def testFromWHY19(self):
bn = gum.fastBN("X->Y;U")
d = csl.CausalModel(bn, [('Z', ["X", "Y", "U"])], True)
_, pot, _ = csl.causalImpact(d, on="Y", doing="X")
self.assertIsNone(pot) # HedgeException
# Causality, Pearl, 2009, p66
bn = gum.fastBN("Z1->Z2->Z3->Y<-X->Z2;Z2->Y;Z1->X->Z3<-Z1")
c = csl.CausalModel(bn, [("Z0", ("X", "Z1", "Z3"))], False)
_, pot, explanation = csl.causalImpact(c, "Y", "X")
self.assertIsNotNone(pot)
self.assertEqual(explanation, "Do-calculus computations")
def test_simpson(self):
m1 = gum.fastBN("Gender->Drug->Patient;Gender->Patient")
# Gender = 0 == male
# Gender = 1 == female
# Drug == 0 - not taking the Drug
# Drug == 1 - taking the Drug
# Patient = 0 -- not healed
# Patient = 1 - healed
m1.cpt("Gender")[:] = [0.5, 0.5]
m1.cpt("Drug")[:] = [[0.25, 0.75], # Gender=0
[0.75, 0.25]] # Gender=1
m1.cpt("Patient")[{'Drug': 0, 'Gender': 0}] = [
0.2, 0.8] # No Drug, Male -> healed in 0.8 of cases
# No Drug, Female -> healed in 0.4 of cases
m1.cpt("Patient")[{'Drug': 0, 'Gender': 1}] = [0.6, 0.4]
m1.cpt("Patient")[{'Drug': 1, 'Gender': 0}] = [
0.3, 0.7] # Drug, Male -> healed 0.7 of cases
m1.cpt("Patient")[{'Drug': 1, 'Gender': 1}] = [
0.8, 0.2] # Drug, Female -> healed in 0.2 of cases
d1 = csl.CausalModel(m1)
# from formula : \sum_{ Gender }{ P(Patient\mid Drug,Gender) \cdot P(Gender) }
margPatient = (m1.cpt("Patient") * m1.cpt("Gender")).margSumOut(["Gender"])
lat, pot, expl = csl.causalImpact(
d1, on="Patient", doing={"Drug"}) # when drug=1
self.assertEqual(pot, margPatient)
def testCounterfactual(self):
# experience=10-4*education+Ux
# salaire=65+2.5*experience+5*education+Us
#
# Ux : [-2,10], sans a priori
# Us : [0,25], sans a priori
# education : 0,1,2 (low, medium, high), a priori [0.4,0.40.2]
# experience : [0,20]
# salaire : [65,150]
edex = gum.fastBN(
"Ux[-2,10]->experience[0,20]<-education{low|medium|high}->salary[65,150]<-Us[0,25];experience->salary")
edex.cpt("Us").fillWith(1).normalize()
edex.cpt("Ux").fillWith(1).normalize()
edex.cpt("education")[:] = [0.4, 0.4, 0.2]
edex.cpt("experience").fillWithFunction("10-4*education+Ux")
edex.cpt("salary").fillWithFunction("round(65+2.5*experience+5*education+Us)")
pot = csl.counterfactual(cm=csl.CausalModel(edex),
profile={'experience': 8, 'education': 'low', 'salary': '86'},
whatif={"education"},
on={"salary"},
values={"education": "medium"})
self.assertEqual(pot[81 - 65], 1.0)
def test_CRAN1(self):
bn = gum.fastBN("w->x->z->y;w->z")
bn.cpt("w")[:] = [0.5, 0.5]
bn.cpt("x")[:] = [[0.4, 0.6], [0.3, 0.7]]
bn.cpt("z")[{'w': 0, 'x': 0}] = [0.2, 0.8]
bn.cpt("z")[{'w': 0, 'x': 1}] = [0.1, 0.9]
bn.cpt("z")[{'w': 1, 'x': 0}] = [0.4, 0.6]
bn.cpt("z")[{'w': 1, 'x': 1}] = [0.5, 0.5]
bn.cpt("y")[:] = [[0.1, 0.9], [0.2, 0.8]]
d = csl.CausalModel(bn, [("lat1", ["x", "y"])])
# from the formula \sum_{ z ,w }{ P(z\mid w,x) \cdot P(w) \cdot
# \sum_{ x' }{ P(y\mid w,x',z) \cdot P(x'\mid w) }
# }
marg = (bn.cpt("x") * bn.cpt("y")).margSumOut(["x"])
