def _get_refinement_operator(self, name):
"""Get the refinement operator.
Args:
name: operator class name as a string
Returns:
object of the operator
Raises:
ValueError: if name is an unknown refinement operation
"""
if name == "CropDiagonal":
return refinement.CropDiagonal()
elif name == "GaussianBlur":
return refinement.GaussianBlur(self.gaussian_blur_sigma)
elif name == "RowWiseThreshold":
return refinement.RowWiseThreshold(
self.p_percentile, self.thresholding_soft_multiplier,
self.thresholding_with_row_max)
elif name == "Symmetrize":
return refinement.Symmetrize()
elif name == "Diffuse":
return refinement.Diffuse()
elif name == "RowWiseNormalize":
return refinement.RowWiseNormalize()
else:
raise ValueError("Unknown refinement operation: {}".format(name))
def test_3by3_matrix(self):
X = np.array([
[0.5, 2.0, 3.0],
[3.0, 4.0, 5.0],
[4.0, 2.0, 1.0]])
Y = refinement.RowWiseNormalize().refine(X)
expected = np.array([
[0.167, 0.667, 1.0],
[0.6, 0.8, 1.0],
[1.0, 0.5, 0.25]])
self.assertTrue(np.allclose(expected, Y, atol=0.001))
def predict(self, X):
"""Perform spectral clustering on data X.
Args:
X: numpy array of shape (n_samples, n_features)
Returns:
labels: numpy array of shape (n_samples,)
Raises:
TypeError: if X has wrong type
ValueError: if X has wrong shape, or we see an unknown refinement
operation
"""
if not isinstance(X, np.ndarray):
raise TypeError("X must be a numpy array")
if len(X.shape) != 2:
raise ValueError("X must be 2-dimensional")
# Compute affinity matrix.
affinity = utils.compute_affinity_matrix(X)
# Refinement opertions on the affinity matrix.
for op in self.refinement_sequence:
if op == "CropDiagonal":
affinity = refinement.CropDiagonal().refine(affinity)
elif op == "GaussianBlur":
affinity = refinement.GaussianBlur(
self.gaussian_blur_sigma).refine(affinity)
elif op == "RowWiseThreshold":
affinity = refinement.RowWiseThreshold(
self.p_percentile,
self.thresholding_soft_multiplier).refine(affinity)
elif op == "Symmetrize":
affinity = refinement.Symmetrize().refine(affinity)
elif op == "Diffuse":
affinity = refinement.Diffuse().refine(affinity)
elif op == "RowWiseNormalize":
affinity = refinement.RowWiseNormalize().refine(affinity)
else:
raise ValueError("Unknown refinement operation: {}".format(op))
# Perform eigen decomposion.
(eigenvalues,
eigenvectors) = utils.compute_sorted_eigenvectors(affinity)
# Get number of clusters.
k = utils.compute_number_of_clusters(eigenvalues, self.stop_eigenvalue)
if self.min_clusters is not None:
k = max(k, self.min_clusters)
if self.max_clusters is not None:
k = min(k, self.max_clusters)
# Get spectral embeddings.
spectral_embeddings = eigenvectors[:, :k]
# Run K-Means++ on spectral embeddings.
# Note: The correct way should be using a K-Means implementation
# that supports customized distance measure such as cosine distance.
# This implemention from scikit-learn does NOT, which is inconsistent
# with the paper.
kmeans_clusterer = KMeans(n_clusters=k,
init="k-means++",
max_iter=300,
random_state=0)
labels = kmeans_clusterer.fit_predict(spectral_embeddings)
return labels