def simulate_cascade(g, p, source=None, return_tree=False):
"""
graph_tool version of simulating cascade
return np.ndarray on vertices as the infection time in cascade
uninfected node has dist -1
"""
gv = sample_graph_by_p(g, p)
if source is None:
# consider the largest cc
infected_nodes = np.nonzero(label_largest_component(gv).a)[0]
source = np.random.choice(infected_nodes)
times = get_infection_time(gv, source)
if return_tree:
# get the tree edges
_, pred_map = shortest_distance(gv, source=source, pred_map=True)
edges = [(pred_map[i], i) for i in infected_nodes if i != source]
# create tree
tree = Graph(directed=True)
tree.add_vertex(g.num_vertices())
for u, v in edges:
tree.add_edge(int(u), int(v))
vfilt = tree.new_vertex_property('bool')
vfilt.a = False
for v in set(itertools.chain(*edges)):
vfilt[v] = True
tree.set_vertex_filter(vfilt)
if return_tree:
return source, times, tree
else:
return source, times
def steiner_tree_mst(g, root, infection_times, source, terminals,
closure_builder=build_closure,
strictly_smaller=True,
return_closure=False,
k=-1,
debug=False,
verbose=True):
gc, eweight, r2pred = closure_builder(g, root, terminals,
infection_times,
strictly_smaller=strictly_smaller,
k=k,
debug=debug,
verbose=verbose)
# get the minimum spanning arborescence
# graph_tool does not provide minimum_spanning_arborescence
if verbose:
print('getting mst')
gx = gt2nx(gc, root, terminals, edge_attrs={'weight': eweight})
try:
nx_tree = nx.minimum_spanning_arborescence(gx, 'weight')
except nx.exception.NetworkXException:
if debug:
print('fail to find mst')
if return_closure:
return None, gc, None
else:
return None
if verbose:
print('returning tree')
mst_tree = Graph(directed=True)
for _ in range(g.num_vertices()):
mst_tree.add_vertex()
for u, v in nx_tree.edges():
mst_tree.add_edge(u, v)
if verbose:
print('extract edges from original graph')
# extract the edges from the original graph
# sort observations by time
# and also topological order
topological_index = {}
for i, e in enumerate(bfs_iterator(mst_tree, source=root)):
topological_index[int(e.target())] = i
sorted_obs = sorted(
set(terminals) - {root},
key=lambda o: (infection_times[o], topological_index[o]))
tree_nodes = {root}
tree_edges = set()
# print('root', root)
for u in sorted_obs:
if u in tree_nodes:
if debug:
print('{} covered already'.format(u))
continue
# print(u)
v, u = map(int, next(mst_tree.vertex(u).in_edges())) # v is ancestor
tree_nodes.add(v)
late_nodes = [n for n in terminals if infection_times[n] > infection_times[u]]
vis = init_visitor(g, u)
# from child to any tree node, including v
cpbfs_search(g, source=u, terminals=list(tree_nodes),
forbidden_nodes=late_nodes,
visitor=vis,
count_threshold=1)
# dist, pred = shortest_distance(g, source=u, pred_map=True)
node_set = {v for v, d in vis.dist.items() if d > 0}
reachable_tree_nodes = node_set.intersection(tree_nodes)
ancestor = min(reachable_tree_nodes, key=vis.dist.__getitem__)
edges = extract_edges_from_pred(g, u, ancestor, vis.pred)
edges = {(j, i) for i, j in edges} # need to reverse it
if debug:
print('tree_nodes', tree_nodes)
print('connecting {} to {}'.format(v, u))
print('using ancestor {}'.format(ancestor))
print('adding edges {}'.format(edges))
tree_nodes |= {u for e in edges for u in e}
tree_edges |= edges
t = Graph(directed=True)
for _ in range(g.num_vertices()):
t.add_vertex()
for u, v in tree_edges:
t.add_edge(t.vertex(u), t.vertex(v))
tree_nodes = {u for e in tree_edges for u in e}
vfilt = t.new_vertex_property('bool')
vfilt.a = False
for v in tree_nodes:
vfilt[t.vertex(v)] = True
t.set_vertex_filter(vfilt)
if return_closure:
return t, gc, mst_tree
else:
return t
prev_q = cur_qual["q"]
prev_c = cur_comp["c"]
ver_attractions = pairs_graph.vertex_properties["attraction"]
# cutting vertices with attractions in [low, hig]
not_deleted = pairs_graph.vertex_properties["notdeleted"]
for v in pairs_graph.vertices():
if low <= ver_attractions[v] <= hig:
neutral.append(ver_names[v])
if ver_part[v] == 1:
positive.remove(ver_names[v])
ver_part[v] = 0
elif ver_part[v] == -1:
negative.remove(ver_names[v])
ver_part[v] = 0
not_deleted[v] = False
pairs_graph.set_vertex_filter(not_deleted)
pairs_graph.purge_vertices()
# recalculating attractions, plotting and calculating quality and completeness
pairs_graph.vertex_properties["attraction"] = get_attractions(pairs_graph)
cur_qual = qual.get_quality(positive, negative, neutral)
cur_comp = compl.get_completeness(positive, negative, neutral)
print("-----------------------------------------------")
print("Sum vol = " + str(len(neutral) + len(positive) + len(negative)))
print("total neutral cutted = " + str(len(neutral)))
print("pos = " + str(len(positive)))
print("neg = " + str(len(negative)))
print("Quality = " + str(cur_qual["q"]))
print("Rude mist. % = " + str(cur_qual["rude"]))
print(cur_qual["notfound"])
print("Completeness = " + str(cur_comp["c"]))
print("-----------------------------------------------")
class PointerProvenancePlot(Plot):
"""
Base class for plots using the pointer provenance graph.
