def test_bde2(self):
myskl = Data(read_csv(open('myksl.dat')))
# > ksbln.prior <- jointprior(kslbn)
# Imaginary sample size: 64
# > kslbn.fit <- getnetwork(learn(kslbn,myksl,ksbln.prior))
# deal scores
# > score(nodes(kslbn.fit)$Smok)
# [1] -637.9544
# > score(nodes(kslbn.fit)$Alc)
# [1] -752.027
# > score(nodes(kslbn.fit)$Work)
# [1] -463.1716
# > score(nodes(kslbn.fit)$Sex)
# [1] -751.0772
# > score(nodes(kslbn.fit)$Year)
# [1] -666.6585
# > score(kslbn.fit)
# [1] -3270.889
node_scores = (-637.9544,-752.027,-463.1716,-751.0772,-666.6585)
net_score = -3270.889
score = 0
for i, cpt in enumerate(self.cpts):
cpt = cpt.get_counts_sql(myskl)
this_score = cpt.bdeu_score(64)
self.assertAlmostEqual(this_score,node_scores[i],places)
score += this_score
self.assertAlmostEqual(score,net_score,places)
def test_bde3(self):
# just tests that myskl has the right counts
myskl = Data(read_csv(open('myksl.dat')))
# > ksbln.prior <- jointprior(kslbn)
# Imaginary sample size: 64
# > kslbn.fit <- getnetwork(learn(kslbn,myksl,ksbln.prior))
# deal scores
# > score(nodes(kslbn.fit)$Smok)
# [1] -637.9544
# > score(nodes(kslbn.fit)$Alc)
# [1] -752.027
# > score(nodes(kslbn.fit)$Work)
# [1] -463.1716
# > score(nodes(kslbn.fit)$Sex)
# [1] -751.0772
# > score(nodes(kslbn.fit)$Year)
# [1] -666.6585
# > score(kslbn.fit)
# [1] -3270.889
node_scores = (-637.9544,-752.027,-463.1716,-751.0772,-666.6585)
net_score = -3270.889
score = 0
for i, cpt in enumerate(self.cpts):
child = cpt.child()
parents = list(cpt.variables() - set([child]))
this_score = myskl.family_score(child,parents,64.0)
self.assertAlmostEqual(this_score,node_scores[i],places)
score += this_score
self.assertAlmostEqual(score,net_score,places)
def test_bigdata_sql(self):
alarm = Data(self.rawdata)
for varset in (['CO', 'MINVOLSET'], ['CO'],
['HRBP', 'EXPCO2', 'PRESS', 'VENTTUBE'], [
'DISCONNECT', 'MINVOLSET', 'VENTMACH', 'VENTTUBE',
'VENTLUNG', 'VENTALV', 'ARTCO2', 'PRESS', 'SHUNT'
]):
factor = alarm[varset]
self.assertEqual(factor.z(), 1000)
def test_smalldata_sql(self):
rawdata = read_csv(open('fake_data'))
dat = Data(rawdata)
self.assertEqual(dat.makeFactor([]).z(), 5)
self.samefactor(dat.makeFactor(['bar']), Factor(['bar'], [2, 2, 1]))
self.samefactor(dat.makeFactor(['blah']), Factor(['blah'], [3, 1, 1]))
self.samefactor(dat.makeFactor(['foo']), Factor(['foo'], [3, 1, 1, 0]))
self.samefactor(
dat.makeFactor(['bar', 'foo']),
Factor(['bar', 'foo'], [2, 0, 0, 0, 1, 1, 0, 0, 0, 0, 1, 0]))