Mercurial > repos > agordon > datamash_wrapper
changeset 10:ee35019e3cba
merged updates to 1.0.6 from test-toolshed
author | Assaf Gordon <agordon@wi.mit.edu> |
---|---|
date | Sat, 22 Nov 2014 21:13:52 -0500 |
parents | f6af66d4ded6 (current diff) fecc95defba2 (diff) |
children | 687db8c37dcf |
files | tool_dependencies.xml |
diffstat | 8 files changed, 322 insertions(+), 2 deletions(-) [+] |
line wrap: on
line diff
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/datamash-ops.xml Sat Nov 22 21:13:52 2014 -0500 @@ -0,0 +1,174 @@ +<tool id="DatamashOps" name="Datamash" version="1.0.6"> + <description>(operations on tabular data)</description> + + <requirements> + <requirement type="package" version="1.0.6">datamash</requirement> + </requirements> + + <command> + datamash + $header_in + $header_out + $need_sort + $print_full_line + $ignore_case + #if str($grouping).strip() + --group '$grouping' + #end if + #for $oper in $operations + ${oper.op_name} + ${oper.op_column} + #end for + < $in_file > $out_file + </command> + <inputs> + <param format="tabular" name="in_file" type="data" label="Select Input Data" help=""/> + + <param name="grouping" label="Group by fields" type="text" help="Example: 1,4 - To group by the first and fourth fields. Leave empty to perform operation on entire file as one group."> + <validator type="regex" message="invalid fields value">^[0-9, ]*$</validator> + </param> + + <param name="header_in" type="boolean" truevalue="--header-in" falsevalue="" + label="Input file has a header line" help="Mark this if the input file's first line is a header line" /> + + <param name="header_out" type="boolean" truevalue="--header-out" falsevalue="" + label="Print header line" help="Mark this if you want the first line to show the field names" /> + + <param name="need_sort" type="boolean" truevalue="--sort" falsevalue="" + label="Sort input" help="Mark if the input file is not sorted. If the input file is already sorted, unmark this option to reduce computing time." /> + + <param name="print_full_line" type="boolean" truevalue="--full" falsevalue="" + label="Print all fields from input file" help="If set, all input fields will be printed. If unset, only fields used for grouping will be printed." /> + + <param name="ignore_case" type="boolean" truevalue="--ignore-case" falsevalue="" + label="Ignore case when grouping" help="If set, upper/lowercase differences will be ignored when grouping fields." /> + + <repeat name="operations" title="Operation to perform on each group" min="1" default="1"> + <param name="op_name" type="select" label="Type"> + <option value="count">count</option> + <option value="sum">sum</option> + <option value="min">minimum</option> + <option value="max">maximum</option> + <option value="absmin">Absolute minimum</option> + <option value="absmax">Absolute maximum</option> + <option value="mean">Mean</option> + <option value="pstdev">Population Standard deviantion</option> + <option value="sstdev">Sample Standard deviantion</option> + <option value="median">Median</option> + <option value="q1">1st quartile</option> + <option value="q3">3rd quartile</option> + <option value="iqr">Inter-quartile range</option> + <option value="mad">Median Absolute Deviation</option> + <option value="pvar">Variance (population)</option> + <option value="svar">Variance (sample)</option> + <option value="sskew">Skewness (sample)</option> + <option value="pskew">Skewness (population)</option> + <option value="skurt">Kurtosis (sample)</option> + <option value="pkurt">Kurtosis (population)</option> + <option value="jarque">Jarque-Bera Normality test</option> + <option value="dpo">DAgostino-Pearson Omnibus Normality Test</option> + <option value="mode">Mode</option> + <option value="antimode">Anti-Mode</option> + <option value="unique">Combine all unique values</option> + <option value="collapse">Combine all values</option> + <option value="countunique">Count Unique values</option> + </param> + <param