def test_multivariate_mi_one_realisation_per_replication():
"""Test boundary case of one realisation per replication."""
# Create a data set where one pattern fits into the time series exactly
# once, this way, we get one realisation per replication for each variable.
# This is easyer to assert/verify later. We also test data.get_realisations
# this way.
settings = {
'cmi_estimator': 'JidtKraskovCMI',
'n_perm_max_stat': 21,
'max_lag_sources': 5,
'min_lag_sources': 4
}
target = 0
data = Data(normalise=False)
n_repl = 10
n_procs = 2
n_points = n_procs * (settings['max_lag_sources'] + 1) * n_repl
data.set_data(
np.arange(n_points).reshape(n_procs, settings['max_lag_sources'] + 1,
n_repl), 'psr')
nw_0 = MultivariateMI()
nw_0._initialise(settings, data, 'all', target)
assert (not nw_0.selected_vars_full)
assert (not nw_0.selected_vars_sources)
assert (not nw_0.selected_vars_target)
assert ((nw_0._replication_index == np.arange(n_repl)).all())
assert (nw_0._current_value == (target, settings['max_lag_sources']))
assert (nw_0._current_value_realisations[:, 0] == data.data[target,
-1, :]).all()
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)
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 = MultivariateMI()
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_add_conditional_manually():
"""Enforce the conditioning on additional variables."""
settings = {
'cmi_estimator': 'JidtKraskovCMI',
'max_lag_sources': 5,
'min_lag_sources': 3
}
nw = MultivariateMI()
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._initialise(settings, data, sources=[1, 2], 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 multivariate 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 = MultivariateMI()
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_te'][0]))
def test_analyse_network():
"""Test method for full network analysis."""
n_processes = 5 # the MuTE network has 5 nodes
data = Data()
data.generate_mute_data(10, 5)
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': 5,
'min_lag_sources': 4
}
nw_0 = MultivariateMI()
# Test all to all analysis
results = nw_0.analyse_network(settings,
data,
targets='all',
sources='all')
targets_analysed = results.targets_analysed
sources = np.arange(n_processes)
assert all(np.array(targets_analysed) == np.arange(n_processes)), (
'Network analysis did not run on all targets.')
for t in targets_analysed:
s = np.array(list(set(sources) - set([t])))
assert all(np.array(results._single_target[t].sources_tested) == s), (
'Network analysis did not run on all sources for target '
'{0}'.format(t))
# Test analysis for subset of targets
target_list = [1, 2, 3]
results = nw_0.analyse_network(settings,
data,
targets=target_list,
sources='all')
targets_analysed = results.targets_analysed
assert all(np.array(targets_analysed) == np.array(target_list)), (
'Network analysis did not run on correct subset of targets.')
for t in targets_analysed:
s = np.array(list(set(sources) - set([t])))
assert all(np.array(results._single_target[t].sources_tested) == s), (
'Network analysis did not run on all sources for target '
'{0}'.format(t))
# Test analysis for subset of sources
source_list = [1, 2, 3]
target_list = [0, 4]
results = nw_0.analyse_network(settings,
data,
targets=target_list,
sources=source_list)
targets_analysed = results.targets_analysed
assert all(np.array(targets_analysed) == np.array(target_list)), (
'Network analysis did not run for all targets.')
for t in targets_analysed:
assert all(
results._single_target[t].sources_tested == np.array(source_list)
), ('Network analysis did not run on the correct subset '
'of sources for target {0}'.format(t))
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 = MultivariateMI()
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 getAnalysisClass(methodname):
# Initialise analysis object
if methodname == "BivariateMI": return BivariateMI()
elif methodname == "MultivariateMI": return MultivariateMI()
elif methodname == "BivariateTE": return BivariateTE()
elif methodname == "MultivariateTE": return MultivariateTE()
else:
raise ValueError("Unexpected method", methodname)
def test_define_candidates():
"""Test candidate definition from a list of procs and a list of samples."""
target = 1
tau_sources = 3
max_lag_sources = 10
current_val = (target, 10)
procs = [target]
samples = np.arange(current_val[1] - 1, current_val[1] - max_lag_sources,
-tau_sources)
nw = MultivariateMI()
candidates = nw._define_candidates(procs, samples)
assert (1, 9) in candidates, 'Sample missing from candidates: (1, 9).'
assert (1, 6) in candidates, 'Sample missing from candidates: (1, 6).'
assert (1, 3) in candidates, 'Sample missing from candidates: (1, 3).'
def analyse_discrete_data():
"""Run network inference on discrete data."""
