block_size = args.block_size
engine = ccc.get_CrossCatClient('hadoop', seed = inf_seed)
if filename is not None:
# Load the data from table and sub-sample entities to max_rows
T, M_r, M_c = du.read_model_data_from_csv(filename, max_rows, gen_seed)
truth_flag = 0
else:
T, M_r, M_c, data_inverse_permutation_indices = \
du.gen_factorial_data_objects(gen_seed, num_clusters,
num_cols, max_rows, num_views,
max_mean=100, max_std=1,
send_data_inverse_permutation_indices=True)
view_assignment_truth, X_D_truth = ctu.truth_from_permute_indices(data_inverse_permutation_indices, max_rows,num_cols,num_views, num_clusters)
truth_flag = 1
num_rows = len(T)
num_cols = len(T[0])
ari_table = []
ari_views = []
print 'Initializing ...'
# Call Initialize and Analyze
M_c, M_r, X_L_list, X_D_list = engine.initialize(M_c, M_r, T, n_chains = numChains)
if truth_flag:
tmp_ari_table, tmp_ari_views = ctu.multi_chain_ARI(X_L_list,X_D_list, view_assignment_truth, X_D_truth)
ari_table.append(tmp_ari_table)
num_cols = 32
num_rows = 400
num_views = 2
n_steps = 1
n_times = 5
n_chains = 3
n_test = 100
CT_KERNEL = 1
get_next_seed = make_get_next_seed(gen_seed)
# generate some data
T, M_r, M_c, data_inverse_permutation_indices = du.gen_factorial_data_objects(
get_next_seed(), num_clusters, num_cols, num_rows, num_views,
max_mean=100, max_std=1, send_data_inverse_permutation_indices=True)
view_assignment_truth, X_D_truth = ctu.truth_from_permute_indices(
data_inverse_permutation_indices, num_rows, num_cols, num_views, num_clusters)
# run some tests
engine = LocalEngine()
multi_state_ARIs = []
multi_state_mean_test_lls = []
X_L_list, X_D_list = engine.initialize(M_c, M_r, T, get_next_seed(),
n_chains=n_chains)
multi_state_ARIs.append(
ctu.get_column_ARIs(X_L_list, view_assignment_truth))
for time_i in range(n_times):
X_L_list, X_D_list = engine.analyze(
M_c, T, X_L_list, X_D_list, get_next_seed(), n_steps=n_steps,
CT_KERNEL=CT_KERNEL)
multi_state_ARIs.append(
