def make_pmfs_from_datasetmatrix(self, X: int, Y: int, Zl: list[int]) -> tuple[CPMF, CPMF, CPMF, PMF]:
PrZ: PMF
PrXcZ: CPMF
PrYcZ: CPMF
PrXYcZ: CPMF
(VarX, VarY, VarZ) = self.load_variables(X, Y, Zl)
if len(Zl) == 0:
PrXY = PMF(JointVariables(VarX, VarY))
PrX = PMF(VarX)
PrY = PMF(VarY)
PrZ = OmegaPMF()
PrXYcZ = OmegaCPMF(PrXY)
PrXcZ = OmegaCPMF(PrX)
PrYcZ = OmegaCPMF(PrY)
else:
PrXYZ = PMF(JointVariables(VarX, VarY, VarZ))
PrXZ = PMF(JointVariables(VarX, VarZ))
PrYZ = PMF(JointVariables(VarY, VarZ))
PrZ = PMF(VarZ)
PrXcZ = PrXZ.condition_on(PrZ)
PrYcZ = PrYZ.condition_on(PrZ)
PrXYcZ = PrXYZ.condition_on(PrZ)
return (PrXYcZ, PrXcZ, PrYcZ, PrZ)
def G_test_conditionally_independent(self, X: int, Y: int,
Z: list[int]) -> CITestResult:
(VarX, VarY, VarZ) = self.load_variables(X, Y, Z)
result = CITestResult()
result.start_timing()
PrZ: PMF
PrXcZ: CPMF
PrYcZ: CPMF
PrXYcZ: CPMF
if len(Z) == 0:
PrXY = PMF(JointVariables(VarX, VarY))
PrX = PMF(VarX)
PrY = PMF(VarY)
PrZ = OmegaPMF()
PrXYcZ = OmegaCPMF(PrXY)
PrXcZ = OmegaCPMF(PrX)
PrYcZ = OmegaCPMF(PrY)
if self.DoF_calculator.requires_pmfs:
self.DoF_calculator.set_context_pmfs(PrXY, PrX, PrY, None)
else:
PrXYZ = PMF(JointVariables(VarX, VarY, VarZ))
PrXZ = PMF(JointVariables(VarX, VarZ))
PrYZ = PMF(JointVariables(VarY, VarZ))
PrZ = PMF(VarZ)
PrXcZ = PrXZ.condition_on(PrZ)
PrYcZ = PrYZ.condition_on(PrZ)
PrXYcZ = PrXYZ.condition_on(PrZ)
if self.DoF_calculator.requires_pmfs:
self.DoF_calculator.set_context_pmfs(PrXYZ, PrXZ, PrYZ, PrZ)
self.DoF_calculator.set_context_variables(X, Y, Z)
if self.DoF_calculator.requires_cpmfs:
self.DoF_calculator.set_context_cpmfs(PrXYcZ, PrXcZ, PrYcZ, PrZ)
DoF = self.DoF_calculator.calculate_DoF(X, Y, Z)
if not self.sufficient_samples(DoF):
result.end_timing()
result.index = self.ci_test_counter + 1
result.set_insufficient_samples()
result.set_variables(VarX, VarY, VarZ)
result.extra_info = ' DoF {}'.format(DoF)
return result
G = self.G_value(PrXYcZ, PrXcZ, PrYcZ, PrZ)
p = chi2.cdf(G, DoF)
independent = None
if p < self.significance:
independent = True
else:
independent = False
result.end_timing()
result.index = self.ci_test_counter + 1
result.set_independent(independent, self.significance)
result.set_variables(VarX, VarY, VarZ)
result.set_statistic('G', G, dict())
result.set_distribution('chi2', p, {'DoF': DoF})
result.extra_info = ' DoF {}'.format(DoF)
return result