marg = (marg * bn.cpt("w") * bn.cpt("z")).margSumOut(["z", "w"])
_, pot, _ = csl.causalImpact(d, on={"y"}, doing={"x"}) # when x=1
self.assertEqual(pot, marg)
_, pot, _ = csl.causalImpact(d, on="y", doing="x") # when x=1
self.assertEqual(pot, marg)
def test_DoCalculusp213(self):
fd = gum.fastBN("w->z->x->y")
fdModele = csl.CausalModel(fd, [("u1", ["w", "x"]),
("u2", ["w", "y"])], True)
formula, impact, explanation = csl.causalImpact(fdModele,
on="y",
doing="x")
def setUp(self):
m = gum.fastBN("z2->x->z1->y;z2->z1;z2->z3->y")
m.cpt("z2")[:] = [0.5, 0.5]
m.cpt("x")[:] = [
[0.4, 0.6], # z2=0
[0.4, 0.6]
] # z2=1
m.cpt("z3")[:] = [
[0.3, 0.7], # z2=0
[0.3, 0.7]
] # z2=1
m.cpt("z1")[{"z2": 0, "x": 0}] = [0.2, 0.8]
m.cpt("z1")[{"z2": 0, "x": 1}] = [0.25, 0.75]
m.cpt("z1")[{"z2": 1, "x": 0}] = [0.1, 0.9]
m.cpt("z1")[{"z2": 1, "x": 1}] = [0.15, 0.85]
m.cpt("y")[{"z1": 0, "z3": 0}] = [0.5, 0.5]
m.cpt("y")[{"z1": 0, "z3": 1}] = [0.45, 0.55]
m.cpt("y")[{"z1": 1, "z3": 0}] = [0.4, 0.6]
m.cpt("y")[{"z1": 1, "z3": 1}] = [0.35, 0.65]
self.d = csl.CausalModel(m,
[("X-Z2", ["x", "z2"]), ("X-Z3", ["x", "z3"]),
("X-Y", ["x", "y"]),
("Y-Z2", ["y", "z2"])], True)
try:
formula, result, msg = csl.causalImpact(self.d,
on={"y", "z2", "z1", "z3"},
doing={"x"})
except csl.HedgeException as h:
self.fail("Should not raise")
def test_CRAN2(self):
bn = gum.fastBN("Z1->X->Z2->Y")
d = csl.CausalModel(bn, [("L1", ["Z1", "X"]),
("L2", ["Z1", "Z2"]),
("L3", ["Z1", "Y"]),
("L4", ["Y", "X"])],
True)
_, pot, _ = csl.causalImpact(d, on="Y", doing={"X"})
self.assertIsNone(pot)
def test_tobacco1(self):
obs1 = gum.fastBN("Smoking->Cancer")
obs1.cpt("Smoking")[:] = [0.6, 0.4]
obs1.cpt("Cancer")[{"Smoking": 0}] = [0.9, 0.1]
obs1.cpt("Cancer")[{"Smoking": 1}] = [0.7, 0.3]
modele1 = csl.CausalModel(obs1)
lat, pot, expl = csl.causalImpact(
modele1, "Cancer", "Smoking") # when doing is 1
self.assertEqual(pot, obs1.cpt("Cancer"))
modele2 = csl.CausalModel(obs1, [("Genotype", ["Smoking", "Cancer"])])
lat, pot, expl = csl.causalImpact(
modele2, "Cancer", {"Smoking"}, values={"Smoking": 1})
margCancer = (obs1.cpt("Smoking") * obs1.cpt("Cancer")
).margSumOut(["Smoking"])
self.assertEqual(pot, margCancer)
modele3 = csl.CausalModel(
obs1, [("Genotype", ["Smoking", "Cancer"])], True)
lat, pot, expl = csl.causalImpact(
modele3, "Cancer", {"Smoking"}, values={"Smoking": 1})
self.assertIsNone(pot)
def testFromNotebooks(self):
bn = gum.fastBN("w->x->z->y;w->z")
bn.cpt("w")[:] = [0.7, 0.3]
bn.cpt("x")[:] = [[0.4, 0.6], [0.3, 0.7]]
bn.cpt("z")[{'w': 0, 'x': 0}] = [0.2, 0.8]
bn.cpt("z")[{'w': 0, 'x': 1}] = [0.1, 0.9]
bn.cpt("z")[{'w': 1, 'x': 0}] = [0.9, 0.1]
bn.cpt("z")[{'w': 1, 'x': 1}] = [0.5, 0.5]
bn.cpt("y")[:] = [[0.1, 0.9], [0.8, 0.2]]
d = csl.CausalModel(bn, [("lat1", ["x", "y"])])
_, pot, _ = csl.causalImpact(d, on="y", doing="x")
self.assertIsNotNone(pot)
