def RunGMMShogun(q):
totalTimer = Timer()
try:
# Load input dataset.
Log.Info("Loading dataset", self.verbose)
dataPoints = np.genfromtxt(self.dataset, delimiter=',')
dataFeat = RealFeatures(dataPoints.T)
# Get all the parameters.
g = re.search("-g (\d+)", options)
n = re.search("-n (\d+)", options)
s = re.search("-n (\d+)", options)
g = 1 if not g else int(g.group(1))
n = 250 if not n else int(n.group(1))
# Create the Gaussian Mixture Model.
model = SGMM(g)
model.set_features(dataFeat)
with totalTimer:
model.train_em(1e-9, n, 1e-9)
except Exception as e:
q.put(-1)
return -1
time = totalTimer.ElapsedTime()
q.put(time)
return time
def RunGMMShogun(q):
totalTimer = Timer()
try:
# Load input dataset.
Log.Info("Loading dataset", self.verbose)
dataPoints = np.genfromtxt(self.dataset, delimiter=',')
dataFeat = RealFeatures(dataPoints.T)
# Get all the parameters.
g = re.search("-g (\d+)", options)
n = re.search("-n (\d+)", options)
s = re.search("-n (\d+)", options)
g = 1 if not g else int(g.group(1))
n = 250 if not n else int(n.group(1))
# Create the Gaussian Mixture Model.
model = SGMM(g)
model.set_features(dataFeat)
with totalTimer:
model.train_em(1e-9, n, 1e-9)
except Exception as e:
q.put(-1)
return -1
time = totalTimer.ElapsedTime()
q.put(time)
return time
def RunGMMShogun():
totalTimer = Timer()
try:
# Load input dataset.
Log.Info("Loading dataset", self.verbose)
dataPoints = np.genfromtxt(self.dataset, delimiter=',')
dataFeat = RealFeatures(dataPoints.T)
# Get all the parameters.
if "gaussians" in options:
g = int(options.pop("gaussians"))
else:
Log.Fatal("Required parameter 'gaussians' not specified!")
raise Exception("missing parameter")
if "max_iterations" in options:
n = int(options.pop("max_iterations"))
else:
n = 0
if len(options) > 0:
Log.Fatal("Unknown parameters: " + str(options))
raise Exception("unknown parameters")
# Create the Gaussian Mixture Model.
model = SGMM(g)
model.set_features(dataFeat)
with totalTimer:
model.train_em(1e-9, n, 1e-9)
except Exception as e:
Log.Info("Exception: " + str(e))
return -1
return totalTimer.ElapsedTime()
def RunGMMShogun():
totalTimer = Timer()
try:
# Load input dataset.
Log.Info("Loading dataset", self.verbose)
dataPoints = np.genfromtxt(self.dataset, delimiter=',')
dataFeat = RealFeatures(dataPoints.T)
# Get all the parameters.
if "gaussians" in options:
g = int(options.pop("gaussians"))
else:
Log.Fatal("Required parameter 'gaussians' not specified!")
raise Exception("missing parameter")
if "max_iterations" in options:
n = int(options.pop("max_iterations"))
else:
n = 0
if len(options) > 0:
Log.Fatal("Unknown parameters: " + str(options))
raise Exception("unknown parameters")
# Create the Gaussian Mixture Model.
model = SGMM(g)
model.set_features(dataFeat)
with totalTimer:
model.train_em(1e-9, n, 1e-9)
except Exception as e:
Log.Info("Exception: " + str(e))
return -1
return totalTimer.ElapsedTime()
def fit_gmm(self, samples):
"""
Runs a couple of em instances on random starting points and returns
internal GMM representation of best instance
"""
features = RealFeatures(samples.T)
gmms = []
log_likelihoods = zeros(self.num_runs_em)
for i in range(self.num_runs_em):
# set up Shogun's GMM class and run em (corresponds to random
# initialisation)
gmm = GMM(self.num_components)
gmm.set_features(features)
log_likelihoods[i] = gmm.train_em()
gmms.append(gmm)
max_idx = log_likelihoods.argmax()
# construct Gaussian mixture components in internal representation
components = []
for i in range(self.num_components):
mu = gmms[max_idx].get_nth_mean(i)
Sigma = gmms[max_idx].get_nth_cov(i)
components.append(Gaussian(mu, Sigma))
# construct a Gaussian mixture model based on the best EM run
pie = gmms[max_idx].get_coef()
proposal = MixtureDistribution(components[0].dimension,
self.num_components, components,
Discrete(pie))
return proposal
def fit_gmm(self, samples):
"""
Runs a couple of em instances on random starting points and returns
internal GMM representation of best instance
"""
features = RealFeatures(samples.T)
gmms = []
log_likelihoods = zeros(self.num_runs_em)
for i in range(self.num_runs_em):
# set up Shogun's GMM class and run em (corresponds to random
# initialisation)
gmm = GMM(self.num_components)
gmm.set_features(features)
