def make_bayes_net(load=False, subtree=True, modelsdir=MODEL_CPDS_DIR):
print('Making bayes net')
graph_file = RUNNING_MODEL_DIR + '/' + 'graph.p'
if os.path.isfile(graph_file) and load == True:
print('Loading saved graph from file...')
G = pickle.load(open(graph_file, 'rb'))
G.check_model()
else:
print('loading data...')
training_labels, go_dict = load_label_data()
if subtree:
labels_list = _subtree_labels()
print(labels_list)
else:
labels_list = go_dict.keys()
print('adding nodes and edges...')
G = BayesianModel()
G.add_edges_from([(label, label + '_hat') for label in labels_list])
obo_graph = obonet.read_obo(OBODB_FILE)
for label in labels_list:
children = [
c for c in networkx.ancestors(obo_graph, label)
if c in labels_list
]
for child in children:
G.add_edge(child, label)
predicted_cpds = get_model_cpds(labels_list=labels_list,
modelsdir=MODEL_CPDS_DIR)
for cpd in predicted_cpds:
G.add_cpds(cpd)
true_label_cpds = get_true_label_cpds(training_labels,
go_dict,
labels_list=labels_list)
for cpd in true_label_cpds:
G.add_cpds(cpd)
remove_list = []
for node in G.nodes():
if G.get_cpds(node) == None:
remove_list.append(node)
# remove_list.append(node+'_hat')
for node in remove_list:
if node in G:
G.remove_node(node)
G.check_model()
pickle.dump(G, open(graph_file, 'wb'))
return G
class Network_handler:
'''
Handles creation and usage of the probabilistic network over CERN's data.
Can deal only with a SINGLE file-priority combination.
Note that the methods of this class have numbers and must be called in order.
'''
def __init__(self, pnh, gh):
'''
Constructor
'''
extractor = pnh.get_data_extractor()
self.best_model = BayesianModel()
self.training_instances = ""
self.device_considered = pnh.get_device()
self.priority_considered = pnh.get_priority()
self.markov = MarkovModel()
self.general_handler = gh
self.variables_names = extractor.get_variable_names()
self.rankedDevices = extractor.get_ranked_devices()
self.data = pnh.get_dataframe()
self.file_writer = pnh.get_file_writer()
self.file_suffix = pnh.get_file_suffix()
def learn_structure(self, method, scoring_method, log=True):
''' (4)
Method that builds the structure of the data
-----------------
Parameters:
method : The technique used to search for the structure
-> scoring_approx - To use an approximated search with scoring method
-> scoring_exhaustive - To use an exhaustive search with scoring method
-> constraint - To use the constraint based technique
scoring_method : K2, bic, bdeu
log - "True" if you want to print debug information in the console
'''
#Select the scoring method for the local search of the structure
if scoring_method == "K2":
scores = K2Score(self.data)
elif scoring_method == "bic":
scores = BicScore(self.data)
elif scoring_method == "bdeu":
scores = BdeuScore(self.data)
#Select the actual method
if method == "scoring_approx":
est = HillClimbSearch(self.data, scores)
elif method == "scoring_exhaustive":
est = ExhaustiveSearch(self.data, scores)
elif method == "constraint":
est = ConstraintBasedEstimator(self.data)
self.best_model = est.estimate()
self.eliminate_isolated_nodes(
) # REMOVE all nodes not connected to anything else
for edge in self.best_model.edges_iter():
self.file_writer.write_txt(str(edge))
self.log("Method used for structural learning: " + method, log)
#self.log("Training instances skipped: " + str(self.extractor.get_skipped_lines()), log)
self.log("Search terminated", log)
def estimate_parameters(self, log=True):
''' (5)
Estimates the parameters of the found network
'''
estimator = BayesianEstimator(self.best_model, self.data)
self.file_writer.write_txt("Number of nodes: " +
str(len(self.variables_names)))
self.file_writer.write_txt("Complete list: " +
str(self.variables_names))
for node in self.best_model.nodes():
cpd = estimator.estimate_cpd(node, prior_type='K2')
self.best_model.add_cpds(cpd)
self.log(cpd, log)
self.file_writer.write_txt(cpd.__str__())
def inference(self, variables, evidence, mode="auto", log=True):
''' (6)
Computes the inference over some variables of the network (given some evidence)
'''
inference = VariableElimination(self.best_model)
#inference = BeliefPropagation(self.markov)
#inference = Mplp(self.best_model)
header = "------------------- INFERENCE ------------------------"
self.log(header, log)
self.file_writer.write_txt(header, newline=True)
self.file_writer.write_txt("(With parents all set to value 1)")
if mode == "auto":
self.log(" (with parents all set to value 1)", log)
for node in self.best_model.nodes():
variables = [node]
parents = self.best_model.get_parents(node)
evidence = dict()
for p in parents:
evidence[p] = 1
phi_query = inference.query(variables, evidence)
for key in phi_query:
self.file_writer.write_txt(str(phi_query[key]))
self.log(phi_query[key], log)
elif mode == "manual":
phi_query = inference.query(variables, evidence)
for key in phi_query:
self.log(phi_query[key], log)
'''
map_query = inference.map_query(variables, evidence)
print(map_query)
'''
def draw_network(self, label_choice, location_choice, location, log):
''' (7)
Draws the bayesian network.
