Mercurial > repos > recetox > matchms_metadata_merge

annotate matchms_split.py @ 18:e052eac8be4a draft default tip

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 a57d984a9850c1faa44b6948981eb1303881ba9c
author recetox
date Thu, 14 Aug 2025 12:35:36 +0000
parents 99ad7552fb10
children
Ignore whitespace changes - Everywhere: Within whitespace: At end of lines:
rev   line source
0
107186a6fcec planemo upload for repository https://github.com/RECETOX/galaxytools/tree/master/tools/matchms commit f5f5a8eff32c9b5de792dce99bc3c63dc971e82c
recetox
parents:
diff changeset
1 import argparse
107186a6fcec planemo upload for repository https://github.com/RECETOX/galaxytools/tree/master/tools/matchms commit f5f5a8eff32c9b5de792dce99bc3c63dc971e82c
recetox
parents:
diff changeset
2 import itertools
107186a6fcec planemo upload for repository https://github.com/RECETOX/galaxytools/tree/master/tools/matchms commit f5f5a8eff32c9b5de792dce99bc3c63dc971e82c
recetox
parents:
diff changeset
3 import os
107186a6fcec planemo upload for repository https://github.com/RECETOX/galaxytools/tree/master/tools/matchms commit f5f5a8eff32c9b5de792dce99bc3c63dc971e82c
recetox
parents:
diff changeset
4
18
e052eac8be4a planemo upload for repository https://github.com/RECETOX/galaxytools/tree/master/tools/matchms commit a57d984a9850c1faa44b6948981eb1303881ba9c
recetox
parents: 8
diff changeset
5 from matchms import Metadata
0
107186a6fcec planemo upload for repository https://github.com/RECETOX/galaxytools/tree/master/tools/matchms commit f5f5a8eff32c9b5de792dce99bc3c63dc971e82c
recetox
parents:
diff changeset
6 from matchms.exporting import save_as_msp
107186a6fcec planemo upload for repository https://github.com/RECETOX/galaxytools/tree/master/tools/matchms commit f5f5a8eff32c9b5de792dce99bc3c63dc971e82c
recetox
parents:
diff changeset
7 from matchms.importing import load_from_msp
107186a6fcec planemo upload for repository https://github.com/RECETOX/galaxytools/tree/master/tools/matchms commit f5f5a8eff32c9b5de792dce99bc3c63dc971e82c
recetox
parents:
diff changeset
8
18
e052eac8be4a planemo upload for repository https://github.com/RECETOX/galaxytools/tree/master/tools/matchms commit a57d984a9850c1faa44b6948981eb1303881ba9c
recetox
parents: 8
diff changeset
9 Metadata.set_key_replacements({})
0
107186a6fcec planemo upload for repository https://github.com/RECETOX/galaxytools/tree/master/tools/matchms commit f5f5a8eff32c9b5de792dce99bc3c63dc971e82c
recetox
parents:
diff changeset
10
107186a6fcec planemo upload for repository https://github.com/RECETOX/galaxytools/tree/master/tools/matchms commit f5f5a8eff32c9b5de792dce99bc3c63dc971e82c
recetox
parents:
diff changeset
11
107186a6fcec planemo upload for repository https://github.com/RECETOX/galaxytools/tree/master/tools/matchms commit f5f5a8eff32c9b5de792dce99bc3c63dc971e82c
recetox
parents:
diff changeset
12 def make_outdir(outdir: str):
107186a6fcec planemo upload for repository https://github.com/RECETOX/galaxytools/tree/master/tools/matchms commit f5f5a8eff32c9b5de792dce99bc3c63dc971e82c
recetox
parents:
diff changeset
13 """Create destination directory.
107186a6fcec planemo upload for repository https://github.com/RECETOX/galaxytools/tree/master/tools/matchms commit f5f5a8eff32c9b5de792dce99bc3c63dc971e82c
recetox
parents:
diff changeset
14
107186a6fcec planemo upload for repository https://github.com/RECETOX/galaxytools/tree/master/tools/matchms commit f5f5a8eff32c9b5de792dce99bc3c63dc971e82c
recetox
parents:
diff changeset
15 Args:
107186a6fcec planemo upload for repository https://github.com/RECETOX/galaxytools/tree/master/tools/matchms commit f5f5a8eff32c9b5de792dce99bc3c63dc971e82c
recetox
parents:
diff changeset
16 outdir (str): Path to destination directory where split spectra files are generated.
