def analyze_helper(table_data, data_dict, command_dict):
M_c = table_data['M_c']
T = table_data['T']
SEED = data_dict['SEED']
X_L = data_dict['X_L']
X_D = data_dict['X_D']
kernel_list = command_dict['kernel_list']
n_steps = command_dict['n_steps']
c = command_dict['c']
r = command_dict['r']
max_time = command_dict['max_time']
engine = LE.LocalEngine(SEED)
X_L_prime, X_D_prime = engine.analyze(M_c,
T,
X_L,
X_D,
kernel_list=kernel_list,
n_steps=n_steps,
c=c,
r=r,
max_time=max_time)
SEED = engine.get_next_seed()
#
ret_dict = dict(SEED=SEED, X_L=X_L_prime, X_D=X_D_prime)
return ret_dict
def mi_analyze_helper(table_data, data_dict, command_dict):
gen_seed = data_dict['SEED']
crosscat_seed = data_dict['CCSEED']
num_clusters = data_dict['num_clusters']
num_cols = data_dict['num_cols']
num_rows = data_dict['num_rows']
num_views = data_dict['num_views']
corr = data_dict['corr']
burn_in = data_dict['burn_in']
mean_range = float(num_clusters)*2.0
# 32 bit signed int
random.seed(gen_seed)
get_next_seed = lambda : random.randrange(2147483647)
# generate the stats
T, M_c, M_r, X_L, X_D, view_assignment = mitu.generate_correlated_state(num_rows,
num_cols, num_views, num_clusters, mean_range, corr, seed=gen_seed);
table_data = dict(T=T,M_c=M_c)
engine = LE.LocalEngine(crosscat_seed)
X_L_prime, X_D_prime = engine.analyze(M_c, T, X_L, X_D, n_steps=burn_in)
X_L = X_L_prime
X_D = X_D_prime
view_assignment = numpy.array(X_L['column_partition']['assignments'])
# for each view calclate the average MI between all pairs of columns
n_views = max(view_assignment)+1
MI = []
Linfoot = []
queries = []
MI = 0.0
pairs = 0.0
for view in range(n_views):
columns_in_view = numpy.nonzero(view_assignment==view)[0]
combinations = itertools.combinations(columns_in_view,2)
for pair in combinations:
any_pairs = True
queries.append(pair)
MI_i, Linfoot_i = iu.mutual_information(M_c, [X_L], [X_D], [pair], n_samples=1000)
MI += MI_i[0][0]
pairs += 1.0
if pairs > 0.0:
MI /= pairs
ret_dict = dict(
id=data_dict['id'],
dataset=data_dict['dataset'],
sample=data_dict['sample'],
mi=MI,
)
return ret_dict
def initialize_helper(table_data, data_dict, command_dict):
M_c = table_data['M_c']
M_r = table_data['M_r']
T = table_data['T']
SEED = data_dict['SEED']
initialization = command_dict['initialization']
engine = LE.LocalEngine(SEED)
X_L, X_D = engine.initialize(M_c, M_r, T, initialization=initialization)
SEED = engine.get_next_seed()
#
ret_dict = dict(SEED=SEED, X_L=X_L, X_D=X_D)
return ret_dict
def convergence_analyze_helper(table_data, data_dict, command_dict):
gen_seed = data_dict['SEED']
num_clusters = data_dict['num_clusters']
num_cols = data_dict['num_cols']
num_rows = data_dict['num_rows']
num_views = data_dict['num_views']
max_mean = data_dict['max_mean']
n_test = data_dict['n_test']
num_transitions = data_dict['n_steps']
block_size = data_dict['block_size']
init_seed = data_dict['init_seed']
# generate some data
T, M_r, M_c, data_inverse_permutation_indices = \
du.gen_factorial_data_objects(gen_seed, num_clusters,
num_cols, num_rows, num_views,
max_mean=max_mean, max_std=1,
send_data_inverse_permutation_indices=True)
view_assignment_ground_truth = \
ctu.determine_synthetic_column_ground_truth_assignments(num_cols,
num_views)
X_L_gen, X_D_gen = ttu.get_generative_clustering(
M_c, M_r, T, data_inverse_permutation_indices, num_clusters, num_views)
T_test = ctu.create_test_set(M_c, T, X_L_gen, X_D_gen, n_test, seed_seed=0)
generative_mean_test_log_likelihood = \
ctu.calc_mean_test_log_likelihood(M_c, T, X_L_gen, X_D_gen, T_test)
# additional set up
engine = LE.LocalEngine(init_seed)
column_ari_list = []
mean_test_ll_list = []
elapsed_seconds_list = []
# get initial ARI, test_ll
with gu.Timer('initialize', verbose=False) as timer:
X_L, X_D = engine.initialize(M_c,
M_r,
T,
initialization='from_the_prior')
column_ari = ctu.get_column_ARI(X_L, view_assignment_ground_truth)
column_ari_list.append(column_ari)
mean_test_ll = ctu.calc_mean_test_log_likelihood(M_c, T, X_L, X_D, T_test)
mean_test_ll_list.append(mean_test_ll)
elapsed_seconds_list.append(timer.elapsed_secs)
# run blocks of transitions, recording ARI, test_ll progression
completed_transitions = 0
n_steps = min(block_size, num_transitions)
while (completed_transitions < num_transitions):
# We won't be limiting by time in the convergence runs
with gu.Timer('initialize', verbose=False) as timer:
X_L, X_D = engine.analyze(M_c,
T,
X_L,
X_D,
kernel_list=(),
n_steps=n_steps,
max_time=-1)
completed_transitions = completed_transitions + block_size
#
column_ari = ctu.get_column_ARI(X_L, view_assignment_ground_truth)
column_ari_list.append(column_ari)
mean_test_ll = ctu.calc_mean_test_log_likelihood(
M_c, T, X_L, X_D, T_test)
mean_test_ll_list.append(mean_test_ll)
elapsed_seconds_list.append(timer.elapsed_secs)
ret_dict = dict(
num_rows=num_rows,
num_cols=num_cols,
num_views=num_views,
num_clusters=num_clusters,
max_mean=max_mean,
column_ari_list=column_ari_list,
mean_test_ll_list=mean_test_ll_list,
generative_mean_test_log_likelihood=generative_mean_test_log_likelihood,
elapsed_seconds_list=elapsed_seconds_list,
n_steps=num_transitions,
block_size=block_size,
)
return ret_dict