datas, heldout = hold_out(allseqs, 0.05)
training_size = sum(data.shape[0] for data in datas)
print('...done!')
print('%d total frames' % sum(data.shape[0] for data in alldata))
print('split into %d training and %d test sequences' %
(len(datas), len(heldout)))
### inference!
Nmax = 20
obs_hypparams = dict(mu_0=np.zeros(2), sigma_0=np.eye(2), kappa_0=0.2, nu_0=5)
hmm = models.HMM(
obs_distns=[distributions.Gaussian(**obs_hypparams) for i in range(Nmax)],
alpha=10.,
init_state_concentration=1.)
scores = []
sgdseq = sgd_passes(tau=0, kappa=0.7, datalist=datas)
for t, (data, rho_t) in progprint(enumerate(sgdseq)):
hmm.meanfield_sgdstep(data, data.shape[0] / training_size, rho_t)
if t % 10 == 0:
scores.append(hmm.log_likelihood(heldout))
plt.figure()
plt.plot(scores)
plt.show()
obs_distns=obs_distns, bern_or_weight = 'weight', svi_or_gibbs = 'svi',
weight_prior_mean = 0, weight_prior_std = 0.1, win_size = win_size, use_obs_features = use_obs_features)
np.random.seed(infseed)
if sgd_or_mf == 'mf':
print('feature weights before mean field: ', '\n', HDPHMMSVImodel.feature_weights, '\n')
for i in range(14):
HDPHMMSVImodel.add_data(datas[i])
for i in range(20):
print(HDPHMMSVImodel.meanfield_coordinate_descent_step(0.5))
print('feature weights after mean field: ', '\n', HDPHMMSVImodel.feature_weights, '\n')
else:
scores = []
sgdseq = sgd_passes(tau=0.8,kappa=0.9,datalist=datas, minibatchsize=4,npasses=30) #4, 3
for t, (data, rho_t) in progprint(enumerate(sgdseq)):
HDPHMMSVImodel.meanfield_sgdstep(data, np.array(data).shape[0] / np.float(training_size) , rho_t)
score = HDPHMMSVImodel.log_likelihood(heldout)
# print 'feature weights after mean field: ', HDPHMMSVImodel.feature_weights
print(score)
print("")
if t % 1 == 0:
scores.append(score)
# plt.plot(scores)
# plt.show()
######################################Plotting the states and segments ###########################
allseqs = np.array_split(alldata,250)
datas, heldout = hold_out(allseqs,0.05)
training_size = sum(data.shape[0] for data in datas)
print '...done!'
print '%d total frames' % sum(data.shape[0] for data in alldata)
print 'split into %d training and %d test sequences' % (len(datas),len(heldout))
### inference!
Nmax = 20
obs_hypparams = dict(mu_0=np.zeros(2),sigma_0=np.eye(2),kappa_0=0.2,nu_0=5)
hmm = models.HMM(
obs_distns=[distributions.Gaussian(**obs_hypparams) for i in range(Nmax)],
alpha=10.,init_state_concentration=1.)
scores = []
sgdseq = sgd_passes(tau=0,kappa=0.7,datalist=datas)
for t, (data, rho_t) in progprint(enumerate(sgdseq)):
hmm.meanfield_sgdstep(data, data.shape[0] / training_size, rho_t)
if t % 10 == 0:
scores.append(hmm.log_likelihood(heldout))
plt.figure()
plt.plot(scores)
plt.show()
obs_distns=obs_distns, bern_or_weight = 'weight', svi_or_gibbs = 'svi',
weight_prior_mean = 0, weight_prior_std = 0.1, win_size = win_size, use_obs_features = use_obs_features)
np.random.seed(infseed)
if sgd_or_mf == 'mf':
print 'feature weights before mean field: ', '\n', HDPHMMSVImodel.feature_weights, '\n'
for i in range(14):
HDPHMMSVImodel.add_data(datas[i])
for i in range(20):
print HDPHMMSVImodel.meanfield_coordinate_descent_step(0.5)
print 'feature weights after mean field: ', '\n', HDPHMMSVImodel.feature_weights, '\n'
else:
scores = []
sgdseq = sgd_passes(tau=0.8,kappa=0.9,datalist=datas, minibatchsize=4,npasses=30) #4, 3
for t, (data, rho_t) in progprint(enumerate(sgdseq)):
HDPHMMSVImodel.meanfield_sgdstep(data, np.array(data).shape[0] / np.float(training_size) , rho_t)
score = HDPHMMSVImodel.log_likelihood(heldout)
# print 'feature weights after mean field: ', HDPHMMSVImodel.feature_weights
print score
print ""
if t % 1 == 0:
scores.append(score)
# plt.plot(scores)
# plt.show()
######################################Plotting the states and segments ###########################