107186a6fcec planemo upload for repository https://github.com/RECETOX/galaxytools/tree/master/tools/matchms commit f5f5a8eff32c9b5de792dce99bc3c63dc971e82c
recetox
parents:
diff changeset
17 """
107186a6fcec planemo upload for repository https://github.com/RECETOX/galaxytools/tree/master/tools/matchms commit f5f5a8eff32c9b5de792dce99bc3c63dc971e82c
recetox
parents:
diff changeset
18 return os.mkdir(outdir)
107186a6fcec planemo upload for repository https://github.com/RECETOX/galaxytools/tree/master/tools/matchms commit f5f5a8eff32c9b5de792dce99bc3c63dc971e82c
recetox
parents:
diff changeset
19
107186a6fcec planemo upload for repository https://github.com/RECETOX/galaxytools/tree/master/tools/matchms commit f5f5a8eff32c9b5de792dce99bc3c63dc971e82c
recetox
parents:
diff changeset
20
107186a6fcec planemo upload for repository https://github.com/RECETOX/galaxytools/tree/master/tools/matchms commit f5f5a8eff32c9b5de792dce99bc3c63dc971e82c
recetox
parents:
diff changeset
21 def write_spectra(spectra, outdir):
107186a6fcec planemo upload for repository https://github.com/RECETOX/galaxytools/tree/master/tools/matchms commit f5f5a8eff32c9b5de792dce99bc3c63dc971e82c
recetox
parents:
diff changeset
22 """Generates MSP files of individual spectra.
107186a6fcec planemo upload for repository https://github.com/RECETOX/galaxytools/tree/master/tools/matchms commit f5f5a8eff32c9b5de792dce99bc3c63dc971e82c
recetox
parents:
diff changeset
23
107186a6fcec planemo upload for repository https://github.com/RECETOX/galaxytools/tree/master/tools/matchms commit f5f5a8eff32c9b5de792dce99bc3c63dc971e82c
recetox
parents:
diff changeset
24 Args:
107186a6fcec planemo upload for repository https://github.com/RECETOX/galaxytools/tree/master/tools/matchms commit f5f5a8eff32c9b5de792dce99bc3c63dc971e82c
recetox
parents:
diff changeset
25 spectra (List[Spectrum]): Spectra to write to file
107186a6fcec planemo upload for repository https://github.com/RECETOX/galaxytools/tree/master/tools/matchms commit f5f5a8eff32c9b5de792dce99bc3c63dc971e82c
recetox
parents:
diff changeset
26 outdir (str): Path to destination directory.
107186a6fcec planemo upload for repository https://github.com/RECETOX/galaxytools/tree/master/tools/matchms commit f5f5a8eff32c9b5de792dce99bc3c63dc971e82c
recetox
parents:
diff changeset
27 """
107186a6fcec planemo upload for repository https://github.com/RECETOX/galaxytools/tree/master/tools/matchms commit f5f5a8eff32c9b5de792dce99bc3c63dc971e82c
recetox
parents:
diff changeset
28 for i in range(len(spectra)):
8
99ad7552fb10 planemo upload for repository https://github.com/RECETOX/galaxytools/tree/master/tools/matchms commit da193865f41a3a840ecc4ba0afab1d358554998a
recetox
parents: 0
diff changeset
29 save_as_msp(spectra[i], os.path.join(outdir, f"{i}.msp"))
0
107186a6fcec planemo upload for repository https://github.com/RECETOX/galaxytools/tree/master/tools/matchms commit f5f5a8eff32c9b5de792dce99bc3c63dc971e82c
recetox
parents:
diff changeset
30
107186a6fcec planemo upload for repository https://github.com/RECETOX/galaxytools/tree/master/tools/matchms commit f5f5a8eff32c9b5de792dce99bc3c63dc971e82c
recetox
parents:
diff changeset
31
107186a6fcec planemo upload for repository https://github.com/RECETOX/galaxytools/tree/master/tools/matchms commit f5f5a8eff32c9b5de792dce99bc3c63dc971e82c
recetox
parents:
diff changeset
32 def split_round_robin(iterable, num_chunks):
107186a6fcec planemo upload for repository https://github.com/RECETOX/galaxytools/tree/master/tools/matchms commit f5f5a8eff32c9b5de792dce99bc3c63dc971e82c
recetox
