def test_to_quadratic_program(self):
"""Test to_quadratic_program"""
portfolio_diversification = PortfolioDiversification(
similarity_matrix=self.similarity_matrix,
num_assets=self.n,
num_clusters=self.q,
)
actual_op = portfolio_diversification.to_quadratic_program()
expected_op = QuadraticProgram(name="Portfolio diversification")
for i in range(self.n):
for j in range(self.n):
expected_op.binary_var(name="x_{0}_{1}".format(i, j))
for i in range(self.n):
expected_op.binary_var(name="y_{0}".format(i))
linear = {"x_0_0": 1, "x_0_1": 0.8, "x_1_0": 0.8, "x_1_1": 1}
expected_op.maximize(linear=linear)
expected_op.linear_constraint(linear={"y_0": 1, "y_1": 1}, sense="==", rhs=1)
expected_op.linear_constraint(linear={"x_0_0": 1, "x_0_1": 1}, sense="==", rhs=1)
expected_op.linear_constraint(linear={"x_1_0": 1, "x_1_1": 1}, sense="==", rhs=1)
expected_op.linear_constraint(linear={"x_0_0": 1, "y_0": -1}, sense="==", rhs=0)
expected_op.linear_constraint(linear={"x_1_1": 1, "y_1": -1}, sense="==", rhs=0)
expected_op.linear_constraint(linear={"x_0_0": 1, "y_0": -1}, sense="<=", rhs=0)
expected_op.linear_constraint(linear={"x_0_1": 1, "y_1": -1}, sense="<=", rhs=0)
expected_op.linear_constraint(linear={"x_1_0": 1, "y_0": -1}, sense="<=", rhs=0)
expected_op.linear_constraint(linear={"x_1_1": 1, "y_1": -1}, sense="<=", rhs=0)
self.assertEqualQuadraticProgram(actual_op, expected_op)
def test_num_clusters(self):
"""test num_clusters"""
portfolio_diversification = PortfolioDiversification(
similarity_matrix=self.similarity_matrix,
num_assets=self.n,
num_clusters=self.q)
portfolio_diversification.num_clusters = 3
self.assertEqual(portfolio_diversification.num_clusters, 3)
def test_interpret(self):
"""Test interpret"""
portfolio_diversification = PortfolioDiversification(
similarity_matrix=self.similarity_matrix,
num_assets=self.n,
num_clusters=self.q)
result_x = np.array([0, 1, 0, 1, 0, 1])
self.assertEqual(portfolio_diversification.interpret(result_x), [1])
def test_smilarity_matrix(self):
"""Test similarity_matrix"""
portfolio_diversification = PortfolioDiversification(
similarity_matrix=self.similarity_matrix,
num_assets=self.n,
num_clusters=self.q,
)
portfolio_diversification.similarity_matrix = np.array([[0, 1], [1, 0]])
self.assertEqual(portfolio_diversification.similarity_matrix.tolist(), [[0, 1], [1, 0]])
def test_to_quadratic_program(self):
"""Test to_quadratic_program"""
portfolio_diversification = PortfolioDiversification(
similarity_matrix=self.similarity_matrix,
num_assets=self.n,
num_clusters=self.q)
actual_op = portfolio_diversification.to_quadratic_program()
expected_op = QuadraticProgram(name='Portfolio diversification')
for i in range(self.n):
for j in range(self.n):
expected_op.binary_var(name='x_{0}_{1}'.format(i, j))
for i in range(self.n):
expected_op.binary_var(name='y_{0}'.format(i))
linear = {'x_0_0': 1, 'x_0_1': 0.8, 'x_1_0': 0.8, 'x_1_1': 1}
expected_op.maximize(linear=linear)
expected_op.linear_constraint(linear={
'y_0': 1,
'y_1': 1
},
sense='==',
rhs=1)
expected_op.linear_constraint(linear={
'x_0_0': 1,
'x_0_1': 1
},
sense='==',
rhs=1)
expected_op.linear_constraint(linear={
'x_1_0': 1,
'x_1_1': 1
},
sense='==',
rhs=1)
expected_op.linear_constraint(linear={
'x_0_0': 1,
'y_0': -1
},
sense='==',
rhs=0)
expected_op.linear_constraint(linear={
'x_1_1': 1,
'y_1': -1
},
sense='==',
rhs=0)
expected_op.linear_constraint(linear={
'x_0_0': 1,
'y_0': -1
},
sense='<=',
rhs=0)
expected_op.linear_constraint(linear={
'x_0_1': 1,
'y_1': -1
},
sense='<=',
rhs=0)
expected_op.linear_constraint(linear={
'x_1_0': 1,
'y_0': -1
},
sense='<=',
rhs=0)
expected_op.linear_constraint(linear={
'x_1_1': 1,
'y_1': -1
},
sense='<=',
rhs=0)
self.assertEqualQuadraticProgram(actual_op, expected_op)