def test_compare_profiles_not_shared(self):
'''Normalizing with a profile containing not_shared and one without'''
result = compare_profiles(self.not_shared_profiles)
exresult = {'taxa1': 0.10, 'taxa2': 0.30, 'taxa3': 0.15, 'taxa4': 0.25,
'not_shared': 0.20}
#make sure the keys in each are the same
self.assertEquals(set(result.keys()), set(exresult.keys()))
#make sure the values are correct-ish
for key in result:
self.assertAlmostEquals(result[key], exresult[key])
def bootstrap_profiles(profiles,
alpha=0.05,
repetitions=1000,
randfunc=randint):
"""Performs bootstrapping over the sample 'profiles'
Inputs:
profiles: list of profiles
alpha: defines the confidence interval as 1 - alpha
repetitions: number of bootstrap iterations
randfunc: random function for generate the bootstrap samples
Returns:
profile: the bootstrapped profile of the profiles list
sample_mean: the bootstrap mean of the amount shared
sample_stdev: the bootstrap standard deviation of the amount shared
ci: the confidence interval for the bootstrap mean
"""
length = len(profiles)
normalize_profiles(profiles)
boot_shared = []
boot_profiles = []
for i in range(repetitions):
# Construct the bootstrap sample
resample = [profiles[randfunc(0, length)] for j in range(length)]
profile = compare_profiles(resample)
# Store the amount shared
boot_shared.append(1.0 - profile['not_shared'])
# Store the result profile
boot_profiles.append(profile)
# Convert data to a numpy array
boot_shared = array(boot_shared)
# Get the mean and the standard deviation of the shared data
sample_mean = mean(boot_shared)
sample_stdev = std(boot_shared)
# Compute the confidence interval for the bootstrapped data
# using bootstrap percentile interval
ci = quantile(boot_shared, [alpha / 2, 1 - (alpha / 2)])
# Compute the bootstrapped profile of the profiles list
profile = compare_profiles(profiles)
return profile, 1.0 - profile['not_shared'], sample_stdev, ci
def test_compare_profiles(self):
'''Comparing three profiles, testing when each are the min and when\
one taxa is equal '''
result = compare_profiles(self.many_profiles)
exresult = {'taxa1': 0.10, 'taxa2': 0.22, 'taxa3': 0.15, 'taxa4': 0.25,
'not_shared': 0.28}
#make sure the keys in each are the same
self.assertEquals(set(result.keys()), set(exresult.keys()))
#make sure the values are correct-ish
for key in result:
self.assertAlmostEquals(result[key], exresult[key])
def bootstrap_profiles(profiles, alpha=0.05, repetitions=1000,
randfunc=randint):
"""Performs bootstrapping over the sample 'profiles'
Inputs:
profiles: list of profiles
alpha: defines the confidence interval as 1 - alpha
repetitions: number of bootstrap iterations
randfunc: random function for generate the bootstrap samples
Returns:
profile: the bootstrapped profile of the profiles list
sample_mean: the bootstrap mean of the amount shared
sample_stdev: the bootstrap standard deviation of the amount shared
ci: the confidence interval for the bootstrap mean
"""
length = len(profiles)
normalize_profiles(profiles)
boot_shared = []
boot_profiles = []
for i in range(repetitions):
# Construct the bootstrap sample
resample = [profiles[randfunc(0, length)] for j in range(length)]
profile = compare_profiles(resample)
# Store the amount shared
boot_shared.append(1.0 - profile['not_shared'])
# Store the result profile
boot_profiles.append(profile)
# Convert data to a numpy array
boot_shared = array(boot_shared)
# Get the mean and the standard deviation of the shared data
sample_mean = mean(boot_shared)
sample_stdev = std(boot_shared)
# Compute the confidence interval for the bootstrapped data
# using bootstrap percentile interval
ci = quantile(boot_shared, [alpha/2, 1-(alpha/2)])
# Compute the bootstrapped profile of the profiles list
profile = compare_profiles(profiles)
return profile, 1.0-profile['not_shared'], sample_stdev, ci
def test_compare_profiles_not_shared(self):
'''Normalizing with one profile containing not_shared and one without'''
result = compare_profiles(self.not_shared_profiles)
exresult = {
'taxa1': 0.10,
'taxa2': 0.30,
'taxa3': 0.15,
'taxa4': 0.25,
'not_shared': 0.20
}
#make sure the keys in each are the same
self.assertEquals(set(result.keys()), set(exresult.keys()))
#make sure the values are correct-ish
for key in result:
self.assertAlmostEquals(result[key], exresult[key])
def test_compare_profiles(self):
'''Comparing three profiles, testing when each are the min and when\
one taxa is equal '''
result = compare_profiles(self.many_profiles)
exresult = {
'taxa1': 0.10,
'taxa2': 0.22,
'taxa3': 0.15,
'taxa4': 0.25,
'not_shared': 0.28
}
#make sure the keys in each are the same
self.assertEquals(set(result.keys()), set(exresult.keys()))
#make sure the values are correct-ish
for key in result:
self.assertAlmostEquals(result[key], exresult[key])
