def fit_lds_model(Xs, Xtest, N_samples=100):
model = MultinomialLDS(K,
D,
init_dynamics_distn=Gaussian(mu_0=np.zeros(D),
sigma_0=np.eye(D),
kappa_0=1.0,
nu_0=D + 1.0),
dynamics_distn=AutoRegression(nu_0=D + 1,
S_0=np.eye(D),
M_0=np.zeros((D, D)),
K_0=np.eye(D)),
sigma_C=1)
for X in Xs:
model.add_data(X)
data = model.data_list[0]
samples = []
lls = []
test_lls = []
mc_test_lls = []
pis = []
psis = []
zs = []
timestamps = [time.time()]
for smpl in progprint_xrange(N_samples):
model.resample_model()
timestamps.append(time.time())
samples.append(model.copy_sample())
# TODO: Use log_likelihood() to marginalize over z
lls.append(model.log_likelihood())
# test_lls.append(model.heldout_log_likelihood(Xtest, M=50)[0])
mc_test_lls.append(model._mc_heldout_log_likelihood(Xtest, M=1)[0])
pis.append(model.pi(data))
psis.append(model.psi(data))
zs.append(data["states"].stateseq)
lls = np.array(lls)
test_lls = np.array(test_lls)
pis = np.array(pis)
psis = np.array(psis)
zs = np.array(zs)
timestamps = np.array(timestamps)
timestamps -= timestamps[0]
return model, lls, test_lls, mc_test_lls, pis, psis, zs, timestamps
def fit_lds_model(Xs, Xtest, N_samples=100):
model = MultinomialLDS(K, D,
init_dynamics_distn=Gaussian(mu_0=np.zeros(D), sigma_0=np.eye(D), kappa_0=1.0, nu_0=D+1.0),
dynamics_distn=AutoRegression(nu_0=D+1,S_0=np.eye(D),M_0=np.zeros((D,D)),K_0=np.eye(D)),
sigma_C=1
)
for X in Xs:
model.add_data(X)
data = model.data_list[0]
samples = []
lls = []
test_lls = []
mc_test_lls = []
pis = []
psis = []
zs = []
timestamps = [time.time()]
for smpl in progprint_xrange(N_samples):
model.resample_model()
timestamps.append(time.time())
samples.append(model.copy_sample())
# TODO: Use log_likelihood() to marginalize over z
lls.append(model.log_likelihood())
# test_lls.append(model.heldout_log_likelihood(Xtest, M=50)[0])
mc_test_lls.append(model._mc_heldout_log_likelihood(Xtest, M=1)[0])
pis.append(model.pi(data))
psis.append(model.psi(data))
zs.append(data["states"].stateseq)
lls = np.array(lls)
test_lls = np.array(test_lls)
pis = np.array(pis)
psis = np.array(psis)
zs = np.array(zs)
timestamps = np.array(timestamps)
timestamps -= timestamps[0]
return model, lls, test_lls, mc_test_lls, pis, psis, zs, timestamps
M_0=np.zeros((D, D)),
K_0=np.eye(D)),
sigma_C=1)
testmodel.add_data(data["x"])
testdata = testmodel.data_list[0]
N_samples = 100
samples = []
lls = []
pis = []
psis = []
zs = []
for smpl in range(N_samples):
print("Iteration ", smpl)
testmodel.resample_model()
samples.append(testmodel.copy_sample())
lls.append(testmodel.log_likelihood())
pis.append(testmodel.pi(testdata))
psis.append(testmodel.psi(testdata))
zs.append(testdata["states"].stateseq)
lls = np.array(lls)
pis = np.array(pis)
psis = np.array(psis)
psi_mean = psis[N_samples // 2:, ...].mean(0)
psi_std = psis[N_samples // 2:, ...].std(0)
zs = np.array(zs)
dynamics_distn=AutoRegression(nu_0=D+1,S_0=np.eye(D),M_0=np.zeros((D,D)),K_0=np.eye(D)),
sigma_C=1
)
testmodel.add_data(data["x"])
testdata = testmodel.data_list[0]
N_samples = 100
samples = []
lls = []
pis = []
psis = []
zs = []
for smpl in xrange(N_samples):
print("Iteration ", smpl)
testmodel.resample_model()
samples.append(testmodel.copy_sample())
lls.append(testmodel.log_likelihood())
pis.append(testmodel.pi(testdata))
psis.append(testmodel.psi(testdata))
zs.append(testdata["states"].stateseq)
lls = np.array(lls)
pis = np.array(pis)
psis = np.array(psis)
psi_mean = psis[N_samples//2:,...].mean(0)
psi_std = psis[N_samples//2:,...].std(0)
zs = np.array(zs)
