def evaluate_single_graph(df_samples, graph, bn_truth, nb_repeat=3):
testing_graph = BayesianModel()
testing_graph.add_nodes_from(bn_truth.causal_graph.nodes())
for edge in remove_bidirected_edges(graph.edges()):
try:
testing_graph.add_edge(edge[0], edge[1])
except Exception as e:
try:
testing_graph.add_edge(edge[1], edge[0])
except Exception as e:
print(e)
continue
testing_graph.fit(df_samples, estimator=BayesianEstimator)
testing_graph.check_model()
bn_test = BayesianNetwork(testing_graph)
set_observe(bn_test.bn)
set_observe(bn_truth.bn)
bn_truth.set_state_names()
bn_test.set_state_names()
return {
'SID':
SID(bn_truth.causal_graph, bn_test.causal_graph),
'SHD':
SHD(bn_truth.causal_graph, bn_test.causal_graph),
'OD':
np.mean([
ODist(bn_truth, bn_test, 1000, discrete=True)
for _ in range(nb_repeat)
]),
'ID':
np.mean([
IDist(bn_truth, bn_test, 1000, discrete=True)
for _ in range(nb_repeat)
])
}
from cdt.causality.graph import CCDr
from cdt.causality.graph import CGNN
from cdt.causality.graph import GES
from cdt.causality.graph import LiNGAM
from cdt.causality.graph import PC
from cdt.causality.graph import CAM
from cdt.utils.graph import clr
import networkx as nx
device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
# Read the data
data = pd.read_csv('combined.csv', header=None)
true_CM = pd.read_csv('true_CM.csv', header=None)
true_CM = np.array(true_CM)
start_time = time.time()
aupr_matrix, dir_adj_matrix = CDVAE()
end_time = time.time() - start_time
print("--- Execution time : %4.4s seconds ---" % end_time)
#Retrieve SHD and AUPR
shd = SHD(true_CM, dir_adj_matrix, double_for_anticausal=False)
print('SHD:', shd)
aupr, curve = precision_recall(true_CM, aupr_matrix)
print('AUPR for aupr_matrix:', aupr)
def evaluate_single_graph(df_samples, graph, bn_truth, nb_repeat=1):
testing_graph = BayesianModel()
testing_graph.add_nodes_from(bn_truth.causal_graph.nodes())
for edge in remove_bidirected_edges(graph.edges()):
try:
testing_graph.add_edge(edge[0], edge[1])
except Exception as e:
try:
testing_graph.add_edge(edge[1], edge[0])
except Exception as e:
print(e)
continue
testing_graph.fit(df_samples, estimator=BayesianEstimator)
testing_graph.check_model()
bn_test = BayesianNetwork(testing_graph)
# print(bn_test.causal_graph.edges())
# exit()
# model_test = BayesianModel()
# model_test.add_nodes_from(graph.nodes())
# for a in graph_diff:
# model_test.add_node(a)
# for edge in remove_bidirected_edges(graph.edges()):
# try:
# model_test.add_edge(edge)
# except Exception as e:
# rev_edge = (edge[1], edge[0])
# try:
# model_test.add_edge(rev_edge)
# except Exception as e:
# continue
# model_test.fit(df_samples, estimator=BayesianEstimator)
# model_test.check_model()
# bn_test = BayesianNetwork(model_test)
set_observe(bn_test.bn)
set_observe(bn_truth.bn)
bn_truth.set_state_names()
bn_test.set_state_names()
# mapping = dict((i, str(i)) for i in bn_truth.bn.nodes())
# nx.relabel_nodes(bn_truth.bn.graph, mapping)
# nx.relabel_nodes(bn_test.bn.graph, mapping)
# print()
# print(bn_truth.causal_graph.edges())
# print(testing_graph.edges())
# print(SID(bn_truth.causal_graph, bn_test.causal_graph))
# print(SHD(bn_truth.causal_graph, bn_test.causal_graph))
return {
'SID':
SID(bn_truth.causal_graph, bn_test.causal_graph),
'SHD':
SHD(bn_truth.causal_graph, bn_test.causal_graph),
'Tau':
Tau(bn_truth.causal_graph, bn_test.causal_graph),
'OD':
np.mean([
ODist(bn_truth, bn_test, 1000, discrete=True)
for _ in range(nb_repeat)
]),
'ID':
np.mean([
IDist(bn_truth, bn_test, 1000, discrete=True)
for _ in range(nb_repeat)
])
}
def test_SHD():
assert SHD(*init()) == 2
assert SHD(*init(), double_for_anticausal=False) == 1
