def test_add_conditional_manually():
"""Enforce the conditioning on additional variables."""
settings = {
'cmi_estimator': 'JidtKraskovCMI',
'max_lag_sources': 5,
'min_lag_sources': 3
}
nw = BivariateMI()
data = Data(seed=SEED)
data.generate_mute_data()
# Add a conditional with a lag bigger than the max_lag requested above
settings['add_conditionals'] = (8, 0)
with pytest.raises(IndexError):
nw.analyse_single_target(settings=settings, data=data, target=0)
# Add valid conditionals and test if they were added
settings['add_conditionals'] = [(0, 1), (1, 3)]
nw._initialise(settings=settings, data=data, target=0, sources=[1, 2])
# Get list of conditionals after intialisation and convert absolute samples
# back to lags for comparison.
cond_list = nw._idx_to_lag(nw.selected_vars_full)
assert settings['add_conditionals'][0] in cond_list, (
'First enforced conditional is missing from results.')
assert settings['add_conditionals'][1] in cond_list, (
'Second enforced conditional is missing from results.')
def test_discrete_input():
"""Test bivariate MI estimation from discrete data."""
# Generate Gaussian test data
covariance = 0.4
data = _get_discrete_gauss_data(covariance=covariance,
n=10000,
delay=1,
normalise=False,
seed=SEED)
corr_expected = covariance / (1 * np.sqrt(covariance**2 +
(1 - covariance)**2))
expected_mi = calculate_mi(corr_expected)
settings = {
'cmi_estimator': 'JidtDiscreteCMI',
'discretise_method': 'none',
'n_discrete_bins': 5, # alphabet size of the variables analysed
'n_perm_max_stat': 21,
'n_perm_omnibus': 30,
'n_perm_max_seq': 30,
'min_lag_sources': 1,
'max_lag_sources': 2
}
nw = BivariateMI()
res = nw.analyse_single_target(settings=settings, data=data, target=1)
assert np.isclose(
res._single_target[1].omnibus_mi, expected_mi, atol=0.05), (
'Estimated MI for discrete variables is not correct. Expected: '
'{0}, Actual results: {1}.'.format(expected_mi,
res['selected_sources_mi'][0]))
def test_zero_lag():
"""Test analysis for 0 lag."""
covariance = 0.4
n = 10000
source = np.random.normal(0, 1, size=n)
target = (covariance * source +
(1 - covariance) * np.random.normal(0, 1, size=n))
# expected_corr = covariance / (np.sqrt(covariance**2 + (1-covariance)**2))
corr = np.corrcoef(source, target)[0, 1]
expected_mi = -0.5 * np.log(1 - corr**2)
data = Data(np.vstack((source, target)), dim_order='ps', normalise=False)
settings = {
'cmi_estimator': 'JidtKraskovCMI',
'n_perm_max_stat': 21,
'n_perm_min_stat': 21,
'n_perm_max_seq': 21,
'n_perm_omnibus': 21,
'max_lag_sources': 0,
'min_lag_sources': 0
}
nw = BivariateMI()
results = nw.analyse_single_target(settings, data, target=1, sources='all')
mi_estimator = JidtKraskovMI(settings={})
jidt_mi = mi_estimator.estimate(source, target)
omnibus_mi = results.get_single_target(1, fdr=False).omnibus_mi
print('Estimated omnibus MI: {0:0.6f}, estimated MI using JIDT core '
'estimator: {1:0.6f} (expected: {2:0.6f}).'.format(
omnibus_mi, jidt_mi, expected_mi))
assert np.isclose(omnibus_mi, jidt_mi, rtol=0.05), (
'Zero-lag omnibus MI ({0:0.6f}) differs from JIDT estimate ({1:0.6f}).'
.format(omnibus_mi, jidt_mi))
assert np.isclose(omnibus_mi, expected_mi, rtol=0.05), (
'Zero-lag omnibus MI ({0:0.6f}) differs from expected MI ({1:0.6f}).'.
format(omnibus_mi, expected_mi))
def test_zero_lag():
"""Test analysis for 0 lag."""
