conditional name="plot_options">
            <param name="plot_options_selector" type="select" label="Set plot types">
                <option value="count" selected="true">Count Histograms</option>
                <option value="density">Density Plots</option>
            </param>
            <when value="density">
                <param name="xscale" type="select" label="Set x-axis scale">
                    <option value="cartesian" selected="true">Cartesian</option>
                    <option value="log2">log2</option>
                    <option value="log10">log10</option>
                </param>
            </when>
            <when value="count">
                <param name="xscale" type="select" label="Set x-axis scale">
                    <option value="cartesian" selected="true">Cartesian</option>
                    <option value="log2">log2</option>
                    <option value="log10">log10</option>
                </param>
                <param name="yscale" type="select" label="Set y-axis scale">
                    <option value="cartesian" selected="true">Cartesian</option>
                    <option value="log2">log2</option>
                    <option value="log10">log10</option>
                </param>
            </when>
        </conditional>
    </inputs>
    <outputs>
        <data name="pdf" format="pdf" label="${tool.name} plots from ${on_string}"/>
        <data name="summary" format="tabular" label="Statistics Summary from ${on_string}"/>
    </outputs>
    <tests>
        <test expect_num_outputs="2">
            <param name="file" value="classic.tsv"/>
            <param name="plot_options_selector" value="count"/>
            <param name="xscale" value="cartesian"/>
            <param name="yscale" value="cartesian"/>
            <output name="pdf" file="classic.pdf"/>
            <output name="summary" file="summary_1.tsv"/>
       </test>
        <test expect_num_outputs="2">
            <param name="file" value="counts.tsv"/>
            <param name="plot_options_selector" value="count"/>
            <param name="xscale" value="log2"/>
            <param name="yscale" value="cartesian"/>
            <output name="pdf" file="count.pdf"/>
            <output name="summary" file="summary_2.tsv"/>
       </test>
        <test expect_num_outputs="2">
            <param name="file" value="headless.tsv"/>
            <param name="plot_options_selector" value="count"/>
            <param name="xscale" value="log10"/>
            <param name="yscale" value="log2"/>
            <output name="pdf" file="headless.pdf"/>
            <output name="summary" file="summary_3.tsv"/>
       </test>
        <test expect_num_outputs="2">
            <param name="file" value="large.tsv"/>
            <param name="plot_options_selector" value="density"/>
            <param name="xscale" value="log2"/>
            <output name="pdf" file="large.pdf"/>
            <output name="summary" file="summary_4.tsv"/>
       </test>
        <test expect_num_outputs="2">
            <param name="file" value="rowheadless.tsv"/>
            <param name="plot_options_selector" value="density"/>
            <param name="xscale" value="cartesian"/>
            <output name="pdf" file="rowheadless.pdf"/>
            <output name="summary" file="summary_5.tsv"/>
       </test>
        <test expect_num_outputs="2">
            <param name="file" value="single_headed_col.tsv"/>
            <param name="plot_options_selector" value="density"/>
            <param name="xscale" value="log10"/>
            <output name="pdf" file="single_headed_col.pdf"/>
            <output name="summary" file="summary_6.tsv"/>
       </test>
        <test expect_num_outputs="2">
            <param name="file" value="misleading_ids.tsv"/>
            <param name="plot_options_selector" value="density"/>
            <param name="xscale" value="cartesian"/>
            <output name="pdf" file="misleading_ids.pdf"/>
            <output name="summary" file="summary_7.tsv"/>
       </test>
    </tests>
    <help><![CDATA[
**What it does**

The tool generates faceted histograms or density plots using the ggplot2 functions
geom_histogram() or geom_density(), respectively.

**Inputs**

Any regular tabular data, provided that the number of columns (tabulations) is unchanged
for any row.

Except for the first one, any column will be considered as one variable with n_rows
observations. However, non-numeric columns will be filtered and will not be considered
variables.

If the first column is not numeric, it will be taken as row names (ie observation identifiers),
otherwise, it will be considered as the first numerical variable of the table.

If the first row is not numerical, it will be considered as a header, ie as describing the
variable names.

If you provide a table without header, variable names will be assigned to each column
following the R default rule: (V1), V2, ..., Vn

**Parameters**

For Count Histograms, both x- and y-axis can have linear (cartesian), log2 or log10 scales.

For Density Plots, only x-axis can be customized with linear (cartesian), log2, or log10
scales

**Outputs**

The ez_histograms Galaxy tool returns

- A pdf file with plots faceted on three columns
- A tsv file with statistics summary of the variables generated by the R package psych

    ]]></help>
    <citations>
        <citation type="bibtex">
@BOOK{Wickham2016-ic,
    title = "Ggplot2: Elegant graphics for data analysis",
    author = "Wickham, Hadley",
    publisher = "Springer International Publishing",
    series = "Use R!",
    edition = 2,
    month = jun,
    year = 2016,
    address = "Cham, Switzerland",
    language = "en",
    isbn = "9783319242774"
}        </citation>
    </citations>
</tool>