def combineArrays_test(self):
'''
spotcheck combineArrays
'''
parallel = [
[[0,1],[[100,101],[102,103],[104,105]], [992,993]],
[[2,3],[[200,201],[202,203],[204,205]], [994,995]],
[[4,5],[[300,301],[302,303],[304,305]], [996,997]],
[[6,7],[[400,401],[402,403],[404,405]], [998,999]]
]
truth, results, ids = main.combineArrays(parallel)
assert numpy.array_equal(truth, [0,1,2,3,4,5,6,7])
assert numpy.array_equal(results, [ [100,101, 200,201, 300,301, 400,401], [102,103, 202,203, 302,303, 402,403], [104,105, 204,205, 304,305, 404,405] ])
assert numpy.array_equal(ids, [992, 993, 994, 995, 996, 997, 998, 999])
def combineArrays_test(self):
'''
spotcheck combineArrays
'''
parallel = [[[0, 1], [[100, 101], [102, 103], [104, 105]], [992, 993]],
[[2, 3], [[200, 201], [202, 203], [204, 205]], [994, 995]],
[[4, 5], [[300, 301], [302, 303], [304, 305]], [996, 997]],
[[6, 7], [[400, 401], [402, 403], [404, 405]], [998, 999]]]
truth, results, ids = main.combineArrays(parallel)
assert numpy.array_equal(truth, [0, 1, 2, 3, 4, 5, 6, 7])
assert numpy.array_equal(results,
[[100, 101, 200, 201, 300, 301, 400, 401],
[102, 103, 202, 203, 302, 303, 402, 403],
[104, 105, 204, 205, 304, 305, 404, 405]])
assert numpy.array_equal(ids, [992, 993, 994, 995, 996, 997, 998, 999])
testNames.sort()
print('{} quality control checks have been found'.format(len(testNames)))
testNames = main.checkQCTestRequirements(testNames)
print('{} quality control checks are able to be run:'.format(
len(testNames)))
for testName in testNames:
print(' {}'.format(testName))
# Identify data files and create a profile list.
filenames = main.readInput('datafiles.json')
profiles = main.extractProfiles(filenames)
data.ds.profiles = profiles
print('\n{} file(s) will be read containing {} profiles'.format(
len(filenames), len(profiles)))
# Parallel processing.
print('\nPlease wait while QC is performed\n')
processFile.parallel = main.parallel_function(processFile, sys.argv[2])
parallel_result = processFile.parallel(filenames)
# Recombine results
truth, results, profileIDs = main.combineArrays(parallel_result)
# Print summary statistics and write output file.
main.printSummary(truth, results, testNames)
main.generateCSV(truth, results, testNames, profileIDs, sys.argv[1])
else:
print 'Please add command line arguments to name your output file and set parallelization:'
print 'python AutoQC myFile 4'
print 'will result in output written to results-myFile.csv, and will run the calculation parallelized across 4 cores.'
# Identify and import tests
testNames = main.importQC('qctests')
testNames.sort()
print('{} quality control checks have been found'.format(len(testNames)))
testNames = main.checkQCTestRequirements(testNames)
print('{} quality control checks are able to be run:'.format(len(testNames)))
for testName in testNames:
print(' {}'.format(testName))
# Identify data files and create a profile list.
filenames = main.readInput('datafiles.json')
profiles = main.extractProfiles(filenames)
data.ds.profiles = profiles
print('\n{} file(s) will be read containing {} profiles'.format(len(filenames), len(profiles)))
# Parallel processing.
print('\nPlease wait while QC is performed\n')
processFile.parallel = main.parallel_function(processFile, sys.argv[2])
parallel_result = processFile.parallel(filenames)
# Recombine results
truth, results, profileIDs = main.combineArrays(parallel_result)
# Print summary statistics and write output file.
main.printSummary(truth, results, testNames)
main.generateCSV(truth, results, testNames, profileIDs, sys.argv[1])
else:
print 'Please add command line arguments to name your output file and set parallelization:'
print 'python AutoQC myFile 4'
print 'will result in output written to results-myFile.csv, and will run the calculation parallelized across 4 cores.'