expected_mi, source, source_uncorr, target = _get_gauss_data()
data = Data(np.hstack((source, target)),
dim_order='sp',
normalise=False,
seed=SEED)
settings = {
'cmi_estimator': 'JidtKraskovCMI',
'n_perm_max_stat': 21,
'n_perm_min_stat': 21,
'n_perm_max_seq': 21,
'n_perm_omnibus': 21,
'tau_sources':
0, # this is not required, but shouldn't throw an error if provided
'max_lag_sources': 0,
'min_lag_sources': 0
}
nw = BivariateMI()
results = nw.analyse_single_target(settings, data, target=1, sources='all')
mi_estimator = JidtKraskovMI(settings={'normalise': False})
jidt_mi = mi_estimator.estimate(source, target)
omnibus_mi = results.get_single_target(1, fdr=False).omnibus_mi
print('Estimated omnibus MI: {0:0.6f}, estimated MI using JIDT core '
'estimator: {1:0.6f} (expected: {2:0.6f}).'.format(
omnibus_mi, jidt_mi, expected_mi))
assert np.isclose(omnibus_mi, jidt_mi, atol=0.005), (
'Zero-lag omnibus MI ({0:0.6f}) differs from JIDT estimate '
'({1:0.6f}).'.format(omnibus_mi, jidt_mi))
assert np.isclose(
omnibus_mi, expected_mi,
atol=0.05), ('Zero-lag omnibus MI ({0:0.6f}) differs from expected MI '
'({1:0.6f}).'.format(omnibus_mi, expected_mi))
def test_gauss_data():
"""Test bivariate MI estimation from correlated Gaussians."""
# Generate data and add a delay one one sample.
expected_mi, source, source_uncorr, target = _get_gauss_data()
source = source[1:]
source_uncorr = source_uncorr[1:]
target = target[:-1]
data = Data(np.hstack((source, source_uncorr, target)), dim_order='sp')
settings = {
'cmi_estimator': 'JidtKraskovCMI',
'n_perm_max_stat': 21,
'n_perm_min_stat': 21,
'n_perm_max_seq': 21,
'n_perm_omnibus': 21,
'max_lag_sources': 2,
'min_lag_sources': 1}
nw = BivariateMI()
results = nw.analyse_single_target(
settings, data, target=2, sources=[0, 1])
mi = results.get_single_target(2, fdr=False)['mi'][0]
sources = results.get_target_sources(2, fdr=False)
# Assert that only the correlated source was detected.
assert len(sources) == 1, 'Wrong no. inferred sources: {0}.'.format(
len(sources))
assert sources[0] == 0, 'Wrong inferred source: {0}.'.format(sources[0])
# Compare BivarateMI() estimate to JIDT estimate.
est = JidtKraskovMI({'lag_mi': 1})
jidt_mi = est.estimate(var1=source, var2=target)
print('Estimated MI: {0:0.6f}, estimated MI using JIDT core estimator: '
'{1:0.6f} (expected: {2:0.6f}).'.format(mi, jidt_mi, expected_mi))
assert np.isclose(mi, jidt_mi, atol=0.005), (
'Estimated MI {0:0.6f} differs from JIDT estimate {1:0.6f} (expected: '
'MI {2:0.6f}).'.format(mi, jidt_mi, expected_mi))
def test_zero_lag():
"""Test analysis for 0 lag."""
covariance = 0.4
n = 10000
source = np.random.normal(0, 1, size=n)
target = (covariance * source + (1 - covariance) *
np.random.normal(0, 1, size=n))
# expected_corr = covariance / (np.sqrt(covariance**2 + (1-covariance)**2))
corr = np.corrcoef(source, target)[0, 1]
expected_mi = -0.5 * np.log(1 - corr**2)
data = Data(np.vstack((source, target)), dim_order='ps', normalise=False)
settings = {
'cmi_estimator': 'JidtKraskovCMI',
'n_perm_max_stat': 21,
'n_perm_min_stat': 21,
'n_perm_max_seq': 21,
'n_perm_omnibus': 21,
'max_lag_sources': 0,
'min_lag_sources': 0}
nw = BivariateMI()
results = nw.analyse_single_target(
settings, data, target=1, sources='all')
mi_estimator = JidtKraskovMI(settings={})
jidt_mi = mi_estimator.estimate(source, target)
omnibus_mi = results.get_single_target(1, fdr=False).omnibus_mi
print('Estimated omnibus MI: {0:0.6f}, estimated MI using JIDT core '
'estimator: {1:0.6f} (expected: {2:0.6f}).'.format(
omnibus_mi, jidt_mi, expected_mi))
assert np.isclose(omnibus_mi, jidt_mi, rtol=0.05), (
'Zero-lag omnibus MI ({0:0.6f}) differs from JIDT estimate ({1:0.6f}).'.format(
omnibus_mi, jidt_mi))
assert np.isclose(omnibus_mi, expected_mi, rtol=0.05), (
'Zero-lag omnibus MI ({0:0.6f}) differs from expected MI ({1:0.6f}).'.format(
omnibus_mi, expected_mi))
def test_add_conditional_manually():
"""Enforce the conditioning on additional variables."""