----
location_choice = True iff we want to show the location of devices in the graph.
label_choice = "single" if we want to show single label, "double" for double label of arcs
location = 0,1,2 depending by the location (H0, H1, H2)
'''
bn_graph = gv.Digraph(format="png")
# Extract color based on the building
if location_choice:
devices = self.variables_names
device_location = dict()
device_locationH1 = dict()
#For H0
for d in devices:
allDevicesLocations = self.general_handler.get_device_locations(
)
device_location[d] = allDevicesLocations[d][0]
device_locationH1[d] = allDevicesLocations[d][1] #temp for H1
location_color = self.assign_color(device_location)
location_colorH1 = self.assign_color(device_locationH1)
'''
# Logging and saving info
self.log(device_location, log)
self.log(location_color, log)
self.file_writer.write_txt(device_location, newline = True)
self.file_writer.write_txt(location_color, newline = True)
'''
# Creating the subgraphs, one for each location:
loc_subgraphs = dict()
for loc in location_color:
name = "cluster_" + loc
loc_subgraphs[loc] = gv.Digraph(name)
loc_subgraphs[loc].graph_attr[
'label'] = loc #Label with name to be visualized in the image
# Create nodes
for node in self.best_model.nodes():
if location_choice:
locationH0 = device_location[node]
locationH1 = device_locationH1[node]
loc_subgraphs[locationH0].node(
node,
style='filled',
fillcolor=location_colorH1[locationH1]
) #add the node to the right subgraph
#loc_subgraphs[locationH0].node(node) #USE THIS TO ADD ONLY H0
else:
bn_graph.node(node)
# Add all subgraphs in the final graph:
if location_choice:
for loc in loc_subgraphs:
bn_graph.subgraph(loc_subgraphs[loc])
# Create and color edges
for edge in self.best_model.edges_iter():
inference = VariableElimination(self.best_model)
label = ""
# Inference for first label and color of edges
variables = [edge[1]]
evidence = dict()
evidence[edge[0]] = 1
phi_query = inference.query(variables, evidence)
value = phi_query[edge[1]].values[1]
value = round(value, 2)
if label_choice == "single":
label = str(value)
if label_choice == "double":
# Inference for second label
variables = [edge[0]]
evidence = dict()
evidence[edge[1]] = 1
phi_query = inference.query(variables, evidence)
value_inv = phi_query[edge[0]].values[1]
value_inv = round(value_inv, 2)
label = str(value) + "|" + str(value_inv)
if value >= 0.75:
bn_graph.edge(edge[0], edge[1], color="red", label=label)
else:
bn_graph.edge(edge[0], edge[1], color="black", label=label)
# Save the .png graph
if self.device_considered == "CUSTOM":
imgPath = '../../output/CUSTOM' + self.file_suffix
else:
if location_choice:
locat = "_H0H1"
else:
locat = ""
imgPath = '../../output/' + self.device_considered + '_' + self.priority_considered + locat
bn_graph.render(imgPath)
os.remove(imgPath) #remove the source code generated by graphviz
def data_info(self, selection, log):
''' (9) Prints or logs some extra information about the data or the network
'''
# 1 - DEVICE FREQUENCY AND OCCURRENCES
if 1 in selection:
self.file_writer.write_txt(
"Device ranking (max 20 devices are visualized)", newline=True)
i = 1
for dr in self.rankedDevices:
self.file_writer.write_txt(dr[0] + " \t" +
str(dr[1]) + "\t" + str(dr[2]))
i = i + 1
if i == 20:
break
# 2 - EDGES OF THE NETWORK
if 2 in selection:
self.file_writer.write_txt("Edges of the network:", newline=True)
for edge in self.best_model.edges_iter():
self.file_writer.write_txt(str(edge))
# 3 - MARKOV NETWORK
if 3 in selection:
self.markov = self.best_model.to_markov_model(
) #create the markov model from the BN
