def test_chain_bernoulli(self):
# runs the sampler on a distribution of infdependent bernoulli variables
# and compares the mean
d = 5
ps = rand(d)
ps /= norm(ps)
distribution = Bernoulli(ps)
num_history = 100
Z = distribution.sample(num_history).samples
threshold = 0.8
spread = 0.2
gamma = 0.2
kernel = HypercubeKernel(gamma)
mcmc_sampler = DiscreteKameleon(distribution, kernel, Z, threshold,
spread)
start = zeros(distribution.dimension, dtype=numpy.bool8)
mcmc_params = MCMCParams(start=start, num_iterations=1000)
chain = MCMCChain(mcmc_sampler, mcmc_params)
chain.run()
self.assertAlmostEqual(norm(mean(chain.samples, 0) - ps), 0, delta=0.2)
def sample_gibbs(distribution, num_samples=1000):
mcmc_sampler = Gibbs(distribution)
current_state = [rand() < 0.5 for _ in range(distribution.dimension)]
mcmc_params = MCMCParams(start=asarray(current_state, dtype=numpy.bool8), num_iterations=num_samples)
chain = MCMCChain(mcmc_sampler, mcmc_params)
chain.run()
return chain.samples
def run_sm_chain(hopfield, start, num_iterations):
current_state = [x for x in start]
spread = 0.03
sampler = StandardMetropolisDiscrete(hopfield, spread)
params = MCMCParams(start=asarray(current_state, dtype=numpy.bool8), num_iterations=num_iterations)
chain = MCMCChain(sampler, params)
chain.append_mcmc_output(StatisticsOutput(plot_times=True, lag=1000))
chain.run()
return chain
def run_kameleon_chain(Z, hopfield, start, num_iterations):
threshold = 0.8
spread = 0.03
gamma = 0.2
kernel = HypercubeKernel(gamma)
sampler = DiscreteKameleon(hopfield, kernel, Z, threshold, spread)
params = MCMCParams(start=start, num_iterations=num_iterations)
chain = MCMCChain(sampler, params)
chain.run()
return chain
def run_kameleon_chain(Z, hopfield, start, num_iterations):
threshold = 0.8
spread = 0.03
gamma = 0.2
kernel = HypercubeKernel(gamma)
sampler = DiscreteKameleon(hopfield, kernel, Z, threshold, spread)
params = MCMCParams(start=start, num_iterations=num_iterations)
chain = MCMCChain(sampler, params)
chain.run()
return chain
def run_gibbs_chain(hopfield, start, num_iterations):
d = hopfield.dimension
current_state = [x for x in start]
distribution = HopfieldFullConditionals(full_target=hopfield,
current_state=current_state)
sampler = Gibbs(distribution)
params = MCMCParams(start=asarray(current_state, dtype=numpy.bool8), num_iterations=num_iterations * d)
chain = MCMCChain(sampler, params)
chain.append_mcmc_output(StatisticsOutput(plot_times=True, lag=1000))
chain.run()
return chain
def main():
distribution = Banana()
# distribution = Flower(amplitude=6, frequency=6, variance=1, radius=10, dimension=8)
# Visualise.visualise_distribution(distribution)
show()
#
sigma = 5
print "using sigma", sigma
kernel = GaussianKernel(sigma=sigma)
mcmc_sampler = KameleonWindowLearnScale(distribution,
kernel,
stop_adapt=inf)
start = asarray([0, -5.])
mcmc_params = MCMCParams(start=start, num_iterations=30000)
chain = MCMCChain(mcmc_sampler, mcmc_params)
chain.append_mcmc_output(
PlottingOutput(distribution,
plot_from=3000,
colour_by_likelihood=False,
num_samples_plot=0))
chain.append_mcmc_output(StatisticsOutput(plot_times=False))
chain.run()
print distribution.emp_quantiles(chain.samples[10000:])
def main():
Log.set_loglevel(logging.DEBUG)
prior = Gaussian(Sigma=eye(2) * 100)
posterior = OzonePosterior(prior,
logdet_alg="scikits",
solve_method="scikits")
proposal_cov = diag([4.000000000000000e-05, 1.072091680000000e+02])
mcmc_sampler = StandardMetropolis(posterior, scale=1.0, cov=proposal_cov)
start = asarray([-11.35, -13.1])
mcmc_params = MCMCParams(start=start, num_iterations=5000)
chain = MCMCChain(mcmc_sampler, mcmc_params)
chain.append_mcmc_output(StatisticsOutput(print_from=1, lag=1))
home = expanduser("~")
folder = os.sep.join([home, "sample_ozone_posterior_average_serial"])
store_chain_output = StoreChainOutput(folder)
chain.append_mcmc_output(store_chain_output)
loaded = store_chain_output.load_last_stored_chain()
if loaded is None:
logging.info("Running chain from scratch")
else:
logging.info("Running chain from iteration %d" % loaded.iteration)
chain = loaded
chain.run()
f = open(folder + os.sep + "final_chain", "w")
dump(chain, f)
f.close()
def main():
d = 5
ps = rand(d)
ps /= norm(ps)
distribution = Bernoulli(ps)
num_history = 100
Z = distribution.sample(num_history).samples
threshold = 0.8
spread = 0.2
gamma = 0.2
kernel = HypercubeKernel(gamma)
mcmc_sampler = DiscreteKameleon(distribution, kernel, Z, threshold, spread)
start = zeros(distribution.dimension, dtype=numpy.bool8)
mcmc_params = MCMCParams(start=start, num_iterations=1000)
chain = MCMCChain(mcmc_sampler, mcmc_params)
chain.append_mcmc_output(StatisticsOutput(plot_times=True))
chain.append_mcmc_output(DiscretePlottingOutput(plot_from=0, lag=100))
chain.run()
print "ps", ps
print "empirical", mean(chain.samples, 0)
def main():
# covariance has stretched Eigenvalues, and rotated basis
Sigma = eye(2)
Sigma[0, 0] = 30
Sigma[1, 1] = 1
theta = -pi / 4
U = MatrixTools.rotation_matrix(theta)
Sigma = U.T.dot(Sigma).dot(U)
gaussian = Gaussian(Sigma=Sigma)
distribution = GaussianFullConditionals(gaussian, [0., 0.])
