def evaluateModel(model, modelName, reader):
if reader == sick_dev_reader:
dataSet = "dev"
elif reader == sick_test_reader:
dataSet = "test"
else:
dataSet = "train"
predictions = []
goldLabels = []
if modelName == "NB":
model.train()
for label, t1, t2 in reader():
goldLabels.append(label)
predictions = model.predictAll(reader)
else:
count = 0
for label, t1, t2 in reader():
if count % 10 == 0:
print "Processed %d examples" %(count)
goldLabels.append(label)
s1 = " ".join(leaves(t1))
s2 = " ".join(leaves(t2))
modelPredict = model.predict(s1, s2)
predictions.append(modelPredict)
count += 1
accuracy = accuracy_score(predictions, goldLabels)
print "Accuracy on SICK %s set: %f" %(dataSet, accuracy)
def evaluateModel(model, modelName, reader):
if reader == sick_dev_reader:
dataSet = "dev"
elif reader == sick_test_reader:
dataSet = "test"
else:
dataSet = "train"
predictions = []
goldLabels = []
if modelName == "NB":
model.train()
for label, t1, t2 in reader():
goldLabels.append(label)
predictions = model.predictAll(reader)
else:
count = 0
for label, t1, t2 in reader():
if count % 10 == 0:
print "Processed %d examples" % (count)
goldLabels.append(label)
s1 = " ".join(leaves(t1))
s2 = " ".join(leaves(t2))
modelPredict = model.predict(s1, s2)
predictions.append(modelPredict)
count += 1
accuracy = accuracy_score(predictions, goldLabels)
print "Accuracy on SICK %s set: %f" % (dataSet, accuracy)
def keyword_overlap_feature(s1, s2, cioClient):
sent1 = " ".join(leaves(s1))
sent2 = " ".join(leaves(s2))
s1Keywords = cioClient.extractKeywords(sent1)
s2Keywords = cioClient.extractKeywords(sent2)
return collections.Counter(set(s1Keywords) & set(s2Keywords))
def keyword_overlap_feature(s1, s2, cioClient):
sent1 = " ".join(leaves(s1))
sent2 = " ".join(leaves(s2))
s1Keywords = cioClient.extractKeywords(sent1)
s2Keywords = cioClient.extractKeywords(sent2)
return collections.Counter(set(s1Keywords) & set(s2Keywords))
def get_modules_to_remove(self):
""" Returns the shortest list of modules to remove"""
states = [States.TO_REMOVE]
graph = self._sub_graph_from_states(self._graph, states=states)
modules = leaves(graph)
lcas = self._lowest_common_ancestors(graph, modules, states=states)
return sorted(lcas)
def leaves(self):
""" Return modules not in dependency of any other module
@:returns list<string> (A module names list)
"""
modules = leaves(self._graph)
return modules
def _lowest_common_ancestors(self,
graph,
names=None,
states=None,
index=0):
""" Recursively return the lowest common ancestor of this modules list
@:parameter graph <pygraphviz.AGraph>
@:parameter names list<string> (A module names list)
@:parameter states list<string> (A state list to filter)
@:returns list<string>
"""
if states is None:
states = []
nx_digraph = nx.DiGraph(graph)
if not names:
names = leaves(graph)
lca = names[0]
sorted_modules = set(sorted(names[index:]))
if states:
sorted_modules = filter(lambda m: self.get_state(m) in states,
sorted_modules)
for next, name in enumerate(sorted_modules):
next_name = names[next] if next in names else None
if not next_name:
return names
lca = nx.algorithms.lowest_common_ancestor(nx_digraph, lca,
next_name)
if lca:
if lca == "base":
return [lca]
del names[next]
else:
names = self._lowest_common_ancestors(nx_digraph, names,
states, next + 1)
return names
def get_modules_to_install(self):
""" Returns the shortest list of modules to install"""
states = [States.TO_INSTALL]
graph = self._sub_graph_from_states(self._graph, states=states)
modules = leaves(graph)
return sorted(modules)
