def test_match_run_on_every_rule(self):
mocked_rules = [rule(True)(mock.MagicMock(return_value=Token("asd")))
] * 10
pipeline = RuleBasedCore(self.person_date_relation, self._candidates,
mocked_rules)
pipeline.start()
for mock_rule in mocked_rules:
self.assertTrue(mock_rule.called)
Subject, Object = mock_rule.call_args[0]
self.assertIsInstance(Subject, Pattern)
def test_rule_that_not_matches(self):
@rule(True)
def test_rule(Subject, Object):
return Subject + Object + Token("something here")
pipeline = RuleBasedCore(self.person_date_relation, self._candidates,
[test_rule])
pipeline.start()
facts = pipeline.known_facts()
candidate = self._candidates[0]
self.assertFalse(facts[candidate])
def test_rule_with_negative_answer(self):
@rule(False)
def test_rule(Subject, Object):
anything = Question(Star(Any()))
return Subject + Token("(") + Object + Token("-") + anything
pipeline = RuleBasedCore(self.person_date_relation, self._candidates,
[test_rule])
pipeline.start()
facts = pipeline.known_facts()
candidate = self._candidates[0]
self.assertFalse(facts[candidate])
def test_rule_that_matches(self):
@rule(True)
def test_rule(Subject, Object):
anything = Question(Star(Any()))
return Subject + Token("(") + Object + Token("-") + anything
pipeline = RuleBasedCore(self.person_date_relation, self._candidates,
[test_rule])
pipeline.start()
facts = pipeline.known_facts()
candidate = self._candidates[0]
self.assertTrue(facts[candidate])
def __call__(self, config):
# Prepare data
if self.data is None or self.relname != config["relation"]:
self.relname = config["relation"]
self.relation = iepy.data.models.Relation.objects.get(
name=config["relation"])
candidates = CEM.candidates_for_relation(self.relation)
self.data = CEM.labels_for(self.relation, candidates,
CEM.conflict_resolution_newest_wins)
self.evidences = []
self.labels = []
for evidence, label in self.data.items():
if label is not None:
self.labels.append(label)
self.evidences.append(evidence)
if not self.data:
raise NotEnoughLabeledData(
"There is no labeled data for training!")
result = {
"dataset_size": len(self.data),
"start_time": time.time(),
}
# Load rules in the config
if config["rules"] == "<all>":
rules = self.rules.values()
else:
for rule_name in config["rules"]:
if rule_name not in self.rules.keys():
raise RuleNotFound(rule_name)
rules = [
rule for rule_name, rule in self.rules.items()
if rule_name in config["rules"]
]
# Run the rule based pipeline
pipeline = RuleBasedCore(self.relation, self.evidences, rules)
pipeline.start()
matched = pipeline.known_facts()
predicted_labels = [e in matched for e in self.evidences]
# Evaluate prediction
result.update(
result_dict_from_predictions(self.evidences, self.labels,
predicted_labels))
return result
def test_rule_priority(self):
matcher = lambda *args: True
not_matcher = lambda *args: None
rule_should_run = rule(True, priority=1)(
mock.MagicMock(return_value=matcher))
rule_should_not_run = rule(True, priority=0)(
mock.MagicMock(return_value=not_matcher))
pipeline = RuleBasedCore(self.person_date_relation, self._candidates,
[rule_should_not_run, rule_should_run])
pipeline.start()
# All rules are compiled on start
self.assertTrue(rule_should_run.called)
self.assertTrue(rule_should_not_run.called)
pipeline.process()
import refo
with mock.patch.object(refo, 'match') as fake_refo_match:
fake_refo_match.side_effect = lambda regex, evidence: regex()
pipeline.predict()
self.assertEqual(fake_refo_match.call_count, len(self._candidates))
# check that on every call, the called is rule_match
for c_args in fake_refo_match.call_args_list:
args, kwargs = c_args
self.assertEqual(args[0], matcher)
def test_rule_priority(self):
def rule_match(Subject, Object):
anything = Question(Star(Any()))
return Subject + Token("(") + Object + Token("-") + anything
rule_should_run = rule(True, priority=1)(
mock.MagicMock(side_effect=rule_match))
rule_should_not_run = rule(True, priority=0)(
mock.MagicMock(side_effect=rule_match))
pipeline = RuleBasedCore(self.person_date_relation, self._candidates,
[rule_should_not_run, rule_should_run])
pipeline.start()
self.assertTrue(rule_should_run.called)
self.assertFalse(rule_should_not_run.called)
def test_rule_priority(self):
matcher = lambda *args: True
not_matcher = lambda *args: None
rule_should_run = rule(True, priority=1)(mock.MagicMock(return_value=matcher))
rule_should_not_run = rule(True, priority=0)(
mock.MagicMock(return_value=not_matcher))
pipeline = RuleBasedCore(self.person_date_relation,
[rule_should_not_run, rule_should_run])
pipeline.start()
# All rules are compiled on start
self.assertTrue(rule_should_run.called)
self.assertTrue(rule_should_not_run.called)
pipeline.process()
import refo
with mock.patch.object(refo, 'match') as fake_refo_match:
fake_refo_match.side_effect = lambda regex, evidence: regex()
pipeline.predict(self._candidates)
self.assertEqual(fake_refo_match.call_count, len(self._candidates))
# check that on every call, the called is rule_match
for c_args in fake_refo_match.call_args_list:
args, kwargs = c_args
self.assertEqual(args[0], matcher)
def test_empty_rules(self):
pipeline = RuleBasedCore(self.person_date_relation, self._candidates,
[])
pipeline.start()
pipeline.process()
facts = pipeline.predict()
self.assertEqual(len([x for x in facts if facts[x]]), 0)
def run_from_command_line():
logging.basicConfig(level=logging.INFO, format='%(message)s')
try:
relation_name = iepy.instance.rules.RELATION
except AttributeError:
logging.error("RELATION not defined in rules file")
sys.exit(1)
try:
relation = models.Relation.objects.get(name=relation_name)
except ObjectDoesNotExist:
logging.error("Relation {!r} not found".format(relation_name))
sys.exit(1)
# Load rules
rules = load_rules()
# Load evidences
evidences = CandidateEvidenceManager.candidates_for_relation(relation)
# Run the pipeline
iextractor = RuleBasedCore(relation, evidences, rules)
iextractor.start()
iextractor.process()
predictions = iextractor.predict()
output.dump_output_loop(predictions)
def run_from_command_line():
logging.basicConfig(level=logging.INFO, format='%(message)s')
try:
relation_name = iepy.instance.rules.RELATION
except AttributeError:
logging.error("RELATION not defined in rules file")
sys.exit(1)
try:
relation = models.Relation.objects.get(name=relation_name)
except ObjectDoesNotExist:
logging.error("Relation {!r} not found".format(relation_name))
sys.exit(1)
# Load rules
rules = load_rules()
# Load evidences
evidences = CandidateEvidenceManager.candidates_for_relation(relation)
# Run the pipeline
iextractor = RuleBasedCore(relation, rules)
iextractor.start()
iextractor.process()
predictions = iextractor.predict(evidences)
output.dump_output_loop(predictions)
def test_empty_rules(self):
pipeline = RuleBasedCore(self.person_date_relation, self._candidates,
[])
pipeline.start()
pipeline.process()
facts = pipeline.predict()
self.assertEqual(len([x for x in facts if facts[x]]), 0)
def test_match_run_on_every_rule(self):
mocked_rules = [
rule(True)(mock.MagicMock(return_value=Token("asd")))
] * 10
pipeline = RuleBasedCore(self.person_date_relation, mocked_rules)
pipeline.start()
pipeline.process()
pipeline.predict(self._candidates)
