Mercurial > repos > nml > biohansel_bionumeric_converter
annotate bionumeric_converter.py @ 1:07dfb8fd47f4 draft default tip
planemo upload commit e0d65bf0850ce95ffb89982e61f2136fcf0359ee
author | nml |
---|---|
date | Mon, 13 May 2019 12:59:15 -0400 |
parents | b000a3130db8 |
children |
rev | line source |
---|---|
0
b000a3130db8
planemo upload commit e5e384ce6c90f595e8d397a7c45ca9c17d4a3e2a
nml
parents:
diff
changeset
|
1 #!/usr/bin/env python |
b000a3130db8
planemo upload commit e5e384ce6c90f595e8d397a7c45ca9c17d4a3e2a
nml
parents:
diff
changeset
|
2 |
b000a3130db8
planemo upload commit e5e384ce6c90f595e8d397a7c45ca9c17d4a3e2a
nml
parents:
diff
changeset
|
3 # Import dependancies needed |
b000a3130db8
planemo upload commit e5e384ce6c90f595e8d397a7c45ca9c17d4a3e2a
nml
parents:
diff
changeset
|
4 import argparse |
b000a3130db8
planemo upload commit e5e384ce6c90f595e8d397a7c45ca9c17d4a3e2a
nml
parents:
diff
changeset
|
5 |
b000a3130db8
planemo upload commit e5e384ce6c90f595e8d397a7c45ca9c17d4a3e2a
nml
parents:
diff
changeset
|
6 import pandas as pd |
b000a3130db8
planemo upload commit e5e384ce6c90f595e8d397a7c45ca9c17d4a3e2a
nml
parents:
diff
changeset
|
7 |
b000a3130db8
planemo upload commit e5e384ce6c90f595e8d397a7c45ca9c17d4a3e2a
nml
parents:
diff
changeset
|
8 # Define the main function: |
b000a3130db8
planemo upload commit e5e384ce6c90f595e8d397a7c45ca9c17d4a3e2a
nml
parents:
diff
changeset
|
9 |
b000a3130db8
planemo upload commit e5e384ce6c90f595e8d397a7c45ca9c17d4a3e2a
nml
parents:
diff
changeset
|
10 |
b000a3130db8
planemo upload commit e5e384ce6c90f595e8d397a7c45ca9c17d4a3e2a
nml
parents:
diff
changeset
|
11 def main(): |
b000a3130db8
planemo upload commit e5e384ce6c90f595e8d397a7c45ca9c17d4a3e2a
nml
parents:
diff
changeset
|
12 parser = argparse.ArgumentParser() |
b000a3130db8
planemo upload commit e5e384ce6c90f595e8d397a7c45ca9c17d4a3e2a
nml
parents:
diff
changeset
|
13 parser.add_argument( |
b000a3130db8
planemo upload commit e5e384ce6c90f595e8d397a7c45ca9c17d4a3e2a
nml
parents:
diff
changeset
|
14 '-f', |
b000a3130db8
planemo upload commit e5e384ce6c90f595e8d397a7c45ca9c17d4a3e2a
nml
parents:
diff
changeset
|
15 '--filename', |
b000a3130db8
planemo upload commit e5e384ce6c90f595e8d397a7c45ca9c17d4a3e2a
nml
parents:
diff
changeset
|
16 required=True, |
1
07dfb8fd47f4
planemo upload commit e0d65bf0850ce95ffb89982e61f2136fcf0359ee
nml
parents:
0
diff
changeset
|
17 help='Specify your biohansel tsv or other tabular separated input') |
0
b000a3130db8
planemo upload commit e5e384ce6c90f595e8d397a7c45ca9c17d4a3e2a
nml
parents:
diff
changeset
|
18 parser.add_argument( |
b000a3130db8
planemo upload commit e5e384ce6c90f595e8d397a7c45ca9c17d4a3e2a
nml
parents:
diff
changeset
|
19 '-o', |
b000a3130db8
planemo upload commit e5e384ce6c90f595e8d397a7c45ca9c17d4a3e2a
nml
parents:
diff
changeset
|
20 '--output', |
b000a3130db8
planemo upload commit e5e384ce6c90f595e8d397a7c45ca9c17d4a3e2a
nml
parents:
diff
changeset
|
21 default='output.csv', |
b000a3130db8
planemo upload commit e5e384ce6c90f595e8d397a7c45ca9c17d4a3e2a
nml
parents:
diff
changeset
|
22 help='Specify output name') |
b000a3130db8
planemo upload commit e5e384ce6c90f595e8d397a7c45ca9c17d4a3e2a
nml
parents:
diff
changeset
|
23 args = parser.parse_args() |
b000a3130db8
planemo upload commit e5e384ce6c90f595e8d397a7c45ca9c17d4a3e2a
nml
parents:
diff
changeset
|
24 tsv_file = args.filename |
b000a3130db8
planemo upload commit e5e384ce6c90f595e8d397a7c45ca9c17d4a3e2a
nml
parents:
diff
changeset
|
25 out_name = args.output |
b000a3130db8
planemo upload commit e5e384ce6c90f595e8d397a7c45ca9c17d4a3e2a
