def _find_partial_match(
self,
hypothesis: PerceptionGraphTemplate,
graph: PerceptionGraph,
*,
required_alignments: Mapping[SyntaxSemanticsVariable,
ObjectSemanticNode], # pylint:disable=unused-argument
) -> "PursuitObjectLearnerNew.ObjectHypothesisPartialMatch":
pattern = hypothesis.graph_pattern
hypothesis_pattern_common_subgraph = get_largest_matching_pattern(
pattern,
graph,
debug_callback=self._debug_callback,
graph_logger=self._hypothesis_logger,
ontology=self._ontology,
match_mode=MatchMode.OBJECT,
)
self.debug_counter += 1
leading_hypothesis_num_nodes = len(pattern)
num_nodes_matched = (len(
hypothesis_pattern_common_subgraph.copy_as_digraph().nodes)
if hypothesis_pattern_common_subgraph else 0)
return PursuitObjectLearnerNew.ObjectHypothesisPartialMatch(
PerceptionGraphTemplate(
graph_pattern=hypothesis_pattern_common_subgraph)
if hypothesis_pattern_common_subgraph else None,
num_nodes_matched=num_nodes_matched,
num_nodes_in_pattern=leading_hypothesis_num_nodes,
)
def _find_partial_match(
self, hypothesis: PerceptionGraphTemplate, graph: PerceptionGraph
) -> "PrepositionPursuitLearner.PrepositionHypothesisPartialMatch":
pattern = hypothesis.graph_pattern
hypothesis_pattern_common_subgraph = get_largest_matching_pattern(
pattern,
graph,
debug_callback=self._debug_callback,
graph_logger=self._hypothesis_logger,
ontology=self._ontology,
match_mode=MatchMode.OBJECT,
)
self.debug_counter += 1
leading_hypothesis_num_nodes = len(pattern)
num_nodes_matched = (len(
hypothesis_pattern_common_subgraph.copy_as_digraph().nodes)
if hypothesis_pattern_common_subgraph else 0)
if hypothesis_pattern_common_subgraph:
partial_hypothesis: Optional[
PerceptionGraphTemplate] = PerceptionGraphTemplate(
graph_pattern=hypothesis_pattern_common_subgraph,
template_variable_to_pattern_node=hypothesis.
template_variable_to_pattern_node,
)
else:
partial_hypothesis = None
return PrepositionPursuitLearner.PrepositionHypothesisPartialMatch(
partial_hypothesis,
num_nodes_matched=num_nodes_matched,
num_nodes_in_pattern=leading_hypothesis_num_nodes,
)
def _find_partial_match(
self, hypothesis: PerceptionGraphTemplate, graph: PerceptionGraph
) -> "ObjectPursuitLearner.ObjectHypothesisPartialMatch":
pattern = hypothesis.graph_pattern
hypothesis_pattern_common_subgraph = get_largest_matching_pattern(
pattern,
graph,
debug_callback=self._debug_callback,
graph_logger=self._hypothesis_logger,
ontology=self._ontology,
match_mode=MatchMode.OBJECT,
)
self.debug_counter += 1
leading_hypothesis_num_nodes = len(pattern)
num_nodes_matched = (len(
hypothesis_pattern_common_subgraph.copy_as_digraph().nodes)
if hypothesis_pattern_common_subgraph else 0)
return ObjectPursuitLearner.ObjectHypothesisPartialMatch(
PerceptionGraphTemplate(
graph_pattern=hypothesis_pattern_common_subgraph)
if hypothesis_pattern_common_subgraph else None,
num_nodes_matched=num_nodes_matched,
num_nodes_in_pattern=leading_hypothesis_num_nodes,
)
def _hypothesis_from_perception(
self, preprocessed_input: LanguageAlignedPerception
) -> PerceptionGraphTemplate:
new_hypothesis = PerceptionGraphPattern.from_graph(
preprocessed_input.perception_graph).perception_graph_pattern
return PerceptionGraphTemplate(
graph_pattern=new_hypothesis,
template_variable_to_pattern_node=immutabledict(),
)
def candidate_object_hypotheses(
language_perception_semantic_alignment: LanguagePerceptionSemanticAlignment
) -> Sequence[PerceptionGraphTemplate]:
"""
Given a learning input, returns all possible meaning hypotheses.
"""
return [
PerceptionGraphTemplate(
graph_pattern=PerceptionGraphPattern.from_graph(
object_
).perception_graph_pattern
)
for object_ in get_objects_from_perception(
language_perception_semantic_alignment.perception_semantic_alignment.perception_graph
)
]
def _hypotheses_from_perception(
self,
learning_state: LanguagePerceptionSemanticAlignment,
bound_surface_template: SurfaceTemplateBoundToSemanticNodes,
) -> AbstractSet[PerceptionGraphTemplate]:
if bound_surface_template.slot_to_semantic_node:
raise RuntimeError(
"Object learner should not have slot to semantic node alignments!"
)
return immutableset(
PerceptionGraphTemplate(
graph_pattern=PerceptionGraphPattern.from_graph(
candidate_object).perception_graph_pattern,
template_variable_to_pattern_node=immutabledict(),
) for candidate_object in extract_candidate_objects(
learning_state.perception_semantic_alignment.perception_graph))
def _find_partial_match(
self,
hypothesis: PerceptionGraphTemplate,
graph: PerceptionGraph,
*,
required_alignments: Mapping[SyntaxSemanticsVariable, ObjectSemanticNode],
) -> "AbstractPursuitLearnerNew.PartialMatch":
pattern = hypothesis.graph_pattern
hypothesis_pattern_common_subgraph = get_largest_matching_pattern(
pattern,
graph,
debug_callback=self._debug_callback,
graph_logger=self._hypothesis_logger,
ontology=self._ontology,
match_mode=MatchMode.NON_OBJECT,
allowed_matches=immutablesetmultidict(
[
(hypothesis.template_variable_to_pattern_node[variable], object_node)
for variable, object_node in required_alignments.items()
]
),
)
self.debug_counter += 1
leading_hypothesis_num_nodes = len(pattern)
num_nodes_matched = (
len(hypothesis_pattern_common_subgraph.copy_as_digraph().nodes)
if hypothesis_pattern_common_subgraph
else 0
)
if hypothesis_pattern_common_subgraph:
partial_hypothesis: Optional[
PerceptionGraphTemplate
] = PerceptionGraphTemplate(
graph_pattern=hypothesis_pattern_common_subgraph,
template_variable_to_pattern_node=hypothesis.template_variable_to_pattern_node,
)
else:
partial_hypothesis = None
return PursuitAttributeLearnerNew.AttributeHypothesisPartialMatch(
partial_hypothesis,
num_nodes_matched=num_nodes_matched,
num_nodes_in_pattern=leading_hypothesis_num_nodes,
)
def _hypothesis_from_perception(
self, perception: PerceptionGraph) -> PerceptionGraphTemplate:
return PerceptionGraphTemplate(
graph_pattern=PerceptionGraphPattern.from_graph(
perception).perception_graph_pattern)