Mercurial > repos > earlhaminst > hcluster_sg_parser
changeset 3:f9e418125021 draft
planemo upload for repository https://github.com/TGAC/earlham-galaxytools/tree/master/tools/hcluster_sg_parser commit 66af14bc1642c1ca6ceb21f6018c8d665da890e8
| author | earlhaminst |
|---|---|
| date | Fri, 28 Apr 2017 12:51:35 -0400 |
| parents | 0a33fd8ead70 |
| children | 02d73e6ca869 |
| files | hcluster_sg_parser.py hcluster_sg_parser.xml test-data/hcluster_sg1.txt test-data/hcluster_sg1_0_output.txt test-data/hcluster_sg1_1_output.txt test-data/hcluster_sg1_2_output.txt test-data/hcluster_sg1_3_output.txt test-data/hcluster_sg1_4_output.txt test-data/hcluster_sg1_5_output.txt test-data/hcluster_sg1_6_output.txt test-data/hcluster_sg1_7_output.txt test-data/hcluster_sg1_8_output.txt |
| diffstat | 12 files changed, 130 insertions(+), 6 deletions(-) [+] |
line wrap: on
line diff
--- a/hcluster_sg_parser.py Fri Mar 24 12:33:12 2017 -0400 +++ b/hcluster_sg_parser.py Fri Apr 28 12:51:35 2017 -0400 @@ -1,5 +1,5 @@ """ -A simple parser to convert the hcluster_sg 3-column output into lists of IDs, one list for each cluster. +A simple parser to convert the hcluster_sg output into lists of IDs, one list for each cluster. When a minimum and/or maximum number of cluster elements are specified, the IDs contained in the filtered-out clusters are collected in the "discarded IDS" output dataset. @@ -21,9 +21,10 @@ with open(args[0]) as fh: for line in fh: line = line.rstrip() - (cluster_id, n_ids, id_list) = line.split('\t') - n_ids = int(n_ids) - id_list = id_list.replace(',', '\n') + line_cols = line.split('\t') + cluster_id = line_cols[0] + n_ids = int(line_cols[-2]) + id_list = line_cols[-1].replace(',', '\n') if n_ids >= options.min and n_ids <= options.max: outfile = cluster_id + '_output.txt' with open(outfile, 'w') as f:
--- a/hcluster_sg_parser.xml Fri Mar 24 12:33:12 2017 -0400 +++ b/hcluster_sg_parser.xml Fri Apr 28 12:51:35 2017 -0400 @@ -13,7 +13,7 @@ ]]> </command> <inputs> - <param name="inputFile" type="data" format="tabular" label="hcluster output file in 3-column format" help="3-columns format: cluster_id cluster-size cluster-members" /> + <param name="inputFile" type="data" format="tabular" label="hcluster output file" help="Tab-separated format: cluster_id [other optional columns] cluster-size cluster-members" /> <param name="min_elems" type="integer" value="" min="0" optional="true" label="Minimum number of cluster elements" /> <param name="max_elems" type="integer" value="" min="2" optional="true" label="Maximum number of cluster elements" /> </inputs> @@ -43,10 +43,25 @@ </output_collection> <output name="discarded" file="discarded.txt" /> </test> + <test> + <param name="inputFile" ftype="tabular" value="hcluster_sg1.txt" /> + <output_collection name="ids_lists" type="list"> + <element name="0" file="hcluster_sg1_0_output.txt" ftype="txt" /> + <element name="1" file="hcluster_sg1_1_output.txt" ftype="txt" /> + <element name="2" file="hcluster_sg1_2_output.txt" ftype="txt" /> + <element name="3" file="hcluster_sg1_3_output.txt" ftype="txt" /> + <element name="4" file="hcluster_sg1_4_output.txt" ftype="txt" /> + <element name="5" file="hcluster_sg1_5_output.txt" ftype="txt" /> + <element name="6" file="hcluster_sg1_6_output.txt" ftype="txt" /> + <element name="7" file="hcluster_sg1_7_output.txt" ftype="txt" /> + <element name="8" file="hcluster_sg1_8_output.txt" ftype="txt" /> + </output_collection> + <output name="discarded" file="empty.txt" /> + </test> </tests> <help> <![CDATA[ -A simple parser to convert the hcluster_sg 3-column output into lists of IDs, one list for each cluster. +A simple parser to convert the hcluster_sg output into lists of IDs, one list for each cluster. When a minimum and/or maximum number of cluster elements are specified, the IDs contained in the filtered-out clusters are collected in the "discarded IDS" output dataset. ]]>
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/hcluster_sg1.txt Fri Apr 28 12:51:35 2017 -0400 @@ -0,0 +1,9 @@ +0 0 57 1.000 0 13 11,0,4,3,5,12,7,10,13,2,1,6,9, +1 0 23 0.671 0 46 45,39,71,83,49,61,64,38,25,72,44,29,90,35,30,28,62,65,63,88,89,34,82,73,52,74,17,55,41,56,59,51,32,33,87,31,85,27,48,66,50,37,60,77,26,54, +2 0 0 1.000 0 1 84, +3 0 33 1.000 0 8 101,96,92,98,94,100,91,99, +4 0 28 1.000 0 4 40,43,76,42, +5 0 0 1.000 0 1 8, +6 0 54 1.000 0 8 18,23,21,15,22,20,14,16, +7 0 15 0.596 0 17 24,95,58,69,78,36,68,70,57,67,97,79,53,47,75,86,46, +8 0 0 1.000 0 1 102,
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/hcluster_sg1_0_output.txt Fri Apr 28 12:51:35 2017 -0400 @@ -0,0 +1,13 @@ +11 +0 +4 +3 +5 +12 +7 +10 +13 +2 +1 +6 +9
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/hcluster_sg1_1_output.txt Fri Apr 28 12:51:35 2017 -0400 @@ -0,0 +1,46 @@ +45 +39 +71 +83 +49 +61 +64 +38 +25 +72 +44 +29 +90 +35 +30 +28 +62 +65 +63 +88 +89 +34 +82 +73 +52 +74 +17 +55 +41 +56 +59 +51 +32 +33 +87 +31 +85 +27 +48 +66 +50 +37 +60 +77 +26 +54
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/hcluster_sg1_2_output.txt Fri Apr 28 12:51:35 2017 -0400 @@ -0,0 +1,1 @@ +84
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/hcluster_sg1_3_output.txt Fri Apr 28 12:51:35 2017 -0400 @@ -0,0 +1,8 @@ +101 +96 +92 +98 +94 +100 +91 +99
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/hcluster_sg1_4_output.txt Fri Apr 28 12:51:35 2017 -0400 @@ -0,0 +1,4 @@ +40 +43 +76 +42
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/hcluster_sg1_5_output.txt Fri Apr 28 12:51:35 2017 -0400 @@ -0,0 +1,1 @@ +8
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/hcluster_sg1_6_output.txt Fri Apr 28 12:51:35 2017 -0400 @@ -0,0 +1,8 @@ +18 +23 +21 +15 +22 +20 +14 +16