Mercurial > repos > nml > biohansel_bionumeric_converter

comparison bionumeric_converter.py @ 0:b000a3130db8 draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
planemo upload commit e5e384ce6c90f595e8d397a7c45ca9c17d4a3e2a
author nml
date Mon, 18 Mar 2019 13:15:57 -0400
parents
children 07dfb8fd47f4
comparison
equal deleted inserted replaced
-1:000000000000 0:b000a3130db8
1 #!/usr/bin/env python
2
3 # Import dependancies needed
4 import argparse
5
6 import pandas as pd
7
8 # Define the main function:
9
10
11 def main():
12 parser = argparse.ArgumentParser()
13 parser.add_argument(
14 '-f',
15 '--filename',
16 required=True,
17 help='Specify your tsv input')
18 parser.add_argument(
19 '-o',
20 '--output',
21 default='output.csv',
22 help='Specify output name')
23 args = parser.parse_args()
24 tsv_file = args.filename
25 out_name = args.output
26
27 no_comma_tsv = comma_remover(tsv_file)
28 df = qc_shortener(no_comma_tsv)
29 df.to_csv(out_name, index=False)
30
31 # Remove comma function:
32
33
34 def comma_remover(tsv_file):
35 # Create a table from the tsv file as an input into the dataframe.
36 df = pd.read_csv(tsv_file, sep='\t')
37 # Change all commas to / in the QC message
38 no_comma_tsv = df.replace(',', '/', regex=True)
39 return no_comma_tsv
40
41 # Shorten QC results:
42
43
44 def qc_shortener(df):
45 for count in df.index:
46 message = str(df.at[count, 'qc_message'])
47 if len(message) > 150:
48 results = message.find('|')
49 new_message = "Truncated after first '|' : " + message[0:results]
50 df['qc_message'] = df['qc_message'].replace(message, new_message)
51 return df
52
53
54 if __name__ == '__main__':
55 main()