def test_edge_case(self, dtype_device, use_rets, edge_case):
dtype, device = dtype_device
n_samples = 2
n_assets = 4
n_clusters = 1 if edge_case == 'single_cluster' else n_assets
single_ = torch.rand(n_assets, n_assets, dtype=dtype, device=device)
single = single_ @ single_.t()
covmat = torch.stack([single for _ in range(n_samples)], dim=0)
rets = torch.rand(n_samples, n_assets, dtype=dtype, device=device) if use_rets else None
true_weights = AnalyticalMarkowitz()(covmat, rets=rets)
pred_weights = NCO(n_clusters=n_clusters)(covmat, rets=rets)
assert torch.allclose(pred_weights, true_weights, atol=1e-3)
assert true_weights.device == pred_weights.device
assert true_weights.dtype == pred_weights.dtype
def test_reproducible(self, dtype_device, use_rets):
dtype, device = dtype_device
n_samples = 2
n_assets = 6
n_clusters = 3
single_ = torch.rand(n_assets, n_assets, dtype=dtype, device=device)
single = single_ @ single_.t()
covmat = torch.stack([single for _ in range(n_samples)], dim=0)
rets = torch.rand(n_samples, n_assets, dtype=dtype, device=device) if use_rets else None
layer = NCO(n_clusters=n_clusters, random_state=2)
weights_1 = layer(covmat, rets=rets)
weights_2 = layer(covmat, rets=rets)
assert torch.allclose(weights_1, weights_2)
assert weights_1.device == weights_2.device
assert weights_1.dtype == weights_2.dtype
def __init__(
self,
n_assets,
max_weight=0.2,
force_symmetric=False,
n_clusters=5,
n_init=100,
init="random",
random_state=None,
):
super().__init__()
self.force_symmetric = force_symmetric
self.matrix = torch.nn.Parameter(torch.eye(n_assets),
requires_grad=True)
self.exp_returns = torch.nn.Parameter(
torch.zeros(n_assets), requires_grad=True
) # torch.FloatTensor(n_assets).uniform_(-0.001, 0.001))#torch.tensor(exp_returns), requires_grad=True) #torch.zeros(n_assets), requires_grad=True)
torch.nn.init.uniform_(self.exp_returns, a=-0.0005, b=0.0005)
# self.gamma_sqrt = torch.nn.Parameter(torch.ones(1), requires_grad=True)
# self.alpha = torch.nn.Parameter(torch.ones(1), requires_grad=True)
# self.n_clusters = torch.nn.Parameter() # TODO: TRY TO IMPLEMENT THIS DIFFERENTIABLE.
self.portfolio_opt_layer = NCO(n_clusters, n_init, init, random_state)