def test_probs(self):
data = Table('iris')[30:130]
fitters = [majority.MajorityFitter(), majority.MajorityFitter()]
results = testing.TestOnTrainingData(k=10)(data, fitters)
self.assertEqual(results.predicted.shape, (2, len(data)))
np.testing.assert_equal(results.predicted, np.ones((2, 100)))
probs = results.probabilities
self.assertTrue((probs[:, :, 0] < probs[:, :, 2]).all())
self.assertTrue((probs[:, :, 2] < probs[:, :, 1]).all())
def test_miss_majority(self):
x = np.zeros((50, 3))
y = x[:, -1]
x[49] = 1
data = Table(x, y)
res = testing.CrossValidation(data, [majority.MajorityFitter()])
np.testing.assert_equal(res.predicted[0][:49], 0)
x[49] = 0
res = testing.CrossValidation(data, [majority.MajorityFitter()])
np.testing.assert_equal(res.predicted[0][:49], 0)
def test_missing(self):
iris = data.Table('iris')
learn = majority_.MajorityFitter()
for e in iris[:len(iris) // 2:2]:
e.set_class("?")
clf = learn(iris)
y = clf(iris)
self.assertTrue((y == 2).all())
iris = data.Table('iris')
learn = majority_.MajorityFitter()
for e in iris:
e.set_class("?")
clf = learn(iris)
y = clf(iris)
self.assertTrue((y == 0).all())
def test_store_models(self):
nrows, ncols = 1000, 10
t = random_data(nrows, ncols)
fitters = [naive_bayes.BayesLearner(), majority.MajorityFitter()]
cv = testing.CrossValidation(k=5)
res = cv(t, fitters)
self.assertIsNone(res.models)
cv = testing.CrossValidation(k=5, store_models=True)
res = cv(t, fitters)
self.assertEqual(len(res.models), 5)
for models in res.models:
self.assertEqual(len(models), 2)
self.assertIsInstance(models[0], naive_bayes.BayesClassifier)
self.assertIsInstance(models[1], majority.ConstantClassifier)
cv = testing.CrossValidation(k=5)
res = cv(t, fitters)
self.assertIsNone(res.models)
res = testing.CrossValidation(t, fitters, k=5, store_models=True)
self.assertEqual(len(res.models), 5)
for models in res.models:
self.assertEqual(len(models), 2)
self.assertIsInstance(models[0], naive_bayes.BayesClassifier)
self.assertIsInstance(models[1], majority.ConstantClassifier)
def test_store_models(self):
nrows, ncols = 50, 10
t = random_data(nrows, ncols)
fitters = [naive_bayes.BayesLearner(), majority.MajorityFitter()]
cv = testing.TestOnTrainingData()
res = cv(t, fitters)
self.assertIsNone(res.models)
cv = testing.TestOnTrainingData(store_models=True)
res = cv(t, fitters)
self.assertEqual(len(res.models), 1)
for models in res.models:
self.assertEqual(len(models), 2)
self.assertIsInstance(models[0], naive_bayes.BayesClassifier)
self.assertIsInstance(models[1], majority.ConstantClassifier)
cv = testing.TestOnTrainingData()
res = cv(t, fitters)
self.assertIsNone(res.models)
res = testing.TestOnTrainingData(t, fitters, store_models=True)
self.assertEqual(len(res.models), 1)
for models in res.models:
self.assertEqual(len(models), 2)
self.assertIsInstance(models[0], naive_bayes.BayesClassifier)
self.assertIsInstance(models[1], majority.ConstantClassifier)
def test_miss_majority(self):
x = np.zeros((50, 3))
y = x[:, -1]
x[49] = 1
data = Table(x, y)
res = testing.TestOnTrainingData(data, [majority.MajorityFitter()])
np.testing.assert_equal(res.predicted[0][:49], 0)
x[49] = 0
res = testing.TestOnTrainingData(data, [majority.MajorityFitter()])
np.testing.assert_equal(res.predicted[0][:49], 0)
x[25:] = 1
y = x[:, -1]
data = Table(x, y)
res = testing.TestOnTrainingData(data, [majority.MajorityFitter()])
np.testing.assert_equal(res.predicted[0], res.predicted[0][0])
def test_miss_majority(self):
x = np.zeros((50, 3))
y = x[:, -1]
x[49] = 1
data = Table(x, y)
res = testing.LeaveOneOut(data, [majority.MajorityFitter()])
np.testing.assert_equal(res.predicted[0][:49], 0)
x[49] = 0
res = testing.LeaveOneOut(data, [majority.MajorityFitter()])
np.testing.assert_equal(res.predicted[0][:49], 0)
x[25:] = 1
y = x[:, -1]
data = Table(x, y)
res = testing.LeaveOneOut(data, [majority.MajorityFitter()])
np.testing.assert_equal(res.predicted[0],
1 - data.Y[res.row_indices].flatten())
def test_majority(self):
nrows = 1000
ncols = 10
x = np.random.random_integers(1, 3, (nrows, ncols))
y = np.random.random_integers(1, 3, (nrows, 1)) // 2
y[0] = 4
t = data.Table(x, y)
learn = majority_.MajorityFitter()
clf = learn(t)
x2 = np.random.random_integers(1, 3, (nrows, ncols))
y2 = clf(x2)
self.assertTrue((y2 == 1).all())
def test_weights(self):
nrows = 100
ncols = 10
x = np.random.random_integers(1, 3, (nrows, ncols))
y = np.random.random_integers(1, 5, (nrows, 1))
heavy = 3
w = (y == heavy) * 123 + 1
t = data.Table(x, y, W=w)
learn = majority_.MajorityFitter()
clf = learn(t)
x2 = np.random.random_integers(1, 3, (nrows, ncols))
y2 = clf(x2)
self.assertTrue((y2 == heavy).all())
def test_continuous(self):
autompg = data.Table('auto-mpg')
learn = majority_.MajorityFitter()
self.assertRaises(ValueError, learn, autompg)
def test_empty(self):
iris = data.Table('iris')
learn = majority_.MajorityFitter()
clf = learn(iris[:0])
y = clf(iris[0], clf.Probs)
self.assertTrue(np.allclose(y, y.sum() / y.size))