parents:
diff changeset
33 chunks = [list() for _ in range(num_chunks)]
107186a6fcec planemo upload for repository https://github.com/RECETOX/galaxytools/tree/master/tools/matchms commit f5f5a8eff32c9b5de792dce99bc3c63dc971e82c
recetox
parents:
diff changeset
34 index = itertools.cycle(range(num_chunks))
107186a6fcec planemo upload for repository https://github.com/RECETOX/galaxytools/tree/master/tools/matchms commit f5f5a8eff32c9b5de792dce99bc3c63dc971e82c
recetox
parents:
diff changeset
35 for value in iterable:
107186a6fcec planemo upload for repository https://github.com/RECETOX/galaxytools/tree/master/tools/matchms commit f5f5a8eff32c9b5de792dce99bc3c63dc971e82c
recetox
parents:
diff changeset
36 chunks[next(index)].append(value)
107186a6fcec planemo upload for repository https://github.com/RECETOX/galaxytools/tree/master/tools/matchms commit f5f5a8eff32c9b5de792dce99bc3c63dc971e82c
recetox
parents:
diff changeset
37 chunks = filter(lambda x: len(x) > 0, chunks)
107186a6fcec planemo upload for repository https://github.com/RECETOX/galaxytools/tree/master/tools/matchms commit f5f5a8eff32c9b5de792dce99bc3c63dc971e82c
recetox
parents:
diff changeset
38 return chunks
107186a6fcec planemo upload for repository https://github.com/RECETOX/galaxytools/tree/master/tools/matchms commit f5f5a8eff32c9b5de792dce99bc3c63dc971e82c
recetox
parents:
diff changeset
39
107186a6fcec planemo upload for repository https://github.com/RECETOX/galaxytools/tree/master/tools/matchms commit f5f5a8eff32c9b5de792dce99bc3c63dc971e82c
recetox
parents:
diff changeset
40
107186a6fcec planemo upload for repository https://github.com/RECETOX/galaxytools/tree/master/tools/matchms commit f5f5a8eff32c9b5de792dce99bc3c63dc971e82c
recetox
parents:
diff changeset
41 listarg = argparse.ArgumentParser()
107186a6fcec planemo upload for repository https://github.com/RECETOX/galaxytools/tree/master/tools/matchms commit f5f5a8eff32c9b5de792dce99bc3c63dc971e82c
recetox
parents:
diff changeset
42 listarg.add_argument('--filename', type=str)
107186a6fcec planemo upload for repository https://github.com/RECETOX/galaxytools/tree/master/tools/matchms commit f5f5a8eff32c9b5de792dce99bc3c63dc971e82c
recetox
parents:
diff changeset
43 listarg.add_argument('--method', type=str)
107186a6fcec planemo upload for repository https://github.com/RECETOX/galaxytools/tree/master/tools/matchms commit f5f5a8eff32c9b5de792dce99bc3c63dc971e82c
recetox
parents:
diff changeset
44 listarg.add_argument('--outdir', type=str)
18
e052eac8be4a planemo upload for repository https://github.com/RECETOX/galaxytools/tree/master/tools/matchms commit a57d984a9850c1faa44b6948981eb1303881ba9c
recetox
parents: 8
diff changeset
45 listarg.add_argument('--parameter', type=int, required=False)
0
107186a6fcec planemo upload for repository https://github.com/RECETOX/galaxytools/tree/master/tools/matchms commit f5f5a8eff32c9b5de792dce99bc3c63dc971e82c
recetox
parents:
diff changeset
46 args = listarg.parse_args()
107186a6fcec planemo upload for repository https://github.com/RECETOX/galaxytools/tree/master/tools/matchms commit f5f5a8eff32c9b5de792dce99bc3c63dc971e82c
recetox
parents:
diff changeset
47 outdir = args.outdir
107186a6fcec planemo upload for repository https://github.com/RECETOX/galaxytools/tree/master/tools/matchms commit f5f5a8eff32c9b5de792dce99bc3c63dc971e82c
recetox
parents:
diff changeset
48 filename = args.filename
107186a6fcec planemo upload for repository https://github.com/RECETOX/galaxytools/tree/master/tools/matchms commit f5f5a8eff32c9b5de792dce99bc3c63dc971e82c
recetox
