def test_find_MAP():
print '-' * 80
G = MarkovModel()
G.add_nodes_from(['x1', 'x2', 'x3'])
G.add_edges_from([('x1', 'x2'), ('x1', 'x3')])
phi = [
DiscreteFactor(['x2', 'x1'],
cardinality=[2, 2],
values=np.array([[1.0 / 1, 1.0 / 2], [1.0 / 3,
1.0 / 4]])),
DiscreteFactor(['x3', 'x1'],
cardinality=[2, 2],
values=np.array([[1.0 / 1, 1.0 / 2], [1.0 / 3,
1.0 / 4]]))
]
# DiscreteFactor(['x1'], cardinality=[2],
# values=np.array([2,2]))]
G.add_factors(*phi)
print "nodes:", G.nodes()
bp = BeliefPropagation(G)
bp.max_calibrate()
# bp.calibrate()
clique_beliefs = bp.get_clique_beliefs()
print clique_beliefs
print clique_beliefs[('x1', 'x2')]
print clique_beliefs[('x1', 'x3')]
# print 'partition function should be', np.sum(clique_beliefs[('x1', 'x3')].values)
phi_query = bp._query(['x1', 'x2', 'x3'], operation='maximize')
# phi_query = bp._query(['x1', 'x2', 'x3'], operation='marginalize')
print phi_query
sleep(52)
class generate(object):
def __init__(self, adj_mat=None, struct=None):
DEBUG = False
self.G = MarkovModel()
self.n_nodes = adj_mat.shape[0]
if DEBUG: print 'struct', struct
if struct == 'complete':
self._complete_graph(adj_mat)
if struct == 'nodes':
self._nodes_only(adj_mat)
if struct is None:
self._import_adj(adj_mat)
self._ising_factors(Wf=5, Wi=5, f_type='mixed')
if DEBUG: print 'generate_init', self.G, self.G.nodes()
def get_model(self):
return self.G
def _complete_graph(self, adj_mat):
"""
generate the complete graph over len(adj_mat)
"""
self._nodes_only(adj_mat)
for i in range(self.n_nodes):
self.G.add_edges_from([(i, j)
for j in range(self.n_nodes)])
def _import_adj(self, adj_mat):
"""
add nodes and edges to graph
adj_mat - square matrix, numpy array like
"""
DEBUG = False
assert (adj_mat is not None), "can't import empty adj mat"
# add nodes
self._nodes_only(adj_mat)
# add edges
for i in range(self.n_nodes):
edges_list = ([(i, j)
for j in range(self.n_nodes)
if adj_mat[i][j]])
if DEBUG: print edges_list
self.G.add_edges_from(edges_list)
if DEBUG: print len(self.G)
def _nodes_only(self, adj_mat):
"""
add nodes to graph
adj_mat - aquare matrix, numpy array like
"""
global DEBUG
assert (adj_mat is not None), "can't import empty adj mat"
assert (self.n_nodes == adj_mat.shape[1]), "adj_mat is not sqaure"
self.G.add_nodes_from([i for i in range(self.n_nodes)])
if DEBUG: print '_nodes_only', [i for i in range(self.n_nodes)]
if DEBUG: print '_nodes_only print G', self.G.nodes()
assert (self.n_nodes == len(self.G)), "graph size is incosistent with adj_mat"
def _ising_factors(self, Wf=1, Wi=1, f_type='mixed'):
"""
Add ising-like factors to model graph
cardinality is the number of possible values
in our case we have boolean nodes, thus cardinality = 2
Wf = \theta_i = ~U[-Wf, Wf]
type = 'mixed' = ~U[-Wi,Wi]
'attractive' = ~U[0,Wi]
"""
self._field_factors(Wf)
self._interact_factors(Wi, f_type)
def _field_factors(self, w, states=2):
"""
this function assigns factor for single node
currently states=2 for ising model generation
"""
for i in self.G.nodes():
phi_i = Factor([i], [states], self._wf(w, states))
self.G.add_factors(phi_i)
def _interact_factors(self, w, f_type, states=2):
"""
this function assigns factor for two interacting nodes
currently states=2 for ising model generation
"""
for e in self.G.edges():