"""
def __init__(self, *args, **kwargs):
super(PointerProvenancePlot, self).__init__(*args, **kwargs)
self._cached_dataset_valid = False
"""Tells whether we need to rebuild the dataset when caching."""
def init_parser(self, dataset, tracefile):
if self.caching and os.path.exists(self._get_cache_file()):
# if caching we will nevere use this
return None
return PointerProvenanceParser(dataset, tracefile)
def init_dataset(self):
logger.debug("Init provenance graph for %s", self.tracefile)
self.dataset = Graph(directed=True)
vdata = self.dataset.new_vertex_property("object")
self.dataset.vp["data"] = vdata
return self.dataset
def _get_cache_file(self):
return self.tracefile + "_provenance_plot.gt"
def build_dataset(self):
"""
Build the provenance tree
"""
if self.caching:
try:
logger.debug("Load cached provenance graph")
self.dataset = load_graph(self._get_cache_file())
except IOError:
self.parser.parse()
self.dataset.save(self._get_cache_file())
else:
self.parser.parse()
num_nodes = self.dataset.num_vertices()
logger.debug("Total nodes %d", num_nodes)
vertex_mask = self.dataset.new_vertex_property("bool")
progress = ProgressPrinter(num_nodes, desc="Search kernel nodes")
for node in self.dataset.vertices():
# remove null capabilities
# remove operations in kernel mode
vertex_data = self.dataset.vp.data
node_data = vertex_data[node]
if ((node_data.pc != 0 and node_data.is_kernel) or
(node_data.cap.length == 0 and node_data.cap.base == 0)):
vertex_mask[node] = True
progress.advance()
progress.finish()
self.dataset.set_vertex_filter(vertex_mask, inverted=True)
vertex_mask = self.dataset.copy_property(vertex_mask)
num_nodes = self.dataset.num_vertices()
logger.debug("Filtered kernel nodes, remaining %d", num_nodes)
progress = ProgressPrinter(
num_nodes, desc="Merge (cfromptr + csetbounds) sequences")
for node in self.dataset.vertices():
progress.advance()
# merge cfromptr -> csetbounds subtrees
num_parents = node.in_degree()
if num_parents == 0:
# root node
continue
elif num_parents > 1:
logger.error("Found node with more than a single parent %s", node)
raise RuntimeError("Too many parents for a node")
parent = next(node.in_neighbours())
parent_data = self.dataset.vp.data[parent]
node_data = self.dataset.vp.data[node]
if (parent_data.origin == CheriNodeOrigin.FROMPTR and
node_data.origin == CheriNodeOrigin.SETBOUNDS):
# the child must be unique to avoid complex logic
# when merging, it may be desirable to do so with
# more complex traces
node_data.origin = CheriNodeOrigin.PTR_SETBOUNDS
if parent.in_degree() == 1:
next_parent = next(parent.in_neighbours())
vertex_mask[parent] = True
self.dataset.add_edge(next_parent, node)
elif parent.in_degree() == 0:
vertex_mask[parent] = True
else:
logger.error("Found node with more than a single parent %s",
parent)
raise RuntimeError("Too many parents for a node")
progress.finish()
self.dataset.set_vertex_filter(vertex_mask, inverted=True)
vertex_mask = self.dataset.copy_property(vertex_mask)
num_nodes = self.dataset.num_vertices()
logger.debug("Merged (cfromptr + csetbounds), remaining %d", num_nodes)
progress = ProgressPrinter(num_nodes, desc="Find short-lived cfromptr")
for node in self.dataset.vertices():
progress.advance()
node_data = self.dataset.vp.data[node]
if node_data.origin == CheriNodeOrigin.FROMPTR:
vertex_mask[node] = True
# if (node_data.origin == CheriNodeOrigin.FROMPTR and
# len(node_data.address) == 0 and
# len(node_data.deref["load"]) == 0 and
# len(node_data.deref["load"]) == 0):
# # remove cfromptr that are never stored or used in
# # a dereference
# remove_list.append(node)
progress.finish()
self.dataset.set_vertex_filter(vertex_mask, inverted=True)
prev_q = cur_qual["q"]
prev_c = cur_comp["c"]
ver_attractions = pairs_graph.vertex_properties["attraction"]
# cutting vertices with attractions in [low, hig]
not_deleted = pairs_graph.vertex_properties["notdeleted"]
