view histogram.xml @ 1:2e7bc1bb2dbe draft default tip

Uploaded

<tool id="histogram_rpy" name="Histogram" version="1.1.0">
  <description>of a numeric column</description>
  <expand macro="requirements" />
    <macros>
        <import>statistic_tools_macros.xml</import>
    </macros>
    <command interpreter="python">
<![CDATA[
        histogram.py
            $input
            $out_file1
            $numerical_column
            "$title"
            "$xlab"
            $breaks
            $density
            $frequency
]]>
    </command>
    <inputs>
        <param name="input" type="data" format="tabular" label="Dataset" help="Dataset missing? See TIP below"/>
        <param name="numerical_column" type="data_column" data_ref="input" numerical="True" label="Numerical column for x axis" />
        <param name="breaks" type="integer" size="4" value="0" label="Number of breaks (bars)"/>
        <param name="title" type="text" size="30" value="Histogram" label="Plot title"/>
        <param name="xlab" type="text" size="30" value="V1" label="Label for x axis"/>
        <param name="density" type="boolean" checked="yes" label="Include smoothed density"/>
        <param name="frequency" type="boolean" checked="no" label="Plot as frequency (counts)"/>
    </inputs>
    <outputs>
        <data format="pdf" name="out_file1" />
    </outputs>
    <tests>
        <test>
            <param name="input" value="histogram_in1.tabular" ftype="tabular"/>
            <param name="numerical_column" value="2"/>
            <param name="breaks" value="0"/>
            <param name="title" value="Histogram"/>
            <param name="xlab" value="V1"/>
            <param name="density" value="true"/>
            <param name="frequency" value="false"/>
            <output name="out_file1" lines_diff="10" file="histogram_out1.pdf"/>
        </test>
    </tests>
  <help>
<![CDATA[

.. class:: infomark

**TIP:** To remove comment lines that do not begin with a *#* character, use *Text Manipulation->Remove beginning*

 .. class:: infomark

**TIP:** If your data is not TAB delimited, use *Text Manipulation->Convert*

-----

**Syntax**

This tool computes a histogram of the numerical values in a column of a dataset.

- All invalid, blank and comment lines in the dataset are skipped.  The number of skipped lines is displayed in the resulting history item.
- **Column for x axis** - only numerical columns are possible.
- **Number of breaks(bars)** - breakpoints between histogram cells. Value of '0' will determine breaks automatically.
- **Plot title** - the histogram title.
- **Label for x axis** - the label of the x axis for the histogram.
- **Include smoothed density** - if checked, the resulting graph will join the given corresponding points with line segments.

-----

**Example**

- Input file::

    1	68	4.1
    2	71	4.6
    3	62	3.8
    4	75	4.4
    5	58	3.2
    6	60	3.1
    7	67	3.8
    8	68	4.1
    9	71	4.3
    10	69	3.7

- Create a histogram on column 2 of the above dataset.

.. image:: $PATH_TO_IMAGES/histogram2.png

]]>
    </help>
</tool>