def test_KMeansMachine():
# Test a KMeansMachine
means = numpy.array([[3, 70, 0], [4, 72, 0]], 'float64')
mean = numpy.array([3,70,1], 'float64')
# Initializes a KMeansMachine
km = KMeansMachine(2,3)
km.means = means
assert km.shape == (2,3)
# Sets and gets
assert (km.means == means).all()
assert (km.get_mean(0) == means[0,:]).all()
assert (km.get_mean(1) == means[1,:]).all()
km.set_mean(0, mean)
assert (km.get_mean(0) == mean).all()
# Distance and closest mean
eps = 1e-10
assert equals( km.get_distance_from_mean(mean, 0), 0, eps)
assert equals( km.get_distance_from_mean(mean, 1), 6, eps)
(index, dist) = km.get_closest_mean(mean)
assert index == 0
assert equals( dist, 0, eps)
assert equals( km.get_min_distance(mean), 0, eps)
# Loads and saves
filename = str(tempfile.mkstemp(".hdf5")[1])
km.save(bob.io.base.HDF5File(filename, 'w'))
km_loaded = KMeansMachine(bob.io.base.HDF5File(filename))
assert km == km_loaded
# Resize
km.resize(4,5)
assert km.shape == (4,5)
# Copy constructor and comparison operators
km.resize(2,3)
km2 = KMeansMachine(km)
assert km2 == km
assert (km2 != km) is False
assert km2.is_similar_to(km)
means2 = numpy.array([[3, 70, 0], [4, 72, 2]], 'float64')
km2.means = means2
assert (km2 == km) is False
assert km2 != km
assert (km2.is_similar_to(km)) is False
# Clean-up
os.unlink(filename)
def test_KMeansMachine():
# Test a KMeansMachine
means = numpy.array([[3, 70, 0], [4, 72, 0]], 'float64')
mean = numpy.array([3, 70, 1], 'float64')
# Initializes a KMeansMachine
km = KMeansMachine(2, 3)
km.means = means
assert km.shape == (2, 3)
# Sets and gets
assert (km.means == means).all()
assert (km.get_mean(0) == means[0, :]).all()
assert (km.get_mean(1) == means[1, :]).all()
km.set_mean(0, mean)
assert (km.get_mean(0) == mean).all()
# Distance and closest mean
eps = 1e-10
assert equals(km.get_distance_from_mean(mean, 0), 0, eps)
assert equals(km.get_distance_from_mean(mean, 1), 6, eps)
(index, dist) = km.get_closest_mean(mean)
assert index == 0
assert equals(dist, 0, eps)
assert equals(km.get_min_distance(mean), 0, eps)
# Loads and saves
filename = str(tempfile.mkstemp(".hdf5")[1])
km.save(bob.io.base.HDF5File(filename, 'w'))
km_loaded = KMeansMachine(bob.io.base.HDF5File(filename))
assert km == km_loaded
# Resize
km.resize(4, 5)
assert km.shape == (4, 5)
# Copy constructor and comparison operators
km.resize(2, 3)
km2 = KMeansMachine(km)
assert km2 == km
assert (km2 != km) is False
assert km2.is_similar_to(km)
means2 = numpy.array([[3, 70, 0], [4, 72, 2]], 'float64')
km2.means = means2
assert (km2 == km) is False
assert km2 != km
assert (km2.is_similar_to(km)) is False
# Clean-up
os.unlink(filename)
def test_kmeans_noduplicate(): # Data/dimensions dim_c = 2 dim_d = 3 seed = 0 data = numpy.array([[1,2,3],[1,2,3],[1,2,3],[4,5,6.]]) # Defines machine and trainer machine = KMeansMachine(dim_c, dim_d) trainer = KMeansTrainer() rng = bob.core.random.mt19937(seed) trainer.initialization_method = 'RANDOM_NO_DUPLICATE' trainer.initialize(machine, data, rng) # Makes sure that the two initial mean vectors selected are different assert equals(machine.get_mean(0), machine.get_mean(1), 1e-8) == False
def test_kmeans_noduplicate():
# Data/dimensions
dim_c = 2
dim_d = 3
seed = 0
data = numpy.array([[1, 2, 3], [1, 2, 3], [1, 2, 3], [4, 5, 6.]])
