def machine_similarities(self, machine1, machine2):
pn1, pn2 = machine1.printname(), machine2.printname()
self.log(u"machine1: {0}, machine2: {1}".format(pn1, pn2))
sims = self.zero_similarities()
links1, nodes1 = self.get_links_nodes(machine1)
links2, nodes2 = self.get_links_nodes(machine2)
self.log("links1: {0}, links2: {1}".format(links1, links2))
self.log("nodes1: {0}, nodes2: {1}".format(nodes1, nodes2))
if self.contains(links1, machine2) or self.contains(links2, machine1):
sims["links_contain"] = 1
if self.contains(nodes1, machine2) or self.contains(nodes2, machine1):
sims["nodes_contain"] = 1
pn1, pn2 = machine1.printname(), machine2.printname()
# TODO
if pn1 in links2 or pn2 in links1:
sims["0-connected"] = 1
entities1 = filter(lambda l: "@" in l, links1)
entities2 = filter(lambda l: "@" in l, links2)
sims["entities_jaccard"] = jaccard(entities1, entities2)
sims["links_jaccard"] = jaccard(links1, links2)
sims["nodes_jaccard"] = jaccard(nodes1, nodes2)
return sims
def _links_and_nodes_similarity(self,
machine1,
machine2,
exclude_nodes=False,
no_contain_score=False):
sim = 0
links1, nodes1 = self.get_links_nodes(machine1)
links2, nodes2 = self.get_links_nodes(machine2)
if not no_contain_score:
if (self.contains(links1, machine2)
or self.contains(links2, machine1)):
sim = max(sim, 0.35)
elif (not exclude_nodes) and (self.contains(nodes1, machine2)
or self.contains(nodes2, machine1)):
sim = max(sim, 0.25)
self.log('links1: {0}, links2: {1}'.format(links1, links2))
self.log('nodes1: {0}, nodes2: {1}'.format(nodes1, nodes2))
if True:
pn1, pn2 = machine1.printname(), machine2.printname()
if pn1 in links2 or pn2 in links1:
self.log("{0} and {1} connected by 0-path, returning 1".format(
pn1, pn2))
return 1
entities1 = filter(lambda l: "@" in l, links1)
entities2 = filter(lambda l: "@" in l, links2)
if entities1 or entities2:
sim = max(sim, jaccard(entities1, entities2))
else:
sim = max(sim, jaccard(links1, links2))
if not exclude_nodes:
node_sim = jaccard(nodes1, nodes2)
if node_sim > sim:
self.log(
'picking node sim ({0}) over link sim ({1})'.format(
node_sim, sim))
sim = node_sim
return sim
def _links_and_nodes_similarity(self, machine1, machine2,
exclude_nodes=False,
no_contain_score=False):
sim = 0
links1, nodes1 = self.get_links_nodes(machine1)
links2, nodes2 = self.get_links_nodes(machine2)
if not no_contain_score:
if (self.contains(links1, machine2) or
self.contains(links2, machine1)):
sim = max(sim, 0.35)
elif (not exclude_nodes) and (self.contains(nodes1, machine2) or
self.contains(nodes2, machine1)):
sim = max(sim, 0.25)
self.log('links1: {0}, links2: {1}'.format(links1, links2))
self.log('nodes1: {0}, nodes2: {1}'.format(nodes1, nodes2))
if True:
pn1, pn2 = machine1.printname(), machine2.printname()
if pn1 in links2 or pn2 in links1:
self.log(
"{0} and {1} connected by 0-path, returning 1".format(
pn1, pn2))
return 1
entities1 = filter(lambda l: "@" in l, links1)
entities2 = filter(lambda l: "@" in l, links2)
if entities1 or entities2:
sim = max(sim, jaccard(entities1, entities2))
else:
sim = max(sim, jaccard(links1, links2))
if not exclude_nodes:
node_sim = jaccard(nodes1, nodes2)
if node_sim > sim:
self.log(
'picking node sim ({0}) over link sim ({1})'.format(
node_sim, sim))
sim = node_sim
return sim
def nodes_jaccard(self, nodes1, nodes2):
return {"nodes_jaccard": jaccard(nodes1, nodes2)}
def entitiess_jaccard(self, links1, links2):
entities1 = filter(lambda l: "@" in l, links1)
entities2 = filter(lambda l: "@" in l, links2)
return {'entities_jaccard': jaccard(entities1, entities2)}
def links_jaccard(self, links1, links2):
return {"links_jaccard": jaccard(links1, links2)}
def graph_similarity(graph1, graph2):
return jaccard(graph1.edges, graph2.edges)
def nodes_jaccard(self, nodes1, nodes2):
return { "nodes_jaccard" : jaccard(nodes1, nodes2)}
def entitiess_jaccard(self, links1, links2):
entities1 = filter(lambda l: "@" in l, links1)
entities2 = filter(lambda l: "@" in l, links2)
return {'entities_jaccard' : jaccard(entities1, entities2)}
def links_jaccard(self, links1, links2):
return { "links_jaccard" : jaccard(links1, links2)}
def graph_similarity(graph1, graph2):
return jaccard(graph1.edges, graph2.edges)