data = generate_discrete_data()
settings = {
'cmi_estimator': 'JidtDiscreteCMI',
'discretise_method': 'none',
'n_discrete_bins': 5, # alphabet size of the variables analysed
'min_lag_sources': 1,
'max_lag_sources': 3,
'max_lag_target': 1
}
nw = MultivariateTE()
res = nw.analyse_network(settings=settings, data=data)
pickle.dump(
res,
open(
'{0}discrete_results_mte_{1}.p'.format(path,
settings['cmi_estimator']),
'wb'))
nw = BivariateTE()
res = nw.analyse_network(settings=settings, data=data)
pickle.dump(
res,
open(
'{0}discrete_results_bte_{1}.p'.format(path,
settings['cmi_estimator']),
'wb'))
nw = MultivariateMI()
res = nw.analyse_network(settings=settings, data=data)
pickle.dump(
res,
open(
'{0}discrete_results_mmi_{1}.p'.format(path,
settings['cmi_estimator']),
'wb'))
nw = BivariateMI()
res = nw.analyse_network(settings=settings, data=data)
pickle.dump(
res,
open(
'{0}discrete_results_bmi_{1}.p'.format(path,
settings['cmi_estimator']),
'wb'))
def test_faes_method():
"""Check if the Faes method is working."""
settings = {
'cmi_estimator': 'JidtKraskovCMI',
'add_conditionals': 'faes',
'max_lag_sources': 5,
'min_lag_sources': 3
}
nw_1 = MultivariateMI()
data = Data()
data.generate_mute_data()
sources = [1, 2, 3]
target = 0
nw_1._initialise(settings, data, sources, target)
assert (nw_1._selected_vars_sources == [
i for i in it.product(sources, [nw_1.current_value[1]])
]), ('Did not add correct additional conditioning vars.')
def analyse_continuous_data():
"""Run network inference on continuous data."""
data = generate_continuous_data()
settings = {
'min_lag_sources': 1,
'max_lag_sources': 3,
'max_lag_target': 1
}
nw = MultivariateTE()
for estimator in ['JidtGaussianCMI', 'JidtKraskovCMI']:
settings['cmi_estimator'] = estimator
res = nw.analyse_network(settings=settings, data=data)
pickle.dump(
res,
open('{0}continuous_results_mte_{1}.p'.format(path, estimator),
'wb'))
nw = BivariateTE()
for estimator in ['JidtGaussianCMI', 'JidtKraskovCMI']:
settings['cmi_estimator'] = estimator
res = nw.analyse_network(settings=settings, data=data)
pickle.dump(
res,
open('{0}continuous_results_bte_{1}.p'.format(path, estimator),
'wb'))
nw = MultivariateMI()
for estimator in ['JidtGaussianCMI', 'JidtKraskovCMI']:
settings['cmi_estimator'] = estimator
res = nw.analyse_network(settings=settings, data=data)
pickle.dump(
res,
open('{0}continuous_results_mmi_{1}.p'.format(path, estimator),
'wb'))
nw = BivariateMI()
for estimator in ['JidtGaussianCMI', 'JidtKraskovCMI']:
settings['cmi_estimator'] = estimator
res = nw.analyse_network(settings=settings, data=data)
pickle.dump(
res,
open('{0}continuous_results_bmi_{1}.p'.format(path, estimator),
'wb'))
def test_gauss_data():
"""Test multivariate 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)
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 = MultivariateMI()
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. Mimick realisations used
# internally by the algorithm.
est = JidtKraskovMI({'lag_mi': 0, 'normalise': False})
jidt_mi = est.estimate(var1=source[1:-1], var2=target[2:])
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 analyze_data(ROI_nodes, file_to_read, counter, analysis):
start_time = time.time() #start timer
n_nodes = len(ROI_nodes)
raw_data = set_up_data(
ROI_nodes,
file_to_read) #parse tsv file and convert to formatted numpy array
data = Data(raw_data,
dim_order='ps') #convert to Data type for use with IDTXL
# b) Initialise analysis object and define settings
if analysis == 1: network_analysis = MultivariateMI()
else: network_analysis = MultivariateTE()
settings = {
'cmi_estimator': 'JidtGaussianCMI',
'max_lag_sources': 5,
'min_lag_sources': 1
}
results = network_analysis.analyse_network(settings=settings, data=data)
time_elapsed = (time.time()) - start_time
adj_matrix = results.get_adjacency_matrix(weights='max_te_lag', fdr=False)
# adj_matrix.print_matrix()
# print(adj_matrix._weight_matrix)
all_adj_matrix.append(adj_matrix._weight_matrix)
# print(type(all_adj_matrix))
# print(type(all_adj_matrix[0]))
if type == 1:
file_name = mMI_pickle_path + file_to_read[:-4] + " mMI - " + str(n_nodes) + \
" ROIs results (min lag 1, max lag 5) pickled.p" #create pickle file name based on analyzed file's name
else:
file_name = mTE_pickle_path + file_to_read[:-4] + " mTE - " + str(n_nodes) + \
" ROIs results (min lag 1, max lag 1) pickled.p"
pickle.dump(results, open(file_name, 'wb')) #pickle results to a file
#results = pickle.load(open('results.p', 'rb')) #open the pickled file
return (time_elapsed)
def test_permute_time():
"""Create surrogates by permuting data in time instead of over replic."""