nice_graph = pydot.Dot(graph_type='graph')
for node in self.markov.nodes():
node_pydot = pydot.Node(node)
nice_graph.add_node(node_pydot)
for edge in self.markov.edges():
edge_pydot = pydot.Edge(edge[0], edge[1], color="black")
nice_graph.add_edge(edge_pydot)
nice_graph.write_png('../../output/' + self.device_considered +
'_' + self.priority_considered +
'-markov.png')
self.file_writer.write_txt("MARKOV NETWORK FACTORS:", newline=True)
for factor in self.markov.factors:
self.log("MARKOV---------------------------------------", log)
self.log(factor, log)
self.file_writer.write_txt(factor.__str__())
# 4 - INFERENCE NETWORK
if 4 in selection:
nice_graph = pydot.Dot(graph_type='digraph')
nodes = self.best_model.nodes()
inference = VariableElimination(self.best_model)
for node1 in nodes:
pos = nodes.index(node1) + 1
for i in range(pos, len(nodes)):
node2 = nodes[i]
variables = [node2]
evidence = dict()
evidence[node1] = 1
phi_query = inference.query(variables, evidence)
prob1 = phi_query[node2].values[
1] #probability of direct activation (inference from node1=1 to node2)
variables = [node1]
evidence = dict()
evidence[node2] = 1
phi_query = inference.query(variables, evidence)
prob2 = phi_query[node1].values[
1] #probability of inverse activation (inference from node2=1 to node1)
prob1 = round(prob1, 2)
prob2 = round(prob2, 2)
if prob1 >= 0.75 and (
prob1 - prob2
) <= 0.40: #add direct arc from node1 to node2
ls = [node1, node2]
self.fix_node_presence(ls, nice_graph)
double_label = str(prob1) + "|" + str(prob2)
nice_graph.add_edge(
pydot.Edge(node1,
node2,
color="red",
label=double_label))
elif prob2 >= 0.75 and (prob2 - prob1) <= 0.40:
ls = [node1, node2]
self.fix_node_presence(ls, nice_graph)
double_label = str(prob2) + "|" + str(prob1)
nice_graph.add_edge(
pydot.Edge(node2,
node1,
color="red",
label=double_label))
elif prob1 >= 0.75 and prob2 >= 0.75:
ls = [node1, node2]
self.fix_node_presence(ls, nice_graph)
if prob1 >= prob2:
double_label = str(prob1) + "|" + str(prob2)
nice_graph.add_edge(
pydot.Edge(node1,
node2,
color="orange",
label=double_label))
else:
double_label = str(prob2) + "|" + str(prob1)
nice_graph.add_edge(
pydot.Edge(node2,
node1,
color="orange",
label=double_label))
elif prob1 >= 0.55 and prob2 >= 0.55:
ls = [node1, node2]
self.fix_node_presence(ls, nice_graph)
if prob1 >= prob2:
double_label = str(prob1) + "|" + str(prob2)
nice_graph.add_edge(
pydot.Edge(node1,
node2,
color="black",
label=double_label))
else:
double_label = str(prob2) + "|" + str(prob1)
nice_graph.add_edge(
pydot.Edge(node2,
node1,
color="black",
label=double_label))
if self.device_considered == "CUSTOM":
imgPath = '../../output/CUSTOM' + self.file_suffix
nice_graph.write_png(imgPath + "-inference_network.png")
else:
nice_graph.write_png('../../output/' + self.device_considered +
'_' + self.priority_considered +
'-inference_network.png')
def fix_node_presence(self, nodes, pydot_graph):
''' Adds the list of nodes to the graph, if they are not already present '''
for node in nodes:
if node not in pydot_graph.get_nodes():
pydot_graph.add_node(pydot.Node(node))
def eliminate_isolated_nodes(self):
'''
If a node doesn't have any incoming or outgoing edge, it is eliminated from the graph
'''
for nodeX in self.best_model.nodes():
tup = [item for item in self.best_model.edges() if nodeX in item]
if not tup:
self.file_writer.write_txt(
"Node " + str(nodeX) +
" has no edges: it has been eliminated.")
self.best_model.remove_node(nodeX)
if self.best_model.nodes() == []:
raise DataError("No nodes left in this file-priority combination.")
