Mercurial > repos > recetox > matchms_remove_spectra

comparison matchms_split.py @ 0:80df426e7e47 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/tree/master/tools/matchms commit 113433b8b9790405c2c5d054aee4a29a21b77dc7
author recetox
date Thu, 30 May 2024 18:07:29 +0000
parents
children c7be8e58a6af
comparison
equal deleted inserted replaced
-1:000000000000 0:80df426e7e47
1 import argparse
2 import itertools
3 import os
4
5 import matchms
6 from matchms.exporting import save_as_msp
7 from matchms.importing import load_from_msp
8
9
10 matchms.Metadata.set_key_replacements({})
11
12
13 def make_outdir(outdir: str):
14 """Create destination directory.
15
16 Args:
17 outdir (str): Path to destination directory where split spectra files are generated.
18 """
19 return os.mkdir(outdir)
20
21
22 def write_spectra(spectra, outdir):
23 """Generates MSP files of individual spectra.
24
25 Args:
26 spectra (List[Spectrum]): Spectra to write to file
27 outdir (str): Path to destination directory.
28 """
29 for i in range(len(spectra)):
30 save_as_msp(spectra[i], os.path.join(outdir, f"{i}.msp"))
31
32
33 def split_round_robin(iterable, num_chunks):
34 chunks = [list() for _ in range(num_chunks)]
35 index = itertools.cycle(range(num_chunks))
36 for value in iterable:
37 chunks[next(index)].append(value)
38 chunks = filter(lambda x: len(x) > 0, chunks)
39 return chunks
40
41
42 listarg = argparse.ArgumentParser()
43 listarg.add_argument('--filename', type=str)
44 listarg.add_argument('--method', type=str)
45 listarg.add_argument('--outdir', type=str)
46 listarg.add_argument('--parameter', type=int)
47 args = listarg.parse_args()
48 outdir = args.outdir
49 filename = args.filename
50 method = args.method
51 parameter = args.parameter
52
53
54 if __name__ == "__main__":
55 spectra = load_from_msp(filename, metadata_harmonization=False)
56 make_outdir(outdir)
57
58 if method == "one-per-file":
59 write_spectra(list(spectra), outdir)
60 else:
61 if method == "chunk-size":
62 chunks = iter(lambda: list(itertools.islice(spectra, parameter)), [])
63 elif method == "num-chunks":
64 chunks = split_round_robin(spectra, parameter)
65 for i, x in enumerate(chunks):
66 save_as_msp(x, os.path.join(outdir, f"chunk_{i}.msp"))