def createData(): nd = NodeData() skel = GraphSkeleton() fpath = "job_interview.txt" nd.load(fpath) skel.load(fpath) skel.toporder() bn = DiscreteBayesianNetwork(skel, nd) learner = PGMLearner() data = bn.randomsample(1000) X, Y = 'Grades', 'Offer' c,p,w=learner.discrete_condind(data, X, Y, ['Interview']) print "independence between X and Y: ", c, " p-value ", p, " witness node: ", w result = learner.discrete_constraint_estimatestruct(data) print result.E
class TestPGMLearner(unittest.TestCase):
def setUp(self):
# instantiate learner
self.l = PGMLearner()
# generate graph skeleton
skel = GraphSkeleton()
skel.load("unittestdict.txt")
skel.toporder()
# generate sample sequence to try to learn from - discrete
nd = NodeData()
nd.load("unittestdict.txt")
self.samplediscbn = DiscreteBayesianNetwork(skel, nd)
self.samplediscseq = self.samplediscbn.randomsample(5000)
# generate sample sequence to try to learn from - discrete
nda = NodeData()
nda.load("unittestlgdict.txt")
self.samplelgbn = LGBayesianNetwork(skel, nda)
self.samplelgseq = self.samplelgbn.randomsample(10000)
self.skel = skel
def test_discrete_mle_estimateparams(self):
result = self.l.discrete_mle_estimateparams(self.skel, self.samplediscseq)
indexa = result.Vdata['SAT']['vals'].index('lowscore')
self.assertTrue(result.Vdata['SAT']['cprob']["['low']"][indexa] < 1 and result.Vdata['SAT']['cprob']["['low']"][indexa] > .9)
indexb = result.Vdata['Letter']['vals'].index('weak')
self.assertTrue(result.Vdata['Letter']['cprob']["['A']"][indexb] < .15 and result.Vdata['Letter']['cprob']["['A']"][indexb] > .05)
def test_lg_mle_estimateparams(self):
result = self.l.lg_mle_estimateparams(self.skel, self.samplelgseq)
self.assertTrue(result.Vdata['SAT']['mean_base'] < 15 and result.Vdata['SAT']['mean_base'] > 5)
self.assertTrue(result.Vdata['Letter']['variance'] < 15 and result.Vdata['Letter']['variance'] > 5)
def test_discrete_constraint_estimatestruct(self):
result = self.l.discrete_constraint_estimatestruct(self.samplediscseq)
self.assertTrue(["Difficulty", "Grade"] in result.E)
def test_lg_constraint_estimatestruct(self):
result = self.l.lg_constraint_estimatestruct(self.samplelgseq)
self.assertTrue(["Intelligence", "Grade"] in result.E)
def test_discrete_condind(self):
chi, pv, witness = self.l.discrete_condind(self.samplediscseq, "Difficulty", "Letter", ["Grade"])
self.assertTrue(pv > .05)
self.assertTrue(witness, ["Grade"])
chia, pva, witnessa = self.l.discrete_condind(self.samplediscseq, "Difficulty", "Intelligence", [])
self.assertTrue(pva < .05)
def test_discrete_estimatebn(self):
result = self.l.discrete_estimatebn(self.samplediscseq)
self.assertTrue(result.V)
self.assertTrue(result.E)
self.assertTrue(result.Vdata["Difficulty"]["cprob"][0])
def test_lg_estimatebn(self):
result = self.l.lg_estimatebn(self.samplelgseq)
self.assertTrue(result.V)
self.assertTrue(result.E)
self.assertTrue(result.Vdata["Intelligence"]["mean_base"])
class TestPGMLearner(unittest.TestCase):
def setUp(self):
# instantiate learner
self.l = PGMLearner()
# generate graph skeleton
skel = GraphSkeleton()
skel.load("unittestdict.txt")
skel.toporder()
# generate sample sequence to try to learn from - discrete
nd = NodeData()
nd.load("unittestdict.txt")
self.samplediscbn = DiscreteBayesianNetwork(skel, nd)
self.samplediscseq = self.samplediscbn.randomsample(5000)
# generate sample sequence to try to learn from - discrete
nda = NodeData()
nda.load("unittestlgdict.txt")
self.samplelgbn = LGBayesianNetwork(skel, nda)
self.samplelgseq = self.samplelgbn.randomsample(10000)
