class TestRegularTree(TestCase):
def setUp(self):
self.data = pd.read_csv('data/iris.data.csv')
self.tau_mat = self.data.corr(method='kendall').values
self.u_matrix = np.empty(self.data.shape)
count = 0
for col in self.data:
uni = GaussianKDE()
uni.fit(self.data[col])
self.u_matrix[:,
count] = uni.cumulative_distribution(self.data[col])
count += 1
self.tree = Tree(TreeTypes.REGULAR)
self.tree.fit(0, 4, self.tau_mat, self.u_matrix)
def test_first_tree(self):
""" Assert the construction of first tree is correct
The first tree should be:
1
0--2--3
"""
sorted_edges = Edge.sort_edge(self.tree.edges)
assert sorted_edges[0].L == 0
assert sorted_edges[0].R == 2
assert sorted_edges[1].L == 1
assert sorted_edges[1].R == 2
assert sorted_edges[2].L == 2
assert sorted_edges[2].R == 3
@pytest.mark.xfail
def test_first_tree_likelihood(self):
""" Assert first tree likehood is correct"""
uni_matrix = np.array([[0.1, 0.2, 0.3, 0.4]])
value, new_u = self.tree.get_likelihood(uni_matrix)
expected = 0.9545348664739628
assert abs(value - expected) < 10E-3
def test_get_constraints(self):
""" Assert get constraint gets correct neighbor nodes"""
self.tree._get_constraints()
assert self.tree.edges[0].neighbors == [1, 2]
assert self.tree.edges[1].neighbors == [0, 2]
def test_get_tau_matrix(self):
""" Assert second tree likelihood is correct """
self.tau = self.tree.get_tau_matrix()
test = np.isnan(self.tau)
self.assertFalse(test.all())
def test_second_tree_likelihood(self):
"""Assert second tree likelihood is correct."""
tau = self.tree.get_tau_matrix()
second_tree = Tree(TreeTypes.REGULAR)
second_tree.fit(1, 3, tau, self.tree)
uni_matrix = np.array([[0.1, 0.2, 0.3, 0.4]])
first_value, new_u = self.tree.get_likelihood(uni_matrix)
second_value, out_u = second_tree.get_likelihood(new_u)
class TestDirectTree(TestCase):
def setUp(self):
self.data = pd.read_csv('data/iris.data.csv')
self.tau_mat = self.data.corr(method='kendall').values
self.u_matrix = np.empty(self.data.shape)
count = 0
for col in self.data:
uni = GaussianKDE()
uni.fit(self.data[col])
self.u_matrix[:,
count] = uni.cumulative_distribution(self.data[col])
count += 1
self.tree = Tree(TreeTypes.DIRECT)
self.tree.fit(0, 4, self.tau_mat, self.u_matrix)
def test_first_tree(self):
""" Assert 0 is the center node"""
assert self.tree.edges[0].L == 0
@pytest.mark.xfail
def test_first_tree_likelihood(self):
""" Assert first tree likehood is correct"""
uni_matrix = np.array([[0.1, 0.2, 0.3, 0.4]])
value, new_u = self.tree.get_likelihood(uni_matrix)
expected = -0.1207611551427385
assert abs(value - expected) < 10E-3
def test_get_constraints(self):
""" Assert get constraint gets correct neighbor nodes"""
self.tree._get_constraints()
assert self.tree.edges[0].neighbors == [1]
assert self.tree.edges[1].neighbors == [0, 2]
def test_get_tau_matrix_no_edges_empty(self):
"""get_tau_matrix returns an empty array if there are no edges."""
# Setup
tree = Tree(TreeTypes.DIRECT)
tree.edges = []
# Run
result = tree.get_tau_matrix()
# Check
assert result.shape == (0, 0)
def test_get_tau_matrix(self):
"""Assert none of get tau matrix is NaN."""
self.tau = self.tree.get_tau_matrix()
test = np.isnan(self.tau)
self.assertFalse(test.all())
@pytest.mark.xfail
def test_second_tree_likelihood(self):
"""Assert second tree likelihood is correct."""
tau = self.tree.get_tau_matrix()
second_tree = Tree(TreeTypes.DIRECT)
second_tree.fit(1, 3, tau, self.tree)
uni_matrix = np.array([[0.1, 0.2, 0.3, 0.4]])
first_value, new_u = self.tree.get_likelihood(uni_matrix)
second_value, out_u = second_tree.get_likelihood(new_u)
expected = 0.24428294700258632
assert abs(second_value - expected) < 10E-3
class TestCenterTree(TestCase):
def setUp(self):
self.data = pd.read_csv('data/iris.data.csv')
self.tau_mat = self.data.corr(method='kendall').values
self.u_matrix = np.empty(self.data.shape)
count = 0
for col in self.data:
uni = GaussianKDE()
uni.fit(self.data[col])
self.u_matrix[:,
count] = uni.cumulative_distribution(self.data[col])
count += 1
self.tree = Tree(TreeTypes.CENTER)
self.tree.fit(0, 4, self.tau_mat, self.u_matrix)
def test_first_tree(self):
"""Assert 0 is the center node on the first tree."""
assert self.tree.edges[0].L == 0
@pytest.mark.xfail
def test_first_tree_likelihood(self):
"""Assert first tree likehood is correct."""
uni_matrix = np.array([[0.1, 0.2, 0.3, 0.4]])
value, new_u = self.tree.get_likelihood(uni_matrix)
expected = -0.19988720707143634
assert abs(value - expected) < 10E-3
def test_get_constraints(self):
"""Assert get constraint gets correct neighbor nodes."""
self.tree._get_constraints()
assert self.tree.edges[0].neighbors == [1, 2]
assert self.tree.edges[1].neighbors == [0, 2]
def test_get_tau_matrix(self):
"""Assert none of get tau matrix is NaN."""
self.tau = self.tree.get_tau_matrix()
test = np.isnan(self.tau)
self.assertFalse(test.all())
@pytest.mark.xfail
def test_second_tree_likelihood(self):
"""Assert second tree likelihood is correct."""
# Setup
# Build first tree
data = pd.read_csv('data/iris.data.csv')
tau_mat = data.corr(method='kendall').values
u_matrix = np.empty(data.shape)
for index, col in enumerate(data):
uni = GaussianKDE()
uni.fit(data[col])
u_matrix[:, index] = uni.cumulative_distribution(data[col])
first_tree = Tree(TreeTypes.CENTER)
first_tree.fit(0, 4, tau_mat, u_matrix)
uni_matrix = np.array([[0.1, 0.2, 0.3, 0.4]])
likelihood_first_tree, conditional_uni_first = first_tree.get_likelihood(
uni_matrix)
tau = first_tree.get_tau_matrix()
# Build second tree
second_tree = Tree(TreeTypes.CENTER)
second_tree.fit(1, 3, tau, first_tree)
expected_likelihood_second_tree = 0.4888802429313932
# Run
likelihood_second_tree, out_u = second_tree.get_likelihood(
conditional_uni_first)
# Check
assert compare_values_epsilon(likelihood_second_tree,
expected_likelihood_second_tree)