# if DEBUG: print 'interact_factors edges,states, values',e,[e[0],
# e[1]],len(e)*[states], self._wi(w, f_type, states)
phi_ij = Factor([e[0], e[1]], [states] * len(e), self._wi(w, f_type, states))
self.G.add_factors(phi_ij)
def _wf(self, w, k):
"""
generate field factor
"""
# if DEBUG: print 'w',type(w),w
return np.random.uniform(low=-1 * w, high=w, size=k)
def _wi(self, w, f_type, k):
"""
generate interaction factor
current support only for k=2
"""
# if DEBUG: print 'w',type(w),w
a_ij = np.random.uniform(low=-1 * w, high=w)
if f_type == 'mixed':
dis_aij = -a_ij
else: # f_type == 'attractive':
dis_aij = 0
# else:
# print 'f_type error'
return [a_ij, dis_aij, dis_aij, a_ij]
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)
import numpy as np import pandas as pd from pgmpy.models import MarkovModel from pgmpy.estimators import MaximumLikelihoodEstimator # Generating random data raw_data = np.random.randint(low=0, high=2, size=(1000, 2)) data = pd.DataFrame(raw_data, columns=['X', 'Y']) model = MarkovModel() model.fit(data, estimator=MaximumLikelihoodEstimator) model.get_factors() model.nodes() model.edges()
class TestMarkovModelCreation(unittest.TestCase):
def setUp(self):
self.graph = MarkovModel()
def test_class_init_without_data(self):
self.assertIsInstance(self.graph, MarkovModel)
def test_class_init_with_data_string(self):
self.g = MarkovModel([("a", "b"), ("b", "c")])
self.assertListEqual(sorted(self.g.nodes()), ["a", "b", "c"])
self.assertListEqual(hf.recursive_sorted(self.g.edges()),
[["a", "b"], ["b", "c"]])
def test_class_init_with_data_nonstring(self):
self.g = MarkovModel([(1, 2), (2, 3)])
def test_add_node_string(self):
self.graph.add_node("a")
self.assertListEqual(list(self.graph.nodes()), ["a"])
def test_add_node_nonstring(self):
self.graph.add_node(1)
def test_add_nodes_from_string(self):
self.graph.add_nodes_from(["a", "b", "c", "d"])
self.assertListEqual(sorted(self.graph.nodes()), ["a", "b", "c", "d"])
def test_add_nodes_from_non_string(self):
self.graph.add_nodes_from([1, 2, 3, 4])
def test_add_edge_string(self):
self.graph.add_edge("d", "e")
self.assertListEqual(sorted(self.graph.nodes()), ["d", "e"])
self.assertListEqual(hf.recursive_sorted(self.graph.edges()),
[["d", "e"]])
self.graph.add_nodes_from(["a", "b", "c"])
self.graph.add_edge("a", "b")
self.assertListEqual(hf.recursive_sorted(self.graph.edges()),
[["a", "b"], ["d", "e"]])
def test_add_edge_nonstring(self):
self.graph.add_edge(1, 2)
def test_add_edge_selfloop(self):
self.assertRaises(ValueError, self.graph.add_edge, "a", "a")
def test_add_edges_from_string(self):
self.graph.add_edges_from([("a", "b"), ("b", "c")])
self.assertListEqual(sorted(self.graph.nodes()), ["a", "b", "c"])
self.assertListEqual(hf.recursive_sorted(self.graph.edges()),
[["a", "b"], ["b", "c"]])
self.graph.add_nodes_from(["d", "e", "f"])
self.graph.add_edges_from([("d", "e"), ("e", "f")])
self.assertListEqual(sorted(self.graph.nodes()),
["a", "b", "c", "d", "e", "f"])
self.assertListEqual(
hf.recursive_sorted(self.graph.edges()),
hf.recursive_sorted([("a", "b"), ("b", "c"), ("d", "e"),
("e", "f")]),
)
def test_add_edges_from_nonstring(self):
self.graph.add_edges_from([(1, 2), (2, 3)])
def test_add_edges_from_self_loop(self):
self.assertRaises(ValueError, self.graph.add_edges_from, [("a", "a")])
