def make_cpmf_PrXcZ(self, X, Z, PrZ=None):
if PrZ is None:
PrZ = self.AD_tree.make_pmf(list(Z))
unsorted_variables = [X] + Z
joint_variables = sorted(unsorted_variables)
index = {var: joint_variables.index(var) for var in joint_variables}
PrXZ = self.AD_tree.make_pmf(joint_variables)
PrXcZ = CPMF(None, None)
for joint_key, joint_p in PrXZ.items():
zkey = tuple([joint_key[index[zvar]] for zvar in Z])
varkey = [
joint_key[index[var]] for var in unsorted_variables
if var not in Z
][0]
if len(zkey) == 1:
zkey = zkey[0]
try:
pmf = PrXcZ.conditional_probabilities[zkey]
except KeyError:
pmf = PMF(None)
PrXcZ.conditional_probabilities[zkey] = pmf
try:
pmf.probabilities[varkey] = joint_p / PrZ.p(zkey)
except ZeroDivisionError:
pass
return (PrXcZ, PrXZ)
def calculate_pmf_for_cmi(
X: Variable,
Y: Variable,
Z: Union[Variable, JointVariables],
) -> tuple[CPMF, CPMF, CPMF, PMF]:
PrXYcZ = CPMF(JointVariables(X, Y), Z)
PrXcZ = CPMF(X, Z)
PrYcZ = CPMF(Y, Z)
PrZ = PMF(Z)
return (PrXYcZ, PrXcZ, PrYcZ, PrZ)
def conditional_mutual_information(
PrXYcZ: CPMF,
PrXcZ: CPMF,
PrYcZ: CPMF,
PrZ: PMF,
base: Union[float, str] = 2,
) -> float:
logarithm = create_logarithm_function(base)
cMI = 0.0
for (z, pz) in PrZ.items():
for (x, pxcz) in PrXcZ.given(z).items():
for (y, pycz) in PrYcZ.given(z).items():
pxycz = PrXYcZ.given(z).p(x, y)
if pxycz == 0 or pxcz == 0 or pycz == 0:
continue
else:
pcMI = pz * pxycz * logarithm(pxycz / (pxcz * pycz))
cMI += pcMI
return abs(cMI)
def assert_cpmf_adtree_vs_dm(dm, adtree, cd_vars, cn_vars):
if isinstance(cd_vars, int):
cd_vars = [cd_vars]
if isinstance(cn_vars, int):
cn_vars = [cn_vars]
cd_vars = dm.get_variables('X', cd_vars)
cn_vars = dm.get_variables('X', cn_vars)
expected_cpmf = CPMF(cd_vars, cn_vars)
calculated_cpmf = adtree.make_cpmf(cd_vars, cn_vars)
assert expected_cpmf == calculated_cpmf
def test_conditional_pmf__from_bayesian_network():
configuration = dict()
configuration['sourcepath'] = testutil.bif_folder / 'survey.bif'
configuration['sample_count'] = int(4e4)
# Using a random seed of 42 somehow requires 2e6 samples to pass, but
# with the seed 1984, it is sufficient to generate only 4e4. Maybe the
# random generator is biased somehow?
configuration['random_seed'] = 1984
configuration['values_as_indices'] = False
configuration['objectives'] = ['R', 'TRN']
bayesian_network = BayesianNetwork.from_bif_file(configuration['sourcepath'], use_cache=False)
bayesian_network.finalize()
sbnds = SampledBayesianNetworkDatasetSource(configuration)
sbnds.reset_random_seed = True
datasetmatrix = sbnds.create_dataset_matrix('test_sbnds')
assert ['AGE', 'EDU', 'OCC', 'SEX'] == datasetmatrix.column_labels_X
assert ['R', 'TRN'] == datasetmatrix.column_labels_Y
AGE = Variable(datasetmatrix.get_column_by_label('X', 'AGE'))
PrAge = PMF(AGE)
SEX = Variable(datasetmatrix.get_column_by_label('X', 'SEX'))
PrSex = PMF(SEX)
assert_PMF_AlmostEquals_BNProbDist(
bayesian_network.variable_nodes['AGE'].probdist,
PrAge)
assert_PMF_AlmostEquals_BNProbDist(
bayesian_network.variable_nodes['SEX'].probdist,
PrSex)
EDU = Variable(datasetmatrix.get_column_by_label('X', 'EDU'))
PrEdu = CPMF(EDU, given=JointVariables(AGE, SEX))
assert_CPMF_AlmostEquals_BNProbDist(
bayesian_network.variable_nodes['EDU'].probdist,
PrEdu)
OCC = Variable(datasetmatrix.get_column_by_label('X', 'OCC'))
PrOcc = CPMF(OCC, given=EDU)
