def test_cla_max_sharpe(self):
"""
Test the calculation of maximum sharpe ratio weights
"""
cla = CLA(weight_bounds=(0, 1), calculate_returns="mean")
cla.allocate(asset_prices=self.data, solution='max_sharpe')
weights = cla.weights.values[0]
assert (weights >= 0).all()
assert len(weights) == self.data.shape[1]
np.testing.assert_almost_equal(np.sum(weights), 1)
def test_cla_with_mean_returns(self):
"""
Test the calculation of CLA turning points using mean returns.
"""
self.data.iloc[1:10, :] = 40
self.data.iloc[11:20, :] = 50
self.data.iloc[21, :] = 100
cla = CLA(weight_bounds=(0, 1), calculate_expected_returns="mean")
cla.allocate(asset_prices=self.data, asset_names=self.data.columns)
weights = cla.weights.values
weights[weights <= 1e-15] = 0 # Convert very very small numbers to 0
for turning_point in weights:
assert (turning_point >= 0).all()
assert len(turning_point) == self.data.shape[1]
np.testing.assert_almost_equal(np.sum(turning_point), 1)
def test_lambda_for_no_bounded_weights(self):
# pylint: disable=protected-access,invalid-name
"""
Test the computation of lambda when there are no bounded weights
"""
cla = CLA(weight_bounds=(0, 1), calculate_returns="mean")
cla.allocate(asset_prices=self.data, solution='min_volatility')
data = self.data.cov()
data = data.values
x, y = cla._compute_lambda(covar_f_inv=data,
covar_fb=data,
mean_f=cla.expected_returns,
w_b=None,
asset_index=1,
b_i=[[0], [1]])
assert isinstance(x, float)
assert isinstance(y, int)