mcmc_sampler = Gibbs(distribution)
start = zeros(distribution.dimension)
mcmc_params = MCMCParams(start=start, num_iterations=20000)
chain = MCMCChain(mcmc_sampler, mcmc_params)
chain.append_mcmc_output(StatisticsOutput(plot_times=True, lag=100))
chain.append_mcmc_output(
PlottingOutput(distribution=gaussian,
plot_from=1,
colour_by_likelihood=False,
num_samples_plot=0,
lag=100))
chain.run()
def main():
# define the MCMC target distribution
# possible distributions are in kameleon_mcmc.distribution: Banana, Flower, Ring
# distribution = Banana(dimension=2, bananicity=0.03, V=100.0)
distribution = Ring()
# create instance of kameleon sampler that learns the length scale
# can be replaced by any other sampler in kameleon_mcmc.mcmc.samplers
kernel = GaussianKernel(sigma=5)
mcmc_sampler = KameleonWindowLearnScale(distribution, kernel, stop_adapt=inf, nu2=0.05)
# mcmc chain and its parameters
start = asarray([0,-3])
mcmc_params = MCMCParams(start=start, num_iterations=30000)
chain = MCMCChain(mcmc_sampler, mcmc_params)
# plot every iteration and print some statistics
chain.append_mcmc_output(PlottingOutput(distribution, plot_from=2000))
chain.append_mcmc_output(StatisticsOutput())
# run cmcm
chain.run()
# print empirical quantiles
burnin=10000
print distribution.emp_quantiles(chain.samples[burnin:])
Visualise.visualise_distribution(distribution, chain.samples)
def main():
d = 5
b = randn(d)
V = randn(d, d)
W = V + V.T
fill_diagonal(W, zeros(d))
hopfield = Hopfield(W, b)
current_state = [rand() < 0.5 for _ in range(d)]
distribution = HopfieldFullConditionals(full_target=hopfield,
current_state=current_state)
print("Running Gibbs to produce chain history")
Z = sample_gibbs(distribution, num_samples=2000)[1500:].astype(numpy.bool8)
inds = permutation(len(Z))
Z = Z[inds[:500]]
print("done")
threshold = 0.8
spread = 0.2
gamma = 0.2
kernel = HypercubeKernel(gamma)
mcmc_sampler = DiscreteKameleon(hopfield, kernel, Z, threshold, spread)
start = zeros(distribution.dimension, dtype=numpy.bool8)
mcmc_params = MCMCParams(start=start, num_iterations=10000)
chain = MCMCChain(mcmc_sampler, mcmc_params)
chain.append_mcmc_output(StatisticsOutput(plot_times=True))
chain.append_mcmc_output(DiscretePlottingOutput(plot_from=0, lag=500))
chain.run()
def main():
distribution = Banana(dimension=8)
sigma=5
print "using sigma", sigma
kernel = GaussianKernel(sigma=sigma)
mcmc_sampler = Kameleon(distribution, kernel, distribution.sample(100).samples)
start = zeros(distribution.dimension)
mcmc_params = MCMCParams(start=start, num_iterations=20000)
chain = MCMCChain(mcmc_sampler, mcmc_params)
chain.append_mcmc_output(StatisticsOutput(plot_times=True))
chain.run()
def main():
Log.set_loglevel(logging.DEBUG)
prior = Gaussian(Sigma=eye(2) * 100)
num_estimates = 1000
home = expanduser("~")
folder = os.sep.join([home, "sample_ozone_posterior_rr_sge"])
# cluster admin set project jump for me to exclusively allocate nodes
parameter_prefix = "" # #$ -P jump"
cluster_parameters = BatchClusterParameters(
foldername=folder,
memory=7.8,
loglevel=logging.DEBUG,
parameter_prefix=parameter_prefix,
max_walltime=60 * 60 * 24 - 1)
computation_engine = SGEComputationEngine(cluster_parameters,
check_interval=10)
rr_instance = RussianRoulette(1e-3, block_size=400)
posterior = OzonePosteriorRREngine(rr_instance=rr_instance,
computation_engine=computation_engine,
num_estimates=num_estimates,
prior=prior)
posterior.logdet_method = "shogun_estimate"
proposal_cov = diag([4.000000000000000e-05, 1.072091680000000e+02])
mcmc_sampler = StandardMetropolis(posterior, scale=1.0, cov=proposal_cov)
start = asarray([-11.55, -10.1])
mcmc_params = MCMCParams(start=start, num_iterations=5000)
chain = MCMCChain(mcmc_sampler, mcmc_params)
# chain.append_mcmc_output(PlottingOutput(None, plot_from=1, lag=1))
chain.append_mcmc_output(StatisticsOutput(print_from=1, lag=1))
store_chain_output = StoreChainOutput(folder, lag=1)
chain.append_mcmc_output(store_chain_output)
loaded = store_chain_output.load_last_stored_chain()
if loaded is None:
logging.info("Running chain from scratch")
else:
logging.info("Running chain from iteration %d" % loaded.iteration)
chain = loaded
chain.run()
f = open(folder + os.sep + "final_chain", "w")
dump(chain, f)
f.close()
def all_tests(gaussian1,gaussian2,n=200):
oracle_samples1 = gaussian1.sample(n=n).samples
oracle_samples2 = gaussian2.sample(n=n).samples
distribution1 = GaussianFullConditionals(gaussian1, list(gaussian1.mu))
distribution2 = GaussianFullConditionals(gaussian2, list(gaussian2.mu))
mcmc_sampler1 = Gibbs(distribution1)
mcmc_sampler2 = Gibbs(distribution2)
start = zeros(2)
mcmc_params = MCMCParams(start=start, num_iterations=2000+n, burnin=2000)
chain1 = MCMCChain(mcmc_sampler1, mcmc_params)
chain1.run()
gibbs_samples1 = chain1.get_samples_after_burnin()
chain2 = MCMCChain(mcmc_sampler2, mcmc_params)
chain2.run()
gibbs_samples2 = chain2.get_samples_after_burnin()
sigma = GaussianKernel.get_sigma_median_heuristic(concatenate((oracle_samples1,oracle_samples2),axis=0))
