Mercurial > repos > rv43 > tomo

comparison tomo_setup.py @ 49:26f99fdd8d61 draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
"planemo upload for repository https://github.com/rolfverberg/galaxytools commit 4f7738d02f4a3fd91373f43937ed311b6fe11a12"
author rv43
date Thu, 28 Jul 2022 16:05:24 +0000
parents ef5c2f7b49ec
children 79c216516ef9
comparison
equal deleted inserted replaced
48:059819ea1f0e 49:26f99fdd8d61
9 import argparse 9 import argparse
10 import numpy as np 10 import numpy as np
11 import tracemalloc 11 import tracemalloc
12 12
13 from tomo import Tomo 13 from tomo import Tomo
14 import msnc_tools as msnc
15 14
16 #from memory_profiler import profile 15 #from memory_profiler import profile
17 #@profile 16 #@profile
18 def __main__(): 17 def __main__():
19 18
20 # Parse command line arguments 19 # Parse command line arguments
21 parser = argparse.ArgumentParser( 20 parser = argparse.ArgumentParser(
22 description='Setup tomography reconstruction') 21 description='Setup tomography reconstruction')
23 parser.add_argument('-i', '--inputfiles', 22 parser.add_argument('-i', '--inputfiles',
23 nargs='+',
24 default='inputfiles.txt', 24 default='inputfiles.txt',
25 help='Input file collections') 25 help='Input file datasets or collections')
26 parser.add_argument('-c', '--config', 26 parser.add_argument('-c', '--config',
27 help='Input config') 27 help='Input config')
28 parser.add_argument('-l', '--log',
29 type=argparse.FileType('w'),
30 default=sys.stdout,
31 help='Log file')
32 parser.add_argument('-t', '--inputfile_types',
33 nargs='+',
34 default='collection',
35 help='Input files type (collection or a list of set types: dark, bright, or data)')
28 parser.add_argument('--theta_range', 36 parser.add_argument('--theta_range',
29 help='Theta range (lower bound, upper bound, number of angles)') 37 help='Theta range (lower bound, upper bound, number of angles)')
30 parser.add_argument('--output_config', 38 parser.add_argument('--output_config',
31 help='Output config') 39 help='Output config')
32 parser.add_argument('--output_data', 40 parser.add_argument('--output_data',
33 help='Preprocessed tomography data') 41 help='Preprocessed tomography data')
34 parser.add_argument('-l', '--log',
35 type=argparse.FileType('w'),
36 default=sys.stdout,
37 help='Log file')
38 parser.add_argument('tomo_ranges', metavar='N', type=int, nargs='+') 42 parser.add_argument('tomo_ranges', metavar='N', type=int, nargs='+')
39 args = parser.parse_args() 43 args = parser.parse_args()
40 44
41 # Starting memory monitoring 45 # Starting memory monitoring
42 tracemalloc.start() 46 tracemalloc.start()
49 raise ValueError(f'Invalid log_level: {log_level}') 53 raise ValueError(f'Invalid log_level: {log_level}')
50 logging.basicConfig(format=logging_format, level=level, force=True, 54 logging.basicConfig(format=logging_format, level=level, force=True,
51 handlers=[logging.StreamHandler()]) 55 handlers=[logging.StreamHandler()])
52 56
53 logging.debug(f'config = {args.config}') 57 logging.debug(f'config = {args.config}')
58 logging.debug(f'inputfiles = {args.inputfiles}')
59 logging.debug(f'inputfile_types = {args.inputfile_types}')
60 logging.debug(f'log = {args.log}')
61 logging.debug(f'is log stdout? {args.log is sys.stdout}')
54 logging.debug(f'theta_range = {args.theta_range.split()}') 62 logging.debug(f'theta_range = {args.theta_range.split()}')
55 logging.debug(f'output_config = {args.output_config}') 63 logging.debug(f'output_config = {args.output_config}')
56 logging.debug(f'output_data = {args.output_data}') 64 logging.debug(f'output_data = {args.output_data}')
57 logging.debug(f'log = {args.log}')
58 logging.debug(f'is log stdout? {args.log is sys.stdout}')
59 logging.debug(f'tomoranges = {args.tomo_ranges}') 65 logging.debug(f'tomoranges = {args.tomo_ranges}')
60 66
61 # Read input files and collect data files info 67 # Check input file type
68 if isinstance(args.inputfile_types, str) and args.inputfile_types == 'collection':
69 input_as_collection = True
70 elif isinstance(args.inputfile_types, list):
71 input_as_collection = False
72 else:
73 raise ValueError(f'Invalid args.inputfile_types: {args.inputfile_types} '+
74 f'{type(args.inputfile_types)}')
75
62 datasets = [] 76 datasets = []
63 with open(args.inputfiles) as cf: 77 collections = []
64 for line in cf: 78 if input_as_collection:
65 if not line.strip() or line.startswith('#'): 79 # Read input file collections and collect data files info
66 continue 80 with open(args.inputfiles) as cf:
67 fields = [x.strip() for x in line.split('\t')] 81 for line in cf:
68 filepath = fields[0] 82 if not line.strip() or line.startswith('#'):
69 element_identifier = fields[1] if len(fields) > 1 else fields[0].split('/')[-1] 83 continue
70 datasets.append({'element_identifier' : fields[1], 'filepath' : filepath}) 84 fields = [x.strip() for x in line.split('\t')]
71 logging.debug(f'datasets:\n{datasets}') 85 filepath = fields[0]
86 element_identifier = fields[1] if len(fields) > 1 else fields[0].split('/')[-1]
87 datasets.append({'element_identifier' : fields[1], 'filepath' : filepath})
88 logging.debug(f'datasets:\n{datasets}')
72 89
73 # Read and sort data files 90 # Read and sort data files
74 collections = [] 91 for dataset in datasets:
75 for dataset in datasets: 92 element_identifier = [x.strip() for x in dataset['element_identifier'].split('_')]
76 element_identifier = [x.strip() for x in dataset['element_identifier'].split('_')] 93 if len(element_identifier) > 1:
77 if len(element_identifier) > 1: 94 name = element_identifier[0]
78 name = element_identifier[0]
79 else:
80 name = 'other'
81 filepath = dataset['filepath']
82 if not len(collections):
83 collections = [{'name' : name, 'filepaths' : [filepath]}]
84 else:
85 collection = [c for c in collections if c['name'] == name]
86 if len(collection):
87 collection[0]['filepaths'].append(filepath)
88 else: 95 else:
89 collection = {'name' : name, 'filepaths' : [filepath]} 96 name = 'other'
90 collections.append(collection) 97 filepath = dataset['filepath']
98 if not len(collections):
99 collections = [{'name' : name, 'filepaths' : [filepath]}]
100 else:
101 collection = [c for c in collections if c['name'] == name]
102 if len(collection):
103 collection[0]['filepaths'].append(filepath)
104 else:
105 collection = {'name' : name, 'filepaths' : [filepath]}
106 collections.append(collection)
107 else:
108 # Collect input file datasets info
109 collections = [{'name' : filetype, 'filepaths' : [filepath]}
110 for filetype, filepath in zip(args.inputfile_types, args.inputfiles)]
91 logging.debug(f'collections:\n{collections}') 111 logging.debug(f'collections:\n{collections}')
92 if len(args.tomo_ranges) != 2*len(collections): 112 if len(args.tomo_ranges) != 2*len(collections):
93 raise ValueError('Inconsistent tomo ranges size.') 113 raise ValueError('Inconsistent tomo ranges size.')
94 114
95 # Instantiate Tomo object 115 # Instantiate Tomo object
140 raise ValueError('Inconsistent number of tomography data image sets') 160 raise ValueError('Inconsistent number of tomography data image sets')
141 tomo_stack_files = [] 161 tomo_stack_files = []
142 for stack in stack_info['stacks']: 162 for stack in stack_info['stacks']:
143 stack['img_offset'] = args.tomo_ranges[2*num_collections] 163 stack['img_offset'] = args.tomo_ranges[2*num_collections]
144 stack['num'] = args.tomo_ranges[2*num_collections+1] 164 stack['num'] = args.tomo_ranges[2*num_collections+1]
145 tomo_files = [c['filepaths'] for c in collections if c['name'] == f'set{stack["index"]}'] 165 if input_as_collection:
166 tomo_files = [c['filepaths'] for c in collections
167 if c['name'] == f'set{stack["index"]}']
168 else:
169 assert(collections[num_collections]['name'] == 'data')
170 tomo_files = [collections[num_collections]['filepaths']]
146 if len(tomo_files) != 1 or len(tomo_files[0]) < 1: 171 if len(tomo_files) != 1 or len(tomo_files[0]) < 1:
147 exit(f'Unable to obtain tomography images for set {stack["index"]}') 172 exit(f'Unable to obtain tomography images for set {stack["index"]}')
148 tomo_stack_files.append(tomo_files[0]) 173 tomo_stack_files.append(tomo_files[0])
149 num_collections += 1 174 num_collections += 1
150 175