def assign_color(self, device_location):
'''
Returns a dictionary with the location as key and the assigned colour as value (WORKS WITH MAX 10 DIFFERENT LOCATIONS)
'''
system_color = [
'Blue', 'Green', 'Red', 'Purple', 'Yellow', 'Red', 'Grey',
'Light Red', 'Light Blue', 'Light Green'
]
location_color = dict() # key = location; value = color
for dev, loc in device_location.items():
if loc not in location_color:
color = system_color[0]
system_color.remove(color)
location_color[loc] = color
return location_color
def log(self, text, log):
''' Prints the text in the console, if the "log" condition is True. '''
if log:
print(text)
class TestBayesianModelMethods(unittest.TestCase):
def setUp(self):
self.G = BayesianModel([('a', 'd'), ('b', 'd'), ('d', 'e'),
('b', 'c')])
self.G1 = BayesianModel([('diff', 'grade'), ('intel', 'grade')])
diff_cpd = TabularCPD('diff', 2, values=[[0.2], [0.8]])
intel_cpd = TabularCPD('intel', 3, values=[[0.5], [0.3], [0.2]])
grade_cpd = TabularCPD('grade',
3,
values=[[0.1, 0.1, 0.1, 0.1, 0.1, 0.1],
[0.1, 0.1, 0.1, 0.1, 0.1, 0.1],
[0.8, 0.8, 0.8, 0.8, 0.8, 0.8]],
evidence=['diff', 'intel'],
evidence_card=[2, 3])
self.G1.add_cpds(diff_cpd, intel_cpd, grade_cpd)
self.G2 = BayesianModel([('d', 'g'), ('g', 'l'), ('i', 'g'),
('i', 'l')])
def test_moral_graph(self):
moral_graph = self.G.moralize()
self.assertListEqual(sorted(moral_graph.nodes()),
['a', 'b', 'c', 'd', 'e'])
for edge in moral_graph.edges():
self.assertTrue(edge in [('a', 'b'), ('a', 'd'), ('b', 'c'),
('d', 'b'), ('e', 'd')]
or (edge[1], edge[0]) in [('a', 'b'), ('a', 'd'),
('b', 'c'), ('d', 'b'),
('e', 'd')])
def test_moral_graph_with_edge_present_over_parents(self):
G = BayesianModel([('a', 'd'), ('d', 'e'), ('b', 'd'), ('b', 'c'),
('a', 'b')])
moral_graph = G.moralize()
self.assertListEqual(sorted(moral_graph.nodes()),
['a', 'b', 'c', 'd', 'e'])
for edge in moral_graph.edges():
self.assertTrue(edge in [('a', 'b'), ('c', 'b'), ('d', 'a'),
('d', 'b'), ('d', 'e')]
or (edge[1], edge[0]) in [('a', 'b'), ('c', 'b'),
('d', 'a'), ('d', 'b'),
('d', 'e')])
def test_get_ancestors_of_success(self):
ancenstors1 = self.G2._get_ancestors_of('g')
ancenstors2 = self.G2._get_ancestors_of('d')
ancenstors3 = self.G2._get_ancestors_of(['i', 'l'])
self.assertEqual(ancenstors1, {'d', 'i', 'g'})
self.assertEqual(ancenstors2, {'d'})
self.assertEqual(ancenstors3, {'g', 'i', 'l', 'd'})
def test_get_ancestors_of_failure(self):
self.assertRaises(ValueError, self.G2._get_ancestors_of, 'h')
def test_local_independencies(self):
self.assertEqual(self.G.local_independencies('a'),
Independencies(['a', ['b', 'c']]))
self.assertEqual(self.G.local_independencies('c'),
Independencies(['c', ['a', 'd', 'e'], 'b']))
self.assertEqual(self.G.local_independencies('d'),
Independencies(['d', 'c', ['b', 'a']]))
self.assertEqual(self.G.local_independencies('e'),
Independencies(['e', ['c', 'b', 'a'], 'd']))
self.assertEqual(self.G.local_independencies('b'),
Independencies(['b', 'a']))
self.assertEqual(self.G1.local_independencies('grade'),
Independencies())
def test_get_independencies(self):
chain = BayesianModel([('X', 'Y'), ('Y', 'Z')])
self.assertEqual(chain.get_independencies(),
Independencies(('X', 'Z', 'Y'), ('Z', 'X', 'Y')))
fork = BayesianModel([('Y', 'X'), ('Y', 'Z')])
self.assertEqual(fork.get_independencies(),
Independencies(('X', 'Z', 'Y'), ('Z', 'X', 'Y')))
collider = BayesianModel([('X', 'Y'), ('Z', 'Y')])