def test_number_of_neighbors(self):
self.graph.add_edges_from([("a", "b"), ("b", "c")])
self.assertEqual(len(list(self.graph.neighbors("b"))), 2)
def tearDown(self):
del self.graph
class TestMarkovModelCreation(unittest.TestCase):
def setUp(self):
self.graph = MarkovModel()
def test_class_init_without_data(self):
self.assertIsInstance(self.graph, MarkovModel)
def test_class_init_with_data_string(self):
self.g = MarkovModel([('a', 'b'), ('b', 'c')])
self.assertListEqual(sorted(self.g.nodes()), ['a', 'b', 'c'])
self.assertListEqual(hf.recursive_sorted(self.g.edges()),
[['a', 'b'], ['b', 'c']])
def test_class_init_with_data_nonstring(self):
self.g = MarkovModel([(1, 2), (2, 3)])
def test_add_node_string(self):
self.graph.add_node('a')
self.assertListEqual(self.graph.nodes(), ['a'])
def test_add_node_nonstring(self):
self.graph.add_node(1)
def test_add_nodes_from_string(self):
self.graph.add_nodes_from(['a', 'b', 'c', 'd'])
self.assertListEqual(sorted(self.graph.nodes()), ['a', 'b', 'c', 'd'])
def test_add_nodes_from_non_string(self):
self.graph.add_nodes_from([1, 2, 3, 4])
def test_add_edge_string(self):
self.graph.add_edge('d', 'e')
self.assertListEqual(sorted(self.graph.nodes()), ['d', 'e'])
self.assertListEqual(hf.recursive_sorted(self.graph.edges()),
[['d', 'e']])
self.graph.add_nodes_from(['a', 'b', 'c'])
self.graph.add_edge('a', 'b')
self.assertListEqual(hf.recursive_sorted(self.graph.edges()),
[['a', 'b'], ['d', 'e']])
def test_add_edge_nonstring(self):
self.graph.add_edge(1, 2)
def test_add_edge_selfloop(self):
self.assertRaises(ValueError, self.graph.add_edge, 'a', 'a')
def test_add_edges_from_string(self):
self.graph.add_edges_from([('a', 'b'), ('b', 'c')])
self.assertListEqual(sorted(self.graph.nodes()), ['a', 'b', 'c'])
self.assertListEqual(hf.recursive_sorted(self.graph.edges()),
[['a', 'b'], ['b', 'c']])
self.graph.add_nodes_from(['d', 'e', 'f'])
self.graph.add_edges_from([('d', 'e'), ('e', 'f')])
self.assertListEqual(sorted(self.graph.nodes()),
['a', 'b', 'c', 'd', 'e', 'f'])
self.assertListEqual(
hf.recursive_sorted(self.graph.edges()),
hf.recursive_sorted([('a', 'b'), ('b', 'c'), ('d', 'e'),
('e', 'f')]))
def test_add_edges_from_nonstring(self):
self.graph.add_edges_from([(1, 2), (2, 3)])
def test_add_edges_from_self_loop(self):
self.assertRaises(ValueError, self.graph.add_edges_from, [('a', 'a')])
def test_number_of_neighbors(self):
self.graph.add_edges_from([('a', 'b'), ('b', 'c')])
self.assertEqual(len(self.graph.neighbors('b')), 2)
def tearDown(self):
del self.graph
class TestMarkovModelCreation(unittest.TestCase):
def setUp(self):
self.graph = MarkovModel()
def test_class_init_without_data(self):
self.assertIsInstance(self.graph, MarkovModel)
def test_class_init_with_data_string(self):
self.g = MarkovModel([('a', 'b'), ('b', 'c')])
self.assertListEqual(sorted(self.g.nodes()), ['a', 'b', 'c'])
self.assertListEqual(hf.recursive_sorted(self.g.edges()),
[['a', 'b'], ['b', 'c']])
def test_class_init_with_data_nonstring(self):
self.g = MarkovModel([(1, 2), (2, 3)])
def test_add_node_string(self):
self.graph.add_node('a')
self.assertListEqual(self.graph.nodes(), ['a'])
def test_add_node_nonstring(self):
self.graph.add_node(1)
def test_add_nodes_from_string(self):
self.graph.add_nodes_from(['a', 'b', 'c', 'd'])
