Skip to content

fix(detection): pass single chunk validation flag to exports #190

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
lipikaramaswamy wants to merge 2 commits into
base: main
Choose a base branch
from
+94 −0
Open

fix(detection): pass single chunk validation flag to exports #190

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
f2ffe44
fix(detection): pass single chunk validation flag to exports
lipikaramaswamy Jun 12, 2026
5a74d0b
fix(detection): expose single chunk validation flag
lipikaramaswamy Jun 12, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
8 changes: 8 additions & 0 deletions src/anonymizer/engine/detection/detection_workflow.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -117,6 +117,7 @@ def detect_and_validate_entities(
gliner_detection_threshold=gliner_detection_threshold,
validation_max_entities_per_call=validation_max_entities_per_call,
validation_excerpt_window_chars=validation_excerpt_window_chars,
validation_single_chunk_full_text=validation_single_chunk_full_text,
entity_labels=entity_labels,
data_summary=data_summary,
)
Expand All @@ -138,6 +139,7 @@ def _build_detection_spec(
gliner_detection_threshold: float,
validation_max_entities_per_call: int = _DEFAULT_VALIDATION_MAX_ENTITIES_PER_CALL,
validation_excerpt_window_chars: int = _DEFAULT_VALIDATION_EXCERPT_WINDOW_CHARS,
validation_single_chunk_full_text: bool = True,
entity_labels: list[str] | None = None,
data_summary: str | None = None,
) -> tuple[list[ModelConfig], list[ColumnConfigT]]:
Expand Down Expand Up @@ -245,6 +247,7 @@ def build_detection_config(
gliner_detection_threshold: float,
validation_max_entities_per_call: int = _DEFAULT_VALIDATION_MAX_ENTITIES_PER_CALL,
validation_excerpt_window_chars: int = _DEFAULT_VALIDATION_EXCERPT_WINDOW_CHARS,
validation_single_chunk_full_text: bool = True,
entity_labels: list[str] | None = None,
data_summary: str | None = None,
) -> DataDesignerConfigBuilder:
Expand All @@ -259,6 +262,7 @@ def build_detection_config(
gliner_detection_threshold=gliner_detection_threshold,
validation_max_entities_per_call=validation_max_entities_per_call,
validation_excerpt_window_chars=validation_excerpt_window_chars,
validation_single_chunk_full_text=validation_single_chunk_full_text,
entity_labels=entity_labels,
data_summary=data_summary,
)
Expand All @@ -278,6 +282,7 @@ def build_detection_builder_for_seed(
gliner_detection_threshold: float,
validation_max_entities_per_call: int = _DEFAULT_VALIDATION_MAX_ENTITIES_PER_CALL,
validation_excerpt_window_chars: int = _DEFAULT_VALIDATION_EXCERPT_WINDOW_CHARS,
validation_single_chunk_full_text: bool = True,
entity_labels: list[str] | None = None,
data_summary: str | None = None,
job_index: int = 0,
Expand All @@ -298,6 +303,7 @@ def build_detection_builder_for_seed(
gliner_detection_threshold=gliner_detection_threshold,
validation_max_entities_per_call=validation_max_entities_per_call,
validation_excerpt_window_chars=validation_excerpt_window_chars,
validation_single_chunk_full_text=validation_single_chunk_full_text,
entity_labels=entity_labels,
data_summary=data_summary,
)
Expand Down Expand Up @@ -362,6 +368,7 @@ def run(
gliner_detection_threshold: float,
validation_max_entities_per_call: int = _DEFAULT_VALIDATION_MAX_ENTITIES_PER_CALL,
validation_excerpt_window_chars: int = _DEFAULT_VALIDATION_EXCERPT_WINDOW_CHARS,
validation_single_chunk_full_text: bool = True,
entity_labels: list[str] | None = None,
privacy_goal: PrivacyGoal | None = None,
data_summary: str | None = None,
Expand Down Expand Up @@ -391,6 +398,7 @@ def run(
gliner_detection_threshold=gliner_detection_threshold,
validation_max_entities_per_call=validation_max_entities_per_call,
validation_excerpt_window_chars=validation_excerpt_window_chars,
validation_single_chunk_full_text=validation_single_chunk_full_text,
entity_labels=entity_labels,
data_summary=data_summary,
preview_num_records=preview_num_records,
Expand Down
86 changes: 86 additions & 0 deletions tests/engine/test_detection_workflow.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -543,6 +543,92 @@ def test_validator_pool_kwargs_thread_through_to_generator_params(
assert params.excerpt_window_chars == 42