nml
parents:
diff
changeset
|
26 |
1
07dfb8fd47f4
planemo upload commit e0d65bf0850ce95ffb89982e61f2136fcf0359ee
nml
parents:
0
diff
changeset
|
27 df_input = pd.read_csv(tsv_file, sep='\t') |
0
b000a3130db8
planemo upload commit e5e384ce6c90f595e8d397a7c45ca9c17d4a3e2a
nml
parents:
diff
changeset
|
28 |
1
07dfb8fd47f4
planemo upload commit e0d65bf0850ce95ffb89982e61f2136fcf0359ee
nml
parents:
0
diff
changeset
|
29 df_no_comma = df_input.replace(',', '/', regex=True) |
07dfb8fd47f4
planemo upload commit e0d65bf0850ce95ffb89982e61f2136fcf0359ee
nml
parents:
0
diff
changeset
|
30 df = qc_shortener(df_no_comma) |
07dfb8fd47f4
planemo upload commit e0d65bf0850ce95ffb89982e61f2136fcf0359ee
nml
parents:
0
diff
changeset
|
31 df.to_csv(out_name, index=False) |
0
b000a3130db8
planemo upload commit e5e384ce6c90f595e8d397a7c45ca9c17d4a3e2a
nml
parents:
diff
changeset
|
32 |
b000a3130db8
planemo upload commit e5e384ce6c90f595e8d397a7c45ca9c17d4a3e2a
nml
parents:
diff
changeset
|
33 # Shorten QC results: |
b000a3130db8
planemo upload commit e5e384ce6c90f595e8d397a7c45ca9c17d4a3e2a
nml
parents:
diff
changeset
|
34 |
b000a3130db8
planemo upload commit e5e384ce6c90f595e8d397a7c45ca9c17d4a3e2a
nml
parents:
diff
changeset
|
35 |
1
07dfb8fd47f4
planemo upload commit e0d65bf0850ce95ffb89982e61f2136fcf0359ee
nml
parents:
0
diff
changeset
|
36 def splittingstrings(string, length): |
07dfb8fd47f4
planemo upload commit e0d65bf0850ce95ffb89982e61f2136fcf0359ee
nml
parents:
0
diff
changeset
|
37 return (string[0+i:length+i] for i in range(0, len(string), length)) |
07dfb8fd47f4
planemo upload commit e0d65bf0850ce95ffb89982e61f2136fcf0359ee
nml
parents:
0
diff
changeset
|
38 |
07dfb8fd47f4
planemo upload commit e0d65bf0850ce95ffb89982e61f2136fcf0359ee
nml
parents:
0
diff
changeset
|
39 |
0
b000a3130db8
planemo upload commit e5e384ce6c90f595e8d397a7c45ca9c17d4a3e2a
nml
parents:
diff
changeset
|
40 def qc_shortener(df): |
1
07dfb8fd47f4
planemo upload commit e0d65bf0850ce95ffb89982e61f2136fcf0359ee
nml
parents:
0
diff
changeset
|
41 for i, row in df.iterrows(): |
07dfb8fd47f4
planemo upload commit e0d65bf0850ce95ffb89982e61f2136fcf0359ee
nml
parents:
0
diff
changeset
|
42 message = str(row['qc_message']) |
0
b000a3130db8
planemo upload commit e5e384ce6c90f595e8d397a7c45ca9c17d4a3e2a
nml
parents:
diff
changeset
|
43 if len(message) > 150: |
1
07dfb8fd47f4
planemo upload commit e0d65bf0850ce95ffb89982e61f2136fcf0359ee
nml
parents:
0
diff
changeset
|
44 message_list = list(splittingstrings(message, 150)) |
07dfb8fd47f4
planemo upload commit e0d65bf0850ce95ffb89982e61f2136fcf0359ee
nml
parents:
0
diff
changeset
|
45 df.at[i, 'qc_message'] = message_list[0] |
07dfb8fd47f4
planemo upload commit e0d65bf0850ce95ffb89982e61f2136fcf0359ee
nml
parents:
0
diff
changeset
|
46 for val in range(1, len(message_list)): |
07dfb8fd47f4
planemo upload commit e0d65bf0850ce95ffb89982e61f2136fcf0359ee
nml
parents:
0
diff
changeset
|
47 df.at[i, 'qc_message_{}'.format(val)] = message_list[val] |
0
b000a3130db8
planemo upload commit e5e384ce6c90f595e8d397a7c45ca9c17d4a3e2a
nml
parents:
diff
changeset
|
48 return df |
b000a3130db8
planemo upload commit e5e384ce6c90f595e8d397a7c45ca9c17d4a3e2a
nml
parents:
diff
changeset
|
49 |
b000a3130db8
planemo upload commit e5e384ce6c90f595e8d397a7c45ca9c17d4a3e2a
nml
parents:
diff
changeset
|
50 |
b000a3130db8
planemo upload commit e5e384ce6c90f595e8d397a7c45ca9c17d4a3e2a
nml
parents:
diff
changeset
|
51 if __name__ == '__main__': |
b000a3130db8
planemo upload commit e5e384ce6c90f595e8d397a7c45ca9c17d4a3e2a
nml
parents:
diff
changeset
|
52 main() |