Mercurial > repos > recetox > aplcms_to_ramclustr_converter

comparison aplcms_to_ramclustr_converter.py @ 3:07667688735e draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
"planemo upload for repository https://github.com/RECETOX/galaxytools/tools/aplcms_to_ramclustr_converter/ commit 521769cd5af12987a119e6302f22e2e1e864ff9a"
author recetox
date Wed, 17 Feb 2021 15:14:33 +0000
parents
children 9ea34e24474f
comparison
equal deleted inserted replaced
2:644192cf22a5 3:07667688735e
1 #!/usr/bin/env python
2
3 import argparse
4 import sys
5 import warnings
6
7 import pandas as pd
8
9
10 warnings.simplefilter('ignore')
11
12 parser = argparse.ArgumentParser()
13 parser.add_argument("--dataframe", help="Name of hdf dataframe")
14 parser.add_argument("--table", help="Name of a table in the dataframe")
15 parser.add_argument('output')
16 args = parser.parse_args()
17
18
19 def extract_data(table):
20 num_samples = int((len(table.columns.tolist()) - 4) / 2)
21 mz_rt = table['mz'].map(str) + "_" + table['rt'].map(str)
22
23 intensities = table.iloc[:, 4:(4 + num_samples)]
24 sample_labels = [label.split('.')[1] for label in intensities.columns.tolist()]
25 ramclustr_data = pd.DataFrame({'mz_rt': mz_rt})
26
27 for idx in range(num_samples):
28 label = sample_labels[idx]
29 ramclustr_data[label] = intensities.iloc[:, idx]
30
31 return ramclustr_data
32
33
34 def format_table(ramclustr_data):
35 ramclustr_data.set_index('mz_rt', inplace=True)
36 ramclustr_data = ramclustr_data.transpose()
37 ramclustr_data.index.rename('sample', inplace=True)
38 return ramclustr_data
39
40
41 def main():
42 try:
43 aplcms_table = pd.read_hdf(args.dataframe, args.table, errors='None')
44 except KeyError:
45 msg = "Selected table does not exist in HDF dataframe"
46 print(msg, file=sys.stderr)
47 sys.exit(1)
48
49 ramclustr_data = extract_data(aplcms_table)
50 ramclustr_table = format_table(ramclustr_data)
51
52 ramclustr_table.to_csv(args.output, sep=',')
53 msg = "Table '{}' of HDF dataset is converted to csv for RamClutsR".format(args.table)
54 print(msg, file=sys.stdout)
55
56
57 if __name__ == "__main__":
58 main()