def graph_score(self, test_graph: nx.DiGraph) -> float:
pr_score, _ = precision_recall(self._ground_truth_graph, test_graph)
shd_score = SHD(self._ground_truth_graph, test_graph)
return float(pr_score - shd_score) # Higher better
def baselines(data):
# Tests
start_time = time.time()
obj = PC()
output = obj.predict(data)
adj_mat = nx.adjacency_matrix(output).todense()
output = clr(adj_mat)
output[np.isnan(output)] = 0
output[np.isposinf(output)] = 1
predicted = retrieve_adjacency_matrix(output)
true_matrix = pd.read_csv('true_CM.csv', header=None)
true_matrix = np.array(true_matrix)
shd = SHD(np.array(true_matrix), predicted, double_for_anticausal=False)
aupr, curve = precision_recall(np.array(true_matrix), output)
end_time = (time.time() - start_time)
print("--- Execution time : %4.4s seconds ---" % end_time)
results_pc = ['PC', aupr, shd, end_time]
print(results_pc)
# Tests
start_time = time.time()
obj = GES()
output = obj.predict(data)
adj_mat = nx.adjacency_matrix(output).todense()
output = clr(adj_mat)
output[np.isnan(output)] = 0
output[np.isposinf(output)] = 1
predicted = retrieve_adjacency_matrix(output)
true_matrix = pd.read_csv('true_CM.csv', header=None)
true_matrix = np.array(true_matrix)
shd = SHD(np.array(true_matrix), predicted, double_for_anticausal=False)
aupr, curve = precision_recall(np.array(true_matrix), output)
end_time = (time.time() - start_time)
print("--- Execution time : %4.4s seconds ---" % end_time)
results_ges = ['GES', aupr, shd, end_time]
print(results_ges)
# Tests
start_time = time.time()
obj = LiNGAM()
output = obj.predict(data)
adj_mat = nx.adjacency_matrix(output).todense()
output = clr(adj_mat)
output[np.isnan(output)] = 0
output[np.isposinf(output)] = 1
predicted = retrieve_adjacency_matrix(output)
true_matrix = pd.read_csv('true_CM.csv', header=None)
true_matrix = np.array(true_matrix)
shd = SHD(np.array(true_matrix), predicted, double_for_anticausal=False)
aupr, curve = precision_recall(np.array(true_matrix), output)
end_time = (time.time() - start_time)
print("--- Execution time : %4.4s seconds ---" % end_time)
results_lingam = ['LiNGAM', aupr, shd, end_time]
print(results_lingam)
# Tests
start_time = time.time()
obj = CCDr()
output = obj.predict(data)
adj_mat = nx.adjacency_matrix(output).todense()
output = clr(adj_mat)
output[np.isnan(output)] = 0
output[np.isposinf(output)] = 1
predicted = retrieve_adjacency_matrix(output)
true_matrix = pd.read_csv('true_CM.csv', header=None)
true_matrix = np.array(true_matrix)
shd = SHD(np.array(true_matrix), predicted, double_for_anticausal=False)
aupr, curve = precision_recall(np.array(true_matrix), output)
end_time = (time.time() - start_time)
print("--- Execution time : %4.4s seconds ---" % end_time)
results_ccdr = ['CCDR', aupr, shd, end_time]
print(results_ccdr)
return results_pc, results_ges, results_lingam, results_ccdr
results_ccdr = ['CCDR', aupr, shd, end_time]
print(results_ccdr)
return results_pc, results_ges, results_lingam, results_ccdr
# Tests
start_time = time.time()
obj = CGNN(nruns=1, train_epochs=500, test_epochs=500)
output = obj.predict(data)
adj_mat = nx.adjacency_matrix(output).todense()
output = clr(adj_mat)
output[np.isnan(output)] = 0
output[np.isposinf(output)] = 1
predicted = retrieve_adjacency_matrix(output)
true_matrix = pd.read_csv('true_CM.csv', header=None)
true_matrix = np.array(true_matrix)
shd = SHD(np.array(true_matrix), predicted, double_for_anticausal=False)
aupr, curve = precision_recall(np.array(true_matrix), output)
end_time = (time.time() - start_time)
print("--- Execution time : %4.4s seconds ---" % end_time)
results_cgnn = ['CGNN', aupr, shd, end_time]
print(results_cgnn)