x = xs[0].copy()
x[z[:,1]] = xs[1][z[:,1]]
x[z[:,2]] = xs[2][z[:,2]]
z_ind = np.zeros(n, dtype=int)
z_ind[z[:,1]] = 1
z_ind[z[:,2]] = 2
# Run SA
# Note that some runs for small sample sizes run have issues with
# singular covariance matrices, so I simply try a couple times
# if there is an issue.
res_sa, _ = sim_anneal(
x, init_mu, init_sigma, init_mix, num_iter=iter_num,
temp_func=lambda i: max(1e-4, 100*.992**i))
# Run EM
res_em, _ = em_alg(
x, init_mu, init_sigma, init_mix, num_iter=iter_num)
# Run DA
res_da, _ = em_alg(
x, init_mu, init_sigma, init_mix, num_iter=iter_num,
beta_func=lambda i: 1.-np.exp(-(i+1)/5))
distances = np.array([cluster_dist(mu, res_sa[0]),
cluster_dist(mu, res_em[0]),
cluster_dist(mu, res_da[0])])
# Store results
init_mix,
num_iter=250)
res_da, (logliks_da,
times_da) = em_alg(x,
init_mu,
init_sigma,
init_mix,
num_iter=250,
beta_func=lambda i: 1. - np.exp(-(i + 1) / 5))
res_sa, (logliks_sa,
times_sa) = sim_anneal(x,
init_mu,
init_sigma,
init_mix,
num_iter=250,
seed=29624,
temp_func=lambda i: max(1e-4, 100 * .992**i))
# Save results
colnames = \
'logliks_em, times_em, logliks_da, times_da, logliks_sa, times_sa'
np.savetxt('./intermediate_data/singlerun_results.csv',
np.column_stack((logliks_em, times_em, logliks_da, times_da,
logliks_sa['best'], times_sa)),
header=colnames,
delimiter=',',
comments='')
np.savetxt('./intermediate_data/sa_singlerun.csv',
fig.savefig('./sim_data.pdf')
# Estimate
init_mu = np.array([[0., 0.], [1., 1.], [2., 2.]])
init_sigma = [np.identity(2) for i in range(3)]
init_mix = np.array([1., 1., 1.])/3
res_em, (logliks_em, times_em) = em_alg(
x, init_mu, init_sigma, init_mix, num_iter=250)
res_da, (logliks_da, times_da) = em_alg(
x, init_mu, init_sigma, init_mix, num_iter=250,
beta_func=lambda i: 1.-np.exp(-(i+1)/5))
res_sa, (logliks_sa, times_sa) = sim_anneal(
x, init_mu, init_sigma, init_mix, num_iter=250, seed=29624,
temp_func=lambda i: max(1e-4, 100*.992**i))
# Save results
colnames = \
'logliks_em, times_em, logliks_da, times_da, logliks_sa, times_sa'
np.savetxt(
'./intermediate_data/singlerun_results.csv',
np.column_stack((logliks_em, times_em,
logliks_da, times_da,
logliks_sa['best'], times_sa)),
header=colnames, delimiter=',', comments='')
np.savetxt('./intermediate_data/sa_singlerun.csv',
np.column_stack((logliks_sa['curr'], logliks_sa['best'])),
header='logliks_curr, logliks_best', delimiter=',', comments='')
x = xs[0].copy()
x[z[:,1]] = xs[1][z[:,1]]
x[z[:,2]] = xs[2][z[:,2]]
z_ind = np.zeros(n, dtype=int)
z_ind[z[:,1]] = 1
z_ind[z[:,2]] = 2
# Run SA
# Note that some runs for small sample sizes run have issues with
# singular covariance matrices, so I simply try a couple times
# if there is an issue.
try:
_, (loglik_sa, time_sa) = sim_anneal(
x, init_mu, init_sigma, init_mix, num_iter=iter_num,
temp_func=lambda i: max(1e-4, 100*.992**i))
except LinAlgError:
try:
_, (loglik_sa, time_sa) = sim_anneal(
x, init_mu, init_sigma, init_mix, num_iter=iter_num,
temp_func=lambda i: max(1e-4, 100*.992**i))
except LinAlgError:
_, (loglik_sa, time_sa) = sim_anneal(
x, init_mu, init_sigma, init_mix, num_iter=iter_num,
temp_func=lambda i: max(1e-4, 100*.992**i))
# Run EM
_, (logliks_em, times_em) = em_alg(
x, init_mu, init_sigma, init_mix, num_iter=iter_num)
