def test_normalize_kernel_matrix(self):
""""""
m = [
[1, 2],
[2, 3],
[1, 3],
]
m = np.array(m)
normalized_matrix = normalize_kernel_matrix(m)
def optimize_projections(
*,
output: str,
repr_similarity_matrix,
full_similarity_matrix,
n_components: int,
similarity_type: str,
use_gpu: bool,
) -> None:
"""
:param output: The output folder
:param repr_similarity_matrix: A square matrix with dimensions |repr| x |repr|
:param full_similarity_matrix: A rectangular matrix with dimensions |full| x |repr|
:param n_components:
:return:
"""
khc = ((kernel_name, KERNEL_TO_PROJECTION[kernel_name], hyperparam)
for kernel_name, hyperparams in kernels.items()
for hyperparam in hyperparams)
for kernel_name, project_with_kernel, hyperparam in khc:
# Make output folder for the optimization with this kernel/hyper-parameter pair
param_folder = os.path.join(output, f'{kernel_name}_{hyperparam}')
os.makedirs(param_folder, exist_ok=True)
secho(
f"({kernel_name}/{hyperparam}) calculating normalized/symmetric kernel matrix"
)
repr_kernel_matrix = project_with_kernel(repr_similarity_matrix,
hyperparam)
repr_kernel_matrix_normalized = normalize_kernel_matrix(
repr_kernel_matrix)
secho(
f"({kernel_name}/{hyperparam}) solving eigenvector/eigenvalues problem"
)
eigenvalues, eigenvectors = eigh(repr_kernel_matrix_normalized)
# Calculate alphas
repr_alphas = np.column_stack(
[eigenvectors[:, -i] for i in range(1, n_components + 1)])
# Save Alphas
_alphas_path = os.path.join(param_folder, f"alphas.p")
secho(
f"({kernel_name}/{hyperparam}) outputting alphas to {_alphas_path}"
)
with open(_alphas_path, "wb") as file:
pickle.dump(repr_alphas, file)
# Calculate lambdas
repr_lambdas = [eigenvalues[-i] for i in range(1, n_components + 1)]
# Save lambdas
_lambdas_path = os.path.join(param_folder, f"lambdas.p")
secho(
f"({kernel_name}/{hyperparam}) outputting lambdas to {_lambdas_path}"
)
with open(_lambdas_path, 'wb') as file:
pickle.dump(repr_lambdas, file)
secho(
f"({kernel_name}/{hyperparam}) projecting known vocabulary to KPCA embeddings"
)
repr_projection_matrix = repr_alphas / repr_lambdas
# Calculate KPCA matrix
if similarity_type == "ngram_intersec": # There is no additional kernel function on top of the similarity function
kpca_matrix = project_full_vocab_linear(
projection_matrix=repr_projection_matrix,
similarity_matrix=full_similarity_matrix,
)
elif use_gpu:
kpca_matrix = project_words_gpu(
projection_matrix=repr_projection_matrix,
similarity_matrix=full_similarity_matrix,
kernel_name=kernel_name,
hyperparam=hyperparam,
)
else:
kpca_matrix = project_similarity_matrix(
projection_matrix=repr_projection_matrix,
similarity_matrix=full_similarity_matrix,
kernel_name=kernel_name,
hyperparam=hyperparam,
)
# Save KPCA matrix
_kpca_path = os.path.join(param_folder, f"kpca.npy")
secho(
f"({kernel_name}/{hyperparam}) outputting KPCA matrix to {_kpca_path}"
)
np.save(_kpca_path, kpca_matrix)