def test_autocorrelation_bad_init(self):
""" Tests that the legacy and fast ac implementations produce identical output
when the sampler is initialized with a bias set of samples
:returns: None
:rtype: None
"""
gaussian = MultimodalGaussian()
sample_df = sample_to_df(MarkovJumpHMC, gaussian, num_steps=1000)
slow_ac_df = slow_autocorrelation(sample_df)
slow_ac = slow_ac_df.autocorrelation.as_matrix()
fast_ac_df = autocorrelation(sample_df)
fast_ac = fast_ac_df.autocorrelation.as_matrix()
self.assertTrue(np.isclose(slow_ac, fast_ac, atol=TOL).all())
def test_autocorrelation_good_init_half_window(self):
""" Tests that the legacy and fast ac implementations produce identical output
when the sampler is not initialized in a biased manner
(meaning we don't have to worry about variance mismatch)
runs on the half window
:returns: None
:rtype: None
"""
gaussian = Gaussian()
sample_df = sample_to_df(MarkovJumpHMC, gaussian, num_steps=1000)
slow_ac_df = slow_autocorrelation(sample_df, half_window=True)
slow_ac = slow_ac_df.autocorrelation.as_matrix()
fast_ac_df = autocorrelation(sample_df, half_window=True)
fast_ac = fast_ac_df.autocorrelation.as_matrix()
self.assertTrue(np.isclose(slow_ac, fast_ac, atol=TOL).all())
nbasis=36
ndims=12
n_steps=1000
half_window=False
rand_val = rand(ndims,nbasis/2,density=0.1)
W = np.concatenate([rand_val.toarray(), -rand_val.toarray()],axis=1)
logalpha = np.random.randn(nbasis,1)
PoT_instance = ProductOfT(nbatch=100,ndims=ndims,nbasis=nbasis,W=W,logalpha=logalpha)
simulate = hmc.wrapper_hmc(s_rng=s_rng,energy_fn=rw.E_val,dim=dim)
a = np.zeros([1,10,n_samples])
b = np.zeros([2,10,n_samples])
for ii in np.arange(n_steps):
a[:,:,ii],b[:,:,ii] = simulate()
print "Acceptance Rate"
print a[:,:,ii]
print "Samples"
print b[:,:,ii]
ac_df = autocorrelation(df,half_window)
#Now, we can run the same autocorrelation from the data we will extract from the data frame
#but with the theano function
ac= hmc.normed_autocorrelation(df)
#We can compare the two plots individually and on a single plot
#Drop Mic and leave.
n_grad_evals = ac_df['num grad'].astype(int)
def plot_ac(distribution,
control_params,
mjhmc_params,
lahmc_params,
max_steps=3000,
sample_steps=1,
truncate=False,
truncate_at=0.0,
nuts=False,
truncate_idx=None):
"""
distribution is an instantiated distribution object
runs the sampler for max steps and then truncates the output to autocorrelation 0.5
throws an error if ac 0.5 is not reached
"""
from mjhmc.samplers.markov_jump_hmc import MarkovJumpHMC, ControlHMC
from mjhmc.misc.autocor import calculate_autocorrelation, autocorrelation
from mjhmc.misc.nutshell import sample_nuts_to_df
# TODO: bring up to speed of DF-less calc autocor
plt.clf()
print('Calculating AutoCorrelation for ControlHMC')
control_ac = calculate_autocorrelation(ControlHMC,
distribution,
num_steps=max_steps,
sample_steps=sample_steps,
half_window=True,
use_cached_var=True,
**control_params)
print('Calculating AutoCorrelation for MJHMC')
mjhmc_ac = calculate_autocorrelation(MarkovJumpHMC,
distribution,
num_steps=max_steps,
sample_steps=sample_steps,
half_window=True,
resample=False,
use_cached_var=True,
**mjhmc_params)
# lahmc_ac = calculate_autocorrelation(LAHMC, distribution,
# num_steps=max_steps,
# sample_steps=sample_steps,
# half_window=True,
# **lahmc_params)
if nuts:
print('Calculating AutoCorrelation for NUTS')
nuts_df = sample_nuts_to_df(distribution, 100000, n_burn_in=10000)
nuts_ac = autocorrelation(nuts_df, half_window=True)
# find idx with autocorrelation closest to truncate_at
if truncate:
control_trunc = control_ac.loc[:, 'autocorrelation'] < truncate_at
mjhmc_trunc = mjhmc_ac.loc[:, 'autocorrelation'] < truncate_at
if truncate_idx is None:
if nuts:
nuts_trunc = nuts_ac.loc[:, 'autocorrelation'] < truncate_at
trunc_idx = max(control_trunc[control_trunc].index[0],
mjhmc_trunc[mjhmc_trunc].index[0])
# nuts_trunc[nuts_trunc].index[0])
nuts_ac = nuts_ac.loc[:trunc_idx]
else:
trunc_idx = max(control_trunc[control_trunc].index[0],
mjhmc_trunc[mjhmc_trunc].index[0])
else:
trunc_idx = truncate_idx
control_ac = control_ac.loc[:trunc_idx]
mjhmc_ac = mjhmc_ac.loc[:trunc_idx]
control_ac.index = control_ac['num grad']
