def test_classifies_instance_correctly(self):
self.__update_stump()
self.assertEqual(
'no',
self.outlook_stump.klass(
instance.GoldInstance(['sunny', 'mild', 'normal', 'true'],
'yes')))
self.assertEqual(
'yes',
self.outlook_stump.klass(
instance.GoldInstance(['overcast', 'mild', 'normal', 'true'],
'yes')))
self.assertEqual(
'yes',
self.outlook_stump.klass(
instance.GoldInstance(['rainy', 'mild', 'normal', 'true'],
'yes')))
self.assertEqual(
'no',
self.outlook_stump.klass(
instance.TestInstance(['sunny', 'mild', 'normal', 'true'])))
self.assertEqual(
'yes',
self.outlook_stump.klass(
instance.TestInstance(['overcast', 'mild', 'normal', 'true'])))
self.assertEqual(
'yes',
self.outlook_stump.klass(
instance.TestInstance(['rainy', 'mild', 'normal', 'true'])))
def test_hamilton_distance(self):
attributes = [
attr.Attribute('A1', ['a', 'b'], 0),
attr.Attribute('A2', ['continuous'], 1),
attr.Attribute('A3', ['continuous'], 2),
attr.Attribute('A4', ['g', 'h'], 3)
]
instance1 = ins.TrainingInstance(['a', 5, 3.4, 'g'], 'y')
instance2 = ins.TestInstance(['a', 5, 3.4, 'g'])
self.assertEqual(
0,
distancemetric.hamiltonian_distance(instance1, instance2,
attributes))
instance2 = ins.TestInstance(['b', 5, 3.4, 'g'])
self.assertEqual(
1,
distancemetric.hamiltonian_distance(instance1, instance2,
attributes))
instance2 = ins.TestInstance(['b', 4, 3.4, 'h'])
self.assertEqual(
3,
distancemetric.hamiltonian_distance(instance1, instance2,
attributes))
instance2 = ins.TestInstance(['b', 4, 1.4, 'h'])
self.assertEqual(
5,
distancemetric.hamiltonian_distance(instance1, instance2,
attributes))
def test_euclidean_distance(self):
attributes = [
attr.Attribute('A1', ['a', 'b'], 0),
attr.Attribute('A2', ['continuous'], 1),
attr.Attribute('A3', ['continuous'], 2),
attr.Attribute('A4', ['g', 'h'], 3)
]
instance1 = ins.TrainingInstance(['a', 5, 3.4, 'g'], 'y')
instance2 = ins.TestInstance(['a', 5, 3.4, 'g'])
self.assertEqual(
0,
distancemetric.euclidean_distance(instance1, instance2,
attributes))
instance2 = ins.TestInstance(['b', 5, 3.4, 'g'])
self.assertEqual(
1,
distancemetric.euclidean_distance(instance1, instance2,
attributes))
instance2 = ins.TestInstance(['b', 4, 3.4, 'h'])
self.assertEqual(
math.sqrt(3),
distancemetric.euclidean_distance(instance1, instance2,
attributes))
instance2 = ins.TestInstance(['b', 4, 1.4, 'h'])
self.assertEqual(
math.sqrt(7),
distancemetric.euclidean_distance(instance1, instance2,
attributes))
def test_should_be_able_to_set_class_on_test_instance(self):
instance = ins.TestInstance(['bar','two'])
try:
instance.set_klass('c')
self.assertEqual('c', instance.classified_klass)
self.assertEqual(None, instance.klass_value)
except AttributeError:
self.fail('should be able to set class in Test Instance')
def test_ib1(self):
path = datasetsDir(self) + 'minigolf' + SEP + 'weather'
_training = training(path)
_attributes, _klass = metadata(path)
classifier = knn.IB1(_training, _attributes, _klass)
test_instance = ins.TestInstance(['sunny', 'hot', 'high', 'false'])
classifier.test(inss.TestInstances([test_instance]))
self.assertEqual('no', test_instance.classified_klass)
def test_get_attribute_value_from_instance_using_attribute(self):
instance = ins.TrainingInstance(['bar','two'],'a')
attr = attribute.Attribute('second', ['two','duo'], 1)
self.assertEqual('two', instance.value(attr))
test = ins.TestInstance(['bar','two'])
self.assertEqual('two', test.value(attr))
gold = ins.GoldInstance(['bar','two'],'a')
self.assertEqual('two', gold.value(attr))
def test_string_representation(self):
instance = ins.TrainingInstance(['bar','two'],'a')
self.assertEqual("[bar,two;a]", instance.__str__());
instance = ins.TestInstance(['bar','two'])
self.assertEqual("[bar,two; ]", instance.__str__());
instance.set_klass('b')
self.assertEqual("[bar,two;b]", instance.__str__());
instance = ins.GoldInstance(['bar','two'],'a')
self.assertEqual("[bar,two;a; ]", instance.__str__());
instance.set_klass('b')
self.assertEqual("[bar,two;a;b]", instance.__str__());
def test_test_instance_has_only_attributes_and_none_as_class(self):
instance = ins.TestInstance(['bar','two'])
self.assertEqual(None, instance.klass_value)
self.assertEqual(['bar', 'two'], instance.attrs)
def test_create_n_validate_instance(self):
instance = ins.TestInstance(['bar','two','a'])
self.assertEqual(3, len(instance.attrs))
self.assertEqual('bar', instance.attrs[0])
self.assertEqual('two', instance.attrs[1])
self.assertEqual('a', instance.attrs[2])
def test_test_intances_creation(self):
instances = test(datasetsDir(self) + 'numerical' + SEP + 'weather')
self.assertEqual(1, len(instances), '1 instance should be present')
self.assertEqual(
ins.TestInstance(['overcast', '25.4', 'high', 'true']),
instances[0])
def test(self, file_path):
all_values = self.__get_all_values(file_path, self.TEST)
return inss.TestInstances([ins.TestInstance(values) for values in all_values if values is not None])