settings = {'cmi_estimator': 'JidtKraskovCMI',
'max_lag_sources': 5,
'min_lag_sources': 3}
nw = BivariateMI()
data = Data()
data.generate_mute_data()
# Add a conditional with a lag bigger than the max_lag requested above
settings['add_conditionals'] = (8, 0)
with pytest.raises(IndexError):
nw.analyse_single_target(settings=settings, data=data, target=0)
# Add valid conditionals and test if they were added
settings['add_conditionals'] = [(0, 1), (1, 3)]
nw._initialise(settings=settings, data=data, target=0, sources=[1, 2])
# Get list of conditionals after intialisation and convert absolute samples
# back to lags for comparison.
cond_list = nw._idx_to_lag(nw.selected_vars_full)
assert settings['add_conditionals'][0] in cond_list, (
'First enforced conditional is missing from results.')
assert settings['add_conditionals'][1] in cond_list, (
'Second enforced conditional is missing from results.')
def test_gauss_data():
"""Test bivariate MI estimation from correlated Gaussians."""
# Generate data and add a delay one one sample.
expected_mi, source, source_uncorr, target = _get_gauss_data()
source = source[1:]
source_uncorr = source_uncorr[1:]
target = target[:-1]
data = Data(np.hstack((source, source_uncorr, target)),
dim_order='sp',
normalise=False,
seed=SEED)
settings = {
'cmi_estimator': 'JidtKraskovCMI',
'n_perm_max_stat': 21,
'n_perm_min_stat': 21,
'n_perm_max_seq': 21,
'n_perm_omnibus': 21,
'max_lag_sources': 1,
'min_lag_sources': 1
}
nw = BivariateMI()
results = nw.analyse_single_target(settings,
data,
target=2,
sources=[0, 1])
mi = results.get_single_target(2, fdr=False)['mi'][0]
sources = results.get_target_sources(2, fdr=False)
# Assert that only the correlated source was detected.
assert len(sources) == 1, 'Wrong no. inferred sources: {0}.'.format(
len(sources))
assert sources[0] == 0, 'Wrong inferred source: {0}.'.format(sources[0])
# Compare BivarateMI() estimate to JIDT estimate.
est = JidtKraskovMI({'lag_mi': 1, 'normalise': False})
jidt_mi = est.estimate(var1=source, var2=target)
print('Estimated MI: {0:0.6f}, estimated MI using JIDT core estimator: '
'{1:0.6f} (expected: ~ {2:0.6f}).'.format(mi, jidt_mi, expected_mi))
assert np.isclose(mi, jidt_mi, atol=0.005), (
'Estimated MI {0:0.6f} differs from JIDT estimate {1:0.6f} (expected: '
'MI {2:0.6f}).'.format(mi, jidt_mi, expected_mi))
assert np.isclose(mi, expected_mi, atol=0.05), (
'Estimated MI {0:0.6f} differs from expected MI {1:0.6f}.'.format(
mi, expected_mi))
def test_discrete_input():
"""Test bivariate MI estimation from discrete data."""
# Generate Gaussian test data
covariance = 0.4
n = 10000
delay = 1
source = np.random.normal(0, 1, size=n)
target = (covariance * source +
(1 - covariance) * np.random.normal(0, 1, size=n))
corr_expected = covariance / (1 * np.sqrt(covariance**2 +
(1 - covariance)**2))
expected_mi = calculate_mi(corr_expected)
source = source[delay:]
target = target[:-delay]
# Discretise data
settings = {'discretise_method': 'equal', 'n_discrete_bins': 5}
est = JidtDiscreteCMI(settings)
source_dis, target_dis = est._discretise_vars(var1=source, var2=target)
data = Data(np.vstack((source_dis, target_dis)),
dim_order='ps',
normalise=False)
settings = {
'cmi_estimator': 'JidtDiscreteCMI',
'discretise_method': 'none',
'n_discrete_bins': 5, # alphabet size of the variables analysed
'n_perm_max_stat': 21,
'n_perm_omnibus': 30,
'n_perm_max_seq': 30,
'min_lag_sources': 1,
'max_lag_sources': 2
}
nw = BivariateMI()
res = nw.analyse_single_target(settings=settings, data=data, target=1)
assert np.isclose(
res._single_target[1].omnibus_mi, expected_mi, atol=0.05), (
'Estimated MI for discrete variables is not correct. Expected: '
'{0}, Actual results: {1}.'.format(expected_mi,
res['selected_sources_mi'][0]))
def test_discrete_input():
"""Test bivariate MI estimation from discrete data."""