self.assertListEqual(sorted(self.graph.nodes()), ['a', 'b', 'c', 'd'])
def test_add_nodes_from_non_string(self):
self.graph.add_nodes_from([1, 2, 3, 4])
def test_add_edge_string(self):
self.graph.add_edge('d', 'e')
self.assertListEqual(sorted(self.graph.nodes()), ['d', 'e'])
self.assertListEqual(hf.recursive_sorted(self.graph.edges()),
[['d', 'e']])
self.graph.add_nodes_from(['a', 'b', 'c'])
self.graph.add_edge('a', 'b')
self.assertListEqual(hf.recursive_sorted(self.graph.edges()),
[['a', 'b'], ['d', 'e']])
def test_add_edge_nonstring(self):
self.graph.add_edge(1, 2)
def test_add_edge_selfloop(self):
self.assertRaises(ValueError, self.graph.add_edge, 'a', 'a')
def test_add_edges_from_string(self):
self.graph.add_edges_from([('a', 'b'), ('b', 'c')])
self.assertListEqual(sorted(self.graph.nodes()), ['a', 'b', 'c'])
self.assertListEqual(hf.recursive_sorted(self.graph.edges()),
[['a', 'b'], ['b', 'c']])
self.graph.add_nodes_from(['d', 'e', 'f'])
self.graph.add_edges_from([('d', 'e'), ('e', 'f')])
self.assertListEqual(sorted(self.graph.nodes()),
['a', 'b', 'c', 'd', 'e', 'f'])
self.assertListEqual(hf.recursive_sorted(self.graph.edges()),
hf.recursive_sorted([('a', 'b'), ('b', 'c'),
('d', 'e'), ('e', 'f')]))
def test_add_edges_from_nonstring(self):
self.graph.add_edges_from([(1, 2), (2, 3)])
def test_add_edges_from_self_loop(self):
self.assertRaises(ValueError, self.graph.add_edges_from,
[('a', 'a')])
def test_number_of_neighbors(self):
self.graph.add_edges_from([('a', 'b'), ('b', 'c')])
self.assertEqual(len(self.graph.neighbors('b')), 2)
def tearDown(self):
del self.graph
class TestGibbsSampling(unittest.TestCase):
def setUp(self):
# A test Bayesian model
diff_cpd = TabularCPD('diff', 2, [[0.6], [0.4]])
intel_cpd = TabularCPD('intel', 2, [[0.7], [0.3]])
grade_cpd = TabularCPD('grade', 3, [[0.3, 0.05, 0.9, 0.5], [0.4, 0.25, 0.08, 0.3], [0.3, 0.7, 0.02, 0.2]],
evidence=['diff', 'intel'], evidence_card=[2, 2])
self.bayesian_model = BayesianModel()
self.bayesian_model.add_nodes_from(['diff', 'intel', 'grade'])
self.bayesian_model.add_edges_from([('diff', 'grade'), ('intel', 'grade')])
self.bayesian_model.add_cpds(diff_cpd, intel_cpd, grade_cpd)
# A test Markov model
self.markov_model = MarkovModel([('A', 'B'), ('C', 'B'), ('B', 'D')])
factor_ab = Factor(['A', 'B'], [2, 3], [1, 2, 3, 4, 5, 6])
factor_cb = Factor(['C', 'B'], [4, 3], [3, 1, 4, 5, 7, 8, 1, 3, 10, 4, 5, 6])
factor_bd = Factor(['B', 'D'], [3, 2], [5, 7, 2, 1, 9, 3])
self.markov_model.add_factors(factor_ab, factor_cb, factor_bd)
self.gibbs = GibbsSampling(self.bayesian_model)
def tearDown(self):
del self.bayesian_model
del self.markov_model
@patch('pgmpy.inference.Sampling.GibbsSampling._get_kernel_from_bayesian_model', autospec=True)
@patch('pgmpy.models.MarkovChain.__init__', autospec=True)
def test_init_bayesian_model(self, init, get_kernel):
model = MagicMock(spec_set=BayesianModel)
gibbs = GibbsSampling(model)
init.assert_called_once_with(gibbs)
get_kernel.assert_called_once_with(gibbs, model)
@patch('pgmpy.inference.Sampling.GibbsSampling._get_kernel_from_markov_model', autospec=True)
def test_init_markov_model(self, get_kernel):
model = MagicMock(spec_set=MarkovModel)
gibbs = GibbsSampling(model)
get_kernel.assert_called_once_with(gibbs, model)
def test_get_kernel_from_bayesian_model(self):