name="op_column" label="On column" type="data_column" data_ref="in_file" /> + </repeat> + </inputs> + + <outputs> + <data format="tabular" name="out_file" /> + </outputs> + + <tests> + <test> + <param name="in_file" value="group_compute_input.txt" /> + <param name="grouping" value="2" /> + <param name="header_in" value="true" /> + <param name="header_out" value="true" /> + <param name="need_sort" value="true" /> + <param name="print_full_line" value="false" /> + <param name="op_column" value="3" /> + <param name="op_name" value="sum" /> + <param name="ignore_case" value="false" /> + <output name="out_file" file="group_compute_output.txt" /> + </test> + </tests> +<help> + +.. class:: infomark + +**TIP:** Input data must be TAB delimited. If the desired dataset does not appear in the input list, use *Text Manipulation->Convert* to convert it to **Tabular** type. + +----- + +**Syntax** + +This tools performs common operations (such as summing, counting, mean, standard-deviation) on input file, based on tabular data. The tool can also optionaly group the input based on a given field. + +----- + +**Example 1** + +- Find the average score in statistics course of college students, grouped by their college major. The input file has three fields (Name,Major,Score) and a header line:: + + Name Major Score + Bryan Arts 68 + Isaiah Arts 80 + Gabriel Health-Medicine 100 + Tysza Business 92 + Zackery Engineering 54 + ... + ... + +- Grouping the input by the second column (*Major*), and performing operations **mean** and **sample standard deviation** on the third column (*Score*), gives:: + + GroupBy(Major) mean(Score) sstdev(Score) + Arts 68.9474 10.4215 + Business 87.3636 5.18214 + Engineering 66.5385 19.8814 + Health-Medicine 90.6154 9.22441 + Life-Sciences 55.3333 20.606 + Social-Sciences 60.2667 17.2273 + +This sample file is available at http://www.gnu.org/software/datamash . + +**Example 2** + +- Using the UCSC RefSeq Human Gene Track, available at: http://hgdownload.soe.ucsc.edu/goldenPath/hg38/database/refGene.txt.gz + +- List the number and identifiers of isoforms per gene. The gene identifier is in column 13, the isoform/transcript identifier is in column 2. Grouping by column 13 and performing **count** and **Combine all values** on column 2, gives:: + + GroupBy(field-13) count(field-2) collapse(field-2) + A1BG 1 NM_130786 + A1BG-AS1 1 NR_015380 + A1CF 6 NM_001198818,NM_001198819,NM_001198820,NM_014576,NM_138932,NM_138933 + A2M 1 NM_000014 + A2M-AS1 1 NR_026971 + A2ML1 2 NM_001282424,NM_144670 + ... + +- Count how many transcripts are listed for each chromosome and strand. Chromosome is on column 3, Strand is in column 4. Transcript identifiers are in column 2. Grouping by columns **3,4** and performing operation **count** on column 2, gives:: + + GroupBy(field-3) GroupBy(field-4) count(field-2) + chr1 + 2456 + chr1 - 2431 + chr2 + 1599 + chr2 - 1419 + chr3 + 1287 + chr3 - 1249 + ... + +----- + +**GNU Datamash** is a Free and Open Source Software, see more details on the Datamash_ Website. + +**GNU Datamash** is also available as a command-line program, see http://www.gnu.org/software/datamash/download/ . + +For more details about supported statistical operations, see Datamash_ website. + +.. _Datamash: http://www.gnu.org/software/datamash/ + +</help> +</tool>
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/datamash-reverse.xml Sat Nov 22 21:13:52 2014 -0500 @@ -0,0 +1,64 @@ +<tool id="DatamashReverse" name="Reverse" version="1.0.6"> + <description>columns in a tabular file</description> + + <requirements> + <requirement type="package" version="1.0.6">datamash</requirement> + </requirements> + + <command> + datamash -W reverse < $in_file > $out_file + </command> + <inputs> + <param format="tabular" name="in_file" type="data" label="Select Input Data" help=""/> + </inputs> + <outputs> + <data format="tabular" name="out_file" /> + </outputs> + <tests> + <test> + <param