def test_get_gen_cand_tree_params():
event_size = 100
participants_n = 10
event = gen_event_with_known_tree_structure(
event_size=event_size,
participants=range(participants_n),
start_time=10, end_time=110,
event_topic_param=random_topic(10, topic_noise=0.1)[0],
topic_noise=1,
alpha=1.0, tau=0.8,
forward_proba=0.3,
reply_proba=0.5,
create_new_proba=0.2
)
event = IU.assign_edge_weights(event, cosine)
params = get_gen_cand_tree_params(event)
assert_true(params['U'] > 0)
assert_equal(99, params['preprune_secs'])
assert_equal([0], params['roots'])
def make_artificial_data(
# for main events
n_events,
event_size_mu, event_size_sigma,
participant_mu, participant_sigma,
# for minor events
n_minor_events,
minor_event_size_mu, minor_event_size_sigma,
minor_event_participant_mu, minor_event_participant_sigma,
# shared
n_total_participants,
min_time, max_time, event_duration_mu, event_duration_sigma,
n_topics, topic_scaling_factor, topic_noise,
n_noisy_interactions, n_noisy_interactions_fraction,
alpha, tau,
forward_proba,
reply_proba,
create_new_proba,
dist_func):
events, taboo_topics = random_events(
n_events, event_size_mu, event_size_sigma,
n_total_participants, participant_mu, participant_sigma,
min_time, max_time, event_duration_mu, event_duration_sigma,
n_topics, topic_scaling_factor, topic_noise,
alpha, tau,
forward_proba,
reply_proba,
create_new_proba,
accumulate_taboo=True
)
minor_events, _ = random_events(
n_minor_events, minor_event_size_mu, minor_event_size_sigma,
n_total_participants, minor_event_participant_mu,
minor_event_participant_sigma,
min_time, max_time, event_duration_mu, event_duration_sigma,
n_topics, topic_scaling_factor, topic_noise,
alpha, tau,
forward_proba,
reply_proba,
create_new_proba,
taboo_topics=taboo_topics,
accumulate_taboo=False
)
(n_noisy_interactions, _) = get_number_and_percentage(
sum([1 for e in events for _ in e]),
n_noisy_interactions, n_noisy_interactions_fraction
)
noisy_interactions = random_noisy_interactions(
n_noisy_interactions,
min_time, max_time,
n_total_participants,
n_topics, topic_noise,
taboo_topics
)
event_interactions = [e.node[n] for e in events
for n in e.nodes_iter()]
minor_event_interactions = [e.node[n] for e in minor_events
for n in e.nodes_iter()]
all_interactions = (event_interactions + minor_event_interactions
+ noisy_interactions)
# add interaction id
for i, intr in enumerate(all_interactions):
intr['message_id'] = i
intr['topics'] = intr['topics'].tolist()
# relabel the nodes
relabeled_events = []
for e in events:
mapping = {n: e.node[n]['message_id'] for n in e.nodes_iter()}
relabeled_events.append(nx.relabel_nodes(e, mapping))
for e in events:
e = IU.assign_edge_weights(e, dist_func)
gen_cand_trees_params = [get_gen_cand_tree_params(e)
for e in events]
return relabeled_events, all_interactions, gen_cand_trees_params
def make_artificial_data(
# for main events
n_events,
event_size_mu,
event_size_sigma,
participant_mu,
participant_sigma,
# for minor events
n_minor_events,
minor_event_size_mu,
minor_event_size_sigma,
minor_event_participant_mu,
minor_event_participant_sigma,
# shared
n_total_participants,
min_time,
max_time,
event_duration_mu,
event_duration_sigma,
n_topics,
topic_scaling_factor,
topic_noise,
n_noisy_interactions,
n_noisy_interactions_fraction,
alpha,
tau,
forward_proba,
reply_proba,
create_new_proba,
dist_func):
events, taboo_topics = random_events(n_events,
event_size_mu,
event_size_sigma,
n_total_participants,
participant_mu,
participant_sigma,
min_time,
max_time,
event_duration_mu,
event_duration_sigma,
n_topics,
topic_scaling_factor,
topic_noise,
alpha,
tau,
forward_proba,
reply_proba,
create_new_proba,
accumulate_taboo=True)
minor_events, _ = random_events(n_minor_events,
minor_event_size_mu,
minor_event_size_sigma,
n_total_participants,
minor_event_participant_mu,
minor_event_participant_sigma,
min_time,
max_time,
event_duration_mu,
event_duration_sigma,
n_topics,
topic_scaling_factor,
topic_noise,
alpha,
tau,
forward_proba,
reply_proba,
create_new_proba,
taboo_topics=taboo_topics,
accumulate_taboo=False)
(n_noisy_interactions,
_) = get_number_and_percentage(sum([1 for e in events for _ in e]),
n_noisy_interactions,
n_noisy_interactions_fraction)
noisy_interactions = random_noisy_interactions(n_noisy_interactions,
min_time, max_time,
n_total_participants,
n_topics, topic_noise,
taboo_topics)
event_interactions = [e.node[n] for e in events for n in e.nodes_iter()]
minor_event_interactions = [
e.node[n] for e in minor_events for n in e.nodes_iter()
]
all_interactions = (event_interactions + minor_event_interactions +
noisy_interactions)
# add interaction id
for i, intr in enumerate(all_interactions):
intr['message_id'] = i
intr['topics'] = intr['topics'].tolist()
# relabel the nodes
relabeled_events = []
for e in events:
mapping = {n: e.node[n]['message_id'] for n in e.nodes_iter()}
relabeled_events.append(nx.relabel_nodes(e, mapping))
for e in events:
e = IU.assign_edge_weights(e, dist_func)
gen_cand_trees_params = [get_gen_cand_tree_params(e) for e in events]
return relabeled_events, all_interactions, gen_cand_trees_params