def test_Carouselp115(self):
ab = gum.fastBN('Elapsed time[11]->Bag on Carousel<-Bag on Plane')
ab.cpt("Bag on Plane").fillWith(1).normalize()
ab.cpt("Elapsed time").fillWith(1).normalize()
ab.cpt("Bag on Carousel").fillWith(
[1.0, 0.0] * 11 +
[1 - i / 20 if i % 2 == 0 else (i - 1) / 20 for i in range(22)])
abModele = csl.CausalModel(ab)
formula, impact, explanation = csl.causalImpact(
abModele,
on={"Bag on Plane"},
doing={"Elapsed time"},
knowing={"Bag on Carousel"},
values={
"Elapsed time": 7,
"Bag on Carousel": 0
})
self.assertAlmostEqual(impact[0], 0.7692, 4)
def test_tobacco2(self):
obs2 = gum.fastBN("Smoking->Tar->Cancer;Smoking->Cancer")
obs2.cpt("Smoking")[:] = [0.6, 0.4]
obs2.cpt("Tar")[{"Smoking": 0}] = [0.9, 0.1]
obs2.cpt("Tar")[{"Smoking": 1}] = [0.7, 0.3]
obs2.cpt("Cancer")[{"Tar": 0, "Smoking": 0}] = [0.9, 0.1]
obs2.cpt("Cancer")[{"Tar": 1, "Smoking": 0}] = [0.8, 0.2]
obs2.cpt("Cancer")[{"Tar": 0, "Smoking": 1}] = [0.7, 0.3]
obs2.cpt("Cancer")[{"Tar": 1, "Smoking": 1}] = [0.6, 0.4]
modele4 = csl.CausalModel(obs2, [("Genotype", ["Smoking", "Cancer"])])
# from formula : \sum_{ Tar }{ P(Tar\mid Smoking) \cdot
# \sum_{ Smoking' }{ P(Cancer\mid Smoking',Tar) \cdot P(Smoking') }
# }
margCancer = (obs2.cpt("Cancer") * obs2.cpt("Smoking")
).margSumOut(['Smoking'])
margCancer = (margCancer * obs2.cpt("Tar")).margSumOut(['Tar'])
lat, pot, _ = csl.causalImpact(
modele4, "Cancer", "Smoking") # when smoking=1
self.assertEqual(pot, margCancer)
def setUp(self):
m1 = gum.fastBN("Gender->Drug->Patient;Gender->Patient")
m1.cpt("Gender")[:] = [0.5, 0.5]
m1.cpt("Drug")[:] = [
[0.25, 0.75], # Gender=0
[0.75, 0.25]
] # Gender=1
m1.cpt("Patient")[{
'Drug': 0,
'Gender': 0
}] = [0.2, 0.8] # No Drug, Male -> healed in 0.8 of cases
# No Drug, Female -> healed in 0.4 of cases
m1.cpt("Patient")[{'Drug': 0, 'Gender': 1}] = [0.6, 0.4]
m1.cpt("Patient")[{
'Drug': 1,
'Gender': 0
}] = [0.3, 0.7] # Drug, Male -> healed 0.7 of cases
m1.cpt("Patient")[{
'Drug': 1,
'Gender': 1
}] = [0.8, 0.2] # Drug, Female -> healed in 0.2 of cases
self.model = csl.CausalModel(m1)
mod.add(gum.LabelizedVariable("tar"))
mod.add(gum.LabelizedVariable("cancer"))
mod.addArc(0, 1) # smoking -> tar -> cancer; smoking -> cancer
mod.addArc(1, 2)
mod.addArc(0, 2)
# Smoking
mod.cpt(0)[:] = [0.5, 0.5]
# Tar deposits
mod.cpt(1)[:] = [0.4, 0.6], [0.3, 0.6]
# Lung Cancer
mod.cpt(2)[{"smoking": 0, "tar": 0}] = [0.1, 0.9]
mod.cpt(2)[{"smoking": 0, "tar": 1}] = [0.15, 0.85]
mod.cpt(2)[{"smoking": 1, "tar": 0}] = [0.2, 0.8]
mod.cpt(2)[{"smoking": 1, "tar": 1}] = [0.25, 0.75]
d = csl.CausalModel(mod, [("Genotype", ["smoking", "cancer"])],
False) # False == do not keep arcs
cslnb.showCausalModel(d)
try:
a = csl.doCalculusWithObservation(d, "cancer", {"smoking"})
except csl.HedgeException as h:
print(h.message)
# the variable "a" shows us the front-door adjustment formula for smoking causes lung cancer
display(Math(a.toLatex()))