log_likelihoods[i] = gmm.train_em()
gmms.append(gmm)
max_idx = log_likelihoods.argmax()
# construct Gaussian mixture components in internal representation
components = []
for i in range(self.num_components):
mu = gmms[max_idx].get_nth_mean(i)
Sigma = gmms[max_idx].get_nth_cov(i)
components.append(Gaussian(mu, Sigma))
# construct a Gaussian mixture model based on the best EM run
pie = gmms[max_idx].get_coef()
proposal = MixtureDistribution(components[0].dimension,
self.num_components, components,
Discrete(pie))
return proposal
real_gmm.set_nth_cov(array([[0.1]]), 1)
real_gmm.set_nth_cov(array([[0.2]]), 2)
real_gmm.set_coef(array([0.3, 0.5, 0.2]))
#generate training set from real GMM
generated=array([real_gmm.sample()])
for i in range(199):
generated=append(generated, array([real_gmm.sample()]), axis=1)
feat_train=RealFeatures(generated)
#train GMM using EM
est_gmm=GMM(3)
est_gmm.train(feat_train)
est_gmm.train_em(min_cov, max_iter, min_change)
#get and print estimated means and covariances
est_mean1=est_gmm.get_nth_mean(0)
est_mean2=est_gmm.get_nth_mean(1)
est_mean3=est_gmm.get_nth_mean(2)
est_cov1=est_gmm.get_nth_cov(0)
est_cov2=est_gmm.get_nth_cov(1)
est_cov3=est_gmm.get_nth_cov(2)
est_coef=est_gmm.get_coef()
print est_mean1
print est_cov1
print est_mean2
print est_cov2
print est_mean3
print est_cov3
#train GMM using EM and bad initial conditions and print log-likelihood
est_em_gmm = GMM(3, cov_type)
est_em_gmm.train(feat_train)
est_em_gmm.set_nth_mean(array([2.0, 0.0]), 0)
est_em_gmm.set_nth_mean(array([-2.0, -2.0]), 1)
est_em_gmm.set_nth_mean(array([-3.0, -3.0]), 2)
est_em_gmm.set_nth_cov(array([[1.0, 0.0], [0.0, 1.0]]), 0)
est_em_gmm.set_nth_cov(array([[1.0, 0.0], [0.0, 1.0]]), 1)
est_em_gmm.set_nth_cov(array([[1.0, 0.0], [0.0, 1.0]]), 2)
est_em_gmm.set_coef(array([0.3333, 0.3333, 0.3334]))
print est_em_gmm.train_em(min_cov, max_em_iter, min_change)
#plot real GMM, data and both estimated GMMs
min_x_gen = min(min(generated[[0]])) - 0.1
max_x_gen = max(max(generated[[0]])) + 0.1
min_y_gen = min(min(generated[[1]])) - 0.1
max_y_gen = max(max(generated[[1]])) + 0.1
plot_real = empty(0)
plot_est_smem = empty(0)
plot_est_em = empty(0)
for i in arange(min_x_gen, max_x_gen, 0.05):
for j in arange(min_y_gen, max_y_gen, 0.05):
plot_real = append(plot_real,
array([exp(real_gmm.cluster(array([i, j]))[3])]))
#train GMM using EM and bad initial conditions and print log-likelihood
est_em_gmm=GMM(3, cov_type)
est_em_gmm.train(feat_train)
est_em_gmm.set_nth_mean(array([2.0, 0.0]), 0)
est_em_gmm.set_nth_mean(array([-2.0, -2.0]), 1)
est_em_gmm.set_nth_mean(array([-3.0, -3.0]), 2)
est_em_gmm.set_nth_cov(array([[1.0, 0.0],[0.0, 1.0]]), 0)
est_em_gmm.set_nth_cov(array([[1.0, 0.0],[0.0, 1.0]]), 1)
est_em_gmm.set_nth_cov(array([[1.0, 0.0],[0.0, 1.0]]), 2)
est_em_gmm.set_coef(array([0.3333, 0.3333, 0.3334]))
print est_em_gmm.train_em(min_cov, max_em_iter, min_change)
#plot real GMM, data and both estimated GMMs
min_x_gen=min(min(generated[[0]]))-0.1
max_x_gen=max(max(generated[[0]]))+0.1
min_y_gen=min(min(generated[[1]]))-0.1
max_y_gen=max(max(generated[[1]]))+0.1
plot_real=empty(0)
plot_est_smem=empty(0)
plot_est_em=empty(0)
for i in arange(min_x_gen, max_x_gen, 0.05):
for j in arange(min_y_gen, max_y_gen, 0.05):
plot_real=append(plot_real, array([exp(real_gmm.cluster(array([i, j]))[3])]))
plot_est_smem=append(plot_est_smem, array([exp(est_smem_gmm.cluster(array([i, j]))[3])]))
real_gmm.set_nth_cov(array([[0.1]]), 1)
real_gmm.set_nth_cov(array([[0.2]]), 2)
real_gmm.set_coef(array([0.3, 0.5, 0.2]))
#generate training set from real GMM
generated = array([real_gmm.sample()])
for i in range(199):
generated = append(generated, array([real_gmm.sample()]), axis=1)
feat_train = RealFeatures(generated)
#train GMM using EM
est_gmm = GMM(3)
est_gmm.train(feat_train)
est_gmm.train_em(min_cov, max_iter, min_change)
#get and print estimated means and covariances
est_mean1 = est_gmm.get_nth_mean(0)
est_mean2 = est_gmm.get_nth_mean(1)
est_mean3 = est_gmm.get_nth_mean(2)
est_cov1 = est_gmm.get_nth_cov(0)
est_cov2 = est_gmm.get_nth_cov(1)
est_cov3 = est_gmm.get_nth_cov(2)
est_coef = est_gmm.get_coef()
print est_mean1
print est_cov1
print est_mean2
print est_cov2
print est_mean3
print est_cov3
