langchain_experimental.data_anonymizer.presidio.PresidioReversibleAnonymizer¶

class langchain_experimental.data_anonymizer.presidio.PresidioReversibleAnonymizer(analyzed_fields: Optional[List[str]] = None, operators: Optional[Dict[str, OperatorConfig]] = None, languages_config: Dict = {'models': [{'lang_code': 'en', 'model_name': 'en_core_web_lg'}], 'nlp_engine_name': 'spacy'}, add_default_faker_operators: bool = True, faker_seed: Optional[int] = None)[source]¶
Parameters

  • analyzed_fields – List of fields to detect and then anonymize. Defaults to all entities supported by Microsoft Presidio.

  • operators – Operators to use for anonymization. Operators allow for custom anonymization of detected PII. Learn more: https://microsoft.github.io/presidio/tutorial/10_simple_anonymization/

  • languages_config – Configuration for the NLP engine. First language in the list will be used as the main language in self.anonymize(…) when no language is specified. Learn more: https://microsoft.github.io/presidio/analyzer/customizing_nlp_models/

  • faker_seed – Seed used to initialize faker. Defaults to None, in which case faker will be seeded randomly and provide random values.

Attributes

anonymizer_mapping

Return the anonymizer mapping This is just the reverse version of the deanonymizer mapping.

deanonymizer_mapping

Return the deanonymizer mapping

Methods

__init__([analyzed_fields, operators, ...])

param analyzed_fields

List of fields to detect and then anonymize.

add_operators(operators)

Add operators to the anonymizer

add_recognizer(recognizer)

Add a recognizer to the analyzer

anonymize(text[, language, allow_list])

Anonymize text

deanonymize(text_to_deanonymize[, ...])

Deanonymize text

load_deanonymizer_mapping(file_path)

Load the deanonymizer mapping from a JSON or YAML file.

reset_deanonymizer_mapping()

Reset the deanonymizer mapping

save_deanonymizer_mapping(file_path)

Save the deanonymizer mapping to a JSON or YAML file.
__init__(analyzed_fields: Optional[List[str]] = None, operators: Optional[Dict[str, OperatorConfig]] = None, languages_config: Dict = {'models': [{'lang_code': 'en', 'model_name': 'en_core_web_lg'}], 'nlp_engine_name': 'spacy'}, add_default_faker_operators: bool = True, faker_seed: Optional[int] = None)[source]¶
Parameters

  • analyzed_fields – List of fields to detect and then anonymize. Defaults to all entities supported by Microsoft Presidio.

  • operators – Operators to use for anonymization. Operators allow for custom anonymization of detected PII. Learn more: https://microsoft.github.io/presidio/tutorial/10_simple_anonymization/

  • languages_config – Configuration for the NLP engine. First language in the list will be used as the main language in self.anonymize(…) when no language is specified. Learn more: https://microsoft.github.io/presidio/analyzer/customizing_nlp_models/

  • faker_seed – Seed used to initialize faker. Defaults to None, in which case faker will be seeded randomly and provide random values.

add_operators(operators: Dict[str, OperatorConfig]) → None¶

Add operators to the anonymizer

Parameters

operators – Operators to add to the anonymizer.

add_recognizer(recognizer: EntityRecognizer) → None¶

Add a recognizer to the analyzer

Parameters

recognizer – Recognizer to add to the analyzer.

anonymize(text: str, language: Optional[str] = None, allow_list: Optional[List[str]] = None) → str¶

Anonymize text

deanonymize(text_to_deanonymize: str, deanonymizer_matching_strategy: ~typing.Callable[[str, ~typing.Dict[str, ~typing.Dict[str, str]]], str] = <function exact_matching_strategy>) → str¶

Deanonymize text

load_deanonymizer_mapping(file_path: Union[Path, str]) → None[source]¶

Load the deanonymizer mapping from a JSON or YAML file.

Parameters

file_path – Path to file to load the mapping from.

Example: .. code-block:: python

anonymizer.load_deanonymizer_mapping(file_path=”path/mapping.json”)

reset_deanonymizer_mapping() → None[source]¶

Reset the deanonymizer mapping

save_deanonymizer_mapping(file_path: Union[Path, str]) → None[source]¶

Save the deanonymizer mapping to a JSON or YAML file.

Parameters

file_path – Path to file to save the mapping to.

Example: .. code-block:: python

anonymizer.save_deanonymizer_mapping(file_path=”path/mapping.json”)