# Test if perm type is set to default
default = 'random'
data = Data()
data.generate_mute_data(10, 5)
settings = {
'cmi_estimator': 'JidtKraskovCMI',
'n_perm_max_stat': 21,
'n_perm_max_seq': 21,
'n_perm_omnibus': 21,
'max_lag_sources': 5,
'min_lag_sources': 4,
'permute_in_time': True
}
nw_0 = MultivariateMI()
results = nw_0.analyse_network(settings,
data,
targets='all',
sources='all')
assert results.settings.perm_type == default, (
'Perm type was not set to default.')
def test_discrete_input():
"""Test multivariate 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 = MultivariateMI()
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_te'][0]))
def test_define_candidates():
"""Test candidate definition from a list of procs and a list of samples."""
target = 1
tau_sources = 3
max_lag_sources = 10
current_val = (target, 10)
procs = [target]
samples = np.arange(current_val[1] - 1, current_val[1] - max_lag_sources,
-tau_sources)
# Test if candidates that are added manually to the conditioning set are
# removed from the candidate set.
nw = MultivariateMI()
nw.current_value = current_val
settings = [{
'add_conditionals': None
}, {
'add_conditionals': (2, 3)
}, {
'add_conditionals': [(2, 3), (4, 1)]
}, {
'add_conditionals': [(1, 9)]
}, {
'add_conditionals': [(1, 9), (2, 3), (4, 1)]
}]
for s in settings:
nw.settings = s
candidates = nw._define_candidates(procs, samples)
assert (1, 9) in candidates, 'Sample missing from candidates: (1, 9).'
assert (1, 6) in candidates, 'Sample missing from candidates: (1, 6).'
assert (1, 3) in candidates, 'Sample missing from candidates: (1, 3).'
if s['add_conditionals'] is not None:
if type(s['add_conditionals']) is tuple:
cond_ind = nw._lag_to_idx([s['add_conditionals']])
else:
cond_ind = nw._lag_to_idx(s['add_conditionals'])
for c in cond_ind:
assert c not in candidates, (
'Sample added erronously to candidates: {}.'.format(c))
def test_define_candidates():
"""Test candidate definition from a list of procs and a list of samples."""
target = 1
tau_sources = 3
max_lag_sources = 10
current_val = (target, 10)
procs = [target]
samples = np.arange(current_val[1] - 1, current_val[1] - max_lag_sources,
-tau_sources)
# Test if candidates that are added manually to the conditioning set are
# removed from the candidate set.
nw = MultivariateMI()
settings = [{
'add_conditionals': None
}, {
'add_conditionals': (2, 3)
}, {
'add_conditionals': [(2, 3), (4, 1)]
}]
for s in settings:
nw.settings = s
candidates = nw._define_candidates(procs, samples)
assert (1, 9) in candidates, 'Sample missing from candidates: (1, 9).'
assert (1, 6) in candidates, 'Sample missing from candidates: (1, 6).'
assert (1, 3) in candidates, 'Sample missing from candidates: (1, 3).'
settings = [{
'add_conditionals': [(1, 9)]
}, {
'add_conditionals': [(1, 9), (2, 3), (4, 1)]
}]
for s in settings:
nw.settings = s
candidates = nw._define_candidates(procs, samples)
assert (1, 9) not in candidates, 'Sample missing from candidates: (1, 9).'
assert (1, 6) in candidates, 'Sample missing from candidates: (1, 6).'
assert (1, 3) in candidates, 'Sample missing from candidates: (1, 3).'
def test_check_source_set():
"""Test the method _check_source_set.
This method sets the list of source processes from which candidates are
taken for multivariate MI estimation.
"""
data = Data()
data.generate_mute_data(100, 5)
nw_0 = MultivariateMI()
nw_0.settings = {'verbose': True}
# Add list of sources.
sources = [1, 2, 3]
nw_0._check_source_set(sources, data.n_processes)
assert nw_0.source_set == sources, 'Sources were not added correctly.'
# Assert that initialisation fails if the target is also in the source list
sources = [0, 1, 2, 3]
nw_0.target = 0
with pytest.raises(RuntimeError):
nw_0._check_source_set(sources=[0, 1, 2, 3],
n_processes=data.n_processes)
# Test if a single source, no list is added correctly.
sources = 1
nw_0._check_source_set(sources, data.n_processes)
assert (type(nw_0.source_set) is list)
# Test if 'all' is handled correctly
nw_0.target = 0
nw_0._check_source_set('all', data.n_processes)
assert nw_0.source_set == [1, 2, 3, 4], 'Sources were not added correctly.'