self.assertEqual(collider.get_independencies(),
Independencies(('X', 'Z'), ('Z', 'X')))
def test_is_imap(self):
val = [
0.01, 0.01, 0.08, 0.006, 0.006, 0.048, 0.004, 0.004, 0.032, 0.04,
0.04, 0.32, 0.024, 0.024, 0.192, 0.016, 0.016, 0.128
]
JPD = JointProbabilityDistribution(['diff', 'intel', 'grade'],
[2, 3, 3], val)
fac = DiscreteFactor(['diff', 'intel', 'grade'], [2, 3, 3], val)
self.assertTrue(self.G1.is_imap(JPD))
self.assertRaises(TypeError, self.G1.is_imap, fac)
def test_get_immoralities(self):
G = BayesianModel([('x', 'y'), ('z', 'y'), ('x', 'z'), ('w', 'y')])
self.assertEqual(G.get_immoralities(), {('w', 'x'), ('w', 'z')})
G1 = BayesianModel([('x', 'y'), ('z', 'y'), ('z', 'x'), ('w', 'y')])
self.assertEqual(G1.get_immoralities(), {('w', 'x'), ('w', 'z')})
G2 = BayesianModel([('x', 'y'), ('z', 'y'), ('x', 'z'), ('w', 'y'),
('w', 'x')])
self.assertEqual(G2.get_immoralities(), {('w', 'z')})
def test_is_iequivalent(self):
G = BayesianModel([('x', 'y'), ('z', 'y'), ('x', 'z'), ('w', 'y')])
self.assertRaises(TypeError, G.is_iequivalent, MarkovModel())
G1 = BayesianModel([('V', 'W'), ('W', 'X'), ('X', 'Y'), ('Z', 'Y')])
G2 = BayesianModel([('W', 'V'), ('X', 'W'), ('X', 'Y'), ('Z', 'Y')])
self.assertTrue(G1.is_iequivalent(G2))
G3 = BayesianModel([('W', 'V'), ('W', 'X'), ('Y', 'X'), ('Z', 'Y')])
self.assertFalse(G3.is_iequivalent(G2))
def test_copy(self):
model_copy = self.G1.copy()
self.assertEqual(sorted(self.G1.nodes()), sorted(model_copy.nodes()))
self.assertEqual(sorted(self.G1.edges()), sorted(model_copy.edges()))
self.assertNotEqual(id(self.G1.get_cpds('diff')),
id(model_copy.get_cpds('diff')))
self.G1.remove_cpds('diff')
diff_cpd = TabularCPD('diff', 2, values=[[0.3], [0.7]])
self.G1.add_cpds(diff_cpd)
self.assertNotEqual(self.G1.get_cpds('diff'),
model_copy.get_cpds('diff'))
self.G1.remove_node('intel')
self.assertNotEqual(sorted(self.G1.nodes()),
sorted(model_copy.nodes()))
self.assertNotEqual(sorted(self.G1.edges()),
sorted(model_copy.edges()))
def test_remove_node(self):
self.G1.remove_node('diff')
self.assertEqual(sorted(self.G1.nodes()), sorted(['grade', 'intel']))
self.assertRaises(ValueError, self.G1.get_cpds, 'diff')
def test_remove_nodes_from(self):
self.G1.remove_nodes_from(['diff', 'grade'])
self.assertEqual(sorted(self.G1.nodes()), sorted(['intel']))
self.assertRaises(ValueError, self.G1.get_cpds, 'diff')
self.assertRaises(ValueError, self.G1.get_cpds, 'grade')
def tearDown(self):
del self.G
del self.G1
class TestBayesianModelMethods(unittest.TestCase):
def setUp(self):
self.G = BayesianModel([("a", "d"), ("b", "d"), ("d", "e"),
("b", "c")])
self.G1 = BayesianModel([("diff", "grade"), ("intel", "grade")])
diff_cpd = TabularCPD("diff", 2, values=[[0.2], [0.8]])
intel_cpd = TabularCPD("intel", 3, values=[[0.5], [0.3], [0.2]])
grade_cpd = TabularCPD(
"grade",
3,
values=[
[0.1, 0.1, 0.1, 0.1, 0.1, 0.1],
[0.1, 0.1, 0.1, 0.1, 0.1, 0.1],
[0.8, 0.8, 0.8, 0.8, 0.8, 0.8],
],
evidence=["diff", "intel"],
evidence_card=[2, 3],
)
self.G1.add_cpds(diff_cpd, intel_cpd, grade_cpd)
self.G2 = BayesianModel([("d", "g"), ("g", "l"), ("i", "g"),
("i", "l")])
def test_moral_graph(self):
moral_graph = self.G.moralize()
self.assertListEqual(sorted(moral_graph.nodes()),
["a", "b", "c", "d", "e"])
for edge in moral_graph.edges():
self.assertTrue(edge in [("a", "b"), ("a", "d"), ("b", "c"),
("d", "b"), ("e", "d")]