def test_validation_single_chunk_full_text_threads_to_generator_params(
stub_detector_model_configs: list[ModelConfig],
stub_detection_model_selection: DetectionModelSelection,
) -> None:
adapter = Mock()
adapter.run_workflow.return_value = WorkflowRunResult(
dataframe=pd.DataFrame(
{
COL_TEXT: ["Alice"],
COL_DETECTED_ENTITIES: [{"entities": [{"value": "Alice", "label": "first_name"}]}],
}
),
failed_records=[],
)
workflow = EntityDetectionWorkflow(adapter=adapter)
workflow.run(
pd.DataFrame({COL_TEXT: ["Alice"]}),
model_configs=stub_detector_model_configs,
selected_models=stub_detection_model_selection,
gliner_detection_threshold=0.5,
validation_single_chunk_full_text=False,
tag_latent_entities=False,
)
columns = adapter.run_workflow.call_args.kwargs["columns"]
params = _find_column(columns, COL_VALIDATION_DECISIONS).generator_params
assert params.single_chunk_full_text is False


def test_build_detection_config_threads_validation_single_chunk_full_text(
tmp_path,
stub_detector_model_configs: list[ModelConfig],
stub_detection_model_selection: DetectionModelSelection,
) -> None:
adapter = Mock()
workflow = EntityDetectionWorkflow(adapter=adapter)
workflow.build_detection_config(
pd.DataFrame({COL_TEXT: ["Alice"]}),
seed_path=tmp_path / "seed.parquet",
model_configs=stub_detector_model_configs,
selected_models=stub_detection_model_selection,
gliner_detection_threshold=0.5,
validation_single_chunk_full_text=False,
)
columns = adapter.build_config.call_args.kwargs["columns"]
params = _find_column(columns, COL_VALIDATION_DECISIONS).generator_params
assert params.single_chunk_full_text is False


def test_build_detection_builder_for_seed_threads_validation_single_chunk_full_text(
tmp_path,
stub_detector_model_configs: list[ModelConfig],
stub_detection_model_selection: DetectionModelSelection,
) -> None:
adapter = Mock()
workflow = EntityDetectionWorkflow(adapter=adapter)
workflow.build_detection_builder_for_seed(
seed_path=tmp_path / "seed.parquet",
model_configs=stub_detector_model_configs,
selected_models=stub_detection_model_selection,
gliner_detection_threshold=0.5,
validation_single_chunk_full_text=False,
)
columns = adapter.build_config_for_seed.call_args.kwargs["columns"]
params = _find_column(columns, COL_VALIDATION_DECISIONS).generator_params
assert params.single_chunk_full_text is False


def test_build_detection_config_uses_default_validation_single_chunk_full_text(
tmp_path,
stub_detector_model_configs: list[ModelConfig],
stub_detection_model_selection: DetectionModelSelection,
) -> None:
adapter = Mock()
workflow = EntityDetectionWorkflow(adapter=adapter)
workflow.build_detection_config(
pd.DataFrame({COL_TEXT: ["Alice"]}),
seed_path=tmp_path / "seed.parquet",
model_configs=stub_detector_model_configs,
selected_models=stub_detection_model_selection,
gliner_detection_threshold=0.5,
)
columns = adapter.build_config.call_args.kwargs["columns"]
params = _find_column(columns, COL_VALIDATION_DECISIONS).generator_params
assert params.single_chunk_full_text is True


def test_pool_size_greater_than_one_emits_warning(
stub_detector_model_configs: list[ModelConfig],
stub_detection_model_selection: DetectionModelSelection,
Expand Down
Loading