def __init__(self, g, B, timespan_secs):
super(UBSampler, self).__init__(g, timespan_secs)
non_leaf_roots = (n for n in g.nodes_iter() if g.out_degree(n) > 0)
self.nodes_sorted_by_upperbound = sorted(
non_leaf_roots,
key=lambda r: quota_upperbound(
IU.get_rooted_subgraph_within_timespan(g, r, timespan_secs), r,
B),
reverse=True)
def __init__(self, g, B, timespan_secs):
super(UBSampler, self).__init__(g, timespan_secs)
non_leaf_roots = (n for n in g.nodes_iter() if g.out_degree(n) > 0)
self.nodes_sorted_by_upperbound = sorted(
non_leaf_roots,
key=lambda r: quota_upperbound(
IU.get_rooted_subgraph_within_timespan(g, r, timespan_secs),
r, B),
reverse=True
)
def test_bs_ensure_result_is_tree(self):
params = pkl.load(
open(make_path('test/data/quota_test_cases/params.pkl')))[0]
root = params['roots'][0]
preprune_secs = params['preprune_secs']
mg = IU.get_topic_meta_graph_from_synthetic(
make_path('test/data/quota_test_cases/interactions.json'),
preprune_secs)
dag = IU.get_rooted_subgraph_within_timespan(mg, root, preprune_secs)
t = charikar_algo(dag, root, dag.nodes(), k=20, level=2)
assert_true(nx.is_arborescence(t))
def __init__(self, g, B, timespan_secs, node_score_func=log_x_density):
super(AdaptiveSampler, self).__init__(g, timespan_secs)
non_leaf_roots = [n for n in g.nodes_iter() if g.out_degree(n) > 0]
print("AdaptiveSampler: #roots to explore {}".format(
len(non_leaf_roots)))
print("AdaptiveSampler: getting upperbounds...")
upperbounds = map(
lambda r: quota_upperbound(
IU.get_rooted_subgraph_within_timespan(g, r, timespan_secs), r,
B), non_leaf_roots)
print("AdaptiveSampler: sorting the roots by upperbound... ")
inds = np.argsort(np.asarray(upperbounds))[::-1] # descending order
self.roots_sorted_by_upperbound = [non_leaf_roots[i] for i in inds]
self.root2upperbound = {
r: u
for r, u in zip(non_leaf_roots, upperbounds)
}
# self.roots_sorted_by_upperbound = sorted(
# non_leaf_roots,
# key=lambda r: quota_upperbound(
# IU.get_rooted_subgraph_within_timespan(g, r, timespan_secs),
# r, B),
# reverse=True
# )
self.node_score_func = node_score_func
# self.root2upperbound = {r: quota_upperbound(
# IU.get_rooted_subgraph_within_timespan(g, r, timespan_secs),
# r, B)
# for r in non_leaf_roots
# }
# updated at each iteration
# nodes that are partially/fully computed
# excluding leaves
self.covered_nodes = set()
# exclude leaves
# self.roots_to_explore = sorted((n for n in g.nodes_iter()
# if g.out_degree(n) > 0))
self.n_nodes_to_cover = len(self.roots_sorted_by_upperbound)
self.node2score = {}
def test_bs_ensure_result_is_tree(self):
params = pkl.load(
open(make_path('test/data/quota_test_cases/params.pkl'))
)[0]
root = params['roots'][0]
preprune_secs = params['preprune_secs']
mg = IU.get_topic_meta_graph_from_synthetic(
make_path('test/data/quota_test_cases/interactions.json'),
preprune_secs
)
dag = IU.get_rooted_subgraph_within_timespan(
mg, root, preprune_secs
)
t = charikar_algo(dag, root, dag.nodes(),
k=20, level=2)
assert_true(nx.is_arborescence(t))
def __init__(self, g, B, timespan_secs, node_score_func=log_x_density):
super(AdaptiveSampler, self).__init__(g, timespan_secs)
non_leaf_roots = [n for n in g.nodes_iter() if g.out_degree(n) > 0]
print("AdaptiveSampler: #roots to explore {}".format(len(non_leaf_roots)))
print("AdaptiveSampler: getting upperbounds...")
upperbounds = map(lambda r: quota_upperbound(
IU.get_rooted_subgraph_within_timespan(g, r, timespan_secs),
r, B),
non_leaf_roots)
print("AdaptiveSampler: sorting the roots by upperbound... ")
inds = np.argsort(np.asarray(upperbounds))[::-1] # descending order
self.roots_sorted_by_upperbound = [non_leaf_roots[i] for i in inds]
self.root2upperbound = {r: u
for r, u in zip(non_leaf_roots, upperbounds)}
# self.roots_sorted_by_upperbound = sorted(
# non_leaf_roots,
# key=lambda r: quota_upperbound(
# IU.get_rooted_subgraph_within_timespan(g, r, timespan_secs),
# r, B),
# reverse=True
# )
self.node_score_func = node_score_func
# self.root2upperbound = {r: quota_upperbound(
# IU.get_rooted_subgraph_within_timespan(g, r, timespan_secs),
# r, B)
# for r in non_leaf_roots
# }
# updated at each iteration
# nodes that are partially/fully computed
# excluding leaves
self.covered_nodes = set()
# exclude leaves
# self.roots_to_explore = sorted((n for n in g.nodes_iter()
# if g.out_degree(n) > 0))
self.n_nodes_to_cover = len(self.roots_sorted_by_upperbound)
self.node2score = {}
def sample_rooted_binary_graphs_within_timespan(
meta_graph_pickle_path,
sample_number,
timespan,
output_path):
g = nx.read_gpickle(meta_graph_pickle_path)
roots = sample_nodes(g, sample_number)
results = []
for i, r in enumerate(roots):
print('done:', i)
sub_g = InteractionsUtil.get_rooted_subgraph_within_timespan(
g, r, timespan
)
binary_sub_g = binarize_dag(sub_g,
InteractionsUtil.VERTEX_REWARD_KEY,
InteractionsUtil.EDGE_COST_KEY,
dummy_node_name_prefix="d_")
if len(binary_sub_g.edges()) > 0:
results.append(binary_sub_g)
pkl.dump(results, open(output_path, 'w'))
def root_and_dag(self, r):
return r, IU.get_rooted_subgraph_within_timespan(
self.g, r, self.timespan_secs)
def root_and_dag(self, r):
return r, IU.get_rooted_subgraph_within_timespan(
self.g, r, self.timespan_secs
)