for v in pairs_graph.vertices():
if low <= ver_attractions[v] <= hig:
neutral.append(ver_names[v])
if ver_part[v] == 1:
positive.remove(ver_names[v])
ver_part[v] = 0
elif ver_part[v] == -1:
negative.remove(ver_names[v])
ver_part[v] = 0
not_deleted[v] = False
pairs_graph.set_vertex_filter(not_deleted)
pairs_graph.purge_vertices()
# recalculating attractions, plotting and calculating quality and completeness
pairs_graph.vertex_properties["attraction"] = get_attractions(pairs_graph)
cur_qual = qual.get_quality(positive, negative, neutral)
cur_comp = compl.get_completeness(positive, negative, neutral)
print("-----------------------------------------------")
print("Sum vol = " + str(len(neutral) + len(positive) + len(negative)))
print("total neutral cutted = " + str(len(neutral)))
print("pos = " + str(len(positive)))
print("neg = " + str(len(negative)))
print("Quality = " + str(cur_qual["q"]))
print("Rude mist. % = " + str(cur_qual["rude"]))
print(cur_qual["notfound"])
print("Completeness = " + str(cur_comp["c"]))
print("-----------------------------------------------")
def steiner_tree_mst(g,
root,
infection_times,
source,
terminals,
closure_builder=build_closure,
strictly_smaller=True,
return_closure=False,
k=-1,
debug=False,
verbose=True):
gc, eweight, r2pred = closure_builder(g,
root,
terminals,
infection_times,
strictly_smaller=strictly_smaller,
k=k,
debug=debug,
verbose=verbose)
# get the minimum spanning arborescence
# graph_tool does not provide minimum_spanning_arborescence
if verbose:
print('getting mst')
gx = gt2nx(gc, root, terminals, edge_attrs={'weight': eweight})
try:
nx_tree = nx.minimum_spanning_arborescence(gx, 'weight')
except nx.exception.NetworkXException:
if debug:
print('fail to find mst')
if return_closure:
return None, gc, None
else:
return None
if verbose:
print('returning tree')
mst_tree = Graph(directed=True)
for _ in range(g.num_vertices()):
mst_tree.add_vertex()
for u, v in nx_tree.edges():
mst_tree.add_edge(u, v)
if verbose:
print('extract edges from original graph')
# extract the edges from the original graph
# sort observations by time
# and also topological order
topological_index = {}
for i, e in enumerate(bfs_iterator(mst_tree, source=root)):
topological_index[int(e.target())] = i
sorted_obs = sorted(set(terminals) - {root},
key=lambda o:
(infection_times[o], topological_index[o]))
tree_nodes = {root}
tree_edges = set()
# print('root', root)
for u in sorted_obs:
if u in tree_nodes:
if debug:
print('{} covered already'.format(u))
continue
# print(u)
v, u = map(int, next(mst_tree.vertex(u).in_edges())) # v is ancestor
tree_nodes.add(v)
late_nodes = [
n for n in terminals if infection_times[n] > infection_times[u]
]
vis = init_visitor(g, u)
# from child to any tree node, including v
cpbfs_search(g,
source=u,
terminals=list(tree_nodes),
forbidden_nodes=late_nodes,
visitor=vis,
count_threshold=1)
# dist, pred = shortest_distance(g, source=u, pred_map=True)
node_set = {v for v, d in vis.dist.items() if d > 0}
reachable_tree_nodes = node_set.intersection(tree_nodes)
ancestor = min(reachable_tree_nodes, key=vis.dist.__getitem__)
edges = extract_edges_from_pred(g, u, ancestor, vis.pred)
edges = {(j, i) for i, j in edges} # need to reverse it
if debug:
print('tree_nodes', tree_nodes)
print('connecting {} to {}'.format(v, u))
print('using ancestor {}'.format(ancestor))
print('adding edges {}'.format(edges))
tree_nodes |= {u for e in edges for u in e}
tree_edges |= edges
t = Graph(directed=True)
for _ in range(g.num_vertices()):
t.add_vertex()
for u, v in tree_edges:
t.add_edge(t.vertex(u), t.vertex(v))
tree_nodes = {u for e in tree_edges for u in e}
vfilt = t.new_vertex_property('bool')
vfilt.a = False
for v in tree_nodes:
vfilt[t.vertex(v)] = True
t.set_vertex_filter(vfilt)
if return_closure:
return t, gc, mst_tree
else:
return t