# Defines machine and trainer
machine = KMeansMachine(dim_c, dim_d)
trainer = KMeansTrainer()
rng = bob.core.random.mt19937(seed)
trainer.initialization_method = 'RANDOM_NO_DUPLICATE'
trainer.initialize(machine, data, rng)
# Makes sure that the two initial mean vectors selected are different
assert equals(machine.get_mean(0), machine.get_mean(1), 1e-8) == False
def test_kmeans_a():
# Trains a KMeansMachine
# This files contains draws from two 1D Gaussian distributions:
# * 100 samples from N(-10,1)
# * 100 samples from N(10,1)
data = bob.io.base.load(datafile("samplesFrom2G_f64.hdf5", __name__, path="../data/"))
machine = KMeansMachine(2, 1)
trainer = KMeansTrainer()
#trainer.train(machine, data)
bob.learn.em.train(trainer,machine,data)
[variances, weights] = machine.get_variances_and_weights_for_each_cluster(data)
variances_b = numpy.ndarray(shape=(2,1), dtype=numpy.float64)
weights_b = numpy.ndarray(shape=(2,), dtype=numpy.float64)
machine.__get_variances_and_weights_for_each_cluster_init__(variances_b, weights_b)
machine.__get_variances_and_weights_for_each_cluster_acc__(data, variances_b, weights_b)
machine.__get_variances_and_weights_for_each_cluster_fin__(variances_b, weights_b)
m1 = machine.get_mean(0)
m2 = machine.get_mean(1)
## Check means [-10,10] / variances [1,1] / weights [0.5,0.5]
if(m1<m2): means=numpy.array(([m1[0],m2[0]]), 'float64')
else: means=numpy.array(([m2[0],m1[0]]), 'float64')
assert equals(means, numpy.array([-10.,10.]), 2e-1)
assert equals(variances, numpy.array([1.,1.]), 2e-1)
assert equals(weights, numpy.array([0.5,0.5]), 1e-3)
assert equals(variances, variances_b, 1e-8)
assert equals(weights, weights_b, 1e-8)
def test_kmeans_a():
# Trains a KMeansMachine
# This files contains draws from two 1D Gaussian distributions:
# * 100 samples from N(-10,1)
# * 100 samples from N(10,1)
data = bob.io.base.load(datafile("samplesFrom2G_f64.hdf5", __name__, path="../data/"))
machine = KMeansMachine(2, 1)
trainer = KMeansTrainer()
# trainer.train(machine, data)
bob.learn.em.train(trainer, machine, data)
[variances, weights] = machine.get_variances_and_weights_for_each_cluster(data)
variances_b = numpy.ndarray(shape=(2, 1), dtype=numpy.float64)
weights_b = numpy.ndarray(shape=(2,), dtype=numpy.float64)
machine.__get_variances_and_weights_for_each_cluster_init__(variances_b, weights_b)
machine.__get_variances_and_weights_for_each_cluster_acc__(data, variances_b, weights_b)
machine.__get_variances_and_weights_for_each_cluster_fin__(variances_b, weights_b)
m1 = machine.get_mean(0)
m2 = machine.get_mean(1)
## Check means [-10,10] / variances [1,1] / weights [0.5,0.5]
if (m1 < m2):
means = numpy.array(([m1[0], m2[0]]), 'float64')
else:
means = numpy.array(([m2[0], m1[0]]), 'float64')
assert equals(means, numpy.array([-10., 10.]), 2e-1)
assert equals(variances, numpy.array([1., 1.]), 2e-1)
assert equals(weights, numpy.array([0.5, 0.5]), 1e-3)
assert equals(variances, variances_b, 1e-8)
assert equals(weights, weights_b, 1e-8)