def test_isomap_reconstruction_error():
# Same setup as in test_isomap_simple_grid, with an added dimension
N_per_side = 5
Npts = N_per_side**2
n_neighbors = Npts - 1
# grid of equidistant points in 2D, n_components = n_dim
X = np.array(list(product(range(N_per_side), repeat=2)))
# add noise in a third dimension
rng = np.random.RandomState(0)
noise = 0.1 * rng.randn(Npts, 1)
X = np.concatenate((X, noise), 1)
# compute input kernel
G = neighbors.kneighbors_graph(X, n_neighbors, mode='distance').toarray()
centerer = preprocessing.KernelCenterer()
K = centerer.fit_transform(-0.5 * G**2)
for eigen_solver in eigen_solvers:
for path_method in path_methods:
clf = manifold.Isomap(n_neighbors=n_neighbors,
n_components=2,
eigen_solver=eigen_solver,
path_method=path_method)
clf.fit(X)
# compute output kernel
G_iso = neighbors.kneighbors_graph(clf.embedding_,
n_neighbors,
mode='distance').toarray()
K_iso = centerer.fit_transform(-0.5 * G_iso**2)
# make sure error agrees
reconstruction_error = np.linalg.norm(K - K_iso) / Npts
assert_almost_equal(reconstruction_error,
clf.reconstruction_error())
def test_isomap_simple_grid():
# Isomap should preserve distances when all neighbors are used
N_per_side = 5
Npts = N_per_side**2
n_neighbors = Npts - 1
# grid of equidistant points in 2D, n_components = n_dim
X = np.array(list(product(range(N_per_side), repeat=2)))
# distances from each point to all others
G = neighbors.kneighbors_graph(X, n_neighbors, mode='distance').toarray()
for eigen_solver in eigen_solvers:
for path_method in path_methods:
clf = manifold.Isomap(n_neighbors=n_neighbors,
n_components=2,
eigen_solver=eigen_solver,
path_method=path_method)
clf.fit(X)
G_iso = neighbors.kneighbors_graph(clf.embedding_,
n_neighbors,
mode='distance').toarray()
assert_array_almost_equal(G, G_iso)
for i_dataset, (dataset, algo_params) in enumerate(datasets):
# update parameters with dataset-specific values
params = default_base.copy()
params.update(algo_params)
X, y = dataset
# normalize dataset for easier parameter selection
X = StandardScaler().fit_transform(X)
# estimate bandwidth for mean shift
bandwidth = cluster.estimate_bandwidth(X, quantile=params['quantile'])
# connectivity matrix for structured Ward
connectivity = kneighbors_graph(
X, n_neighbors=params['n_neighbors'], include_self=False)
# make connectivity symmetric
connectivity = 0.5 * (connectivity + connectivity.T)
# ============
# Create cluster objects
# ============
ms = cluster.MeanShift(bandwidth=bandwidth, bin_seeding=True)
two_means = cluster.MiniBatchKMeans(n_clusters=params['n_clusters'])
ward = cluster.AgglomerativeClustering(
n_clusters=params['n_clusters'], linkage='ward',
connectivity=connectivity)
spectral = cluster.SpectralClustering(
n_clusters=params['n_clusters'], eigen_solver='arpack',
affinity="nearest_neighbors")
dbscan = cluster.DBSCAN(eps=params['eps'])
fig = plt.figure()
ax = p3.Axes3D(fig)
ax.view_init(7, -80)
for l in np.unique(label):
ax.scatter(X[label == l, 0],
X[label == l, 1],
X[label == l, 2],
color=plt.cm.jet(np.float(l) / np.max(label + 1)),
s=20,
edgecolor='k')
plt.title('Without connectivity constraints (time %.2fs)' % elapsed_time)
# #############################################################################
# Define the structure A of the data. Here a 10 nearest neighbors
from mrex.neighbors import kneighbors_graph
connectivity = kneighbors_graph(X, n_neighbors=10, include_self=False)
# #############################################################################
# Compute clustering
print("Compute structured hierarchical clustering...")
st = time.time()
ward = AgglomerativeClustering(n_clusters=6,
connectivity=connectivity,
linkage='ward').fit(X)
elapsed_time = time.time() - st
label = ward.labels_
print("Elapsed time: %.2fs" % elapsed_time)
print("Number of points: %i" % label.size)
# #############################################################################
# Plot result
np.random.seed(0)
t = 1.5 * np.pi * (1 + 3 * np.random.rand(1, n_samples))
x = t * np.cos(t)
y = t * np.sin(t)
X = np.concatenate((x, y))
X += .7 * np.random.randn(2, n_samples)
X = X.T
# Create a graph capturing local connectivity. Larger number of neighbors
# will give more homogeneous clusters to the cost of computation
# time. A very large number of neighbors gives more evenly distributed
# cluster sizes, but may not impose the local manifold structure of
# the data
knn_graph = kneighbors_graph(X, 30, include_self=False)
for connectivity in (None, knn_graph):
for n_clusters in (30, 3):
plt.figure(figsize=(10, 4))
for index, linkage in enumerate(('average',
'complete',
'ward',
'single')):
plt.subplot(1, 4, index + 1)
model = AgglomerativeClustering(linkage=linkage,
connectivity=connectivity,
n_clusters=n_clusters)
t0 = time.time()
model.fit(X)
elapsed_time = time.time() - t0