def test_domainContingency(self):
d = orange.ExampleTable("zoo")
dc = orange.DomainContingency(d)
cd = orange.get_class_distribution(d)
for i, c in enumerate(dc):
self.assertEqual(id(d.domain.attributes[i]), id(c.outer_variable))
self.assertEqual(id(dc[d.domain.attributes[i]]), id(c))
self.assertFalse(dc.class_is_outer)
self.assertEqual(dc.classes, cd)
dc.normalize()
self.assertEqual(sum(dc[0][0]), 1)
dc.foo = 42
s = pickle.dumps(dc)
dc2 = pickle.loads(s)
self.assertEqual(dc2.foo, dc.foo)
self.assertEqual(dc2.classes, dc.classes)
self.assertEqual(dc2[0].outer_variable, dc[0].outer_variable)
# Description: Demonstrates the use of DomainContingency
# Category: statistics
# Classes: DomainContingency, ContingencyClassAttr, ContingencyAttrClass
# Uses: monk1
# Referenced: contingency.htm
import orange
data = orange.ExampleTable("monk1")
print "Distributions of classes given the attribute value"
dc = orange.DomainContingency(data)
print "a: ", dc["a"]
print "b: ", dc["b"]
print "c: ", dc["e"]
print
print "Distributions of attribute values given the class value"
dc = orange.DomainContingency(data, classIsOuter=1)
print "a: ", dc["a"]
print "b: ", dc["b"]
print "c: ", dc["e"]
print
# Description: Read data, show mean for continuous attributes and contingency matrix for nominal attributes
# Category: description
# Uses: adult_sample.tab
# Classes: DomainContingency
# Referenced: basic_exploration.htm
import orange
data = orange.ExampleTable("adult_sample.tab")
print "Continuous attributes:"
for a in range(len(data.domain.attributes)):
if data.domain.attributes[a].varType == orange.VarTypes.Continuous:
d = 0.; n = 0
for e in data:
if not e[a].isSpecial():
d += e[a]
n += 1
print " %s, mean=%3.2f" % (data.domain.attributes[a].name, d / n)
print "\nNominal attributes (contingency matrix for classes:", data.domain.classVar.values, ")"
cont = orange.DomainContingency(data)
for a in data.domain.attributes:
if a.varType == orange.VarTypes.Discrete:
print " %s:" % a.name
for v in range(len(a.values)):
sum = 0
for cv in cont[a][v]:
sum += cv
print " %s, total %d, %s" % (a.values[v], sum, cont[a][v])
print