def test_ward_clustering():
"""
Check that we obtain the correct number of clusters with Ward clustering.
"""
np.random.seed(0)
mask = np.ones([10, 10], dtype=np.bool)
X = np.random.randn(100, 50)
connectivity = grid_to_graph(*mask.shape)
clustering = Ward(n_clusters=10, connectivity=connectivity)
clustering.fit(X)
assert(np.size(np.unique(clustering.labels_)) == 10)
"""
Bench the scikit's ward implement compared to scipy's
"""
import time
import numpy as np
from scipy.cluster import hierarchy
import pylab as pl
from scikits.learn.cluster import Ward
ward = Ward(n_clusters=15)
n_samples = np.logspace(.5, 3, 9)
n_features = np.logspace(1, 3.5, 7)
N_samples, N_features = np.meshgrid(n_samples, n_features)
scikits_time = np.zeros(N_samples.shape)
scipy_time = np.zeros(N_samples.shape)
for i, n in enumerate(n_samples):
for j, p in enumerate(n_features):
X = np.random.normal(size=(n, p))
t0 = time.time()
ward.fit(X)
scikits_time[j, i] = time.time() - t0
t0 = time.time()
hierarchy.ward(X)
scipy_time[j, i] = time.time() - t0
ratio = scikits_time / scipy_time
###############################################################################
# Generate data (swiss roll dataset)
n_samples = 5000
noise = 0.05
X = swiss_roll(n_samples, noise)
###############################################################################
# Define the structure A of the data. Here a 10 nearest neighbors
connectivity = kneighbors_graph(X, n_neighbors=10)
###############################################################################
# Compute clustering
print "Compute structured hierarchical clustering..."
st = time.time()
ward = Ward(n_clusters=10).fit(X, connectivity=connectivity)
label = ward.labels_
print "Elapsed time: ", time.time() - st
print "Number of points: ", label.size
print "Number of clusters: ", np.unique(label).size
###############################################################################
# Plot result
fig = pl.figure()
ax = p3.Axes3D(fig)
ax.view_init(7, -80)
for l in np.unique(label):
ax.plot3D(X[label == l, 0],
X[label == l, 1],
X[label == l, 2],
'o',
"""
Bench the scikit's ward implement compared to scipy's
"""
import time
import numpy as np
from scipy.cluster import hierarchy
import pylab as pl
from scikits.learn.cluster import Ward
ward = Ward(n_clusters=15)
n_samples = np.logspace(.5, 3, 9)
n_features = np.logspace(1, 3.5, 7)
N_samples, N_features = np.meshgrid(n_samples,
n_features)
scikits_time = np.zeros(N_samples.shape)
scipy_time = np.zeros(N_samples.shape)
for i, n in enumerate(n_samples):
for j, p in enumerate(n_features):
X = np.random.normal(size=(n, p))
t0 = time.time()
ward.fit(X)
scikits_time[j, i] = time.time() - t0
t0 = time.time()
hierarchy.ward(X)
scipy_time[j, i] = time.time() - t0
import pylab as pl
import mpl_toolkits.mplot3d.axes3d as p3
from scikits.learn.cluster import Ward
from scikits.learn.datasets.samples_generator import swiss_roll
###############################################################################
# Generate data (swiss roll dataset)
n_samples = 1000
noise = 0.05
X = swiss_roll(n_samples, noise)
###############################################################################
# Compute clustering
print "Compute unstructured hierarchical clustering..."
st = time.time()
ward = Ward(n_clusters=5).fit(X)
label = ward.labels_
print "Elapsed time: ", time.time() - st
print "Number of points: ", label.size
print "Number of clusters: ", np.unique(label).size
###############################################################################
# Plot result
fig = pl.figure()
ax = p3.Axes3D(fig)
ax.view_init(7, -80)
for l in np.unique(label):
ax.plot3D(X[label == l, 0],
X[label == l, 1],
X[label == l, 2],
'o',