def main():
# Generate synthetic data
x = 2 * npr.rand(N,D) - 1 # data features, an (N,D) array
x[:, 0] = 1
th_true = 10.0 * np.array([0, 1, 1])
y = np.dot(x, th_true[:, None])[:, 0]
t = npr.rand(N) > (1 / ( 1 + np.exp(y))) # data targets, an (N) array of 0s and 1s
# Obtain joint distributions over z and th
model = ff.LogisticModel(x, t, th0=th0, y0=y0)
# Set up step functions
th = np.random.randn(D) * th0
z = ff.BrightnessVars(N)
th_stepper = ff.ThetaStepMH(model.log_p_joint, stepsize)
z__stepper = ff.zStepMH(model.log_pseudo_lik, q)
plt.ion()
ax = plt.figure(figsize=(8, 6)).add_subplot(111)
while True:
th = th_stepper.step(th, z) # Markov transition step for theta
z = z__stepper.step(th ,z) # Markov transition step for z
update_fig(ax, x, y, z, th, t)
plt.draw()
plt.pause(0.05)
def main():
# Generate synthetic data
x = 2 * npr.rand(N, D) - 1 # data features, an (N,D) array
x[:, 0] = 1
th_true = 10.0 * np.array([0, 1, 1])
y = np.dot(x, th_true[:, None])[:, 0]
t = npr.rand(N) > (1 / (1 + np.exp(y))
) # data targets, an (N) array of 0s and 1s
# Obtain joint distributions over z and th
model = ff.LogisticModel(x, t, th0=th0, y0=y0)
# Set up step functions
th = np.random.randn(D) * th0
z = ff.BrightnessVars(N)
th_stepper = ff.ThetaStepMH(model.log_p_joint, stepsize)
z__stepper = ff.zStepMH(model.log_pseudo_lik, q)
plt.ion()
ax = plt.figure(figsize=(8, 6)).add_subplot(111)
while True:
th = th_stepper.step(th, z) # Markov transition step for theta
z = z__stepper.step(th, z) # Markov transition step for z
update_fig(ax, x, y, z, th, t)
plt.draw()
plt.pause(0.05)
def run_model(model, q=0.1, fly=False):
th = np.random.randn(K, D) * th0
if fly:
z = ff.BrightnessVars(N)
else:
z = ff.BrightnessVars(N, range(N))
th_stepper = ff.ThetaStepLangevin(model.log_p_joint,
model.D_log_p_joint, stepsize)
if fly:
z__stepper = ff.zStepMH(model.log_pseudo_lik, q)
ths = []
for _ in range(N_steps):
num_lik_prev = model.num_lik_evals
if _ % N_ess == 0 and _ > 0:
#print pypmc.tools.convergence.ess(ths) # TODO: is this correct?
#print ess(ths)
np.savetxt('softmax-trace-untuned-{0}.csv'.format(_),
np.array(ths))
ths = []
th = th_stepper.step(th, z) # Markov transition step for theta
if fly:
z = z__stepper.step(th, z) # Markov transition step for z
ths.append(th)
print "Likelihood evals in iter {0}: {1}".format(
_, model.num_lik_evals - num_lik_prev)
print "Number bright points: {0}".format(len(z.bright))
return th
def run_model(model, th_init=np.random.randn(D) * th0, q=0.1, fly=False):
th = th_init
if fly:
z = ff.BrightnessVars(N)
else:
z = ff.BrightnessVars(N, range(N))
th_stepper = ff.ThetaStepMH(model.log_p_joint, stepsize)
if fly:
z__stepper = ff.zStepMH(model.log_pseudo_lik, q)
ths = []
num_rejects = 0
for i in range(N_steps):
num_lik_prev = model.num_lik_evals
if i % N_ess == 0 and i > 0:
#print pypmc.tools.convergence.ess(ths) # TODO: is this correct?