or (edge[1], edge[0]) in [("a", "b"), ("a", "d"),
("b", "c"), ("d", "b"),
("e", "d")])
def test_moral_graph_with_edge_present_over_parents(self):
G = BayesianModel([("a", "d"), ("d", "e"), ("b", "d"), ("b", "c"),
("a", "b")])
moral_graph = G.moralize()
self.assertListEqual(sorted(moral_graph.nodes()),
["a", "b", "c", "d", "e"])
for edge in moral_graph.edges():
self.assertTrue(edge in [("a", "b"), ("c", "b"), ("d", "a"),
("d", "b"), ("d", "e")]
or (edge[1], edge[0]) in [("a", "b"), ("c", "b"),
("d", "a"), ("d", "b"),
("d", "e")])
def test_get_ancestors_of_success(self):
ancenstors1 = self.G2._get_ancestors_of("g")
ancenstors2 = self.G2._get_ancestors_of("d")
ancenstors3 = self.G2._get_ancestors_of(["i", "l"])
self.assertEqual(ancenstors1, {"d", "i", "g"})
self.assertEqual(ancenstors2, {"d"})
self.assertEqual(ancenstors3, {"g", "i", "l", "d"})
def test_get_ancestors_of_failure(self):
self.assertRaises(ValueError, self.G2._get_ancestors_of, "h")
def test_get_cardinality(self):
self.assertDictEqual(self.G1.get_cardinality(), {
"diff": 2,
"intel": 3,
"grade": 3
})
def test_get_cardinality_with_node(self):
self.assertEqual(self.G1.get_cardinality("diff"), 2)
self.assertEqual(self.G1.get_cardinality("intel"), 3)
self.assertEqual(self.G1.get_cardinality("grade"), 3)
def test_local_independencies(self):
self.assertEqual(self.G.local_independencies("a"),
Independencies(["a", ["b", "c"]]))
self.assertEqual(
self.G.local_independencies("c"),
Independencies(["c", ["a", "d", "e"], "b"]),
)
self.assertEqual(self.G.local_independencies("d"),
Independencies(["d", "c", ["b", "a"]]))
self.assertEqual(
self.G.local_independencies("e"),
Independencies(["e", ["c", "b", "a"], "d"]),
)
self.assertEqual(self.G.local_independencies("b"),
Independencies(["b", "a"]))
self.assertEqual(self.G1.local_independencies("grade"),
Independencies())
def test_get_independencies(self):
chain = BayesianModel([("X", "Y"), ("Y", "Z")])
self.assertEqual(chain.get_independencies(),
Independencies(("X", "Z", "Y"), ("Z", "X", "Y")))
fork = BayesianModel([("Y", "X"), ("Y", "Z")])
self.assertEqual(fork.get_independencies(),
Independencies(("X", "Z", "Y"), ("Z", "X", "Y")))
collider = BayesianModel([("X", "Y"), ("Z", "Y")])
self.assertEqual(collider.get_independencies(),
Independencies(("X", "Z"), ("Z", "X")))
def test_is_imap(self):
val = [
0.01,
0.01,
0.08,
0.006,
0.006,
0.048,
0.004,
0.004,
0.032,
0.04,
0.04,
0.32,
0.024,
0.024,
0.192,
0.016,
0.016,
0.128,
]
JPD = JointProbabilityDistribution(["diff", "intel", "grade"],
[2, 3, 3], val)
fac = DiscreteFactor(["diff", "intel", "grade"], [2, 3, 3], val)
self.assertTrue(self.G1.is_imap(JPD))
self.assertRaises(TypeError, self.G1.is_imap, fac)
def test_markov_blanet(self):
G = DAG([
("x", "y"),
("z", "y"),
("y", "w"),
("y", "v"),
("u", "w"),
("s", "v"),
("w", "t"),
("w", "m"),
("v", "n"),
("v", "q"),
])
self.assertEqual(set(G.get_markov_blanket("y")),
set(["s", "w", "x", "u", "z", "v"]))
def test_get_immoralities(self):
G = BayesianModel([("x", "y"), ("z", "y"), ("x", "z"), ("w", "y")])
self.assertEqual(G.get_immoralities(), {("w", "x"), ("w", "z")})
G1 = BayesianModel([("x", "y"), ("z", "y"), ("z", "x"), ("w", "y")])
self.assertEqual(G1.get_immoralities(), {("w", "x"), ("w", "z")})
G2 = BayesianModel([("x", "y"), ("z", "y"), ("x", "z"), ("w", "y"),
("w", "x")])
self.assertEqual(G2.get_immoralities(), {("w", "z")})
def test_is_iequivalent(self):