kernel = GaussianKernel(sigma=sigma)
vanillap=empty((2,2))
blockp=empty((2,2))
wildp=empty((2,2))
vanillap[0,0]=kernel.TwoSampleTest(oracle_samples1,oracle_samples2,method='vanilla')
vanillap[0,1]=kernel.TwoSampleTest(oracle_samples1,gibbs_samples2,method='vanilla')
vanillap[1,0]=kernel.TwoSampleTest(gibbs_samples1,oracle_samples2,method='vanilla')
vanillap[1,1]=kernel.TwoSampleTest(gibbs_samples1,gibbs_samples2,method='vanilla')
blockp[0,0]=kernel.TwoSampleTest(oracle_samples1,oracle_samples2,method='block')
blockp[0,1]=kernel.TwoSampleTest(oracle_samples1,gibbs_samples2,method='block')
blockp[1,0]=kernel.TwoSampleTest(gibbs_samples1,oracle_samples2,method='block')
blockp[1,1]=kernel.TwoSampleTest(gibbs_samples1,gibbs_samples2,method='block')
wildp[0,0]=kernel.TwoSampleTest(oracle_samples1,oracle_samples2,method='wild')
wildp[0,1]=kernel.TwoSampleTest(oracle_samples1,gibbs_samples2,method='wild')
wildp[1,0]=kernel.TwoSampleTest(gibbs_samples1,oracle_samples2,method='wild')
wildp[1,1]=kernel.TwoSampleTest(gibbs_samples1,gibbs_samples2,method='wild')
return vanillap,blockp,wildp
def main():
d = 5
ps = rand(d)
ps /= norm(ps)
distribution = Bernoulli(ps)
num_history = 100
Z = distribution.sample(num_history).samples
threshold = 0.8
spread = 0.2
gamma = 0.2
kernel = HypercubeKernel(gamma)
mcmc_sampler = DiscreteKameleon(distribution, kernel, Z, threshold, spread)
start = zeros(distribution.dimension, dtype=numpy.bool8)
mcmc_params = MCMCParams(start=start, num_iterations=1000)
chain = MCMCChain(mcmc_sampler, mcmc_params)
chain.append_mcmc_output(StatisticsOutput(plot_times=True))
chain.append_mcmc_output(DiscretePlottingOutput(plot_from=0, lag=100))
chain.run()
print "ps", ps
print "empirical", mean(chain.samples, 0)
def main():
Log.set_loglevel(logging.DEBUG)
modulename = "sample_ozone_posterior_average_slurm"
if not FileSystem.cmd_exists("sbatch"):
engine = SerialComputationEngine()
else:
johns_slurm_hack = "#SBATCH --partition=intel-ivy,wrkstn,compute"
johns_slurm_hack = "#SBATCH --partition=intel-ivy,compute"
folder = os.sep + os.sep.join(["nfs", "data3", "ucabhst", modulename])
batch_parameters = BatchClusterParameters(
foldername=folder,
max_walltime=24 * 60 * 60,
resubmit_on_timeout=False,
memory=3,
parameter_prefix=johns_slurm_hack)
engine = SlurmComputationEngine(batch_parameters,
check_interval=1,
do_clean_up=True)
prior = Gaussian(Sigma=eye(2) * 100)
num_estimates = 100
posterior = OzonePosteriorAverageEngine(computation_engine=engine,
num_estimates=num_estimates,
prior=prior)
posterior.logdet_method = "shogun_estimate"
proposal_cov = diag([4.000000000000000e-05, 1.072091680000000e+02])
mcmc_sampler = StandardMetropolis(posterior, scale=1.0, cov=proposal_cov)
start = asarray([-11.35, -13.1])
mcmc_params = MCMCParams(start=start, num_iterations=2000)
chain = MCMCChain(mcmc_sampler, mcmc_params)
chain.append_mcmc_output(StatisticsOutput(print_from=1, lag=1))
home = expanduser("~")
folder = os.sep.join([home, modulename])
store_chain_output = StoreChainOutput(folder)
chain.append_mcmc_output(store_chain_output)
loaded = store_chain_output.load_last_stored_chain()
if loaded is None:
logging.info("Running chain from scratch")
else:
logging.info("Running chain from iteration %d" % loaded.iteration)
chain = loaded
chain.run()
f = open(folder + os.sep + "final_chain", "w")
dump(chain, f)
f.close()
def main():
Log.set_loglevel(logging.DEBUG)
prior = Gaussian(Sigma=eye(2) * 100)
posterior = OzonePosterior(prior, logdet_alg="scikits",
solve_method="scikits")
proposal_cov = diag([ 4.000000000000000e-05, 1.072091680000000e+02])
mcmc_sampler = StandardMetropolis(posterior, scale=1.0, cov=proposal_cov)
start = asarray([-11.35, -13.1])
mcmc_params = MCMCParams(start=start, num_iterations=5000)
chain = MCMCChain(mcmc_sampler, mcmc_params)
chain.append_mcmc_output(StatisticsOutput(print_from=1, lag=1))
home = expanduser("~")
folder = os.sep.join([home, "sample_ozone_posterior_average_serial"])
store_chain_output = StoreChainOutput(folder)
chain.append_mcmc_output(store_chain_output)
loaded = store_chain_output.load_last_stored_chain()
if loaded is None:
logging.info("Running chain from scratch")
else:
logging.info("Running chain from iteration %d" % loaded.iteration)
chain = loaded
chain.run()
f = open(folder + os.sep + "final_chain", "w")
dump(chain, f)
f.close()
def main():
distribution = Banana(dimension=8, bananicity=0.1, V=100.0)
sigma = 5
print "using sigma", sigma
kernel = GaussianKernel(sigma=sigma)
mcmc_sampler = KameleonWindow(distribution, kernel)
start = zeros(distribution.dimension)
mcmc_params = MCMCParams(start=start, num_iterations=80000)
chain = MCMCChain(mcmc_sampler, mcmc_params)
# chain.append_mcmc_output(PlottingOutput(distribution, plot_from=3000))
chain.append_mcmc_output(StatisticsOutput(plot_times=True))
chain.run()
print distribution.emp_quantiles(chain.samples)
def main():
distribution = Banana(dimension=2, bananicity=0.03, V=100.0)
mcmc_sampler = StandardMetropolis(distribution)
start=zeros(distribution.dimension)
start=asarray([0.,-2.])