# Test invalid inputs.
with pytest.raises(RuntimeError): # sources greater than no. procs
nw_0._check_source_set(8, data.n_processes)
with pytest.raises(RuntimeError): # negative value as source
nw_0._check_source_set(-3, data.n_processes)
def test_results_network_inference():
"""Test results class for multivariate TE network inference."""
covariance = 0.4
n = 10000
delay = 1
normalisation = False
source = np.random.normal(0, 1, size=n)
target_1 = (covariance * source +
(1 - covariance) * np.random.normal(0, 1, size=n))
target_2 = (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_1 = target_1[:-delay]
target_2 = target_2[:-delay]
# Discretise data for speed
settings_dis = {'discretise_method': 'equal', 'n_discrete_bins': 5}
est = JidtDiscreteCMI(settings_dis)
source_dis, target_1_dis = est._discretise_vars(var1=source, var2=target_1)
source_dis, target_2_dis = est._discretise_vars(var1=source, var2=target_2)
data = Data(np.vstack((source_dis, target_1_dis, target_2_dis)),
dim_order='ps',
normalise=normalisation)
nw = MultivariateTE()
# TE - single target
res_single_multi_te = nw.analyse_single_target(settings=settings,
data=data,
target=1)
# TE whole network
res_network_multi_te = nw.analyse_network(settings=settings, data=data)
nw = BivariateTE()
# TE - single target
res_single_biv_te = nw.analyse_single_target(settings=settings,
data=data,
target=1)
# TE whole network
res_network_biv_te = nw.analyse_network(settings=settings, data=data)
nw = MultivariateMI()
# TE - single target
res_single_multi_mi = nw.analyse_single_target(settings=settings,
data=data,
target=1)
# TE whole network
res_network_multi_mi = nw.analyse_network(settings=settings, data=data)
nw = BivariateMI()
# TE - single target
res_single_biv_mi = nw.analyse_single_target(settings=settings,
data=data,
target=1)
# TE whole network
res_network_biv_mi = nw.analyse_network(settings=settings, data=data)
res_te = [
res_single_multi_te, res_network_multi_te, res_single_biv_te,
res_network_biv_te
]
res_mi = [
res_single_multi_mi, res_network_multi_mi, res_single_biv_mi,
res_network_biv_mi
]
res_all = res_te + res_mi
# Check estimated values
for res in res_te:
est_te = res._single_target[1].omnibus_te
assert np.isclose(est_te, expected_mi, atol=0.05), (
'Estimated TE for discrete variables is not correct. Expected: '
'{0}, Actual results: {1}.'.format(expected_mi, est_te))
for res in res_mi:
est_mi = res._single_target[1].omnibus_mi
assert np.isclose(est_mi, expected_mi, atol=0.05), (
'Estimated TE for discrete variables is not correct. Expected: '
'{0}, Actual results: {1}.'.format(expected_mi, est_mi))
est_te = res_network_multi_te._single_target[2].omnibus_te
assert np.isclose(est_te, expected_mi, atol=0.05), (
'Estimated TE for discrete variables is not correct. Expected: {0}, '
'Actual results: {1}.'.format(expected_mi, est_te))
est_mi = res_network_multi_mi._single_target[2].omnibus_mi
assert np.isclose(est_mi, expected_mi, atol=0.05), (
'Estimated TE for discrete variables is not correct. Expected: {0}, '
'Actual results: {1}.'.format(expected_mi, est_mi))
# Check data parameters in results objects
n_nodes = 3
n_realisations = n - delay - max(settings['max_lag_sources'],
settings['max_lag_target'])
for res in res_all:
assert res.data_properties.n_nodes == n_nodes, 'Incorrect no. nodes.'
assert res.data_properties.n_nodes == n_nodes, 'Incorrect no. nodes.'
assert res.data_properties.n_realisations == n_realisations, (
'Incorrect no. realisations.')
assert res.data_properties.n_realisations == n_realisations, (
'Incorrect no. realisations.')
assert res.data_properties.normalised == normalisation, (
'Incorrect value for data normalisation.')
assert res.data_properties.normalised == normalisation, (
'Incorrect value for data normalisation.')
adj_matrix = res.get_adjacency_matrix('binary', fdr=False)
assert adj_matrix._edge_matrix.shape[0] == n_nodes, (
'Incorrect number of rows in adjacency matrix.')
assert adj_matrix._edge_matrix.shape[1] == n_nodes, (
'Incorrect number of columns in adjacency matrix.')
assert adj_matrix._edge_matrix.shape[0] == n_nodes, (
'Incorrect number of rows in adjacency matrix.')
assert adj_matrix._edge_matrix.shape[1] == n_nodes, (
'Incorrect number of columns in adjacency matrix.')
