def generateCSV_test(self):
'''
make sure things are being packed into dataframes correctly;
assumes Pandas writes dataframes to csv correctly.
'''
truth = [True, False, False]
results = [
[False, False, False],
[True, True, True]
]
tests = ['x', 'y']
keys = [1000,1001,1002]
df = main.generateCSV(truth, results, tests, keys, 'test')
dfTrue = pandas.DataFrame([[True, False, True],[False, False, True],[False, False, True]], index=keys, columns=['True Flags', 'x', 'y'])
assert_frame_equal(df, dfTrue, check_names=True)
def generateCSV_test(self):
'''
make sure things are being packed into dataframes correctly;
assumes Pandas writes dataframes to csv correctly.
'''
truth = [True, False, False]
results = [[False, False, False], [True, True, True]]
tests = ['x', 'y']
keys = [1000, 1001, 1002]
df = main.generateCSV(truth, results, tests, keys, 'test')
dfTrue = pandas.DataFrame(
[[True, False, True], [False, False, True], [False, False, True]],
index=keys,
columns=['True Flags', 'x', 'y'])
assert_frame_equal(df, dfTrue, check_names=True)
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.'