G = BayesianModel([("x", "y"), ("z", "y"), ("x", "z"), ("w", "y")])
self.assertRaises(TypeError, G.is_iequivalent, MarkovModel())
G1 = BayesianModel([("V", "W"), ("W", "X"), ("X", "Y"), ("Z", "Y")])
G2 = BayesianModel([("W", "V"), ("X", "W"), ("X", "Y"), ("Z", "Y")])
self.assertTrue(G1.is_iequivalent(G2))
G3 = BayesianModel([("W", "V"), ("W", "X"), ("Y", "X"), ("Z", "Y")])
self.assertFalse(G3.is_iequivalent(G2))
def test_copy(self):
model_copy = self.G1.copy()
self.assertEqual(sorted(self.G1.nodes()), sorted(model_copy.nodes()))
self.assertEqual(sorted(self.G1.edges()), sorted(model_copy.edges()))
self.assertNotEqual(id(self.G1.get_cpds("diff")),
id(model_copy.get_cpds("diff")))
self.G1.remove_cpds("diff")
diff_cpd = TabularCPD("diff", 2, values=[[0.3], [0.7]])
self.G1.add_cpds(diff_cpd)
self.assertNotEqual(self.G1.get_cpds("diff"),
model_copy.get_cpds("diff"))
self.G1.remove_node("intel")
self.assertNotEqual(sorted(self.G1.nodes()),
sorted(model_copy.nodes()))
self.assertNotEqual(sorted(self.G1.edges()),
sorted(model_copy.edges()))
def test_remove_node(self):
self.G1.remove_node("diff")
self.assertEqual(sorted(self.G1.nodes()), sorted(["grade", "intel"]))
self.assertRaises(ValueError, self.G1.get_cpds, "diff")
def test_remove_nodes_from(self):
self.G1.remove_nodes_from(["diff", "grade"])
self.assertEqual(sorted(self.G1.nodes()), sorted(["intel"]))
self.assertRaises(ValueError, self.G1.get_cpds, "diff")
self.assertRaises(ValueError, self.G1.get_cpds, "grade")
def tearDown(self):
del self.G
del self.G1
class TestBayesianModelMethods(unittest.TestCase):
def setUp(self):
self.G = BayesianModel([('a', 'd'), ('b', 'd'),
('d', 'e'), ('b', 'c')])
self.G1 = BayesianModel([('diff', 'grade'), ('intel', 'grade')])
diff_cpd = TabularCPD('diff', 2, values=[[0.2], [0.8]])
intel_cpd = TabularCPD('intel', 3, values=[[0.5], [0.3], [0.2]])
grade_cpd = TabularCPD('grade', 3, values=[[0.1, 0.1, 0.1, 0.1, 0.1, 0.1],
[0.1, 0.1, 0.1, 0.1, 0.1, 0.1],
[0.8, 0.8, 0.8, 0.8, 0.8, 0.8]],
evidence=['diff', 'intel'], evidence_card=[2, 3])
self.G1.add_cpds(diff_cpd, intel_cpd, grade_cpd)
self.G2 = BayesianModel([('d', 'g'), ('g', 'l'), ('i', 'g'), ('i', 'l')])
def test_moral_graph(self):
moral_graph = self.G.moralize()
self.assertListEqual(sorted(moral_graph.nodes()), ['a', 'b', 'c', 'd', 'e'])
for edge in moral_graph.edges():
self.assertTrue(edge in [('a', 'b'), ('a', 'd'), ('b', 'c'), ('d', 'b'), ('e', 'd')] or
(edge[1], edge[0]) in [('a', 'b'), ('a', 'd'), ('b', 'c'), ('d', 'b'), ('e', 'd')])
def test_moral_graph_with_edge_present_over_parents(self):
G = BayesianModel([('a', 'd'), ('d', 'e'), ('b', 'd'), ('b', 'c'), ('a', 'b')])
moral_graph = G.moralize()
self.assertListEqual(sorted(moral_graph.nodes()), ['a', 'b', 'c', 'd', 'e'])
for edge in moral_graph.edges():
self.assertTrue(edge in [('a', 'b'), ('c', 'b'), ('d', 'a'), ('d', 'b'), ('d', 'e')] or
(edge[1], edge[0]) in [('a', 'b'), ('c', 'b'), ('d', 'a'), ('d', 'b'), ('d', 'e')])
def test_get_ancestors_of_success(self):
ancenstors1 = self.G2._get_ancestors_of('g')
ancenstors2 = self.G2._get_ancestors_of('d')
ancenstors3 = self.G2._get_ancestors_of(['i', 'l'])
self.assertEqual(ancenstors1, {'d', 'i', 'g'})
self.assertEqual(ancenstors2, {'d'})
self.assertEqual(ancenstors3, {'g', 'i', 'l', 'd'})
def test_get_ancestors_of_failure(self):
self.assertRaises(ValueError, self.G2._get_ancestors_of, 'h')
