From 79c0e4ddec6bbb71856a5dc91e1a78fe69f9b2b3 Mon Sep 17 00:00:00 2001 From: "enrique.botia" Date: Wed, 13 Dec 2023 14:00:15 +0100 Subject: [PATCH 1/2] Update LOW_SCORE_ENTITY_NAMES to use a set instead of an empty dictionary --- .../presidio_analyzer/nlp_engine/ner_model_configuration.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/presidio-analyzer/presidio_analyzer/nlp_engine/ner_model_configuration.py b/presidio-analyzer/presidio_analyzer/nlp_engine/ner_model_configuration.py index a88545090..dd8e30498 100644 --- a/presidio-analyzer/presidio_analyzer/nlp_engine/ner_model_configuration.py +++ b/presidio-analyzer/presidio_analyzer/nlp_engine/ner_model_configuration.py @@ -26,7 +26,7 @@ HOSPITAL="ORGANIZATION", ) -LOW_SCORE_ENTITY_NAMES = {} +LOW_SCORE_ENTITY_NAMES = set() LABELS_TO_IGNORE = { "O", "ORG", From 746f0d0b8dad5415c0665bb8d25e6f99f34cde9c Mon Sep 17 00:00:00 2001 From: "enrique.botia" Date: Wed, 13 Dec 2023 14:03:06 +0100 Subject: [PATCH 2/2] Update data types in NerModelConfiguration validation --- .../presidio_analyzer/nlp_engine/ner_model_configuration.py | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/presidio-analyzer/presidio_analyzer/nlp_engine/ner_model_configuration.py b/presidio-analyzer/presidio_analyzer/nlp_engine/ner_model_configuration.py index dd8e30498..8408f776a 100644 --- a/presidio-analyzer/presidio_analyzer/nlp_engine/ner_model_configuration.py +++ b/presidio-analyzer/presidio_analyzer/nlp_engine/ner_model_configuration.py @@ -94,12 +94,12 @@ def __post_init__(self): @classmethod def _validate_input(cls, ner_model_configuration_dict: Dict) -> None: key_to_type = { - "labels_to_ignore": list, + "labels_to_ignore": Collection, "aggregation_strategy": str, "alignment_mode": str, "model_to_presidio_entity_mapping": dict, "low_confidence_score_multiplier": float, - "low_score_entity_names": list, + "low_score_entity_names": Collection, "stride": int, }