Mercurial > repos > nml > csvtk_summary
diff summary.xml @ 0:ceb70f0dd898 draft default tip
"planemo upload for repository https://github.com/shenwei356/csvtk commit 3a97e1b79bf0c6cdd37d5c8fb497b85531a563ab"
| author | nml |
|---|---|
| date | Tue, 19 May 2020 17:23:57 -0400 |
| parents | |
| children |
line wrap: on
line diff
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/summary.xml Tue May 19 17:23:57 2020 -0400 @@ -0,0 +1,396 @@ +<tool id="csvtk_summary" name="csvtk-summary" version="@VERSION@+@GALAXY_VERSION@"> + <description> statistics of selected fields</description> + <macros> + <import>macros.xml</import> + </macros> + <expand macro="requirements" /> + <expand macro="version_cmd" /> + <command detect_errors="exit_code"><![CDATA[ + +## Set Up Input ## +################## + +#set input_list = list() +#for $repeat in $field + #silent $input_list.append(str($repeat.column_text.in_text) + ":" + str($repeat.analysis_type)) +#end for + +#set input_total = ",".join($input_list) + +################### +## Start Command ## +################### + +csvtk summary --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' + + ## Specify fields ## + #################### + -f '$input_total' + + ## other ## + ########### + + #if $group_field.select_group != "none" + -g '$group_field.in_text' + #end if + + -s '$extra.separator' + -S '$extra.rand_int' + -n '$decimal_width' + $ignore_non_digits + + + ## To output ## + ############### + > summary + + ]]></command> + <inputs> + <expand macro="singular_input" /> + <repeat name="field" title="Select Column and Operator" min="1"> + <expand macro="singular_fields_input" /> + <param name="analysis_type" type="select" label="Analysis Type" help="Select analysis type to do on the chosen field"> + <option value="collapse">Collapse</option> + <option value="count">Count</option> + <option value="countn">Count of Digits (countn)</option> + <option value="countunique">Count Unique</option> + <option value="first">First Value</option> + <option value="last">Last Value</option> + <option value="max">Maximum</option> + <option value="mean">Mean</option> + <option value="median">Median</option> + <option value="min">Minimum</option> + <option value="prod">Product of the Elements</option> + <option value="q1">q1</option> + <option value="q2">q2</option> + <option value="q3">q3</option> + <option value="rand">Random Value</option> + <option value="entropy">Shannon Entropy</option> + <option value="stdev">Standard Deviation</option> + <option value="sum">Sum</option> + <option value="uniq">Unique</option> + <option value="variance">Variance</option> + </param> + </repeat> + <expand macro="groups_input" /> + <param name="decimal_width" type="integer" value="2" argument="-n" + label="Number of Decimals" + help="Limit float to N decimal places" + /> + <param name="ignore_non_digits" type="boolean" checked="false" argument="-i" + truevalue="-i" + falsevalue="" + label="Ignore non-digits" + help="Ignore non-digit values in columns. Ex. NA or N/A" + /> + <section name="extra" title="Specific Optional Analysis Modifiers" expanded="false"> + <param name="separator" type="text" value="; " argument="-s" + label="Collapse Separator String" + help="Input string of characters that will separate collapsed columns. The ' character is not allowed"> + <expand macro="text_sanitizer" /> + </param> + <param name="rand_int" type="integer" value="11" argument="-S" + label="Random Value Seed" + help="specify an integer" + /> + </section> + <expand macro="global_parameters" /> + </inputs> + <outputs> + <data format_source="in_1" name="summary" from_work_dir="summary" label="${in_1.name} summary of analyses" /> + </outputs> + <tests> + <test> + <param name="in_1" value="plot.csv" /> + <repeat name="field"> + <conditional name="column_text"> + <param name="select" value="string" /> + <param name="in_text" value="2" /> + </conditional> + <param name="analysis_type" value="collapse" /> + </repeat> + <repeat name="field"> + <conditional name="column_text"> + <param name="select" value="string" /> + <param name="in_text" value="3" /> + </conditional> + <param name="analysis_type" value="count" /> + </repeat> + <repeat name="field"> + <conditional name="column_text"> + <param name="select" value="string" /> + <param name="in_text" value="2" /> + </conditional> + <param name="analysis_type" value="countn" /> + </repeat> + <repeat name="field"> + <conditional name="column_text"> + <param name="select" value="string" /> + <param name="in_text" value="3" /> + </conditional> + <param name="analysis_type" value="countunique" /> + </repeat> + <repeat name="field"> + <conditional name="column_text"> + <param name="select" value="string" /> + <param name="in_text" value="2" /> + </conditional> + <param name="analysis_type" value="entropy" /> + </repeat> + <repeat name="field"> + <conditional name="column_text"> + <param name="select" value="string" /> + <param name="in_text" value="3" /> + </conditional> + <param name="analysis_type" value="first" /> + </repeat> + <repeat name="field"> + <conditional name="column_text"> + <param name="select" value="string" /> + <param name="in_text" value="2" /> + </conditional> + <param name="analysis_type" value="last" /> + </repeat> + <repeat name="field"> + <conditional name="column_text"> + <param name="select" value="string" /> + <param