# Load time series
dat = Data(time_series,
dim_order=dim_order,
normalise=(network_inference.z_standardise & can_be_z_standardised))
network_inference = traj.parameters.network_inference
print('network_inference.p_value = {0}\n'.format(network_inference.p_value))
algorithm = network_inference.algorithm
if algorithm in ['bMI', 'mMI_greedy', 'bTE_greedy', 'mTE_greedy']:
# Set analysis options
if algorithm == 'bMI':
network_analysis = BivariateMI()
if algorithm == 'mMI_greedy':
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(
def test_multivariate_mi_init():
"""Test instance creation for MultivariateMI class."""
# Test error on missing estimator
settings = {
'n_perm_max_stat': 21,
'n_perm_omnibus': 30,
'max_lag_sources': 7,
'min_lag_sources': 2
}
nw = MultivariateMI()
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: tau 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['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)
# 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])
def test_JidtKraskovCMI_MMI_checkpoint():
""" run test without checkpointing, with checkpointing without resume and checkpointing with resume to compare the results"""
filename_ckp1 = os.path.join(
os.path.dirname(__file__), 'data', 'run_checkpoint')
filename_ckp2 = os.path.join(
os.path.dirname(__file__), 'data', 'resume_checkpoint')
"""Test running analysis without any checkpoint setting."""
# Generate test data
data = Data(seed=SEED)
data.generate_mute_data(n_samples=N_SAMPLES, n_replications=1)
# Initialise analysis object and define settings
network_analysis1 = MultivariateMI()
network_analysis2 = MultivariateMI()
network_analysis3 = MultivariateMI()
network_analysis4 = MultivariateMI()
# Settings without checkpointing.
settings1 = {'cmi_estimator': 'JidtKraskovCMI',
'n_perm_max_stat': N_PERM,
'n_perm_min_stat': N_PERM,
'n_perm_max_seq': N_PERM,
'n_perm_omnibus': N_PERM,
'max_lag_sources': 3,
'min_lag_sources': 2,
'noise_level': 0
}
# Settings with checkpointing.
settings2 = {'cmi_estimator': 'JidtKraskovCMI',
'n_perm_max_stat': N_PERM,
'n_perm_min_stat': N_PERM,
'n_perm_max_seq': N_PERM,
'n_perm_omnibus': N_PERM,
'max_lag_sources': 3,
'min_lag_sources': 2,
'noise_level': 0,
'write_ckp': True,
'filename_ckp': filename_ckp1}
# Settings resuming from checkpoint.
settings3 = {'cmi_estimator': 'JidtKraskovCMI',
'n_perm_max_stat': N_PERM,
'n_perm_min_stat': N_PERM,
'n_perm_max_seq': N_PERM,
'n_perm_omnibus': N_PERM,
'max_lag_sources': 3,
'min_lag_sources': 2,
'noise_level': 0,
'write_ckp': True,
'filename_ckp': filename_ckp2}
# Setting sources and targets for the analysis
sources = [0, 1]
targets = [2, 3]
targets2 = [3]
# Starting Analysis of the Network
# results of a network analysis without checkpointing
results1 = network_analysis1.analyse_network(
settings=settings1, data=data, targets=targets, sources=sources)
# results of a network analysis with checkpointing
results2 = network_analysis2.analyse_network(
settings=settings2, data=data, targets=targets, sources=sources)
# Creating a checkpoint similar to the above settings where the targets of
# of the first source have been already analyzed
with open(filename_ckp1 + ".ckp", "r+") as f:
tarsource = f.readlines()
tarsource = tarsource[8]
tarsource = (tarsource[:-1])
network_analysis3._set_checkpointing_defaults(
settings3, data, sources, targets)
with open(filename_ckp2 + ".ckp") as f:
lines = f.read().splitlines()
lines[8] = tarsource
with open(filename_ckp2 + ".ckp", 'w') as f:
f.write('\n'.join(lines))
print(lines)
# Resume analysis.
network_analysis_res = MultivariateMI()
data, settings, targets, sources = network_analysis_res.resume_checkpoint(
filename_ckp2)
# results of a network analysis resuming from checkpoint
results3 = network_analysis_res.analyse_network(
settings=settings3, data=data, targets=targets, sources=sources)
# results of a network analysis without checkpointing but other targets/sources
results4 = network_analysis4.analyse_network(
settings=settings1, data=data, targets=targets2, sources=sources)
adj_matrix1 = results1.get_adjacency_matrix(weights='binary', fdr=False)
adj_matrix2 = results2.get_adjacency_matrix(weights='binary', fdr=False)
adj_matrix3 = results3.get_adjacency_matrix(weights='binary', fdr=False)
adj_matrix4 = results4.get_adjacency_matrix(weights='binary', fdr=False)
result1 = adj_matrix1.get_edge_list()
result2 = adj_matrix2.get_edge_list()
result3 = adj_matrix3.get_edge_list()
result4 = adj_matrix4.get_edge_list()
print("Printing results:")
print("Result 1: without checkpoint")
print(result1)
print("Result 2: with checkpoint")
print(result2)
print("Result 3: resuming from checkpoint")
print(result3)
print("Result 4: without checkpoint and different targets and sources")
print(result4)
print("Comparing the results:")
assert np.array_equal(result1, result2), 'Result 1 and 2 not equal!'