def test_local_independencies(self):
self.assertEqual(self.G.local_independencies('a'), Independencies(['a', ['b', 'c']]))
self.assertEqual(self.G.local_independencies('c'), Independencies(['c', ['a', 'd', 'e'], 'b']))
self.assertEqual(self.G.local_independencies('d'), Independencies(['d', 'c', ['b', 'a']]))
self.assertEqual(self.G.local_independencies('e'), Independencies(['e', ['c', 'b', 'a'], 'd']))
self.assertEqual(self.G.local_independencies('b'), Independencies(['b', 'a']))
self.assertEqual(self.G1.local_independencies('grade'), Independencies())
def test_get_independencies(self):
chain = BayesianModel([('X', 'Y'), ('Y', 'Z')])
self.assertEqual(chain.get_independencies(), Independencies(('X', 'Z', 'Y'), ('Z', 'X', 'Y')))
fork = BayesianModel([('Y', 'X'), ('Y', 'Z')])
self.assertEqual(fork.get_independencies(), Independencies(('X', 'Z', 'Y'), ('Z', 'X', 'Y')))
collider = BayesianModel([('X', 'Y'), ('Z', 'Y')])
self.assertEqual(collider.get_independencies(), Independencies(('X', 'Z'), ('Z', 'X')))
def test_is_imap(self):
val = [0.01, 0.01, 0.08, 0.006, 0.006, 0.048, 0.004, 0.004, 0.032,
0.04, 0.04, 0.32, 0.024, 0.024, 0.192, 0.016, 0.016, 0.128]
JPD = JointProbabilityDistribution(['diff', 'intel', 'grade'], [2, 3, 3], val)
fac = DiscreteFactor(['diff', 'intel', 'grade'], [2, 3, 3], val)
self.assertTrue(self.G1.is_imap(JPD))
self.assertRaises(TypeError, self.G1.is_imap, fac)
def test_get_immoralities(self):
G = BayesianModel([('x', 'y'), ('z', 'y'), ('x', 'z'), ('w', 'y')])
self.assertEqual(G.get_immoralities(), {('w', 'x'), ('w', 'z')})
G1 = BayesianModel([('x', 'y'), ('z', 'y'), ('z', 'x'), ('w', 'y')])
self.assertEqual(G1.get_immoralities(), {('w', 'x'), ('w', 'z')})
G2 = BayesianModel([('x', 'y'), ('z', 'y'), ('x', 'z'), ('w', 'y'), ('w', 'x')])
self.assertEqual(G2.get_immoralities(), {('w', 'z')})
def test_is_iequivalent(self):
G = BayesianModel([('x', 'y'), ('z', 'y'), ('x', 'z'), ('w', 'y')])
self.assertRaises(TypeError, G.is_iequivalent, MarkovModel())
G1 = BayesianModel([('V', 'W'), ('W', 'X'), ('X', 'Y'), ('Z', 'Y')])
G2 = BayesianModel([('W', 'V'), ('X', 'W'), ('X', 'Y'), ('Z', 'Y')])
self.assertTrue(G1.is_iequivalent(G2))
G3 = BayesianModel([('W', 'V'), ('W', 'X'), ('Y', 'X'), ('Z', 'Y')])
self.assertFalse(G3.is_iequivalent(G2))
def test_copy(self):
model_copy = self.G1.copy()
self.assertEqual(sorted(self.G1.nodes()), sorted(model_copy.nodes()))
self.assertEqual(sorted(self.G1.edges()), sorted(model_copy.edges()))
self.assertNotEqual(id(self.G1.get_cpds('diff')),
id(model_copy.get_cpds('diff')))
self.G1.remove_cpds('diff')
diff_cpd = TabularCPD('diff', 2, values=[[0.3], [0.7]])
self.G1.add_cpds(diff_cpd)
self.assertNotEqual(self.G1.get_cpds('diff'),
model_copy.get_cpds('diff'))
self.G1.remove_node('intel')
self.assertNotEqual(sorted(self.G1.nodes()), sorted(model_copy.nodes()))
self.assertNotEqual(sorted(self.G1.edges()), sorted(model_copy.edges()))
def test_remove_node(self):
self.G1.remove_node('diff')
self.assertEqual(sorted(self.G1.nodes()), sorted(['grade', 'intel']))
self.assertRaises(ValueError, self.G1.get_cpds, 'diff')
def test_remove_nodes_from(self):
self.G1.remove_nodes_from(['diff', 'grade'])
self.assertEqual(sorted(self.G1.nodes()), sorted(['intel']))
self.assertRaises(ValueError, self.G1.get_cpds, 'diff')
self.assertRaises(ValueError, self.G1.get_cpds, 'grade')
def tearDown(self):
del self.G
del self.G1