name="in_text" value="3" /> + </conditional> + <param name="analysis_type" value="max" /> + </repeat> + <repeat name="field"> + <conditional name="column_text"> + <param name="select" value="string" /> + <param name="in_text" value="2" /> + </conditional> + <param name="analysis_type" value="mean" /> + </repeat> + <repeat name="field"> + <conditional name="column_text"> + <param name="select" value="string" /> + <param name="in_text" value="3" /> + </conditional> + <param name="analysis_type" value="median" /> + </repeat> + <repeat name="field"> + <conditional name="column_text"> + <param name="select" value="string" /> + <param name="in_text" value="2" /> + </conditional> + <param name="analysis_type" value="min" /> + </repeat> + <repeat name="field"> + <conditional name="column_text"> + <param name="select" value="string" /> + <param name="in_text" value="3" /> + </conditional> + <param name="analysis_type" value="prod" /> + </repeat> + <repeat name="field"> + <conditional name="column_text"> + <param name="select" value="string" /> + <param name="in_text" value="2" /> + </conditional> + <param name="analysis_type" value="q1" /> + </repeat> + <repeat name="field"> + <conditional name="column_text"> + <param name="select" value="string" /> + <param name="in_text" value="3" /> + </conditional> + <param name="analysis_type" value="q2" /> + </repeat> + <repeat name="field"> + <conditional name="column_text"> + <param name="select" value="string" /> + <param name="in_text" value="2" /> + </conditional> + <param name="analysis_type" value="q3" /> + </repeat> + <repeat name="field"> + <conditional name="column_text"> + <param name="select" value="string" /> + <param name="in_text" value="3" /> + </conditional> + <param name="analysis_type" value="rand" /> + </repeat> + <repeat name="field"> + <conditional name="column_text"> + <param name="select" value="string" /> + <param name="in_text" value="2" /> + </conditional> + <param name="analysis_type" value="stdev" /> + </repeat> + <repeat name="field"> + <conditional name="column_text"> + <param name="select" value="string" /> + <param name="in_text" value="3" /> + </conditional> + <param name="analysis_type" value="sum" /> + </repeat> + <repeat name="field"> + <conditional name="column_text"> + <param name="select" value="string" /> + <param name="in_text" value="2" /> + </conditional> + <param name="analysis_type" value="uniq" /> + </repeat> + <repeat name="field"> + <conditional name="column_text"> + <param name="select" value="string" /> + <param name="in_text" value="3" /> + </conditional> + <param name="analysis_type" value="variance" /> + </repeat> + <conditional name="group_field"> + <param name="select_group" value="string" /> + <param name="in_text" value="1" /> + </conditional> + <output name="summary" > + <assert_contents> + <has_text text="collapse" /> + <has_text text="count" /> + <has_text text="countn" /> + <has_text text="countunique" /> + <has_text text="entropy" /> + <has_text text="first" /> + <has_text text="last" /> + <has_text text="max" /> + <has_text text="mean" /> + <has_text text="median" /> + <has_text text="min" /> + <has_text text="prod" /> + <has_text text="q1" /> + <has_text text="q2" /> + <has_text text="q3" /> + <has_text text="rand" /> + <has_text text="stdev" /> + <has_text text="sum" /> + <has_text text="uniq" /> + <has_text text="variance" /> + </assert_contents> + </output> + </test> + </tests> + <help><![CDATA[ + +Csvtk - Summary Help +-------------------- + +Info +#### + +Csvtk Summary works to allow the use of a variety of analysis tools on the selected columns(s) and display one output at the end + +.. class:: warningmark + + Single quotes are not allowed in text inputs! + +@HELP_INPUT_DATA@ + + +Usage +##### + +To run csvtk-summary, all you need is a valid (as defined above) CSV or TSV file with any column(s) that you want to +run one of the analyses on. + +Analyses include: + +- Collapse + +- Count + +- Count Numbers (countn) + +- Count Unique + +- First Value Selection + +- Last Value Selection + +- Maximum + +- Mean + +- Median + +- Minimum + +- q1 + +- q2 + +- q3 + +- Random Value Selection + +- Shannon Entropy + +- Sum + +- Unique Values + +- Variance + +More information on these can be found on the `csvtk website. <https://bioinf.shenwei.me/csvtk/usage/#summary>`_ + +**Example Summary Input** + +Input table: + ++-------+--------+ +| Group | Length | ++=======+========+ +| A | 1500 | ++-------+--------+ +| B | 1000 | ++-------+--------+ +| B | 1500 | ++-------+--------+ +| B | 2000 | ++-------+--------+ + +Suppose you wanted to group the values based on column 1 of the input table and then find out the mean lenght and maximum length for each group. +You would input this into csvtk-summary by creating 2 input repeats where the first one selects "column 2" and an analysis of "mean" and the +second one selects "column 2" with an analysis of "maximum". + +Running this would generate the following output: + ++-------+-------------+------------+ +| Group | Length:mean | Length:max | ++=======+=============+============+ +| A | 1500 | 1500 | ++-------+-------------+------------+ +| B | 1500 | 2000 | ++-------+-------------+------------+ + +-------- + + +@HELP_COLUMNS@ + + +@HELP_END_STATEMENT@ + + + ]]></help> + <expand macro="citations" /> +</tool> \ No newline at end of file