mjhmc_ac.index = control_ac['num grad']
if nuts:
nuts_ac.index = nuts_ac['num grad']
nuts_ac['autocorrelation'].plot(label='NUTS')
# control_ac['autocorrelation'].plot(label='Control HMC;\n {}'.format(str(control_params)))
# mjhmc_ac['autocorrelation'].plot(label='Markov Jump HMC;\n {}'.format(str(mjhmc_params)))
control_ac['autocorrelation'].plot(label='Control HMC')
mjhmc_ac['autocorrelation'].plot(label='Markov Jump HMC')
plt.xlabel("Gradient Evaluations")
plt.ylabel("Autocorrelation")
plt.title("{}D {}".format(distribution.ndims, type(distribution).__name__))
plt.legend()
plt.show()
plt.savefig("{}_{}_dim_ac_{}_steps.pdf".format(
type(distribution).__name__, distribution.ndims, max_steps))
plt.show()
nbasis=36
ndims=12
n_steps=30000
half_window=False
rand_val = rand(ndims,nbasis/2,density=0.1)
W = np.concatenate([rand_val.toarray(), -rand_val.toarray()],axis=1)
logalpha = np.random.randn(nbasis,1)
#PoT_instance = ProductOfT(nbatch=100,ndims=ndims,nbasis=nbasis,W=W,lognu=logalpha)
df = sample_to_df(MarkovJumpHMC,Gaussian(ndims=10),num_steps=n_steps)
tm1 = time.time()
ac_df = slow_autocorrelation(df,half_window)
tm2 = time.time()
print tm2-tm1
#Now, we can run the same autocorrelation from the data we will extract from the data frame
#but with the theano function
tm1 = time.time()
ac= autocorrelation(df)
tm2 = time.time()
print tm2-tm1
#We can compare the two plots individually and on a single plot
#Drop Mic and leave.
n_grad_evals = ac_df['num grad'].astype(int)
fig = plt.figure()
plt.plot(n_grad_evals,ac['autocorrelation'],'r')
plt.plot(n_grad_evals,ac_df['autocorrelation'],'g')
fig.savefig('tmp_autocorr.png')
def plot_ac(distribution, control_params, mjhmc_params, lahmc_params, max_steps=3000,
sample_steps=1, truncate=False, truncate_at=0.0, nuts=False, truncate_idx=None):
"""
distribution is an instantiated distribution object
runs the sampler for max steps and then truncates the output to autocorrelation 0.5
throws an error if ac 0.5 is not reached
"""
plt.clf()
print('Calculating AutoCorrelation for ControlHMC')
control_ac = calculate_autocorrelation(ControlHMC, distribution,
num_steps=max_steps,
sample_steps=sample_steps,
half_window=True,
use_cached_var=True,
**control_params)
print('Calculating AutoCorrelation for MJHMC')
mjhmc_ac = calculate_autocorrelation(MarkovJumpHMC, distribution,
num_steps=max_steps,
sample_steps=sample_steps,
half_window=True,
resample=False,
use_cached_var=True,
**mjhmc_params)
# lahmc_ac = calculate_autocorrelation(LAHMC, distribution,
# num_steps=max_steps,
# sample_steps=sample_steps,
# half_window=True,
# **lahmc_params)
if nuts:
print('Calculating AutoCorrelation for NUTS')
nuts_df = sample_nuts_to_df(distribution, 100000, n_burn_in=10000)
nuts_ac = autocorrelation(nuts_df, half_window=True)
# find idx with autocorrelation closest to truncate_at
if truncate:
control_trunc = control_ac.loc[:, 'autocorrelation'] < truncate_at
mjhmc_trunc = mjhmc_ac.loc[:, 'autocorrelation'] < truncate_at
if truncate_idx is None:
if nuts:
nuts_trunc = nuts_ac.loc[:, 'autocorrelation'] < truncate_at
trunc_idx = max(control_trunc[control_trunc].index[0],
mjhmc_trunc[mjhmc_trunc].index[0])
# nuts_trunc[nuts_trunc].index[0])
nuts_ac = nuts_ac.loc[:trunc_idx]
else:
trunc_idx = max(control_trunc[control_trunc].index[0],
mjhmc_trunc[mjhmc_trunc].index[0])
else:
trunc_idx = truncate_idx
control_ac = control_ac.loc[:trunc_idx]
mjhmc_ac = mjhmc_ac.loc[:trunc_idx]
control_ac.index = control_ac['num grad']
mjhmc_ac.index = control_ac['num grad']
if nuts:
nuts_ac.index = nuts_ac['num grad']
nuts_ac['autocorrelation'].plot(label='NUTS')
# control_ac['autocorrelation'].plot(label='Control HMC;\n {}'.format(str(control_params)))
# mjhmc_ac['autocorrelation'].plot(label='Markov Jump HMC;\n {}'.format(str(mjhmc_params)))
control_ac['autocorrelation'].plot(label='Control HMC')
mjhmc_ac['autocorrelation'].plot(label='Markov Jump HMC')
plt.xlabel("Gradient Evaluations")
plt.ylabel("Autocorrelation")
plt.title("{}D {}".format(distribution.ndims, type(distribution).__name__))
plt.legend()
plt.show()
plt.savefig("{}_{}_dim_ac_{}_steps.pdf".format(type(distribution).__name__, distribution.ndims, max_steps))
plt.show()
