Mercurial > repos > nml > biohansel_bionumeric_converter

comparison bionumeric_converter.py @ 1:07dfb8fd47f4 draft default tip

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
planemo upload commit e0d65bf0850ce95ffb89982e61f2136fcf0359ee
author nml
date Mon, 13 May 2019 12:59:15 -0400
parents b000a3130db8
children
comparison
equal deleted inserted replaced
0:b000a3130db8 1:07dfb8fd47f4
12 parser = argparse.ArgumentParser() 12 parser = argparse.ArgumentParser()
13 parser.add_argument( 13 parser.add_argument(
14 '-f', 14 '-f',
15 '--filename', 15 '--filename',
16 required=True, 16 required=True,
17 help='Specify your tsv input') 17 help='Specify your biohansel tsv or other tabular separated input')
18 parser.add_argument( 18 parser.add_argument(
19 '-o', 19 '-o',
20 '--output', 20 '--output',
21 default='output.csv', 21 default='output.csv',
22 help='Specify output name') 22 help='Specify output name')
23 args = parser.parse_args() 23 args = parser.parse_args()
24 tsv_file = args.filename 24 tsv_file = args.filename
25 out_name = args.output 25 out_name = args.output
26 26
27 no_comma_tsv = comma_remover(tsv_file) 27 df_input = pd.read_csv(tsv_file, sep='\t')
28 df = qc_shortener(no_comma_tsv) 28
29 df_no_comma = df_input.replace(',', '/', regex=True)
30 df = qc_shortener(df_no_comma)
29 df.to_csv(out_name, index=False) 31 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 32
41 # Shorten QC results: 33 # Shorten QC results:
42 34
43 35
36 def splittingstrings(string, length):
37 return (string[0+i:length+i] for i in range(0, len(string), length))
38
39
44 def qc_shortener(df): 40 def qc_shortener(df):
45 for count in df.index: 41 for i, row in df.iterrows():
46 message = str(df.at[count, 'qc_message']) 42 message = str(row['qc_message'])
47 if len(message) > 150: 43 if len(message) > 150:
48 results = message.find('|') 44 message_list = list(splittingstrings(message, 150))
49 new_message = "Truncated after first '|' : " + message[0:results] 45 df.at[i, 'qc_message'] = message_list[0]
50 df['qc_message'] = df['qc_message'].replace(message, new_message) 46 for val in range(1, len(message_list)):
47 df.at[i, 'qc_message_{}'.format(val)] = message_list[val]
51 return df 48 return df
52 49
53 50
54 if __name__ == '__main__': 51 if __name__ == '__main__':
55 main() 52 main()