def data_gen():
### IN
## experiment stuff
np.random.seed(1234)
data_dir = 'data'
n_exp = 1 # number of experiments
## LDA stuff
W = 25 # word vocabulary
L = int(np.sqrt(W)) # image size
T = 2*L # topics
D = 1000 # documents
N = 100 # words per document
alpha = 1. # hyper-param for mixture of topics (theta)
beta = 1. # hyper-param for topic distribs (phi),
# used only as param in pb
# stan
chains = 1
# phi is given as the horizontal and vertical topics on the 5X5 images
phi = [np.zeros((L, L)) for i in range(T)]
line = 0
for phi_t in phi:
if line >= L:
trueLine = int(line - L)
phi_t[:,trueLine] = 1./L*np.ones(L)
else:
phi_t[line] = 1./L*np.ones(L)
line += 1
rewrite_dir(data_dir)
[write_data(data_dir, i, W, L, T, D, N, phi, alpha, beta, chains)
for i in range(n_exp)]
def data_gen():
K = 6
beta = 50./float(K)
gamma = 0.1
fin_name = 'data/sushi3/sushi3a.5000.10.order'
fout_name = 'data/sushi3/sushi3.pb'
rewrite_dir('data')
call_cmd('sh get_data.sh')
N, data = read_data(fin_name)
write_pb(fout_name, N, data, K, beta, gamma)
def data_gen(seed, n_exp, W, L, T, D, N, alpha, beta):
np.random.seed(seed)
data_dir = 'data'
# phi is given as the horizontal and vertical topics on the 5X5 images
phi = [np.zeros((L, L)) for i in range(T)]
line = 0
for phi_t in phi:
if line >= L:
trueLine = int(line - L)
phi_t[:,trueLine] = 1./L*np.ones(L)
else:
phi_t[line] = 1./L*np.ones(L)
line += 1
rewrite_dir(data_dir)
plot_topics(T, phi, 'data/lda_ground_phi')
[write_pb_txt(data_dir, i, W, L, T, D, N, phi, alpha, beta)
for i in range(n_exp)]