assert np.array_equal(result1, result3), 'Result 1 and 3 not equal!'
assert not np.array_equal(result1, result4), 'Result 1 and 4 equal, expected to be different!'
cmp1 = list(set(result1).intersection(result2))
cmp2 = list(set(result1).intersection(result3))
cmp3 = list(set(result1).intersection(result4))
len1 = len(result1)
assert len(cmp1) == len1 and len(cmp2) == len1 and len(cmp3) != len1, (
"Discrete MultivariateMI Running with checkpoints does not give the expected results")
print("Final")
print("Elements of comparison between result 1 and 2")
print(cmp1)
print("Elements of comparison between result 1 and 3")
print(cmp2)
print("Elements of comparison between result 1 and 4")
print(cmp3)
_clear_ckp(filename_ckp1)
_clear_ckp(filename_ckp2)
def infer_network(network_inference,
time_series,
parallel_target_analysis=False):
# Define parameter options dictionaries
network_inference_algorithms = pd.DataFrame()
network_inference_algorithms['Description'] = pd.Series({
'bMI_greedy':
'Bivariate Mutual Information via greedy algorithm',
'bTE_greedy':
'Bivariate Transfer Entropy via greedy algorithm',
'mMI_greedy':
'Multivariate Mutual Information via greedy algorithm',
'mTE_greedy':
'Multivariate Transfer Entropy via greedy algorithm',
'cross_corr':
'Cross-correlation thresholding algorithm'
})
network_inference_algorithms['Required parameters'] = pd.Series({
'bMI_greedy': [
'min_lag_sources', 'max_lag_sources', 'tau_sources', 'tau_target',
'cmi_estimator', 'z_standardise', 'permute_in_time',
'n_perm_max_stat', 'n_perm_min_stat', 'n_perm_omnibus',
'n_perm_max_seq', 'fdr_correction', 'p_value'
# 'alpha_max_stats',
# 'alpha_min_stats',
# 'alpha_omnibus',
# 'alpha_max_seq',
# 'alpha_fdr'
],
'bTE_greedy': [
'min_lag_sources', 'max_lag_sources', 'tau_sources',
'max_lag_target', 'tau_target', 'cmi_estimator', 'z_standardise',
'permute_in_time', 'n_perm_max_stat', 'n_perm_min_stat',
'n_perm_omnibus', 'n_perm_max_seq', 'fdr_correction', 'p_value'
# 'alpha_max_stats',
# 'alpha_min_stats',
# 'alpha_omnibus',
# 'alpha_max_seq',
# 'alpha_fdr'
],
'mMI_greedy': [
'min_lag_sources', 'max_lag_sources', 'tau_sources', 'tau_target',
'cmi_estimator', 'z_standardise', 'permute_in_time',
'n_perm_max_stat', 'n_perm_min_stat', 'n_perm_omnibus',
'n_perm_max_seq', 'fdr_correction', 'p_value'
# 'alpha_max_stats',
# 'alpha_min_stats',
# 'alpha_omnibus',
# 'alpha_max_seq',
# 'alpha_fdr'
],
'mTE_greedy': [
'min_lag_sources', 'max_lag_sources', 'tau_sources',
'max_lag_target', 'tau_target', 'cmi_estimator', 'z_standardise',
'permute_in_time', 'n_perm_max_stat', 'n_perm_min_stat',
'n_perm_omnibus', 'n_perm_max_seq', 'fdr_correction', 'p_value'
# 'alpha_max_stats',
# 'alpha_min_stats',
# 'alpha_omnibus',
# 'alpha_max_seq',
# 'alpha_fdr'
],
'cross_corr': ['min_lag_sources', 'max_lag_sources']
})
try:
# Ensure that a network inference algorithm has been specified
if 'algorithm' not in network_inference:
raise ParameterMissing('algorithm')
# Ensure that the provided algorithm is implemented
if network_inference.algorithm not in network_inference_algorithms.index:
raise ParameterValue(network_inference.algorithm)
# Ensure that all the parameters required by the algorithm have been provided
par_required = network_inference_algorithms['Required parameters'][
network_inference.algorithm]
for par in par_required:
if par not in network_inference:
raise ParameterMissing(par)
except ParameterMissing as e:
print(e.msg, e.par_names)
raise
except ParameterValue as e:
print(e.msg, e.par_value)
raise
else:
nodes_n = np.shape(time_series)[0]
can_be_z_standardised = True
if network_inference.z_standardise:
# Check if data can be normalised per process (assuming the
# first dimension represents processes, as in the rest of the code)
can_be_z_standardised = np.all(np.std(time_series, axis=1) > 0)
if not can_be_z_standardised:
print('Time series can not be z-standardised')
if len(time_series.shape) == 2:
dim_order = 'ps'
else:
dim_order = 'psr'
# initialise an empty data object
dat = Data()
# Load time series
dat = Data(time_series,
dim_order=dim_order,
normalise=(network_inference.z_standardise
& can_be_z_standardised))
algorithm = network_inference.algorithm
if algorithm in [
'bMI_greedy', 'mMI_greedy', 'bTE_greedy', 'mTE_greedy'
]:
# Set analysis options
if algorithm == 'bMI_greedy':
network_analysis = BivariateMI()
if algorithm == 'mMI_greedy':
network_analysis = MultivariateMI()
if algorithm == 'bTE_greedy':
network_analysis = BivariateTE()
if algorithm == 'mTE_greedy':
network_analysis = MultivariateTE()
settings = {
'min_lag_sources': network_inference.min_lag_sources,
'max_lag_sources': network_inference.max_lag_sources,
'tau_sources': network_inference.tau_sources,
'max_lag_target': network_inference.max_lag_target,
'tau_target': network_inference.tau_target,
'cmi_estimator': network_inference.cmi_estimator,
'kraskov_k': network_inference.kraskov_k,
'num_threads': network_inference.jidt_threads_n,
'permute_in_time': network_inference.permute_in_time,
'n_perm_max_stat': network_inference.n_perm_max_stat,
'n_perm_min_stat': network_inference.n_perm_min_stat,
'n_perm_omnibus': network_inference.n_perm_omnibus,
'n_perm_max_seq': network_inference.n_perm_max_seq,
'fdr_correction': network_inference.fdr_correction,
'alpha_max_stat': network_inference.p_value,
'alpha_min_stat': network_inference.p_value,
'alpha_omnibus': network_inference.p_value,
'alpha_max_seq': network_inference.p_value,
'alpha_fdr': network_inference.p_value
}
# # 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}'.format(
# key_last,
# traj[key])
# )
if parallel_target_analysis:
# Use SCOOP to create a generator of map results, each
# correspinding to one map iteration
res_iterator = futures.map_as_completed(
network_analysis.analyse_single_target,
itertools.repeat(settings, nodes_n),
itertools.repeat(dat, nodes_n), list(range(nodes_n)))
# Run analysis
res_list = list(res_iterator)
if settings['fdr_correction']:
res = network_fdr({'alpha_fdr': settings['alpha_fdr']},
*res_list)
else:
res = res_list[0]
res.combine_results(*res_list[1:])
else:
# Run analysis
res = network_analysis.analyse_network(settings=settings,
data=dat)
return res
else:
raise ParameterValue(
algorithm,
msg='Network inference algorithm not yet implemented')
def test_return_local_values():
"""Test estimation of local values."""
max_lag = 5
data = Data()
data.generate_mute_data(500, 5)
settings = {
'cmi_estimator': 'JidtKraskovCMI',
'noise_level': 0,
'local_values': True, # request calculation of local values
'n_perm_max_stat': 21,
'n_perm_min_stat': 21,
'n_perm_max_seq': 21,
'n_perm_omnibus': 21,
'max_lag_sources': max_lag,
'min_lag_sources': 4,
'max_lag_target': max_lag
}
target = 3
sources = [0, 4]
mi = MultivariateMI()
results = mi.analyse_single_target(settings,
data,
target=target,
sources=sources)
settings['local_values'] = False
results_avg = mi.analyse_single_target(settings,
data,
target=target,
sources=sources)
# Test if any sources were inferred. If not, return (this may happen
# sometimes due to too few samples, however, a higher no. samples is not
# feasible for a unit test).
if results.get_single_target(target, fdr=False)['mi'] is None:
return
if results_avg.get_single_target(target, fdr=False)['mi'] is None:
return
lmi = results.get_single_target(target, fdr=False)['mi']
n_sources = len(results.get_target_sources(target, fdr=False))
assert type(lmi) is np.ndarray, (
'LMI estimation did not return an array of values: {0}'.format(lmi))
assert lmi.shape[0] == n_sources, (
'Wrong dim (no. sources) in LMI estimate: {0}'.format(lmi.shape))
assert lmi.shape[1] == data.n_realisations_samples(
(0, max_lag)), ('Wrong dim (no. samples) in LMI estimate: {0}'.format(
lmi.shape))
assert lmi.shape[2] == data.n_replications, (
'Wrong dim (no. replications) in LMI estimate: {0}'.format(lmi.shape))
