Mercurial > repos > iuc > datamash_transpose

comparison datamash-transpose.xml @ 9:a1cdc32ea989 draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/datamash commit 9edd054251bc74685d627360bb0fbe8ea60fa6a2
author iuc
date Thu, 23 Mar 2023 20:46:30 +0000
parents 70522b458053
children 3dcdff1ab5ac
comparison
equal deleted inserted replaced
8:6b5617f5d4ce 9:a1cdc32ea989
1 <tool id="datamash_transpose" name="Transpose" version="@TOOL_VERSION@+galaxy@VERSION_SUFFIX@" profile="@PROFILE@"> 1 <tool id="datamash_transpose" name="Transpose" version="@TOOL_VERSION@+galaxy@VERSION_SUFFIX@" profile="@PROFILE@">
2 <description>rows/columns in a tabular file</description> 2 <description>rows/columns in a tabular file</description>
3 <macros> 3 <macros>
4 <import>macros.xml</import> 4 <import>macros.xml</import>
5 </macros> 5 </macros>
6 <expand macro="requirements" /> 6 <edam_topics>
7 <expand macro="stdio" /> 7 <edam_topic>topic_3570</edam_topic> <!-- Pure math / linear algebra -->
8 </edam_topics>
9 <edam_operations>
10 <!-- <edam_operation>operation_1234</edam_operation> -->
11 </edam_operations>
12 <expand macro="requirements"/>
13 <expand macro="stdio"/>
8 <command><![CDATA[ 14 <command><![CDATA[
9 datamash transpose 15 #import os
10 @FIELD_SEPARATOR@ 16 #set file_size_MB = os.path.getsize(str($in_file)) / (1024 * 1024)
11 < $in_file > $out_file 17 #set size_threshold_MB = 1024
18 #if $file_size_MB <= $size_threshold_MB:
19 datamash transpose @FIELD_SEPARATOR@ < $in_file > $out_file
20 #else:
21 ## Input matrix is very big: divide and conquer
22 ## If the input file is very big, datamash runs out of memory (much earlier than file size ~ available RAM.
23 ## Split into managable chunks of row vectors, transpose the chunks and juxtapose column vector chunks.
24 #set num_chunks = 1 + int(file_size_MB/size_threshold_MB)
25 echo Huge matrix detected, processing in $num_chunks chunks. &&
26 split -n l/$num_chunks $in_file split_input_ &&
27 for chunk in \$(ls split_input*); do
28 datamash transpose @FIELD_SEPARATOR@ < \$chunk > \${chunk}_transposed;
29 done &&
30 paste split_input_*_transposed > $out_file
31 #end if
12 ]]></command> 32 ]]></command>
13 <expand macro="inputs_outputs" /> 33 <expand macro="inputs_outputs"/>
14 <tests> 34 <tests>
35 <test expect_num_outputs="1">
36 <param name="in_file" value="datamash_transpose_input.txt"/>
37 <output file="datamash_transpose_output.txt" name="out_file"/>
38 </test>
39 <!-- Test for transposing an extremely big input matrix
40 Disabled to keep the repository size reasonable.
41 For testing, manually download a pathological in- and output from:
42 https://usegalaxy.eu/u/tunc/h/very-big-scrna-matrix
43 -->
44 <!--
15 <test> 45 <test>
16 <param name="in_file" value="datamash_transpose_input.txt" /> 46 <param name="in_file" value="big.tabular"/>
17 <output file="datamash_transpose_output.txt" name="out_file" /> 47 <output file="transposed_big.tabular" name="out_file"/>
18 </test> 48 </test>
49 -->
50 <!-- transpose(transpose(A)) = A -->
51 <!--
52 <test>
53 <param name="in_file" value="transposed_big.tabular"/>
54 <output file="big.tabular" name="out_file"/>
55 </test>
56 -->
19 </tests> 57 </tests>
20 <help> 58 <help>
21 <![CDATA[ 59 <![CDATA[
22 @HELP_HEADER@ 60 @HELP_HEADER@
23 61
43 HH B3 490 81 HH B3 490
44 82
45 @HELP_FOOTER@ 83 @HELP_FOOTER@
46 ]]> 84 ]]>
47 </help> 85 </help>
86 <expand macro="citation"/>
48 </tool> 87 </tool>