mcmc_params = MCMCParams(start=start, num_iterations=10000)
chain = MCMCChain(mcmc_sampler, mcmc_params)
chain.append_mcmc_output(StatisticsOutput(plot_times=True, lag=1000))
# chain.append_mcmc_output(PlottingOutput(distribution, plot_from=1, num_samples_plot=0,
# colour_by_likelihood=False))
chain.run()
f=open("std_metropolis_chain_gaussian.bin", 'w')
dump(chain, f)
f.close()
def main():
Log.set_loglevel(logging.DEBUG)
prior = Gaussian(Sigma=eye(2) * 100)
num_estimates = 1000
home = expanduser("~")
folder = os.sep.join([home, "sample_ozone_posterior_rr_sge"])
# cluster admin set project jump for me to exclusively allocate nodes
parameter_prefix = "" # #$ -P jump"
cluster_parameters = BatchClusterParameters(foldername=folder,
memory=7.8,
loglevel=logging.DEBUG,
parameter_prefix=parameter_prefix,
max_walltime=60 * 60 * 24 - 1)
computation_engine = SGEComputationEngine(cluster_parameters, check_interval=10)
rr_instance = RussianRoulette(1e-3, block_size=400)
posterior = OzonePosteriorRREngine(rr_instance=rr_instance,
computation_engine=computation_engine,
num_estimates=num_estimates,
prior=prior)
posterior.logdet_method = "shogun_estimate"
proposal_cov = diag([ 4.000000000000000e-05, 1.072091680000000e+02])
mcmc_sampler = StandardMetropolis(posterior, scale=1.0, cov=proposal_cov)
start = asarray([-11.55, -10.1])
mcmc_params = MCMCParams(start=start, num_iterations=5000)
chain = MCMCChain(mcmc_sampler, mcmc_params)
# chain.append_mcmc_output(PlottingOutput(None, plot_from=1, lag=1))
chain.append_mcmc_output(StatisticsOutput(print_from=1, lag=1))
store_chain_output = StoreChainOutput(folder, lag=1)
chain.append_mcmc_output(store_chain_output)
loaded = store_chain_output.load_last_stored_chain()
if loaded is None:
logging.info("Running chain from scratch")
else:
logging.info("Running chain from iteration %d" % loaded.iteration)
chain = loaded
chain.run()
f = open(folder + os.sep + "final_chain", "w")
dump(chain, f)
f.close()
def main():
Log.set_loglevel(logging.DEBUG)
modulename = "sample_ozone_posterior_average_slurm"
if not FileSystem.cmd_exists("sbatch"):
engine = SerialComputationEngine()
else:
johns_slurm_hack = "#SBATCH --partition=intel-ivy,wrkstn,compute"
johns_slurm_hack = "#SBATCH --partition=intel-ivy,compute"
folder = os.sep + os.sep.join(["nfs", "data3", "ucabhst", modulename])
batch_parameters = BatchClusterParameters(foldername=folder, max_walltime=24 * 60 * 60,
resubmit_on_timeout=False, memory=3,
parameter_prefix=johns_slurm_hack)
engine = SlurmComputationEngine(batch_parameters, check_interval=1,
do_clean_up=True)
prior = Gaussian(Sigma=eye(2) * 100)
num_estimates = 100
posterior = OzonePosteriorAverageEngine(computation_engine=engine,
num_estimates=num_estimates,
prior=prior)
posterior.logdet_method = "shogun_estimate"
proposal_cov = diag([ 4.000000000000000e-05, 1.072091680000000e+02])
mcmc_sampler = StandardMetropolis(posterior, scale=1.0, cov=proposal_cov)
start = asarray([-11.35, -13.1])
mcmc_params = MCMCParams(start=start, num_iterations=2000)
chain = MCMCChain(mcmc_sampler, mcmc_params)
chain.append_mcmc_output(StatisticsOutput(print_from=1, lag=1))
home = expanduser("~")
folder = os.sep.join([home, modulename])
store_chain_output = StoreChainOutput(folder)
chain.append_mcmc_output(store_chain_output)
loaded = store_chain_output.load_last_stored_chain()
if loaded is None:
logging.info("Running chain from scratch")
else:
logging.info("Running chain from iteration %d" % loaded.iteration)
chain = loaded
chain.run()
f = open(folder + os.sep + "final_chain", "w")
dump(chain, f)
f.close()
def test_chain_bernoulli(self):
# runs the sampler on a distribution of infdependent bernoulli variables
# and compares the mean
d = 5
ps = rand(d)
ps /= norm(ps)
distribution = Bernoulli(ps)
num_history = 100
Z = distribution.sample(num_history).samples
threshold = 0.8
spread = 0.2
gamma = 0.2
kernel = HypercubeKernel(gamma)
mcmc_sampler = DiscreteKameleon(distribution, kernel, Z, threshold, spread)
start = zeros(distribution.dimension, dtype=numpy.bool8)
mcmc_params = MCMCParams(start=start, num_iterations=1000)
chain = MCMCChain(mcmc_sampler, mcmc_params)
chain.run()
self.assertAlmostEqual(norm(mean(chain.samples, 0) - ps), 0, delta=0.2)
def main():
Log.set_loglevel(logging.DEBUG)
prior = Gaussian(Sigma=eye(2) * 100)
num_estimates = 2
home = expanduser("~")
folder = os.sep.join([home, "sample_ozone_posterior_rr_sge"])
computation_engine = SerialComputationEngine()
rr_instance = RussianRoulette(1e-3, block_size=10)
posterior = OzonePosteriorRREngine(rr_instance=rr_instance,
computation_engine=computation_engine,
num_estimates=num_estimates,
prior=prior)
posterior.logdet_method = "shogun_estimate"
proposal_cov = diag([4.000000000000000e-05, 1.072091680000000e+02])
mcmc_sampler = StandardMetropolis(posterior, scale=1.0, cov=proposal_cov)
start = asarray([-11.35, -13.1])
mcmc_params = MCMCParams(start=start, num_iterations=200)
chain = MCMCChain(mcmc_sampler, mcmc_params)
# chain.append_mcmc_output(PlottingOutput(None, plot_from=1, lag=1))
chain.append_mcmc_output(StatisticsOutput(print_from=1, lag=1))