parents:
diff changeset
49 method = args.method
107186a6fcec planemo upload for repository https://github.com/RECETOX/galaxytools/tree/master/tools/matchms commit f5f5a8eff32c9b5de792dce99bc3c63dc971e82c
recetox
parents:
diff changeset
50 parameter = args.parameter
107186a6fcec planemo upload for repository https://github.com/RECETOX/galaxytools/tree/master/tools/matchms commit f5f5a8eff32c9b5de792dce99bc3c63dc971e82c
recetox
parents:
diff changeset
51
107186a6fcec planemo upload for repository https://github.com/RECETOX/galaxytools/tree/master/tools/matchms commit f5f5a8eff32c9b5de792dce99bc3c63dc971e82c
recetox
parents:
diff changeset
52
107186a6fcec planemo upload for repository https://github.com/RECETOX/galaxytools/tree/master/tools/matchms commit f5f5a8eff32c9b5de792dce99bc3c63dc971e82c
recetox
parents:
diff changeset
53 if __name__ == "__main__":
8
99ad7552fb10 planemo upload for repository https://github.com/RECETOX/galaxytools/tree/master/tools/matchms commit da193865f41a3a840ecc4ba0afab1d358554998a
recetox
parents: 0
diff changeset
54 spectra = load_from_msp(filename, metadata_harmonization=False)
0
107186a6fcec planemo upload for repository https://github.com/RECETOX/galaxytools/tree/master/tools/matchms commit f5f5a8eff32c9b5de792dce99bc3c63dc971e82c
recetox
parents:
diff changeset
55 make_outdir(outdir)
107186a6fcec planemo upload for repository https://github.com/RECETOX/galaxytools/tree/master/tools/matchms commit f5f5a8eff32c9b5de792dce99bc3c63dc971e82c
recetox
parents:
diff changeset
56
107186a6fcec planemo upload for repository https://github.com/RECETOX/galaxytools/tree/master/tools/matchms commit f5f5a8eff32c9b5de792dce99bc3c63dc971e82c
recetox
parents:
diff changeset
57 if method == "one-per-file":
107186a6fcec planemo upload for repository https://github.com/RECETOX/galaxytools/tree/master/tools/matchms commit f5f5a8eff32c9b5de792dce99bc3c63dc971e82c
recetox
parents:
diff changeset
58 write_spectra(list(spectra), outdir)
107186a6fcec planemo upload for repository https://github.com/RECETOX/galaxytools/tree/master/tools/matchms commit f5f5a8eff32c9b5de792dce99bc3c63dc971e82c
recetox
parents:
diff changeset
59 else:
107186a6fcec planemo upload for repository https://github.com/RECETOX/galaxytools/tree/master/tools/matchms commit f5f5a8eff32c9b5de792dce99bc3c63dc971e82c
recetox
parents:
diff changeset
60 if method == "chunk-size":
107186a6fcec planemo upload for repository https://github.com/RECETOX/galaxytools/tree/master/tools/matchms commit f5f5a8eff32c9b5de792dce99bc3c63dc971e82c
recetox
parents:
diff changeset
61 chunks = iter(lambda: list(itertools.islice(spectra, parameter)), [])
107186a6fcec planemo upload for repository https://github.com/RECETOX/galaxytools/tree/master/tools/matchms commit f5f5a8eff32c9b5de792dce99bc3c63dc971e82c
recetox
parents:
diff changeset
62 elif method == "num-chunks":
107186a6fcec planemo upload for repository https://github.com/RECETOX/galaxytools/tree/master/tools/matchms commit f5f5a8eff32c9b5de792dce99bc3c63dc971e82c
recetox
parents:
diff changeset
63 chunks = split_round_robin(spectra, parameter)
107186a6fcec planemo upload for repository https://github.com/RECETOX/galaxytools/tree/master/tools/matchms commit f5f5a8eff32c9b5de792dce99bc3c63dc971e82c
recetox
parents:
diff changeset
64 for i, x in enumerate(chunks):
107186a6fcec planemo upload for repository https://github.com/RECETOX/galaxytools/tree/master/tools/matchms commit f5f5a8eff32c9b5de792dce99bc3c63dc971e82c
recetox
parents:
diff changeset
65 save_as_msp(x, os.path.join(outdir, f"chunk_{i}.msp"))