gibbs = GibbsSampling()
gibbs._get_kernel_from_bayesian_model(self.bayesian_model)
self.assertListEqual(list(gibbs.variables), self.bayesian_model.nodes())
self.assertDictEqual(gibbs.cardinalities, {'diff': 2, 'intel': 2, 'grade': 3})
def test_get_kernel_from_markov_model(self):
gibbs = GibbsSampling()
gibbs._get_kernel_from_markov_model(self.markov_model)
self.assertListEqual(list(gibbs.variables), self.markov_model.nodes())
self.assertDictEqual(gibbs.cardinalities, {'A': 2, 'B': 3, 'C': 4, 'D': 2})
def test_sample(self):
start_state = [State('diff', 0), State('intel', 0), State('grade', 0)]
sample = self.gibbs.sample(start_state, 2)
self.assertEquals(len(sample), 2)
self.assertEquals(len(sample.columns), 3)
self.assertIn('diff', sample.columns)
self.assertIn('intel', sample.columns)
self.assertIn('grade', sample.columns)
self.assertTrue(set(sample['diff']).issubset({0, 1}))
self.assertTrue(set(sample['intel']).issubset({0, 1}))
self.assertTrue(set(sample['grade']).issubset({0, 1, 2}))
@patch("pgmpy.inference.Sampling.GibbsSampling.random_state", autospec=True)
def test_sample_less_arg(self, random_state):
self.gibbs.state = None
random_state.return_value = [State('diff', 0), State('intel', 0), State('grade', 0)]
sample = self.gibbs.sample(size=2)
random_state.assert_called_once_with(self.gibbs)
self.assertEqual(len(sample), 2)
def test_generate_sample(self):
start_state = [State('diff', 0), State('intel', 0), State('grade', 0)]
gen = self.gibbs.generate_sample(start_state, 2)
samples = [sample for sample in gen]
self.assertEqual(len(samples), 2)
self.assertEqual({samples[0][0].var, samples[0][1].var, samples[0][2].var}, {'diff', 'intel', 'grade'})
self.assertEqual({samples[1][0].var, samples[1][1].var, samples[1][2].var}, {'diff', 'intel', 'grade'})
@patch("pgmpy.inference.Sampling.GibbsSampling.random_state", autospec=True)
def test_generate_sample_less_arg(self, random_state):
self.gibbs.state = None
gen = self.gibbs.generate_sample(size=2)
samples = [sample for sample in gen]
random_state.assert_called_once_with(self.gibbs)
self.assertEqual(len(samples), 2)
" [0, 0]])"
data = pd.DataFrame(raw_data, columns=['A', 'B'])
print(data) # Two coins toss result
" X Y "
"0 1 1 "
" ......."
"98 0 0 "
# Markov Model
markov_model = MarkovModel()
markov_model.fit(data, estimator=MaximumLikelihoodEstimator)
markov_model.get_factors()
" <Factor representing Phi(A: 2, B:2) at ejbdfouaeboidjfnaeif>, "
markov_model.nodes()
" ['A', 'B'] "
markov_model.edges()
" [('A','B')] "
-2- " Bayesian Score for learning structure "
import numpy as np
import pandas as pd
from pgmpy.models import MarkovModel
from pgmpy.estimators import BayesianEstimator
# Generating some data
raw_data = np.random.randint(low=0, high=2, size=(1000,2))
class TestGibbsSampling(unittest.TestCase):
def setUp(self):
# A test Bayesian model
diff_cpd = TabularCPD('diff', 2, [[0.6], [0.4]])
intel_cpd = TabularCPD('intel', 2, [[0.7], [0.3]])
grade_cpd = TabularCPD('grade',
3,
[[0.3, 0.05, 0.9, 0.5], [0.4, 0.25, 0.08, 0.3],
[0.3, 0.7, 0.02, 0.2]],
evidence=['diff', 'intel'],
evidence_card=[2, 2])
self.bayesian_model = BayesianModel()
self.bayesian_model.add_nodes_from(['diff', 'intel', 'grade'])
self.bayesian_model.add_edges_from([('diff', 'grade'),
('intel', 'grade')])
