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)
def test_graph_segments():
np.random.seed(0)
N = 4
X = np.random.random((N, 2))
G = np.zeros([N, N])
G[0, 1] = 1
G[2, 1] = 1
G[2, 3] = 1
ind = np.array([[0, 2, 2], [1, 1, 3]])
xseg_check = X[ind, 0]
yseg_check = X[ind, 1]
xseg, yseg = get_graph_segments(X, G)
assert_allclose(xseg, xseg_check)
assert_allclose(yseg, yseg_check)
def test_graph_segments():
np.random.seed(0)
N = 4
X = np.random.random((N, 2))
G = np.zeros([N, N])
G[0, 1] = 1
G[2, 1] = 1
G[2, 3] = 1
ind = np.array([[0, 2, 2],
[1, 1, 3]])
xseg_check = X[ind, 0]
yseg_check = X[ind, 1]
xseg, yseg = get_graph_segments(X, G)
assert_allclose(xseg, xseg_check)
assert_allclose(yseg, yseg_check)
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 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)
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
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()
def mst_clustering(data_to_cluster):
x = data['x'][data_to_cluster]
y = data['y'][data_to_cluster]
X = [x, y]
xmin, xmax = (0, 5000)
ymin, ymax = (0, 5000)
#------------------------------------------------------------
# Compute the MST clustering model
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))
#----------------------------------------------------------------------
# Plot the results
fig = plt.figure(figsize=(5, 6))
fig.subplots_adjust(hspace=0, left=0.1, right=0.95, bottom=0.1, top=0.9)
ax = fig.add_subplot(311, aspect='equal')
ax.scatter(X[:, 1], X[:, 0], s=1, lw=0, c='k')
ax.set_xlim(ymin, ymax)
ax.set_ylim(xmin, xmax)
ax.xaxis.set_major_formatter(plt.NullFormatter())
ax.set_ylabel('(Mpc)')
ax = fig.add_subplot(312, aspect='equal')
ax.plot(T_y, T_x, c='k', lw=0.5)
ax.set_xlim(ymin, ymax)
ax.set_ylim(xmin, xmax)
ax.xaxis.set_major_formatter(plt.NullFormatter())
ax.set_ylabel('(Mpc)')
ax = fig.add_subplot(313, aspect='equal')
ax.plot(T_trunc_y, T_trunc_x, c='k', lw=0.5)
ax.imshow(density.T, origin='lower', cmap=plt.cm.hot_r, extent=[ymin, ymax, xmin, xmax])
ax.set_xlim(ymin, ymax)
ax.set_ylim(xmin, xmax)
ax.set_xlabel('(Mpc)')
ax.set_ylabel('(Mpc)')
plt.show()
return(scale)