for mock_rule in mocked_rules:
self.assertTrue(mock_rule.called)
Subject, Object = mock_rule.call_args[0]
self.assertIsInstance(Subject, Pattern)
def test_rule_with_negative_answer(self):
@rule(False)
def test_rule(Subject, Object):
anything = Question(Star(Any()))
return Subject + Token("(") + Object + Token("-") + anything
pipeline = RuleBasedCore(self.person_date_relation, [test_rule])
pipeline.start()
pipeline.process()
facts = pipeline.predict(self._candidates)
candidate = self._candidates[0]
self.assertFalse(facts[candidate])
def test_rule_that_not_matches(self):
@rule(True)
def test_rule(Subject, Object):
return Subject + Object + Token("something here")
pipeline = RuleBasedCore(self.person_date_relation, [test_rule])
pipeline.start()
pipeline.process()
facts = pipeline.predict(self._candidates)
candidate = self._candidates[0]
self.assertFalse(facts[candidate])
def test_rule_priority(self):
def rule_match(Subject, Object):
anything = Question(Star(Any()))
return Subject + Token("(") + Object + Token("-") + anything
rule_should_run = rule(True, priority=1)(mock.MagicMock(side_effect=rule_match))
rule_should_not_run = rule(True, priority=0)(mock.MagicMock(side_effect=rule_match))
pipeline = RuleBasedCore(self.person_date_relation, self._candidates,
[rule_should_not_run, rule_should_run])
pipeline.start()
pipeline.process()
pipeline.predict()
self.assertTrue(rule_should_run.called)
self.assertFalse(rule_should_not_run.called)
def test_rule_that_matches(self):
@rule(True)
def test_rule(Subject, Object):
anything = Question(Star(Any()))
return Subject + Token("(") + Object + Token("-") + anything
pipeline = RuleBasedCore(self.person_date_relation, [test_rule])
pipeline.start()
pipeline.process()
facts = pipeline.predict(self._candidates)
candidate = self._candidates[0]
self.assertTrue(facts[candidate])
if __name__ == u'__main__':
logging.basicConfig(level=logging.INFO, format='%(message)s')
opts = docopt(__doc__, version=iepy.__version__)
try:
relation = rules.RELATION
except AttributeError:
logging.error("RELATION not defined in rules file")
sys.exit(1)
relation = models.Relation.objects.get(name=rules.RELATION)
# Load rules
rules = []
for attr_name in dir(rules):
attr = getattr(rules, attr_name)
if hasattr(attr, '__call__'): # is callable
if hasattr(attr, "is_rule") and attr.is_rule:
rules.append(attr)
# Load evidences
evidences = CandidateEvidenceManager.candidates_for_relation(relation)
# Run the pipeline
iextractor = RuleBasedCore(relation, evidences, rules)
iextractor.start()
iextractor.process()
predictions = iextractor.predict()
output.dump_output_loop(predictions)
def test_empty_rules(self):
pipeline = RuleBasedCore(self.person_date_relation, self._candidates,
[])
pipeline.start()
facts = pipeline.known_facts()
self.assertEqual(len(facts), 0)
from iepy.extraction.rules_core import RuleBasedCore
from iepy.data import models
from iepy.data.db import CandidateEvidenceManager
import rules
if __name__ == u'__main__':
logging.basicConfig(
level=logging.DEBUG,
format="%(asctime)s - %(name)s - %(levelname)s - %(message)s")
relation = models.Relation.objects.get(name=rules.RELATION)
# Load rules
rules = []
for attr_name in dir(rules):
attr = getattr(rules, attr_name)
if hasattr(attr, '__call__'): # is callable
if hasattr(attr, "is_rule") and attr.is_rule:
rules.append(attr)
# Load evidences
evidences = CandidateEvidenceManager.candidates_for_relation(relation)
# Run the pipeline
iextractor = RuleBasedCore(relation, evidences, rules)
iextractor.start()
facts = iextractor.known_facts()
print(facts)