self.bayesian_model.add_cpds(diff_cpd, intel_cpd, grade_cpd)
# A test Markov model
self.markov_model = MarkovModel([('A', 'B'), ('C', 'B'), ('B', 'D')])
factor_ab = DiscreteFactor(['A', 'B'], [2, 3], [1, 2, 3, 4, 5, 6])
factor_cb = DiscreteFactor(['C', 'B'], [4, 3],
[3, 1, 4, 5, 7, 8, 1, 3, 10, 4, 5, 6])
factor_bd = DiscreteFactor(['B', 'D'], [3, 2], [5, 7, 2, 1, 9, 3])
self.markov_model.add_factors(factor_ab, factor_cb, factor_bd)
self.gibbs = GibbsSampling(self.bayesian_model)
def tearDown(self):
del self.bayesian_model
del self.markov_model
@patch('pgmpy.sampling.GibbsSampling._get_kernel_from_bayesian_model',
autospec=True)
@patch('pgmpy.models.MarkovChain.__init__', autospec=True)
def test_init_bayesian_model(self, init, get_kernel):
model = MagicMock(spec_set=BayesianModel)
gibbs = GibbsSampling(model)
init.assert_called_once_with(gibbs)
get_kernel.assert_called_once_with(gibbs, model)
@patch('pgmpy.sampling.GibbsSampling._get_kernel_from_markov_model',
autospec=True)
def test_init_markov_model(self, get_kernel):
model = MagicMock(spec_set=MarkovModel)
gibbs = GibbsSampling(model)
get_kernel.assert_called_once_with(gibbs, model)
def test_get_kernel_from_bayesian_model(self):
gibbs = GibbsSampling()
gibbs._get_kernel_from_bayesian_model(self.bayesian_model)
self.assertListEqual(list(gibbs.variables),
self.bayesian_model.nodes())
self.assertDictEqual(gibbs.cardinalities, {
'diff': 2,
'intel': 2,
'grade': 3
})
def test_get_kernel_from_markov_model(self):
gibbs = GibbsSampling()
gibbs._get_kernel_from_markov_model(self.markov_model)
self.assertListEqual(list(gibbs.variables), self.markov_model.nodes())
self.assertDictEqual(gibbs.cardinalities, {
'A': 2,
'B': 3,
'C': 4,
'D': 2
})
def test_sample(self):
start_state = [State('diff', 0), State('intel', 0), State('grade', 0)]
sample = self.gibbs.sample(start_state, 2)
self.assertEquals(len(sample), 2)
self.assertEquals(len(sample.columns), 3)
self.assertIn('diff', sample.columns)
self.assertIn('intel', sample.columns)
self.assertIn('grade', sample.columns)
self.assertTrue(set(sample['diff']).issubset({0, 1}))
self.assertTrue(set(sample['intel']).issubset({0, 1}))
self.assertTrue(set(sample['grade']).issubset({0, 1, 2}))
@patch("pgmpy.sampling.GibbsSampling.random_state", autospec=True)
def test_sample_less_arg(self, random_state):
self.gibbs.state = None
random_state.return_value = [
State('diff', 0),
State('intel', 0),
State('grade', 0)
]
sample = self.gibbs.sample(size=2)
random_state.assert_called_once_with(self.gibbs)
self.assertEqual(len(sample), 2)
def test_generate_sample(self):
start_state = [State('diff', 0), State('intel', 0), State('grade', 0)]
gen = self.gibbs.generate_sample(start_state, 2)
samples = [sample for sample in gen]
self.assertEqual(len(samples), 2)
self.assertEqual(
{samples[0][0].var, samples[0][1].var, samples[0][2].var},
{'diff', 'intel', 'grade'})
self.assertEqual(
{samples[1][0].var, samples[1][1].var, samples[1][2].var},
{'diff', 'intel', 'grade'})
@patch("pgmpy.sampling.GibbsSampling.random_state", autospec=True)
def test_generate_sample_less_arg(self, random_state):
self.gibbs.state = None
gen = self.gibbs.generate_sample(size=2)
samples = [sample for sample in gen]
random_state.assert_called_once_with(self.gibbs)
self.assertEqual(len(samples), 2)
