def test_cluster_cutoff():
np.random.seed(0)
N = 100
X = np.random.random((N, 2))
model = HierarchicalClustering(8, edge_cutoff=0.9, min_cluster_size=10)
model.fit(X)
assert_allclose(np.unique(model.labels_),
np.arange(-1, model.n_components_))
def test_simple_clustering():
np.random.seed(0)
N = 10
X = np.random.random((N, 2))
model = HierarchicalClustering(8, edge_cutoff=0.5)
model.fit(X)
assert_(model.n_components_ == N / 2)
assert_(np.sum(model.full_tree_.toarray() > 0) == N - 1)
assert_(np.sum(model.cluster_graph_.toarray() > 0) == N / 2)
assert_allclose(np.unique(model.labels_), np.arange(N / 2))
def mst_clustering(make_plots, x, y, band1, band2, band3, band4, p_path):
X = np.vstack([x, y]).T
# Boundaries for plots
xmin, xmax = (min(x), max(x))
ymin, ymax = (min(y), max(y))
'''Compute MST clustering'''
n_neighbors = 5
edge_cutoff = 0.9
cluster_cutoff = 20
model = HierarchicalClustering(n_neighbors=n_neighbors,
edge_cutoff=edge_cutoff,
min_cluster_size=cluster_cutoff)
model.fit(X)
scale = np.percentile(model.full_tree_.data, 100 * edge_cutoff)
n_components = model.n_components_
labels = model.labels_
# Get the x, y coordinates of the beginning and end of each line segment
T_x, T_y = get_graph_segments(model.X_train_, model.full_tree_)
T_trunc_x, T_trunc_y = get_graph_segments(model.X_train_,
model.cluster_graph_)
# Fit a GMM to each individual cluster
Nx = 100
Ny = 250
Xgrid = np.vstack(map(np.ravel, np.meshgrid(np.linspace(xmin, xmax, Nx),
np.linspace(ymin,
ymax, Ny)))).T
density = np.zeros(Xgrid.shape[0])
for i in range(n_components):
ind = (labels == i)
Npts = ind.sum()
Nclusters = min(12, Npts / 5)
gmm = GMM(Nclusters).fit(X[ind])
dens = np.exp(gmm.score(Xgrid))
density += dens / dens.max()
density = density.reshape((Ny, Nx))
if "mst" in make_plots:
mst_plots(X, ymin, ymax, xmin, xmax, T_x, T_y, T_trunc_x, T_trunc_y,
density, band1, band2, band3, band4, p_path)
return(scale)
setup_text_plots(fontsize=8, usetex=True)
#------------------------------------------------------------
# get data
X = fetch_great_wall()
xmin, xmax = (-375, -175)
ymin, ymax = (-300, 200)
#------------------------------------------------------------
# Compute the MST clustering model
n_neighbors = 10
edge_cutoff = 0.9
cluster_cutoff = 10
model = HierarchicalClustering(n_neighbors=10,
edge_cutoff=edge_cutoff,
min_cluster_size=cluster_cutoff)
model.fit(X)
print(" scale: %2g Mpc" %
np.percentile(model.full_tree_.data, 100 * edge_cutoff))
n_components = model.n_components_
labels = model.labels_
#------------------------------------------------------------
# Get the x, y coordinates of the beginning and end of each line segment
T_x, T_y = get_graph_segments(model.X_train_, model.full_tree_)
T_trunc_x, T_trunc_y = get_graph_segments(model.X_train_, model.cluster_graph_)
#------------------------------------------------------------
# Fit a GaussianMixture to each individual cluster