assert_CPMF_AlmostEquals_BNProbDist(
bayesian_network.variable_nodes['OCC'].probdist,
PrOcc)
R = Variable(datasetmatrix.get_column_by_label('Y', 'R'))
PrR = CPMF(R, given=EDU)
assert_CPMF_AlmostEquals_BNProbDist(
bayesian_network.variable_nodes['R'].probdist,
PrR)
TRN = Variable(datasetmatrix.get_column_by_label('Y', 'TRN'))
PrTRN = CPMF(TRN, given=JointVariables(OCC, R))
assert_CPMF_AlmostEquals_BNProbDist(
bayesian_network.variable_nodes['TRN'].probdist,
PrTRN)
def test_conditional_pmf__multiple_values():
sizes = Variable(['small', 'small', 'large', 'small', 'normal', 'small'])
sizes.ID = 1
sizes.name = 'sizes'
colors = Variable(['gray', 'yellow', 'brown', 'silver', 'white', 'gray'])
colors.ID = 2
colors.name = 'colors'
animals = Variable(['cat', 'dog', 'cat', 'snake', 'dog', 'cat'])
animals.ID = 3
animals.name = 'animals'
is_pet = Variable(['yes', 'yes', 'yes', 'maybe', 'yes', 'yes'])
is_pet.ID = 4
is_pet.name = 'is_pet'
Pr = CPMF(JointVariables(colors, is_pet), JointVariables(sizes, animals))
assert Pr.given('small', 'cat').p('gray', 'yes') == 2 / 2
assert Pr.given('small', 'cat').p('yellow', 'yes') == 0 / 1
assert Pr.given('small', 'cat').p('brown', 'maybe') == 0 / 1
assert Pr.given('small', 'dog').p('yellow', 'yes') == 1 / 1
assert Pr.given('small', 'dog').p('yellow', 'maybe') == 0 / 1
assert Pr.given('small', 'dog').p('silver', 'maybe') == 0 / 1
assert Pr.given('large', 'cat').p('brown', 'yes') == 1 / 1
assert Pr.given('large', 'cat').p('yellow', 'yes') == 0 / 1
assert Pr.given('small', 'snake').p('silver', 'maybe') == 1 / 1
assert Pr.given('small', 'snake').p('silver', 'no') == 0 / 1
assert Pr.given('normal', 'dog').p('white', 'yes') == 1 / 1
assert Pr.given('normal', 'dog').p('silver', 'yes') == 0 / 1
assert Pr.given('normal', 'dog').p('yellow', 'maybe') == 0 / 1
SA = JointVariables(sizes, animals)
PrAll = CPMF(JointVariables(colors, is_pet), SA)
PrSA = PMF(SA)
PrCcSA = CPMF(colors, SA)
PrIPcSA = CPMF(is_pet, SA)
test_p_all = 0.0
test_p_c = 0.0
test_p_ip = 0.0
for (sa, psa) in PrSA.items():
for (c, pcsa) in PrCcSA.given(sa).items():
test_p_c += pcsa * PrSA.p(sa)
for (ip, pipsa) in PrIPcSA.given(sa).items():
pall = PrAll.given(sa).p(c, ip)
test_p_all += pall * PrSA.p(sa)
test_p_ip += pipsa * PrSA.p(sa)
assert almostEqual(1, test_p_all)
assert almostEqual(1, test_p_c)
assert almostEqual(1, test_p_ip)
def test_conditional_pmf__binary():
V0 = Variable([0, 1, 0, 1, 0, 1, 0, 1])
V1 = Variable([0, 0, 1, 1, 0, 0, 1, 1])
V2 = Variable([0, 0, 0, 0, 1, 1, 1, 1])
V78 = Variable([0, 0, 0, 0, 0, 0, 1, 1])
Pr = CPMF(V0, V78)
assert Pr.given(0).p(0) == 3 / 6
assert Pr.given(0).p(1) == 3 / 6
assert Pr.given(1).p(0) == 1 / 2
assert Pr.given(1).p(1) == 1 / 2
Pr = CPMF(V2, V78)
assert Pr.given(0).p(0) == 4 / 6
assert Pr.given(0).p(1) == 2 / 6
assert Pr.given(1).p(0) == 0 / 2
assert Pr.given(1).p(1) == 2 / 2
Pr = CPMF(V78, V1)
assert Pr.given(0).p(0) == 4 / 4
assert Pr.given(0).p(1) == 0 / 4
assert Pr.given(1).p(0) == 2 / 4
assert Pr.given(1).p(1) == 2 / 4
Pr = CPMF(V1, JointVariables(V2, V78))
assert Pr.given(0, 0).p(0) == 2 / 4
assert Pr.given(0, 0).p(1) == 2 / 4
assert Pr.given(0, 1).p(0) == 0 / 1
assert Pr.given(0, 1).p(1) == 0 / 1
assert Pr.given(1, 0).p(0) == 2 / 2
assert Pr.given(1, 0).p(1) == 0 / 2
assert Pr.given(1, 1).p(0) == 0 / 2
assert Pr.given(1, 1).p(1) == 2 / 2