# Check if average and mean local values are the same. Test each source
# separately. Inferred sources and variables may differ between the two
# calls to analyse_single_target() due to low number of surrogates used in
# unit testing.
mi_single_link = results_avg.get_single_target(target, fdr=False)['mi']
sources_local = results.get_target_sources(target, fdr=False)
sources_avg = results_avg.get_target_sources(target, fdr=False)
for s in list(set(sources_avg).intersection(sources_local)):
i1 = np.where(sources_avg == s)[0][0]
i2 = np.where(sources_local == s)[0][0]
# Skip comparison if inferred variables differ between links.
vars_local = [
v for v in results.get_single_target(
target, fdr=False).selected_vars_sources if v[0] == s
]
vars_avg = [
v for v in results_avg.get_single_target(
target, fdr=False).selected_vars_sources if v[0] == s
]
if vars_local != vars_avg:
continue
print('Compare average ({0:.4f}) and local values ({1:.4f}).'.format(
mi_single_link[i1], np.mean(lmi[i2, :, :])))
assert np.isclose(
mi_single_link[i1], np.mean(lmi[i2, :, :]), rtol=0.00005), (
'Single link average MI ({0:.6f}) and mean LMI ({1:.6f}) '
' deviate.'.format(mi_single_link[i1], np.mean(lmi[i2, :, :])))
def test_return_local_values():
"""Test estimation of local values."""
max_lag = 5
data = Data()
data.generate_mute_data(500, 5)
settings = {
'cmi_estimator': 'JidtKraskovCMI',
'local_values': True, # request calculation of local values
'n_perm_max_stat': 21,
'n_perm_min_stat': 21,
'n_perm_max_seq': 21,
'n_perm_omnibus': 21,
'max_lag_sources': max_lag,
'min_lag_sources': 4,
'max_lag_target': max_lag
}
target = 1
mi = MultivariateMI()
results = mi.analyse_network(settings, data, targets=[target])
# Test if any sources were inferred. If not, return (this may happen
# sometimes due to too few samples, however, a higher no. samples is not
# feasible for a unit test).
if results.get_single_target(target, fdr=False)['mi'] is None:
return
lmi = results.get_single_target(target, fdr=False)['mi']
n_sources = len(results.get_target_sources(target, fdr=False))
assert type(lmi) is np.ndarray, (
'LMI estimation did not return an array of values: {0}'.format(lmi))
assert lmi.shape[0] == n_sources, (
'Wrong dim (no. sources) in LMI estimate: {0}'.format(lmi.shape))
assert lmi.shape[1] == data.n_realisations_samples(
(0, max_lag)), ('Wrong dim (no. samples) in LMI estimate: {0}'.format(
lmi.shape))
assert lmi.shape[2] == data.n_replications, (
'Wrong dim (no. replications) in LMI estimate: {0}'.format(lmi.shape))
# Test for correctnes of single link MI estimation by comparing it to the
# omnibus MI. In this case (single source), the two should be the same.
# Skip assertion if more than one source was inferred (this happens
# sometime due to random data and low no. permutations for statistical
# testing in unit tests).
settings['local_values'] = False
results_avg = mi.analyse_network(settings, data, targets=[target])
if results_avg.get_single_target(target, fdr=False)['mi'] is None:
return
mi_single_link = results_avg.get_single_target(target, fdr=False)['mi']
mi_omnibus = results_avg.get_single_target(target, fdr=False)['omnibus_mi']
sources_local = results.get_target_sources(target, fdr=False)
sources_avg = results_avg.get_target_sources(target, fdr=False)
if len(sources_avg) == 1:
print('Compare single link and omnibus MI.')
assert np.isclose(mi_single_link, mi_omnibus, rtol=0.00005), (
'Single link MI ({0:.6f}) is not equal to omnibus information '
'({1:.6f}).'.format(mi_single_link[0], mi_omnibus))
# Check if average and mean local values are the same. Test each source
# separately. Inferred sources may differ between the two calls to
# analyse_network() due to low number of surrogates used in unit testing.
for s in list(set(sources_avg).intersection(sources_local)):
print('Compare average and local values.')
i1 = np.where(sources_avg == s)[0][0]
i2 = np.where(sources_local == s)[0][0]
assert np.isclose(
mi_single_link[i1], np.mean(lmi[i2, :, :]), rtol=0.00005), (
'Single link average MI ({0:.6f}) and mean LMI ({1:.6f}) '
' deviate.'.format(mi_single_link, np.mean(lmi)))