def test_AccentsInVariables(self):
bn = gum.fastBN("héhé->hoho")
cm = csl.CausalModel(bn)
formula, impact, explanation = csl.causalImpact(cm, "héhé", "hoho")
bn = gum.fastBN("w->x->z->y;w->z")
# -- conditional probability tables
bn.cpt('w')[:] = [0.7, 0.3]
bn.cpt('x')[:] = [0.4, 0.6], [0.3, 0.7]
bn.cpt('z')[{'w': 0, 'x': 0}] = [0.2, 0.8]
bn.cpt('z')[{'w': 0, 'x': 1}] = [0.1, 0.9]
bn.cpt('z')[{'w': 1, 'x': 0}] = [0.9, 0.1]
bn.cpt('z')[{'w': 1, 'x': 1}] = [0.5, 0.5]
bn.cpt('y')[:] = [0.1, 0.9], [0.8, 0.2]
# **** Causal model plot ****
# d is a causal model! It receives a bayesian network and the unmeasured variables in it along
# with the variables that are affected by these latent variables
# -- "lat1" is an unmeasured variable that affects X and Y (its parent of both -- the common cause in the fork)
d = csl.CausalModel(bn, [("lat1", ['x', 'y'])])
# -- causal impact of X on Y when we do(X = 0)
# this works but the representation of the causal impact returned isn't very good
###### csl.causalImpact(d, 'y', 'x', '', {'x':0})
# shows the causal impact of X on Y, when we do(X = 0), on the causal model D
cslnb.showCausalImpact(d, "y", "x", values={"x": 0})
# causal impact of X on Y when do(X = 1), on causal model d
cslnb.showCausalImpact(d, "y", "x", values={"x": 1})
# This example is from the book --- Causal Inference in Statistics: A Primer
# page 62, figure 3.6
from IPython.display import display, Math, Latex, HTML
import pyAgrum as gum
import pyAgrum.lib.notebook as gnb
import pyAgrum.causal as csl
import pyAgrum.causal.notebook as cslnb
bn = gum.fastBN("x->y<-w")
# -- conditional probabilities table
bn.cpt('w')[:] = [0.7, 0.3]
bn.cpt('x')[:] = [0.4, 0.6]
bn.cpt('y')[{'x': 0, 'w': 0}] = [0.2, 0.8]
bn.cpt('y')[{'x': 0, 'w': 1}] = [0.1, 0.9]
bn.cpt('y')[{'x': 1, 'w': 0}] = [0.9, 0.1]
bn.cpt('y')[{'x': 1, 'w': 0}] = [0.5, 0.5]
# ** making the Causal Model
d = csl.CausalModel(bn, [('z', ['x', 'w'])])
cslnb.showCausalImpact(d, 'y', 'x', values={'x': 0})
cslnb.showCausalImpact(d, 'y', 'x', values={'x': 1})
from IPython.display import display, Math, Latex, HTML
import pyAgrum as gum
import pyAgrum.lib.notebook as gnb
import pyAgrum.causal as csl
import pyAgrum.causal.notebook as cslnb
bn = gum.fastBN("smoking->tar->cancer")
# -- conditional probabilities table --
bn.cpt("smoking")[:] = [0.5, 0.5]
bn.cpt("tar")[{"smoking": 0}] = [380 / 400, 20 / 400]
bn.cpt("tar")[{"smoking": 1}] = [20 / 400, 380 / 400]
bn.cpt("cancer")[{"tar": 0, "smoking": 0}] = [0.1, 0.9]
bn.cpt("cancer")[{"tar": 0, "smoking": 1}] = [0.9, 0.1]
bn.cpt("cancer")[{"tar": 1, "smoking": 0}] = [0.05, 0.95]
bn.cpt("cancer")[{"tar": 1, "smoking": 1}] = [0.85, 0.15]
d = csl.CausalModel(bn, [("genes", ["smoking", "cancer"])])
cslnb.showCausalImpact(d, "cancer", "smoking", values={"smoking": 1})
cslnb.showCausalImpact(d, "cancer", "smoking", values={"smoking": 0})
