# HG changeset patch
# User bebatut
# Date 1460724160 14400
# Node ID 72633301cc0df7970d1a927340b57b6ee309739c
planemo upload for repository https://github.com/asaim/galaxytools/tree/master/tools/normalize_dataset commit 21b25425f77162c0edae4dd87b3a9e33608c5a95-dirty
diff -r 000000000000 -r 72633301cc0d normalize_dataset.py
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/normalize_dataset.py Fri Apr 15 08:42:40 2016 -0400
@@ -0,0 +1,75 @@
+#!/usr/bin/env python
+# -*- coding: utf-8 -*-
+
+import sys
+import os
+import argparse
+import re
+
+def isfloat(value):
+ try:
+ float(value)
+ return True
+ except ValueError:
+ return False
+
+def normalize_dataset(args):
+ with open(args.input_file, 'r') as input_file:
+ input_file_content = input_file.readlines()
+ if args.normalization == 'column':
+ column_number = len(input_file_content[0][:-1].split('\t'))
+ column_sum = [0] * column_number
+
+ with open(args.output_file, 'w') as output_file:
+ for line in input_file_content:
+ split_line = line[:-1].split('\t')
+
+ if args.normalization == 'row':
+ row_sum = 0
+
+ for col in split_line:
+ if isfloat(col):
+ row_sum += float(col)
+
+ sep = ''
+ for col in split_line:
+ if isfloat(col):
+ if args.format == 'percentage':
+ output_file.write(sep + str(100*float(col)/row_sum))
+ else:
+ output_file.write(sep + str(float(col)/row_sum))
+ else:
+ output_file.write(sep + col)
+ sep = '\t'
+ output_file.write('\n')
+
+ elif args.normalization == 'column':
+ for i in range(len(split_line)):
+ if isfloat(split_line[i]):
+ column_sum[i] += float(split_line[i])
+
+ if args.normalization == 'column':
+ for line in input_file_content:
+ split_line = line[:-1].split('\t')
+ sep = ''
+ for i in range(len(split_line)):
+ if isfloat(split_line[i]):
+ if args.format == 'percentage':
+ output_file.write(sep + str(100*float(split_line[i])/column_sum[i]))
+ else:
+ output_file.write(sep + str(float(split_line[i])/column_sum[i]))
+ else:
+ output_file.write(sep + split_line[i])
+ sep = '\t'
+ output_file.write('\n')
+
+if __name__ == '__main__':
+ parser = argparse.ArgumentParser()
+ parser.add_argument('--input_file', required=True)
+ parser.add_argument('--output_file', required=True)
+ parser.add_argument('--normalization', required=True,
+ choices= ['column','row'])
+ parser.add_argument('--format', required=True,
+ choices= ['proportion','percentage'])
+ args = parser.parse_args()
+ normalize_dataset(args)
\ No newline at end of file
diff -r 000000000000 -r 72633301cc0d normalize_dataset.xml
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/normalize_dataset.xml Fri Apr 15 08:42:40 2016 -0400
@@ -0,0 +1,73 @@
+<tool id="normalize_dataset" name="Normalize a dataset by" version="0.1.0">
+ <description>row or column sum to obtain proportion or percentage</description>
+
+ <requirements>
+ </requirements>
+
+ <stdio>
+ <exit_code range="1:" />
+ <exit_code range=":-1" />
+ </stdio>
+
+ <version_command></version_command>
+
+ <command><![CDATA[
+ python $__tool_directory__/normalize_dataset.py
+ --input_file $input_file
+ --output_file $output_file
+ --normalization $normalization
+ --format $format
+ ]]></command>
+
+ <inputs>
+ <param name="input_file" type="data" format="tabular,tsv,csv" label="Input file" help="File in tabular format with tab-separated columns and header in first line (--input_file)"/>
+
+ <param name="normalization" label="Normalization on" type="select" help="(--normalization)">
+ <option value="column" selected="True">Column</option>
+ <option value="row">Row</option>
+ </param>
+
+ <param name="format" label="Output format" type="select" help="(--format)">
+ <option value="proportion" selected="True">Proportion</option>
+ <option value="percentage">Percentage</option>
+ </param>
+ </inputs>
+
+ <outputs>
+ <data name="output_file" format="tabular"
+ label="${tool.name} on ${on_string}: Normalized dataset" />
+ </outputs>
+
+ <tests>
+ <test>
+ <param name="input_file" value="input_file.tabular"/>
+ <param name="normalization" value="column"/>
+ <param name="format" value="proportion"/>
+ <output name="output_file" file="output_column_proportion.tabular"/>
+ </test>
+ <test>
+ <param name="input_file" value="input_file.tabular"/>
+ <param name="normalization" value="row"/>
+ <param name="format" value="proportion"/>
+ <output name="output_file" file="output_row_proportion.tabular"/>
+ </test>
+ <test>
+ <param name="input_file" value="input_file.tabular"/>
+ <param name="normalization" value="column"/>
+ <param name="format" value="percentage"/>
+ <output name="output_file" file="output_column_percentage.tabular"/>
+ </test>
+ </tests>
+
+ <help><![CDATA[
+**What it does**
+
+This tool normalizes each row or column of a dataset by the row or column sum.
+The results can be in proportion or percentage.
+
+The input file must be in tabular format with tab-separated columns. Only data will be used for normalization.
+ ]]></help>
+
+ <citations>
+ </citations>
+</tool>