def test_validate_cross_regression(self):
tab = shuffle_data(Table('housing'))
eps = 0.1
correct, num, all = 0, 0, len(tab)
for i in range(all):
train, test = get_instance(tab, i)
ccr = CrossRegressor(AbsError(LinearRegressionLearner()), 5,
shuffle_data(train))
y_min, y_max = ccr(test.x, eps)
if y_min <= test.y <= y_max: correct += 1
num += y_max - y_min
self.assertAlmostEqual(correct / all, 1.0 - eps, delta=0.02)
def test_validate_AbsErrorKNN(self):
eps = 0.1
correct, num, all = 0, 0, 0
for it in range(10):
train, test = split_data(shuffle_data(Table('housing')), 4, 1)
train, calibrate = split_data(shuffle_data(train), 3, 1)
icr = InductiveRegressor(
AbsErrorKNN(Euclidean, 10, average=True, variance=True), train,
calibrate)
for i, inst in enumerate(test):
y_min, y_max = icr(inst.x, eps)
if y_min <= inst.y <= y_max: correct += 1
num += y_max - y_min
all += 1
print(correct / all, num / all)
self.assertAlmostEqual(correct / all, 1.0 - eps, delta=0.03)
def test_run_train_test(self):
tab = shuffle_data(Table('iris'))
cp = CrossClassifier(InverseProbability(LogisticRegressionLearner()),
4)
r = run_train_test(cp, 0.1, tab[:100], tab[100:])
cp = InductiveClassifier(
InverseProbability(LogisticRegressionLearner()))
r = run_train_test(cp, 0.1, tab[:50], tab[100:], tab[50:100])
def test_validate_cross_classification(self):
tab = shuffle_data(Table('iris'))
eps = 0.1
correct, num, all = 0, 0, len(tab)
for i in range(all):
train, test = get_instance(tab, i)
ccp = CrossClassifier(InverseProbability(NaiveBayesLearner()), 5,
train)
pred = ccp(test.x, eps)
if test.get_class() in pred: correct += 1
num += len(pred)
self.assertAlmostEqual(correct / all, 1.0 - eps, delta=0.02)
def test_validate_regression(self):
tab = Table('housing')
eps = 0.1
correct, num, all = 0, 0, len(tab)
for i in range(all):
train, test = get_instance(tab, i)
train, calibrate = split_data(shuffle_data(train), 2, 1)
icr = InductiveRegressor(AbsError(LinearRegressionLearner()),
train, calibrate)
y_min, y_max = icr(test.x, eps)
if y_min <= test.y <= y_max: correct += 1
num += y_max - y_min
self.assertAlmostEqual(correct / all, 1.0 - eps, delta=0.02)
def test_validate_inductive(self):
eps = 0.1
correct, num, all = 0, 0, len(self.tab)
for i in range(all):
train, test = get_instance(self.tab, i)
train, calibrate = split_data(shuffle_data(train), 2, 1)
icp = InductiveClassifier(
InverseProbability(LogisticRegressionLearner()), train,
calibrate)
pred = icp(test.x, eps)
if test.get_class() in pred: correct += 1
num += len(pred)
self.assertAlmostEqual(correct / all, 1.0 - eps, delta=0.01)
def test_individual_classification(self):
train, test = get_instance(Table('iris'), 123) # borderline case
train = shuffle_data(train)
ccp = CrossClassifier(InverseProbability(LogisticRegressionLearner()),
3, train)
pred = ccp.predict(test.x)
cred, conf = pred.credibility(), pred.confidence()
self.assertLess(cred, 0.5)
d = 1e-6
self.assertEqual(len(ccp(test.x, 1 - (conf - d))), 1)
self.assertGreater(len(ccp(test.x, 1 - (conf + d))), 1)
self.assertEqual(len(ccp(test.x, (cred + d))), 0)
self.assertGreater(len(ccp(test.x, (cred - d))), 0)
def test_cross_classification(self):
tab = Table('iris')
train, test = get_instance(tab, 0)
train = shuffle_data(train)
ccp = CrossClassifier(InverseProbability(LogisticRegressionLearner()),
3, train)
pred = ccp(test.x, 0.1)
self.assertEqual(pred, ['Iris-setosa'])
ccp = CrossClassifier(InverseProbability(LogisticRegressionLearner()),
3)
ccp.fit(train)
pred = ccp(test.x, 0.1)
self.assertEqual(pred, ['Iris-setosa'])
def setUp(self):
self.tab = Table('iris')
train, self.test = get_instance(self.tab, 0)
self.train, self.calibrate = split_data(shuffle_data(train), 2, 1)
def setUp(self):
self.train, self.test = get_instance(Table('housing'), 0)
self.train, self.calibrate = split_data(shuffle_data(self.train), 2, 1)