store_chain_output = StoreChainOutput(folder, lag=50)
chain.append_mcmc_output(store_chain_output)
loaded = store_chain_output.load_last_stored_chain()
if loaded is None:
logging.info("Running chain from scratch")
else:
logging.info("Running chain from iteration %d" % loaded.iteration)
chain = loaded
chain.run()
f = open(folder + os.sep + "final_chain", "w")
dump(chain, f)
f.close()
def run_sm_chain(hopfield, start, num_iterations):
current_state = [x for x in start]
spread = 0.03
sampler = StandardMetropolisDiscrete(hopfield, spread)
params = MCMCParams(start=asarray(current_state, dtype=numpy.bool8),
num_iterations=num_iterations)
chain = MCMCChain(sampler, params)
chain.append_mcmc_output(StatisticsOutput(plot_times=True, lag=1000))
chain.run()
return chain
def all_tests(gaussian1, gaussian2, n=200):
oracle_samples1 = gaussian1.sample(n=n).samples
oracle_samples2 = gaussian2.sample(n=n).samples
distribution1 = GaussianFullConditionals(gaussian1, list(gaussian1.mu))
distribution2 = GaussianFullConditionals(gaussian2, list(gaussian2.mu))
mcmc_sampler1 = Gibbs(distribution1)
mcmc_sampler2 = Gibbs(distribution2)
start = zeros(2)
mcmc_params = MCMCParams(start=start, num_iterations=2000 + n, burnin=2000)
chain1 = MCMCChain(mcmc_sampler1, mcmc_params)
chain1.run()
gibbs_samples1 = chain1.get_samples_after_burnin()
chain2 = MCMCChain(mcmc_sampler2, mcmc_params)
chain2.run()
gibbs_samples2 = chain2.get_samples_after_burnin()
sigma = GaussianKernel.get_sigma_median_heuristic(concatenate((oracle_samples1, oracle_samples2), axis=0))
kernel = GaussianKernel(sigma=sigma)
vanillap = empty((2, 2))
blockp = empty((2, 2))
wildp = empty((2, 2))
vanillap[0, 0] = kernel.TwoSampleTest(oracle_samples1, oracle_samples2, method="vanilla")
vanillap[0, 1] = kernel.TwoSampleTest(oracle_samples1, gibbs_samples2, method="vanilla")
vanillap[1, 0] = kernel.TwoSampleTest(gibbs_samples1, oracle_samples2, method="vanilla")
vanillap[1, 1] = kernel.TwoSampleTest(gibbs_samples1, gibbs_samples2, method="vanilla")
blockp[0, 0] = kernel.TwoSampleTest(oracle_samples1, oracle_samples2, method="block")
blockp[0, 1] = kernel.TwoSampleTest(oracle_samples1, gibbs_samples2, method="block")
blockp[1, 0] = kernel.TwoSampleTest(gibbs_samples1, oracle_samples2, method="block")
blockp[1, 1] = kernel.TwoSampleTest(gibbs_samples1, gibbs_samples2, method="block")
wildp[0, 0] = kernel.TwoSampleTest(oracle_samples1, oracle_samples2, method="wild")
wildp[0, 1] = kernel.TwoSampleTest(oracle_samples1, gibbs_samples2, method="wild")
wildp[1, 0] = kernel.TwoSampleTest(gibbs_samples1, oracle_samples2, method="wild")
wildp[1, 1] = kernel.TwoSampleTest(gibbs_samples1, gibbs_samples2, method="wild")
return vanillap, blockp, wildp
def run_gibbs_chain(hopfield, start, num_iterations):
d = hopfield.dimension
current_state = [x for x in start]
distribution = HopfieldFullConditionals(full_target=hopfield,
current_state=current_state)
sampler = Gibbs(distribution)
params = MCMCParams(start=asarray(current_state, dtype=numpy.bool8),
num_iterations=num_iterations * d)
chain = MCMCChain(sampler, params)
chain.append_mcmc_output(StatisticsOutput(plot_times=True, lag=1000))
chain.run()
return chain
def main():
d = 5
b = randn(d)
V = randn(d, d)
W = V + V.T
fill_diagonal(W, zeros(d))
hopfield = Hopfield(W, b)
current_state = [rand() < 0.5 for _ in range(d)]
distribution = HopfieldFullConditionals(full_target=hopfield,
current_state=current_state)
mcmc_sampler = Gibbs(distribution)
mcmc_params = MCMCParams(start=asarray(current_state, dtype=numpy.bool8),
num_iterations=10000)
chain = MCMCChain(mcmc_sampler, mcmc_params)
chain.append_mcmc_output(StatisticsOutput(plot_times=True, lag=100))
chain.append_mcmc_output(DiscretePlottingOutput(plot_from=0, lag=100))
chain.run()
def main():
d = 5
ps = rand(d)
ps /= norm(ps)
print "ps", ps
full_target = Bernoulli(ps)
current_state = [0. for _ in range(d)]
distribution = BernoulliFullConditionals(full_target, current_state)
mcmc_sampler = Gibbs(distribution)
mcmc_params = MCMCParams(start=asarray(current_state, dtype=numpy.bool8),
num_iterations=10000)
chain = MCMCChain(mcmc_sampler, mcmc_params)
chain.append_mcmc_output(StatisticsOutput(plot_times=True, lag=1000))
chain.append_mcmc_output(DiscretePlottingOutput(plot_from=0, lag=1000))
chain.run()
print "marginals:", ps
print "estimated:", mean(chain.samples, 0)
def main():
Log.set_loglevel(logging.DEBUG)
prior = Gaussian(Sigma=eye(2) * 100)
num_estimates = 2
home = expanduser("~")
folder = os.sep.join([home, "sample_ozone_posterior_rr_sge"])
computation_engine = SerialComputationEngine()
rr_instance = RussianRoulette(1e-3, block_size=10)
posterior = OzonePosteriorRREngine(
rr_instance=rr_instance, computation_engine=computation_engine, num_estimates=num_estimates, prior=prior
)
posterior.logdet_method = "shogun_estimate"
proposal_cov = diag([4.000000000000000e-05, 1.072091680000000e02])
mcmc_sampler = StandardMetropolis(posterior, scale=1.0, cov=proposal_cov)
start = asarray([-11.35, -13.1])