#print ess(ths)
np.savetxt('trace-untuned-{0}.csv'.format(i), np.array(ths))
ths = []
th = th_stepper.step(th, z) # Markov transition step for theta
num_rejects += th_stepper.num_rejects
if fly:
z = z__stepper.step(th, z) # Markov transition step for z
ths.append(th)
print "\t\t".join(
map(lambda x: "{0:.5f}".format(x), [
i,
len(z.bright), model.num_lik_evals - num_lik_prev,
1.0 - num_rejects / float(i + 1),
-1.0 * model.log_p_marg(th, increment_ctr=False)
]))
return th
def logistic_regression_chain(x, t, N_iter=100, stepsize=1, th0=1, q=0.1, y0=1, seed=None):
# Set seed
npr.seed(seed)
# Obtain joint distributions over z and th and set step functions
model = ff.LogisticModel(x, t, th0=th0, y0=y0)
z__stepper = ff.zStepMH(model.log_pseudo_lik , q)
th_stepper = ff.ThetaStepMH(model.log_p_joint, stepsize)
# Initialize
N, D = x.shape
th = np.random.randn(D)*th0
z = ff.BrightnessVars(N)
# run chain
th_chain = np.zeros((N_iter, ) + th.shape)
z_chain = np.zeros((N_iter, N), dtype=bool)
for i in range(N_iter):
th = th_stepper.step(th, z)
z = z__stepper.step(th ,z)
# Record the intermediate results
th_chain[i,:] = th.copy()
z_chain[i,z.bright] = 1
print "th0 = ", th0, "frac accepted is", th_stepper.frac_accepted, "bright frac is:", np.mean(z_chain)
return th_chain, z_chain
def check_flymc_converges(model, correct_moments, th_stepper):
tol = 0.2
q = 0.5
z_stepper = ff.zStepMH(model.log_pseudo_lik, q)
th_init = model.draw_from_prior()
z_init = ff.BrightnessVars(model.N)
chain_gen = chain_generator_th_z(th_stepper, z_stepper, th_init, z_init)
est_moments = mcmc_estimator(chain_gen, tol)
assert (np.all(np.abs(est_moments - correct_moments) < tol))
def check_flymc_converges(model, correct_moments, th_stepper):
tol = 0.2
q = 0.5
z_stepper = ff.zStepMH(model.log_pseudo_lik , q)
th_init = model.draw_from_prior()
z_init = ff.BrightnessVars(model.N)
chain_gen = chain_generator_th_z(th_stepper, z_stepper,
th_init, z_init)
est_moments = mcmc_estimator(chain_gen, tol)
assert(np.all(np.abs(est_moments - correct_moments) < tol))
def run_model(model, q=0.1, fly=False):
'''
function to run model
'''
th = np.random.randn(D) * th0
if fly:
z = ff.BrightnessVars(N, range(int(q * N)))
else:
z = ff.BrightnessVars(N, range(N))
th_stepper = ff.ThetaStepMH(model.log_p_joint, stepsize)
if fly:
z__stepper = ff.zStepMH(model.log_pseudo_lik, q)
th_lists = [] # trace of th
num_rejects_list = [] #
num_iter_list = [] # number of num_lik_evals for each iteration
for _ in range(N_steps):
num_lik_prev = model.num_lik_evals
if _ % N_ess == 0 and _ > 0:
#print pypmc.tools.convergence.ess(th_lists) # TODO: is this correct?
