Mercurial > repos > mvdbeek > damidseq_average_scores
comparison average_scores.xml @ 0:427f5dda8854 draft
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/damidseq_average_score commit 3f1b0838d9fd6256d61490c3b2b52936b9ce2123
| author | mvdbeek |
|---|---|
| date | Fri, 27 Apr 2018 14:54:05 -0400 |
| parents | |
| children | 7fd65542efc2 |
comparison
equal
deleted
inserted
replaced
| -1:000000000000 | 0:427f5dda8854 |
|---|---|
| 1 <tool id="average_score" name="Calculate average scores" version="0.1.3"> | |
| 2 <description>for fixed step interval files</description> | |
| 3 <requirements> | |
| 4 <requirement type="package" version="0.22">pandas</requirement> | |
| 5 </requirements> | |
| 6 <command detect_errors="exit_code"><![CDATA[ | |
| 7 python '$average_script' | |
| 8 ]]></command> | |
| 9 <configfiles> | |
| 10 <configfile name="average_script"> | |
| 11 import pandas as pd | |
| 12 | |
| 13 #set files = [str(f) for f in $input_files] | |
| 14 #set column = 3 if $input_files[0].ext in ['bed', 'bedgraph'] else 5 | |
| 15 d = {} | |
| 16 #for f in $files: | |
| 17 d['$f'] = pd.read_csv('$f', usecols=[$column], sep="\t", skiprows=$skiprows, header=None, squeeze=True) | |
| 18 #end for | |
| 19 df = pd.DataFrame.from_dict(d) | |
| 20 mean = df.mean(axis=1) | |
| 21 with open('$averaged_output', 'w') as out, open('$files[0]') as first_file: | |
| 22 for i, line in enumerate(first_file): | |
| 23 fields = line.strip().split("\t") | |
| 24 if i >= $skiprows: | |
| 25 fields[$column] = str(mean[i - $skiprows]) | |
| 26 out.write("%s\n" % "\t".join(fields)) | |
| 27 </configfile> | |
| 28 </configfiles> | |
| 29 <inputs> | |
| 30 <param name="input_files" type="data" multiple="true" format="bed,bedgraph,gff" label="Select the files for which to average the score"/> | |
| 31 <param name="skiprows" type="integer" min="0" value="0" label="Skip the first N rows" help="To skip comments and track definition lines"/> | |
| 32 </inputs> | |
| 33 <outputs> | |
| 34 <data name="averaged_output" format_source="input_files" label="${tool.name} on ${on_string}"/> | |
| 35 </outputs> | |
| 36 <tests> | |
| 37 <test> | |
| 38 <param name="input_files" value="1.bed,2.bed" ftype="bed"/> | |
| 39 <output name="averaged_output" value="averaged.bed" ftype="bed"/> | |
| 40 </test> | |
| 41 </tests> | |
| 42 <help><![CDATA[ | |
| 43 What it does | |
| 44 ------------ | |
| 45 | |
| 46 This tool calculates the average value for the score column across many datasets. | |
| 47 | |
| 48 ]]></help> | |
| 49 </tool> |