mcmc_params = MCMCParams(start=start, num_iterations=200)
chain = MCMCChain(mcmc_sampler, mcmc_params)
# chain.append_mcmc_output(PlottingOutput(None, plot_from=1, lag=1))
chain.append_mcmc_output(StatisticsOutput(print_from=1, lag=1))
store_chain_output = StoreChainOutput(folder, lag=50)
chain.append_mcmc_output(store_chain_output)
loaded = store_chain_output.load_last_stored_chain()
if loaded is None:
logging.info("Running chain from scratch")
else:
logging.info("Running chain from iteration %d" % loaded.iteration)
chain = loaded
chain.run()
f = open(folder + os.sep + "final_chain", "w")
dump(chain, f)
f.close()
def main():
d = 5
b = randn(d)
V = randn(d, d)
W = V + V.T
fill_diagonal(W, zeros(d))
hopfield = Hopfield(W, b)
current_state = [rand() < 0.5 for _ in range(d)]
distribution = HopfieldFullConditionals(full_target=hopfield,
current_state=current_state)
mcmc_sampler = Gibbs(distribution)
mcmc_params = MCMCParams(start=asarray(current_state, dtype=numpy.bool8), num_iterations=10000)
chain = MCMCChain(mcmc_sampler, mcmc_params)
chain.append_mcmc_output(StatisticsOutput(plot_times=True, lag=100))
chain.append_mcmc_output(DiscretePlottingOutput(plot_from=0, lag=100))
chain.run()
def main():
distribution = Banana(dimension=8)
sigma = 5
print "using sigma", sigma
kernel = GaussianKernel(sigma=sigma)
mcmc_sampler = Kameleon(distribution, kernel,
distribution.sample(100).samples)
start = zeros(distribution.dimension)
mcmc_params = MCMCParams(start=start, num_iterations=20000)
chain = MCMCChain(mcmc_sampler, mcmc_params)
chain.append_mcmc_output(StatisticsOutput(plot_times=True))
chain.run()
def main():
d = 5
ps = rand(d)
ps /= norm(ps)
print "ps", ps
full_target=Bernoulli(ps)
current_state=[0. for _ in range(d)]
distribution = BernoulliFullConditionals(full_target, current_state)
mcmc_sampler = Gibbs(distribution)
mcmc_params = MCMCParams(start=asarray(current_state, dtype=numpy.bool8), num_iterations=10000)
chain = MCMCChain(mcmc_sampler, mcmc_params)
chain.append_mcmc_output(StatisticsOutput(plot_times=True, lag=1000))
chain.append_mcmc_output(DiscretePlottingOutput(plot_from=0, lag=1000))
chain.run()
print "marginals:", ps
print "estimated:", mean(chain.samples, 0)
def main():
distribution = Banana()
# distribution = Flower(amplitude=6, frequency=6, variance=1, radius=10, dimension=8)
# Visualise.visualise_distribution(distribution)
show()
#
sigma = 5
print "using sigma", sigma
kernel = GaussianKernel(sigma=sigma)
mcmc_sampler = KameleonWindowLearnScale(distribution, kernel, stop_adapt=inf)
start = asarray([0,-5.])
mcmc_params = MCMCParams(start=start, num_iterations=30000)
chain = MCMCChain(mcmc_sampler, mcmc_params)
chain.append_mcmc_output(PlottingOutput(distribution, plot_from=3000, colour_by_likelihood=False, num_samples_plot=0))
chain.append_mcmc_output(StatisticsOutput(plot_times=False))
chain.run()
print distribution.emp_quantiles(chain.samples[10000:])
def main():
distribution = Banana(dimension=8, bananicity=0.1, V=100.0)
sigma = 5
print "using sigma", sigma
kernel = GaussianKernel(sigma=sigma)
mcmc_sampler = KameleonWindow(distribution, kernel)
start = zeros(distribution.dimension)
mcmc_params = MCMCParams(start=start, num_iterations=80000)
chain = MCMCChain(mcmc_sampler, mcmc_params)
# chain.append_mcmc_output(PlottingOutput(distribution, plot_from=3000))
chain.append_mcmc_output(StatisticsOutput(plot_times=True))
chain.run()
print distribution.emp_quantiles(chain.samples)
def main():
distribution = Banana(dimension=2, bananicity=0.03, V=100.0)
mcmc_sampler = StandardMetropolis(distribution)
start = zeros(distribution.dimension)
start = asarray([0., -2.])
mcmc_params = MCMCParams(start=start, num_iterations=10000)
chain = MCMCChain(mcmc_sampler, mcmc_params)
chain.append_mcmc_output(StatisticsOutput(plot_times=True, lag=1000))
# chain.append_mcmc_output(PlottingOutput(distribution, plot_from=1, num_samples_plot=0,
# colour_by_likelihood=False))
chain.run()
f = open("std_metropolis_chain_gaussian.bin", 'w')
dump(chain, f)
f.close()
def main():
# covariance has stretched Eigenvalues, and rotated basis
Sigma = eye(2)
Sigma[0, 0] = 30
Sigma[1, 1] = 1
theta = -pi / 4
U = MatrixTools.rotation_matrix(theta)
Sigma = U.T.dot(Sigma).dot(U)
gaussian = Gaussian(Sigma=Sigma)
distribution = GaussianFullConditionals(gaussian, [0., 0.])
mcmc_sampler = Gibbs(distribution)
start = zeros(distribution.dimension)
mcmc_params = MCMCParams(start=start, num_iterations=20000)
chain = MCMCChain(mcmc_sampler, mcmc_params)
chain.append_mcmc_output(StatisticsOutput(plot_times=True, lag=100))
chain.append_mcmc_output(PlottingOutput(distribution=gaussian, plot_from=1,
colour_by_likelihood=False,
num_samples_plot=0, lag=100))
chain.run()
def create_ground_truth():
filename_chain = "chain.bin"
filename_Z = "Z.bin"
filename_hopfield = "hopfield.bin"
try:
f = open(filename_Z, "r")
Z = load(f)
f.close()
f = open(filename_hopfield, "r")
hopfield = load(f)
f.close()
print("Loaded existing ground truth samples and hopfield netword.")
except IOError:
print("No existing ground truth samples. Creating.")
