def disc_to_unthinned(ref_set, generated):
## DISCREPANCIES TO UNTHINNED SET.
ref_set_n = len(ref_set)
n_sample = len(generated)
# Compute MMD, Energy, and KL, between simulations and unthinned data.
mmd_, _ = compute_mmd(
generated, ref_set[np.random.choice(ref_set_n, n_sample)])
energy_ = compute_energy(
generated, ref_set[np.random.choice(ref_set_n, n_sample)])
kl_ = compute_kl(generated,
ref_set[np.random.choice(ref_set_n, n_sample)],
k=5)
return mmd_, energy_, kl_
def compute_discrepancies(cand_set, ref_set):
"""Computes discrepancies between two sets."""
cand_set_n = len(cand_set)
ref_set_n = len(ref_set)
n_sample = 1000
assert ((cand_set_n >= n_sample) & (ref_set_n >= n_sample)), \
'n_sample too high for one of the inputs.'
# Compute MMD, Energy, and KL, between simulations and unthinned data.
mmd_, _ = compute_mmd(cand_set[np.random.choice(cand_set_n, n_sample)],
ref_set[np.random.choice(ref_set_n, n_sample)])
energy_ = compute_energy(
cand_set[np.random.choice(cand_set_n, n_sample)],
ref_set[np.random.choice(ref_set_n, n_sample)])
kl_ = compute_kl(cand_set[np.random.choice(cand_set_n, n_sample)],
ref_set[np.random.choice(ref_set_n, n_sample)],
k=5)
return mmd_, energy_, kl_
g_out = sess.run(g, feed_dict={z: z_sample})
generated_normed = g_out
generated = np.array(generated_normed) * data_raw_std + data_raw_mean
# Compute MMD between simulations and unthinned (target) data.
mmd_gen_vs_unthinned, _ = compute_mmd(
generated[np.random.choice(n_sample, 500)],
data_raw_unthinned[np.random.choice(data_num_original, 500)])
# Compute energy between simulations and unthinned (target) data.
energy_gen_vs_unthinned = compute_energy(
generated[np.random.choice(n_sample, 500)],
data_raw_unthinned[np.random.choice(data_num_original, 500)])
# Compute KL between simulations and unthinned (target) data.
kl_gen_vs_unthinned = compute_kl(
generated[np.random.choice(n_sample, 500)],
data_raw_unthinned[np.random.choice(data_num_original, 500)],
k=5)
if data_dim == 2:
fig = plot(generated, data_raw, data_raw_unthinned,
data_raw_upsampled, it, mmd_gen_vs_unthinned)
if np.isnan(d_loss_):
sys.exit('got nan')
# Print diagnostics.
print("#################")
print('upsample_{}'.format(tag))
print('Iter: {}'.format(it))
print(' d_loss: {:.4}'.format(d_loss_))
print(' g_loss: {:.4}'.format(g_loss_))
g_out = sess.run(g, feed_dict={z: z_sample, label: label_sample})
generated_normed = np.hstack((latent_sample, g_out))
generated = np.array(generated_normed) * data_raw_std + data_raw_mean
####################################################
# Compute MMD only between data dimensions, and not latent ones.
mmd_gen_vs_unthinned, _ = compute_mmd(
generated[np.random.choice(n_sample, 500), -data_dim:],
data_raw_unthinned[np.random.choice(data_num, 500), -data_dim:])
# Compute energy only between data dimensions, and not latent ones.
energy_gen_vs_unthinned = compute_energy(
generated[np.random.choice(n_sample, 500), -data_dim:],
data_raw_unthinned[np.random.choice(data_num, 500), -data_dim:])
# Compute KL only between data dimensions, and not latent ones.
kl_gen_vs_unthinned = compute_kl(
generated[np.random.choice(n_sample, 500), -data_dim:],
data_raw_unthinned[np.random.choice(data_num, 500), -data_dim:], k=5)
if data_dim == 2:
fig = plot(generated, data_raw, data_raw_unthinned, it,
mmd_gen_vs_unthinned)
if np.isnan(d_loss_):
sys.exit('got nan')
# Print diagnostics.
print("#################")
print('cgan_{}'.format(tag))
print('Iter: {}'.format(it))
print(' d_loss: {:.4}'.format(d_loss_))
print(' g_loss: {:.4}'.format(g_loss_))
