def test_nonexchangeability(self):
tab = Table(os.path.join(os.path.dirname(__file__),
'../data/usps.tab'))
train, test = split_data(tab, 7291, 2007)
test = test[:200]
train, calibrate = split_data(train, 3, 1)
icp = InductiveClassifier(
InverseProbability(LogisticRegressionLearner()), train, calibrate)
err = [inst.get_class() not in icp(inst.x, 0.1) for inst in test]
self.assertGreater(sum(err) / len(test), 0.13)
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_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 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)