Mercurial > repos > bcclaywell > microbiome_pplacer_suite

comparison bootstrap.py @ 2:ce6db18f5fd3 draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
Uploaded
author bcclaywell
date Thu, 26 Feb 2015 19:31:20 -0500
parents d4690e65afcd
children
comparison
equal deleted inserted replaced
1:c8cc6529038c 2:ce6db18f5fd3
1 #!/usr/bin/env python
2
3 from __future__ import print_function
4 import csv
5 import sys
6 import os
7 import argparse
8
9 def warning(*objs):
10 print("WARNING: ", *objs, file=sys.stderr)
11
12 def main(arguments):
13
14 parser = argparse.ArgumentParser(arguments, description=__doc__,
15 formatter_class=argparse.RawDescriptionHelpFormatter)
16 parser.add_argument('infile', help = "CSV input",
17 type = argparse.FileType('r'), default = sys.stdin)
18 parser.add_argument('--junior', help = "use junior run specimen naming convention", action = 'store_true')
19 parser.add_argument('--plate', help = "plate number", type = int, required = True)
20 parser.add_argument('--zone', help = "zone number", type = int, required = True)
21 parser.add_argument('--barcodes', help = "name of barcodes file",
22 type = argparse.FileType('w'), default = 'barcodes.csv')
23 parser.add_argument('--labels', help = "name of labels file",
24 type = argparse.FileType('w'), default = 'labels.csv')
25 parser.add_argument('--metadata', help = "name of metadata template file",
26 type = argparse.FileType('w'), default = 'metadata.csv')
27
28 args = parser.parse_args(arguments)
29
30 label_key = 'sampleid'
31 primer_key = 'reverse'
32 barcode_key = 'barcode'
33 zone_key = 'zone'
34
35 fstr = "j{plate_id}{primer_id}" if args.junior else "p{plate_id}z{zone_id}{primer_id}"
36
37 reader = csv.DictReader(sys.stdin)
38
39 barcodes = csv.writer(args.barcodes)
40 labels = csv.writer(args.labels)
41 metadata = csv.writer(args.metadata)
42
43 barcodes.writerow(['stub', 'barcode'])
44 labels.writerow(['specimen', 'label'])
45 metadata.writerow(['specimen', 'plate', 'zone', 'label', 'primer'])
46
47 seen_labels = {}
48 seen_primers = {}
49
50 # TODO: add checks for duplicates, empty fields, etc., and bail if something goes wrong
51 for i, d in enumerate(reader):
52 if not all (k in d for k in (label_key, primer_key, barcode_key)):
53 return "Expected columns not found"
54
55 if zone_key in d and d[zone_key] != str(args.zone):
56 continue
57
58 label = d[label_key]
59 primer = d[primer_key]
60 barcode = d[barcode_key]
61 zone = args.zone
62
63 if not all((label, primer, barcode)):
64 # only print a warning if at least one of the fields is non-empty
65 if any((label, primer, barcode)):
66 warning("Missing required field on row {}, skipping".format(i+2))
67 continue
68
69 if label in seen_labels:
70 return "Duplicate label '{}' found on rows {} and {}".format(label, seen_labels[label]+2, i+2)
71
72 if primer in seen_primers:
73 return "Duplicate primer '{}' found on rows {} and {}".format(primer, seen_primers[primer]+2, i+2)
74
75 seen_labels[label] = i
76 seen_primers[primer] = i
77
78 specimen = fstr.format(plate_id=args.plate, zone_id=zone, primer_id=primer.strip().lower().replace('-',''))
79 barcodes.writerow([specimen, barcode])
80 labels.writerow([specimen, label])
81 metadata.writerow([specimen, args.plate, zone, label, primer])
82
83 if __name__ == '__main__':
84 sys.exit(main(sys.argv[1:]))