class TestDoOperator(unittest.TestCase):
def setUp(self):
self.graph = DAG()
self.graph.add_edges_from([("X", "A"), ("A", "Y"), ("A", "B")])
def test_do(self):
dag_do_x = self.graph.do("A")
self.assertEqual(set(dag_do_x.nodes()), set(self.graph.nodes()))
self.assertEqual(sorted(list(dag_do_x.edges())), [("A", "B"), ("A", "Y")])
def estimate(
self, start=None, tabu_length=0, max_indegree=None, epsilon=1e-4, max_iter=1e6
):
"""
Performs local hill climb search to estimates the `DAG` structure
that has optimal score, according to the scoring method supplied in the constructor.
Starts at model `start` and proceeds by step-by-step network modifications
until a local maximum is reached. Only estimates network structure, no parametrization.
Parameters
----------
start: DAG instance
The starting point for the local search. By default a completely disconnected network is used.
tabu_length: int
If provided, the last `tabu_length` graph modifications cannot be reversed
during the search procedure. This serves to enforce a wider exploration
of the search space. Default value: 100.
max_indegree: int or None
If provided and unequal None, the procedure only searches among models
where all nodes have at most `max_indegree` parents. Defaults to None.
epsilon: float (default: 1e-4)
Defines the exit condition. If the improvement in score is less than `epsilon`,
the learned model is returned.
max_iter: int (default: 1e6)
The maximum number of iterations allowed. Returns the learned model when the
number of iterations is greater than `max_iter`.
Returns
-------
model: `DAG` instance
A `DAG` at a (local) score maximum.
Examples
--------
>>> import pandas as pd
>>> import numpy as np
>>> from pgmpy.estimators import HillClimbSearch, BicScore
>>> # create data sample with 9 random variables:
... data = pd.DataFrame(np.random.randint(0, 5, size=(5000, 9)), columns=list('ABCDEFGHI'))
>>> # add 10th dependent variable
... data['J'] = data['A'] * data['B']
>>> est = HillClimbSearch(data, scoring_method=BicScore(data))
>>> best_model = est.estimate()
>>> sorted(best_model.nodes())
['A', 'B', 'C', 'D', 'E', 'F', 'G', 'H', 'I', 'J']
>>> best_model.edges()
[('B', 'J'), ('A', 'J')]
>>> # search a model with restriction on the number of parents:
>>> est.estimate(max_indegree=1).edges()
[('J', 'A'), ('B', 'J')]
"""
nodes = self.state_names.keys()
if start is None:
start = DAG()
start.add_nodes_from(nodes)
elif not isinstance(start, DAG) or not set(start.nodes()) == set(nodes):
raise ValueError(
"'start' should be a DAG with the same variables as the data set, or 'None'."
)
tabu_list = []
current_model = start
iter_no = 0
while iter_no <= max_iter:
iter_no += 1
best_score_delta = 0
best_operation = None
for operation, score_delta in self._legal_operations(
current_model, tabu_list, max_indegree
):
if score_delta > best_score_delta:
best_operation = operation
best_score_delta = score_delta
if best_operation is None or best_score_delta < epsilon:
break
elif best_operation[0] == "+":
current_model.add_edge(*best_operation[1])
tabu_list = ([("-", best_operation[1])] + tabu_list)[:tabu_length]
elif best_operation[0] == "-":
current_model.remove_edge(*best_operation[1])
tabu_list = ([("+", best_operation[1])] + tabu_list)[:tabu_length]
elif best_operation[0] == "flip":
X, Y = best_operation[1]
current_model.remove_edge(X, Y)
current_model.add_edge(Y, X)
tabu_list = ([best_operation] + tabu_list)[:tabu_length]
return current_model
class TestDAGCreation(unittest.TestCase):
def setUp(self):
self.graph = DAG()
def test_class_init_without_data(self):
self.assertIsInstance(self.graph, DAG)
def test_class_init_with_data_string(self):
self.graph = DAG([("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"]]
)
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_node_weight(self):
self.graph.add_node("weighted_a", 0.3)
self.assertEqual(self.graph.nodes["weighted_a"]["weight"], 0.3)
def test_add_nodes_from_weight(self):
self.graph.add_nodes_from(["weighted_b", "weighted_c"], [0.5, 0.6])
self.assertEqual(self.graph.nodes["weighted_b"]["weight"], 0.5)
self.assertEqual(self.graph.nodes["weighted_c"]["weight"], 0.6)
self.graph.add_nodes_from(["e", "f"])
self.assertEqual(self.graph.nodes["e"]["weight"], None)
self.assertEqual(self.graph.nodes["f"]["weight"], None)
def test_add_edge_string(self):
self.graph.add_edge("d", "e")
self.assertListEqual(sorted(self.graph.nodes()), ["d", "e"])
self.assertListEqual(list(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_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_edge_weight(self):
self.graph.add_edge("a", "b", weight=0.3)
if nx.__version__.startswith("1"):
self.assertEqual(self.graph.edge["a"]["b"]["weight"], 0.3)
else:
self.assertEqual(self.graph.adj["a"]["b"]["weight"], 0.3)
def test_add_edges_from_weight(self):
self.graph.add_edges_from([("b", "c"), ("c", "d")], weights=[0.5, 0.6])
if nx.__version__.startswith("1"):
self.assertEqual(self.graph.edge["b"]["c"]["weight"], 0.5)
self.assertEqual(self.graph.edge["c"]["d"]["weight"], 0.6)
self.graph.add_edges_from([("e", "f")])
self.assertEqual(self.graph.edge["e"]["f"]["weight"], None)
else:
self.assertEqual(self.graph.adj["b"]["c"]["weight"], 0.5)
self.assertEqual(self.graph.adj["c"]["d"]["weight"], 0.6)
self.graph.add_edges_from([("e", "f")])
self.assertEqual(self.graph.adj["e"]["f"]["weight"], None)
def test_update_node_parents_bm_constructor(self):
self.graph = DAG([("a", "b"), ("b", "c")])
self.assertListEqual(list(self.graph.predecessors("a")), [])
self.assertListEqual(list(self.graph.predecessors("b")), ["a"])
self.assertListEqual(list(self.graph.predecessors("c")), ["b"])
def test_update_node_parents(self):
self.graph.add_nodes_from(["a", "b", "c"])
self.graph.add_edges_from([("a", "b"), ("b", "c")])
self.assertListEqual(list(self.graph.predecessors("a")), [])
self.assertListEqual(list(self.graph.predecessors("b")), ["a"])
self.assertListEqual(list(self.graph.predecessors("c")), ["b"])
def test_get_leaves(self):
self.graph.add_edges_from(
[("A", "B"), ("B", "C"), ("B", "D"), ("D", "E"), ("D", "F"), ("A", "G")]
)
self.assertEqual(sorted(self.graph.get_leaves()), sorted(["C", "G", "E", "F"]))
def test_get_roots(self):
self.graph.add_edges_from(
[("A", "B"), ("B", "C"), ("B", "D"), ("D", "E"), ("D", "F"), ("A", "G")]
)
self.assertEqual(["A"], self.graph.get_roots())
self.graph.add_edge("H", "G")
self.assertEqual(sorted(["A", "H"]), sorted(self.graph.get_roots()))
def test_init_with_cycle(self):
self.assertRaises(ValueError, DAG, [("a", "a")])
self.assertRaises(ValueError, DAG, [("a", "b"), ("b", "a")])
self.assertRaises(ValueError, DAG, [("a", "b"), ("b", "c"), ("c", "a")])
def tearDown(self):
del self.graph