#print ess(th_lists)
np.savetxt('trace-untuned-{0}.csv'.format(_),
np.array(th_lists))
th_lists = []
th = th_stepper.step(th, z) # Markov transition step for theta
if fly:
z = z__stepper.step(th, z) # Markov transition step for z
th_lists.append(th)
num_rejects_list.append(th_stepper.num_rejects)
num_iter_list.append(model.num_lik_evals - num_lik_prev)
print "Accept rate: {0}".format(1.0 - sum(num_rejects_list) /
float(_ + 1))
print "Likelihood evals in iter {0}: {1}".format(
_, model.num_lik_evals - num_lik_prev)
print "Neg log posterior: {0}".format(
-1.0 * model.log_p_marg(th, increment_ctr=False))
print "Number bright points: {0}".format(len(z.bright))
return th, num_iter_list, th_lists
def logistic_regression_chain(x,
t,
N_iter=100,
stepsize=1,
th0=1,
q=0.1,
y0=1,
seed=None):
# Set seed
npr.seed(seed)
# Obtain joint distributions over z and th and set step functions
model = ff.LogisticModel(x, t, th0=th0, y0=y0)
z__stepper = ff.zStepMH(model.log_pseudo_lik, q)
th_stepper = ff.ThetaStepMH(model.log_p_joint, stepsize)
# Initialize
N, D = x.shape
th = np.random.randn(D) * th0
z = ff.BrightnessVars(N)
# run chain
th_chain = np.zeros((N_iter, ) + th.shape)
z_chain = np.zeros((N_iter, N), dtype=bool)
for i in range(N_iter):
th = th_stepper.step(th, z)
z = z__stepper.step(th, z)
# Record the intermediate results
th_chain[i, :] = th.copy()
z_chain[i, z.bright] = 1
print "th0 = ", th0, "frac accepted is", th_stepper.frac_accepted, "bright frac is:", np.mean(
z_chain)
return th_chain, z_chain
def run_model(model, q=0.1, fly=False, verbose=False):
'''
function to run model
'''
th = np.random.randn(D) * th0
# Init steppers
if fly:
z = ff.BrightnessVars(N, range(int(q * N)))
else:
z = ff.BrightnessVars(N, range(N))
th_stepper = ff.ThetaStepMH(model.log_p_joint, stepsize)
if fly:
z_stepper = ff.zStepMH(model.log_pseudo_lik, q)
# Trace list
num_rejects_list = []
acceptance_list = []
num_lik_evals_list = []
neg_log_list = []
performance_dict = {}
# Trace - Sampling
sample_num_lik_evals_list = []
sample_th_list = []
# Run chain
for _ in range(N_steps + N_ess):
num_lik_prev = model.num_lik_evals
# Markov transition
th = th_stepper.step(th, z) # Markov transition step for theta
if fly:
z = z_stepper.step(th, z) # Markov transition step for z
# Record performance
num_rejects = th_stepper.num_rejects
num_lik_evals = model.num_lik_evals - num_lik_prev
acceptance = 1.0 - sum(num_rejects_list) / float(_ + 1)
neg_log = -1.0 * model.log_p_marg(th, increment_ctr=False)
if _ < N_steps:
num_rejects_list.append(num_rejects)
num_lik_evals_list.append(num_lik_evals)
acceptance_list.append(acceptance)
neg_log_list.append(neg_log)
else:
# _ >= N_steps
sample_num_lik_evals_list.append(num_lik_evals)
sample_th_list.append(th)
# Print info
if verbose or (_ % 50 == 0):
print "Accept rate: {0}".format(acceptance)
print "Likelihood evals in iter {0}: {1}".format(_, num_lik_evals)
print "Neg log posterior: {0}".format(neg_log)
print "Number bright points: {0}".format(len(z.bright))
sample_evals = sum(sample_num_lik_evals_list)
np.savetxt('trace-{0}-{1}.csv'.format(model.name, N_ess),
np.array(sample_th_list))
performance_dict[KEY_NAME] = model.name
performance_dict[KEY_NUM_REJECTS] = num_rejects_list
performance_dict[KEY_LIK_EVALS] = num_lik_evals_list
performance_dict[KEY_ACCEPTANCE] = acceptance_list
performance_dict[KEY_NEG_LOG] = neg_log_list
performance_dict[KEY_SAMPLE_EVALS] = sample_evals
return performance_dict