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 mutual_information(
PrXY: PMF,
PrX: PMF,
PrY: PMF,
base=2,
) -> float:
logarithm = create_logarithm_function(base)
MI = 0.0
for (x, px) in PrX.items():
for (y, py) in PrY.items():
pxy = PrXY.p(x, y)
if pxy == 0 or px == 0 or py == 0:
continue
else:
pMI = pxy * logarithm(pxy / (px * py))
MI += pMI
return MI
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 test_single_variable_pmf():
variable = Variable(numpy.array([3, 5, 1, 1, 4, 3, 7, 0, 2, 1, 0, 5, 4, 7, 2, 4]))
variable.ID = 1
variable.name = 'test_variable_1'
variable.update_values()
assert [0, 1, 2, 3, 4, 5, 7] == variable.values
PrVariable = PMF(variable)
expected_counts = {0: 2,
1: 3,
2: 2,
3: 2,
4: 3,
5: 2,
7: 2}
assert PrVariable.value_counts == expected_counts
expected_counts = {0: 2 / 16,
1: 3 / 16,
2: 2 / 16,
3: 2 / 16,
4: 3 / 16,
5: 2 / 16,
7: 2 / 16}
assert PrVariable.probabilities == expected_counts
assert 1 == sum(PrVariable.values())
assert 2 / 16 == PrVariable.p(3)
assert 2 / 16 == PrVariable.p(2)
assert 2 / 16 == PrVariable.p(5)
ev = 0
for (v, pv) in PrVariable.items():
ev += pv * v
assert 3.0625 == ev