name="in_file" value="datamash_reverse_input.txt" /> + <output name="out_file" file="datamash_reverse_output.txt" /> + </test> + </tests> +<help> + +.. class:: infomark + +**TIP:** Input data must be TAB delimited. If the desired dataset does not appear in the input list, use *Text Manipulation->Convert* to convert it to **Tabular** type. + +----- + +**Syntax** + +This tools reverses the order of columns in a tabular input file. + +----- + +**Example** + +Input file:: + + Genes Sample Counts + NOX1 A1 514 + DcP A2 542 + HH B3 490 + +Output file:: + + Counts Sample Genes + 514 A1 NOX1 + 542 A2 DcP + 490 B3 HH + +----- + +**GNU Datamash** is a Free and Open Source Software, see more details on the Datamash_ Website. + +**GNU Datamash** is also available as a command-line program, see http://www.gnu.org/software/datamash/download/ . + +For more details about supported statistical operations, see Datamash_ website. + +.. _Datamash: http://www.gnu.org/software/datamash/ + +</help> +</tool>
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/datamash-transpose.xml Sat Nov 22 21:13:52 2014 -0500 @@ -0,0 +1,64 @@ +<tool id="DatamashTranspose" name="Transpose" version="1.0.6"> + <description>rows/columns in a tabular file</description> + + <requirements> + <requirement type="package" version="1.0.6">datamash</requirement> + </requirements> + + <command> + datamash -W transpose < $in_file > $out_file + </command> + <inputs> + <param format="tabular" name="in_file" type="data" label="Select Input Data" help=""/> + </inputs> + <outputs> + <data format="tabular" name="out_file" /> + </outputs> + <tests> + <test> + <param name="in_file" value="datamash_transpose_input.txt" /> + <output name="out_file" file="datamash_transpose_output.txt" /> + </test> + </tests> +<help> + +.. class:: infomark + +**TIP:** Input data must be TAB delimited. If the desired dataset does not appear in the input list, use *Text Manipulation->Convert* to convert it to **Tabular** type. + +----- + +**Syntax** + +This tools transposes (swaps) rows/columns in a tabular input file. + +----- + +**Example** + +Input file:: + + Genes NOX1 DcP HH + Sample A1 A2 B3 + Counts 514 542 490 + +Output file:: + + Genes Sample Counts + NOX1 A1 514 + DcP A2 542 + HH B3 490 + + +----- + +**GNU Datamash** is a Free and Open Source Software, see more details on the Datamash_ Website. + +**GNU Datamash** is also available as a command-line program, see http://www.gnu.org/software/datamash/download/ . + +For more details about supported statistical operations, see Datamash_ website. + +.. _Datamash: http://www.gnu.org/software/datamash/ + +</help> +</tool>
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/datamash_reverse_input.txt Sat Nov 22 21:13:52 2014 -0500 @@ -0,0 +1,4 @@ +Genes Sample Counts +NOX1 A1 514 +DcP A2 542 +HH B3 490
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/datamash_reverse_output.txt Sat Nov 22 21:13:52 2014 -0500 @@ -0,0 +1,4 @@ +Counts Sample Genes +514 A1 NOX1 +542 A2 DcP +490 B3 HH
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/datamash_transpose_input.txt Sat Nov 22 21:13:52 2014 -0500 @@ -0,0 +1,3 @@ +Genes NOX1 DcP HH +Sample A1 A2 B3 +Counts 514 542 490
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/datamash_transpose_output.txt Sat Nov 22 21:13:52 2014 -0500 @@ -0,0 +1,4 @@ +Genes Sample Counts +NOX1 A1 514 +DcP A2 542 +HH B3 490
--- a/tool_dependencies.xml Thu Jul 17 13:05:50 2014 -0400 +++ b/tool_dependencies.xml Sat Nov 22 21:13:52 2014 -0500 @@ -1,6 +1,9 @@ <?xml version="1.0"?> <tool_dependency> - <package name="datamash" version="1.0.5"> - <repository changeset_revision="3754fb0b3b76" name="package_datamash_1_0_5" owner="agordon" toolshed="http://toolshed.g2.bx.psu.edu" /> + <package name="datamash" version="1.0.6"> + <repository changeset_revision="2929953d00e1" + name="package_datamash_1_0_6" + owner="agordon" + toolshed="http://toolshed.g2.bx.psu.edu" /> </package> </tool_dependency>