# Generate Gaussian test data
covariance = 0.4
n = 10000
delay = 1
source = np.random.normal(0, 1, size=n)
target = (covariance * source + (1 - covariance) *
np.random.normal(0, 1, size=n))
corr_expected = covariance / (
1 * np.sqrt(covariance**2 + (1-covariance)**2))
expected_mi = calculate_mi(corr_expected)
source = source[delay:]
target = target[:-delay]
# Discretise data
settings = {'discretise_method': 'equal',
'n_discrete_bins': 5}
est = JidtDiscreteCMI(settings)
source_dis, target_dis = est._discretise_vars(var1=source, var2=target)
data = Data(np.vstack((source_dis, target_dis)),
dim_order='ps', normalise=False)
settings = {
'cmi_estimator': 'JidtDiscreteCMI',
'discretise_method': 'none',
'n_discrete_bins': 5, # alphabet size of the variables analysed
'n_perm_max_stat': 21,
'n_perm_omnibus': 30,
'n_perm_max_seq': 30,
'min_lag_sources': 1,
'max_lag_sources': 2}
nw = BivariateMI()
res = nw.analyse_single_target(settings=settings, data=data, target=1)
assert np.isclose(
res._single_target[1].omnibus_mi, expected_mi, atol=0.05), (
'Estimated MI for discrete variables is not correct. Expected: '
'{0}, Actual results: {1}.'.format(
expected_mi, res['selected_sources_mi'][0]))
def test_bivariate_mi_init():
"""Test instance creation for BivariateMI class."""
# Test error on missing estimator
settings = {
'n_perm_max_stat': 21,
'n_perm_omnibus': 30,
'n_perm_max_seq': 30,
'max_lag_sources': 7,
'min_lag_sources': 2
}
nw = BivariateMI()
with pytest.raises(RuntimeError):
nw.analyse_single_target(settings=settings, data=Data(), target=1)
# Test setting of min and max lags
settings['cmi_estimator'] = 'JidtKraskovCMI'
data = Data(seed=SEED)
data.generate_mute_data(n_samples=10, n_replications=5)
# Invalid: min lag sources bigger than max lag
settings['min_lag_sources'] = 8
settings['max_lag_sources'] = 7
with pytest.raises(RuntimeError):
nw.analyse_single_target(settings=settings, data=data, target=1)
# Invalid: taus bigger than lags
settings['min_lag_sources'] = 2
settings['max_lag_sources'] = 4
settings['tau_sources'] = 10
with pytest.raises(RuntimeError):
nw.analyse_single_target(settings=settings, data=data, target=1)
# Invalid: negative lags or taus
settings['tau_sources'] = 1
settings['min_lag_sources'] = 1
settings['max_lag_sources'] = -7
with pytest.raises(RuntimeError):
nw.analyse_single_target(settings=settings, data=data, target=1)
settings['max_lag_sources'] = 7
settings['min_lag_sources'] = -4
with pytest.raises(RuntimeError):
nw.analyse_single_target(settings=settings, data=data, target=1)
settings['min_lag_sources'] = 4
settings['tau_sources'] = -1
with pytest.raises(RuntimeError):
nw.analyse_single_target(settings=settings, data=data, target=1)
# Invalid: lags or taus are no integers
settings['tau_sources'] = 1
settings['min_lag_sources'] = 1.5
with pytest.raises(RuntimeError):
nw.analyse_single_target(settings=settings, data=data, target=1)
settings['min_lag_sources'] = 1
settings['max_lag_sources'] = 1.5
with pytest.raises(RuntimeError):
nw.analyse_single_target(settings=settings, data=data, target=1)
settings['max_lag_sources'] = 7
settings['tau_sources'] = 1.5
with pytest.raises(RuntimeError):
nw.analyse_single_target(settings=settings, data=data, target=1)
settings['tau_sources'] = 1
# Invalid: sources or target is no int
with pytest.raises(RuntimeError): # no int
nw.analyse_single_target(settings=settings, data=data, target=1.5)
with pytest.raises(RuntimeError): # negative
nw.analyse_single_target(settings=settings, data=data, target=-1)
with pytest.raises(RuntimeError): # not in data
nw.analyse_single_target(settings=settings, data=data, target=10)
with pytest.raises(RuntimeError): # wrong type
nw.analyse_single_target(settings=settings, data=data, target={})
with pytest.raises(RuntimeError): # negative
nw.analyse_single_target(settings=settings,
data=data,
target=0,
sources=-1)
with pytest.raises(RuntimeError): # negative
nw.analyse_single_target(settings=settings,
data=data,
target=0,
sources=[-1])
with pytest.raises(RuntimeError): # not in data
nw.analyse_single_target(settings=settings,
data=data,
target=0,
sources=20)
with pytest.raises(RuntimeError): # not in data
nw.analyse_single_target(settings=settings,
data=data,
target=0,
sources=[20])
network_analysis = MultivariateMI()
if algorithm == 'bTE_greedy':
network_analysis = BivariateTE()
if algorithm == 'mTE_greedy':
network_analysis = MultivariateTE()
#settings['add_conditionals'] = [(35, 3), (26, 1), (17, 5), (25, 4)]
# Add optional settings
optional_settings_keys = {'config.debug', 'config.max_mem_frac'}
for key in optional_settings_keys:
if traj.f_contains(key, shortcuts=True):
key_last = key.rpartition('.')[-1]
settings[key_last] = traj[key]
print('Using optional setting \'{0}\'={1}\n'.format(
key_last, traj[key]))
print('settings = {0}\n'.format(settings))
# Run analysis
res = network_analysis.analyse_single_target(settings=settings,
data=dat,
target=target_id)
# Save results dictionary using pickle
save_obj(
res, traj_dir,
'.'.join([file_prefix, 'network_analysis.res',
str(target_id), 'pkl']))
def test_bivariate_mi_init():
"""Test instance creation for BivariateMI class."""
