def test_infer_dim_1():
# TODO: explain what this is testing
# Or at least use explicit variable names...
n, p = 1000, 5
rng = np.random.RandomState(0)
X = (rng.randn(n, p) * .1 + rng.randn(n, 1) * np.array([3, 4, 5, 1, 2]) +
np.array([1, 0, 7, 4, 6]))
pca = PCA(n_components=p, svd_solver='full')
pca.fit(X)
spect = pca.explained_variance_
ll = np.array([_assess_dimension_(spect, k, n, p) for k in range(p)])
assert_greater(ll[1], ll.max() - .01 * n)
def test_infer_dim_1():
# TODO: explain what this is testing
# Or at least use explicit variable names...
n, p = 1000, 5
rng = np.random.RandomState(0)
X = (rng.randn(n, p) * .1 + rng.randn(n, 1) * np.array([3, 4, 5, 1, 2]) +
np.array([1, 0, 7, 4, 6]))
pca = PCA(n_components=p, svd_solver='full')
pca.fit(X)
spect = pca.explained_variance_
ll = np.array([_assess_dimension_(spect, k, n, p) for k in range(p)])
assert_greater(ll[1], ll.max() - .01 * n)
def test_infer_dim_1():
"""TODO: explain what this is testing
Or at least use explicit variable names...
"""
n, p = 1000, 5
rng = np.random.RandomState(0)
X = rng.randn(n, p) * 0.1 + rng.randn(n, 1) * np.array([3, 4, 5, 1, 2]) + np.array([1, 0, 7, 4, 6])
pca = PCA(n_components=p)
pca.fit(X)
spect = pca.explained_variance_
ll = []
for k in range(p):
ll.append(_assess_dimension_(spect, k, n, p))
ll = np.array(ll)
assert_greater(ll[1], ll.max() - 0.01 * n)
def test_infer_dim_1():
# TODO: explain what this is testing
# Or at least use explicit variable names...
n, p = 1000, 5
rng = np.random.RandomState(0)
X = (rng.randn(n, p) * 0.1 + rng.randn(n, 1) * np.array([3, 4, 5, 1, 2]) +
np.array([1, 0, 7, 4, 6]))
X = da.from_array(X, chunks=(n, p))
pca = dd.PCA(n_components=p, svd_solver="full")
pca.fit(X)
spect = pca.explained_variance_
ll = []
for k in range(p):
ll.append(_assess_dimension_(spect, k, n, p))
ll = np.array(ll)
assert ll[1] > ll.max() - 0.01 * n
def get_space(self):
cov_mat_sqrt_np = self.cov_mat_sqrt.clone().cpu().numpy()
# perform PCA on DD'
cov_mat_sqrt_np /= (max(1, self.rank.item() - 1))**0.5
if self.pca_rank == 'mle':
pca_rank = self.rank.item()
else:
pca_rank = self.pca_rank
pca_rank = max(1, min(pca_rank, self.rank.item()))
pca_decomp = TruncatedSVD(n_components=pca_rank)
pca_decomp.fit(cov_mat_sqrt_np)
_, s, Vt = randomized_svd(cov_mat_sqrt_np,
n_components=pca_rank,
n_iter=5)
# perform post-selection fitting
if self.pca_rank == 'mle':
eigs = s**2.0
ll = np.zeros(len(eigs))
correction = np.zeros(len(eigs))
# compute minka's PCA marginal log likelihood and the correction term
for rank in range(len(eigs)):
# secondary correction term based on the rank of the matrix + degrees of freedom
m = cov_mat_sqrt_np.shape[1] * rank - rank * (rank + 1) / 2.
correction[rank] = 0.5 * m * np.log(cov_mat_sqrt_np.shape[0])
ll[rank] = _assess_dimension_(
spectrum=eigs,
rank=rank,
n_features=min(cov_mat_sqrt_np.shape),
n_samples=max(cov_mat_sqrt_np.shape))
self.ll = ll
self.corrected_ll = ll - correction
self.pca_rank = np.nanargmax(self.corrected_ll)
print('PCA Rank is: ', self.pca_rank)
return torch.FloatTensor(s[:self.pca_rank, None] *
Vt[:self.pca_rank, :])
else:
return torch.FloatTensor(s[:, None] * Vt)