self.skel = skel
def test_discrete_mle_estimateparams(self):
result = self.l.discrete_mle_estimateparams(self.skel, self.samplediscseq)
indexa = result.Vdata['SAT']['vals'].index('lowscore')
self.assertTrue(result.Vdata['SAT']['cprob']["['low']"][indexa] < 1 and result.Vdata['SAT']['cprob']["['low']"][indexa] > .9)
indexb = result.Vdata['Letter']['vals'].index('weak')
self.assertTrue(result.Vdata['Letter']['cprob']["['A']"][indexb] < .15 and result.Vdata['Letter']['cprob']["['A']"][indexb] > .05)
def test_lg_mle_estimateparams(self):
result = self.l.lg_mle_estimateparams(self.skel, self.samplelgseq)
self.assertTrue(result.Vdata['SAT']['mean_base'] < 15 and result.Vdata['SAT']['mean_base'] > 5)
self.assertTrue(result.Vdata['Letter']['variance'] < 15 and result.Vdata['Letter']['variance'] > 5)
def test_discrete_constraint_estimatestruct(self):
result = self.l.discrete_constraint_estimatestruct(self.samplediscseq)
self.assertTrue(["Difficulty", "Grade"] in result.E)
def test_lg_constraint_estimatestruct(self):
result = self.l.lg_constraint_estimatestruct(self.samplelgseq)
self.assertTrue(["Intelligence", "Grade"] in result.E)
def test_discrete_condind(self):
chi, pv, witness = self.l.discrete_condind(self.samplediscseq, "Difficulty", "Letter", ["Grade"])
self.assertTrue(pv > .05)
self.assertTrue(witness, ["Grade"])
chia, pva, witnessa = self.l.discrete_condind(self.samplediscseq, "Difficulty", "Intelligence", [])
self.assertTrue(pva < .05)
def test_discrete_estimatebn(self):
result = self.l.discrete_estimatebn(self.samplediscseq)
self.assertTrue(result.V)
self.assertTrue(result.E)
self.assertTrue(result.Vdata["Difficulty"]["cprob"][0])
def test_lg_estimatebn(self):
result = self.l.lg_estimatebn(self.samplelgseq)
self.assertTrue(result.V)
self.assertTrue(result.E)
self.assertTrue(result.Vdata["Intelligence"]["mean_base"])
result_full_bn = learner_full.discrete_estimatebn(training_data)
#result_full_bn.E
# In[ ]:
# We can also manually test and verify how independent two varaibles are
# In[ ]:
learner_indep = PGMLearner()
learner_indep.discrete_condind(training_data,'Surv', 'Fare', ['Class'])
# In this case, the result is chi, pval et variable U
learner_indep = PGMLearner()
print("Chi, pval, U: {}{}".format(learner_indep.discrete_condind(training_data,'Surv', 'Fare', ['Class']),
"(Ho can't be rejected since Surv and Fare are cond independent)"))
print("Chi, pval, U: {}{}".format(learner_indep.discrete_condind(training_data,'Surv', 'Class', ['Fare']),
"(Ho is rejected: Surv and Class are not indep)"))
print("Chi, pval, U: {}{}".format(learner_indep.discrete_condind(training_data,'Sex', 'Class', ['Surv']),
"(Ho is rejected: Sex and Class are not indep)"))
print("Chi, pval, U: {}".format(learner_indep.discrete_condind(training_data,'Fare', 'Class', ['Sex'])))
print("Chi, pval, U: {}".format(learner_indep.discrete_condind(training_data,'Fare', 'Sex', ['Sex'])))
chi – The result of the chi-squared test on the data (compare the actual and the expected distri of X and Y given U). The expected distribution is P(X,Y,U)=P(U)P(X|U)P(Y|U). The Chi squared is a measure of the deviance between two distributions.
pval – The p-value of the test, meaning the probability of attaining a chi-square result as extreme as or more extreme than the one found, assuming that the null hypothesis is true. (e.g., a p-value of .05 means that if X and Y were independent given U, the chance of getting a chi-squared result this high or higher are .05). The Null H (independence) is rejected if the p-value is smaller than 0.05.
