def experiment_mwu_n_rounds(rounds,
g,
p, q, epsilon,
sampling_method,
active_method,
reward_method,
n1=100,
seed=None):
np.random.seed(seed)
random.seed(seed)
results = []
gvs = get_gvs(g, p, n1)
for i in tqdm(range(rounds)):
infection_times, source, obs_nodes = gen_nontrivial_cascade(
g, p, q)
r = mwu(g, gvs,
source, obs_nodes, infection_times, o2src_time=None,
active_method=active_method,
reward_method=reward_method,
eps=0.2,
max_iter=g.num_vertices(),
use_uninfected=True,
debug=False)
if r > 0:
results.append(r)
return results
def experiment_mwu_n_rounds(rounds,
g,
p,
q,
epsilon,
sampling_method,
active_method,
reward_method,
n1=100,
seed=None):
np.random.seed(seed)
random.seed(seed)
results = []
gvs = get_gvs(g, p, n1)
for i in tqdm(range(rounds)):
infection_times, source, obs_nodes = gen_nontrivial_cascade(g, p, q)
r = mwu(g,
gvs,
source,
obs_nodes,
infection_times,
o2src_time=None,
active_method=active_method,
reward_method=reward_method,
eps=0.2,
max_iter=g.num_vertices(),
use_uninfected=True,
debug=False)
if r > 0:
results.append(r)
return results
def test_full_observation_tree_region_mst(tree_and_cascade):
g = tree_and_cascade[0]
for p in np.arange(0.2, 1.0, 0.1):
infection_times, source, obs_nodes = gen_nontrivial_cascade(g, p, 1.0)
scores = tree_sizes_by_roots(g, obs_nodes, infection_times, source,
method='region_mst')
assert get_rank_index(scores, source) == 0
def test_full_observation_grid_region_mst(grid_and_cascade):
g = grid_and_cascade[0]
for p in np.arange(0.5, 1.0, 0.1):
print('p={}'.format(p))
infection_times, source, obs_nodes = gen_nontrivial_cascade(g, p, 1.0)
scores = tree_sizes_by_roots(g, obs_nodes, infection_times, source,
method='region_mst')
assert get_rank_index(scores, source) <= 0
def test_full_observation_tree_tbfs(tree_and_cascade):
g = tree_and_cascade[0]
for p in np.arange(0.2, 1.0, 0.1):
infection_times, source, obs_nodes = gen_nontrivial_cascade(g, p, 1.0)
scores = tree_sizes_by_roots(g,
obs_nodes,
infection_times,
source,
method='tbfs')
assert get_rank_index(scores, source) == 0
def test_full_observation_grid_tbfs(grid_and_cascade):
g = grid_and_cascade[0]
for p in np.arange(0.5, 1.0, 0.1):
print('p={}'.format(p))
infection_times, source, obs_nodes = gen_nontrivial_cascade(g, p, 1.0)
scores = tree_sizes_by_roots(g,
obs_nodes,
infection_times,
source,
method='tbfs')
assert get_rank_index(scores, source) <= 1.0
def source_likelihood_stat(g,
gvs,
p,
q,
N1,
estimation_method,
precond_method,
eps,
debug=True):
sll_array = []
sources = []
dist_array = []
if debug:
iters = tqdm(range(N1))
else:
iters = range(N1)
for i in iters:
infection_times, source, obs_nodes = gen_nontrivial_cascade(g, p, q)
sources.append(source)
if estimation_method == 'steiner-tree-exact':
if debug:
print('using steiner tree exact')
sll = best_tree_sizes(g, obs_nodes, infection_times)
else:
if debug:
print(
'using steiner tree order ({})'.format(estimation_method))
sll = tree_sizes_by_roots(g,
obs_nodes,
infection_times,
source,
method=estimation_method)
winner = np.argmax(sll)
dist_to_max_n = shortest_distance(g, source=source, target=winner)
dist_array.append(dist_to_max_n)
sll_array.append(sll)
source_likelihood_array = np.array(sll_array, dtype=np.float64)
source_llh = np.array(
[source_likelihood_array[i, src] for i, src in enumerate(sources)])
ranks = np.array([
get_rank_index(source_likelihood_array[i, :], src)
for i, src in enumerate(sources)
])
return {
'dist': pd.Series(dist_array).describe(),
'mu[s]': pd.Series(source_llh).describe(),
'rank': pd.Series(ranks).describe(),
}
def source_likelihood_stat(g,
gvs, p, q, N1,
estimation_method,
precond_method,
eps,
debug=True):
sll_array = []
sources = []
dist_array = []
if debug:
iters = tqdm(range(N1))
else:
iters = range(N1)
for i in iters:
infection_times, source, obs_nodes = gen_nontrivial_cascade(g, p, q)
sources.append(source)
if estimation_method == 'steiner-tree-exact':
if debug:
print('using steiner tree exact')
sll = best_tree_sizes(g, obs_nodes, infection_times)
else:
if debug:
print('using steiner tree order ({})'.format(estimation_method))
sll = tree_sizes_by_roots(g, obs_nodes, infection_times, source,
method=estimation_method)
winner = np.argmax(sll)
dist_to_max_n = shortest_distance(g, source=source, target=winner)
dist_array.append(dist_to_max_n)
sll_array.append(sll)
source_likelihood_array = np.array(sll_array, dtype=np.float64)
source_llh = np.array([source_likelihood_array[i, src]
for i, src in enumerate(sources)])
ranks = np.array([get_rank_index(source_likelihood_array[i, :], src)
for i, src in enumerate(sources)])
return {
'dist': pd.Series(dist_array).describe(),
'mu[s]': pd.Series(source_llh).describe(),
'rank': pd.Series(ranks).describe(),
}
def test_full_observation_grid(grid_and_cascade):
g = grid_and_cascade[0]
for p in np.arange(0.5, 1.0, 0.1):
infection_times, source, obs_nodes = gen_nontrivial_cascade(g, p, 1.0)
scores = best_tree_sizes(g, obs_nodes, infection_times)
assert get_rank_index(scores, source) == 0
def grid_and_cascade():
g = load_graph('data/grid/2-6/graph.gt')
c, s, o = gen_nontrivial_cascade(g, 0.8, 0.5)
return g, get_gvs(g, 0.5, 100), c, s, o
def tree_and_cascade():
g = load_graph('data/balanced-tree/2-6/graph.gt')
c, s, o = gen_nontrivial_cascade(g, 0.8, 0.5)
return g, get_gvs(g, 0.5, 100), c, s, o
def test_full_observation_grid(grid_and_cascade):
g = grid_and_cascade[0]
for p in np.arange(0.5, 1.0, 0.1):
infection_times, source, obs_nodes = gen_nontrivial_cascade(g, p, 1.0)
scores = best_tree_sizes(g, obs_nodes, infection_times)
assert get_rank_index(scores, source) == 0