# the network to sample from
try:
f = open(filename_hopfield, "r")
hopfield = load(f)
f.close()
d = hopfield.dimension
print("Loaded hopfield network")
except IOError:
d = 50
b = randn(d)
V = randn(d, d)
W = V + V.T
fill_diagonal(W, zeros(d))
hopfield = Hopfield(W, b)
# dump hopfield network
f = open(filename_hopfield, "w")
dump(hopfield, f)
f.close()
# iterations
num_iterations = 10000000
warm_up = 100000
thin = 2000
current_state = [rand() < 0.5 for _ in range(d)]
distribution = HopfieldFullConditionals(full_target=hopfield,
current_state=current_state,
schedule="random_permutation")
mcmc_sampler = Gibbs(distribution)
# spread = .0001
# mcmc_sampler = StandardMetropolisDiscrete(hopfield, spread)
mcmc_params = MCMCParams(start=asarray(current_state,
dtype=numpy.bool8),
num_iterations=num_iterations)
chain = MCMCChain(mcmc_sampler, mcmc_params)
chain.append_mcmc_output(StatisticsOutput(plot_times=True, lag=1000))
# chain.append_mcmc_output(StoreChainOutput(".", lag=100000))
# chain.append_mcmc_output(DiscretePlottingOutput(plot_from=0, lag=100))
chain.run()
# dump chain
try:
f = open(filename_chain, "w")
dump(chain, f)
f.close()
except IOError:
print("Could not save MCMC chain")
# warmup and thin
Z = chain.samples[(warm_up):]
Z = Z[arange(len(Z), step=thin)]
Z = Z.astype(numpy.bool8)
# dump ground truth samples
try:
f = open(filename_Z, "w")
dump(Z, f)
f.close()
except IOError:
print("Could not save Z")
return Z, hopfield
KameleonWindowLearnScale
from kameleon_mcmc.mcmc.samplers.StandardMetropolis import StandardMetropolis
if __name__ == '__main__':
experiment_dir = str(os.path.abspath(sys.argv[0])).split(os.sep)[-1].split(".")[0] + os.sep
distribution = Flower(amplitude=6, frequency=6, variance=1, radius=10, dimension=8)
sigma = 5
kernel = GaussianKernel(sigma=sigma)
burnin = 60000
num_iterations = 120000
#mcmc_sampler = KameleonWindowLearnScale(distribution, kernel, stop_adapt=burnin)
mean_est = zeros(distribution.dimension, dtype="float64")
cov_est = 1.0 * eye(distribution.dimension)
#mcmc_sampler = AdaptiveMetropolisLearnScale(distribution, mean_est=mean_est, cov_est=cov_est)
#mcmc_sampler = AdaptiveMetropolis(distribution, mean_est=mean_est, cov_est=cov_est)
mcmc_sampler = StandardMetropolis(distribution)
start = zeros(distribution.dimension, dtype="float64")
mcmc_params = MCMCParams(start=start, num_iterations=num_iterations, burnin=burnin)
mcmc_chain = MCMCChain(mcmc_sampler, mcmc_params)
mcmc_chain.append_mcmc_output(StatisticsOutput())
experiment = SingleChainExperiment(mcmc_chain, experiment_dir)
experiment.run()
cov_est=cov_est))
mcmc_samplers.append(
AdaptiveMetropolis(distribution,
mean_est=mean_est,
cov_est=cov_est))
#
# num_eigen = distribution.dimension
# mcmc_samplers.append(AdaptiveMetropolisPCA(distribution, num_eigen=num_eigen, mean_est=mean_est, cov_est=cov_est))
#
mcmc_samplers.append(StandardMetropolis(distribution))
start = zeros(distribution.dimension, dtype="float64")
mcmc_params = MCMCParams(start=start,
num_iterations=num_iterations,
burnin=burnin)
mcmc_chains = [
MCMCChain(mcmc_sampler, mcmc_params)
for mcmc_sampler in mcmc_samplers
]
for mcmc_chain in mcmc_chains:
mcmc_chain.append_mcmc_output(StatisticsOutput())
experiments = [
SingleChainExperiment(mcmc_chain, experiment_dir)
for mcmc_chain in mcmc_chains
]
for experiment in experiments:
ClusterTools.submit_experiment(experiment)
print "using sigma", sigma
kernel = GaussianKernel(sigma=sigma)
for i in range(n):
mcmc_samplers = []
burnin=50000
num_iterations=500000
#mcmc_samplers.append(KameleonWindowLearnScale(distribution, kernel, stop_adapt=burnin))
#mean_est = zeros(distribution.dimension, dtype="float64")
#cov_est = 1.0 * eye(distribution.dimension)
#cov_est[0, 0] = distribution.V
#mcmc_samplers.append(AdaptiveMetropolisLearnScale(distribution, mean_est=mean_est, cov_est=cov_est))
#mcmc_samplers.append(AdaptiveMetropolis(distribution, mean_est=mean_est, cov_est=cov_est))
mcmc_samplers.append(StandardMetropolis(distribution))
start = zeros(distribution.dimension, dtype="float64")
mcmc_params = MCMCParams(start=start, num_iterations=num_iterations, burnin=burnin)
mcmc_chains = [MCMCChain(mcmc_sampler, mcmc_params) for mcmc_sampler in mcmc_samplers]
for mcmc_chain in mcmc_chains:
mcmc_chain.append_mcmc_output(StatisticsOutput())
experiments = [SingleChainExperiment(mcmc_chain, experiment_dir) for mcmc_chain in mcmc_chains]
for experiment in experiments:
ClusterTools.submit_experiment(experiment)
def create_ground_truth():
filename_chain = "chain.bin"
filename_Z = "Z.bin"
filename_hopfield = "hopfield.bin"
try:
f = open(filename_Z, "r")
Z = load(f)
f.close()
f = open(filename_hopfield, "r")
hopfield = load(f)
f.close()
print("Loaded existing ground truth samples and hopfield netword.")
except IOError:
print("No existing ground truth samples. Creating.")