# Test error on missing estimator
settings = {
'n_perm_max_stat': 21,
'n_perm_omnibus': 30,
'n_perm_max_seq': 30,
'max_lag_sources': 7,
'min_lag_sources': 2}
nw = BivariateMI()
with pytest.raises(RuntimeError):
nw.analyse_single_target(settings=settings, data=Data(), target=1)
# Test setting of min and max lags
settings['cmi_estimator'] = 'JidtKraskovCMI'
data = Data()
data.generate_mute_data(n_samples=10, n_replications=5)
# Invalid: min lag sources bigger than max lag
settings['min_lag_sources'] = 8
settings['max_lag_sources'] = 7
with pytest.raises(RuntimeError):
nw.analyse_single_target(settings=settings, data=data, target=1)
# Invalid: taus bigger than lags
settings['min_lag_sources'] = 2
settings['max_lag_sources'] = 4
settings['tau_sources'] = 10
with pytest.raises(RuntimeError):
nw.analyse_single_target(settings=settings, data=data, target=1)
# Invalid: negative lags or taus
settings['tau_sources'] = 1
settings['min_lag_sources'] = 1
settings['max_lag_sources'] = -7
with pytest.raises(RuntimeError):
nw.analyse_single_target(settings=settings, data=data, target=1)
settings['max_lag_sources'] = 7
settings['min_lag_sources'] = -4
with pytest.raises(RuntimeError):
nw.analyse_single_target(settings=settings, data=data, target=1)
settings['min_lag_sources'] = 4
settings['tau_sources'] = -1
with pytest.raises(RuntimeError):
nw.analyse_single_target(settings=settings, data=data, target=1)
# Invalid: lags or taus are no integers
settings['tau_sources'] = 1
settings['min_lag_sources'] = 1.5
with pytest.raises(RuntimeError):
nw.analyse_single_target(settings=settings, data=data, target=1)
settings['min_lag_sources'] = 1
settings['max_lag_sources'] = 1.5
with pytest.raises(RuntimeError):
nw.analyse_single_target(settings=settings, data=data, target=1)
settings['max_lag_sources'] = 7
settings['tau_sources'] = 1.5
with pytest.raises(RuntimeError):
nw.analyse_single_target(settings=settings, data=data, target=1)
settings['tau_sources'] = 1
# Invalid: sources or target is no int
with pytest.raises(RuntimeError): # no int
nw.analyse_single_target(settings=settings, data=data, target=1.5)
with pytest.raises(RuntimeError): # negative
nw.analyse_single_target(settings=settings, data=data, target=-1)
with pytest.raises(RuntimeError): # not in data
nw.analyse_single_target(settings=settings, data=data, target=10)
with pytest.raises(RuntimeError): # wrong type
nw.analyse_single_target(settings=settings, data=data, target={})
with pytest.raises(RuntimeError): # negative
nw.analyse_single_target(settings=settings, data=data, target=0,
sources=-1)
with pytest.raises(RuntimeError): # negative
nw.analyse_single_target(settings=settings, data=data, target=0,
sources=[-1])
with pytest.raises(RuntimeError): # not in data
nw.analyse_single_target(settings=settings, data=data, target=0,
sources=20)
with pytest.raises(RuntimeError): # not in data
nw.analyse_single_target(settings=settings, data=data, target=0,
sources=[20])