# the network to sample from
try:
f = open(filename_hopfield, "r")
hopfield = load(f)
f.close()
d = hopfield.dimension
print("Loaded hopfield network")
except IOError:
d = 50
b = randn(d)
V = randn(d, d)
W = V + V.T
fill_diagonal(W, zeros(d))
hopfield = Hopfield(W, b)
# dump hopfield network
f = open(filename_hopfield, "w")
dump(hopfield, f)
f.close()
# iterations
num_iterations = 10000000
warm_up = 100000
thin = 2000
current_state = [rand() < 0.5 for _ in range(d)]
distribution = HopfieldFullConditionals(full_target=hopfield,
current_state=current_state,
schedule="random_permutation")
mcmc_sampler = Gibbs(distribution)
# spread = .0001
# mcmc_sampler = StandardMetropolisDiscrete(hopfield, spread)
mcmc_params = MCMCParams(start=asarray(current_state, dtype=numpy.bool8), num_iterations=num_iterations)
chain = MCMCChain(mcmc_sampler, mcmc_params)
chain.append_mcmc_output(StatisticsOutput(plot_times=True, lag=1000))
# chain.append_mcmc_output(StoreChainOutput(".", lag=100000))
# chain.append_mcmc_output(DiscretePlottingOutput(plot_from=0, lag=100))
chain.run()
# dump chain
try:
f = open(filename_chain, "w")
dump(chain, f)
f.close()
except IOError:
print("Could not save MCMC chain")
# warmup and thin
Z = chain.samples[(warm_up):]
Z = Z[arange(len(Z), step=thin)]
Z = Z.astype(numpy.bool8)
# dump ground truth samples
try:
f = open(filename_Z, "w")
dump(Z, f)
f.close()
except IOError:
print("Could not save Z")
return Z, hopfield
# prior on theta and posterior target estimate
theta_prior=Gaussian(mu=0*ones(dim), Sigma=eye(dim)*5)
target=PseudoMarginalHyperparameterDistribution(data, labels, \
n_importance=100, prior=theta_prior, \
ridge=1e-3)
# create sampler
burnin=10000
num_iterations=burnin+300000
kernel = GaussianKernel(sigma=23.0)
sampler=KameleonWindowLearnScale(target, kernel, stop_adapt=burnin)
# sampler=AdaptiveMetropolisLearnScale(target)
# sampler=StandardMetropolis(target)
# posterior mode derived by initial tests
start=zeros(target.dimension)
params = MCMCParams(start=start, num_iterations=num_iterations, burnin=burnin)
# create MCMC chain
chain=MCMCChain(sampler, params)
chain.append_mcmc_output(StatisticsOutput(print_from=0, lag=100))
#chain.append_mcmc_output(PlottingOutput(plot_from=0, lag=500))
# create experiment instance to store results
experiment_dir = str(os.path.abspath(sys.argv[0])).split(os.sep)[-1].split(".")[0] + os.sep
experiment = SingleChainExperiment(chain, experiment_dir)
experiment.run()
sigma=GaussianKernel.get_sigma_median_heuristic(experiment.mcmc_chain.samples.T)
print "median kernel width", sigma
distribution = Banana(dimension=8, bananicity=0.03, V=100)
sigma = GaussianKernel.get_sigma_median_heuristic(
distribution.sample(1000).samples)
sigma = 10
print "using sigma", sigma
kernel = GaussianKernel(sigma=sigma)
burnin = 20000
num_iterations = 40000
mcmc_sampler = KameleonWindowLearnScale(distribution,
kernel,
stop_adapt=burnin)
mean_est = zeros(distribution.dimension, dtype="float64")
cov_est = 1.0 * eye(distribution.dimension)
cov_est[0, 0] = distribution.V
#mcmc_sampler = AdaptiveMetropolisLearnScale(distribution, mean_est=mean_est, cov_est=cov_est)
#mcmc_sampler = AdaptiveMetropolis(distribution, mean_est=mean_est, cov_est=cov_est)
#mcmc_sampler = StandardMetropolis(distribution)
start = zeros(distribution.dimension, dtype="float64")
mcmc_params = MCMCParams(start=start,
num_iterations=num_iterations,
burnin=burnin)
mcmc_chain = MCMCChain(mcmc_sampler, mcmc_params)
mcmc_chain.append_mcmc_output(StatisticsOutput())
experiment = SingleChainExperiment(mcmc_chain, experiment_dir)
experiment.run()
n_importance=100, prior=theta_prior, \
ridge=1e-3)
# create sampler
burnin = 10000
num_iterations = burnin + 300000
kernel = GaussianKernel(sigma=23.0)
sampler = KameleonWindowLearnScale(target, kernel, stop_adapt=burnin)
# sampler=AdaptiveMetropolisLearnScale(target)
# sampler=StandardMetropolis(target)
# posterior mode derived by initial tests
start = zeros(target.dimension)
params = MCMCParams(start=start,
num_iterations=num_iterations,
burnin=burnin)
# create MCMC chain
chain = MCMCChain(sampler, params)
chain.append_mcmc_output(StatisticsOutput(print_from=0, lag=100))
#chain.append_mcmc_output(PlottingOutput(plot_from=0, lag=500))
# create experiment instance to store results
experiment_dir = str(os.path.abspath(sys.argv[0])).split(
os.sep)[-1].split(".")[0] + os.sep
experiment = SingleChainExperiment(chain, experiment_dir)
experiment.run()
sigma = GaussianKernel.get_sigma_median_heuristic(
experiment.mcmc_chain.samples.T)
print "median kernel width", sigma
