lexnlp.extract.en.pii
: Extracting personally-identifiable information (PII)¶
The lexnlp.extract.en.pii
module contains methods that allow for the extraction
of personally identifying information from text. Examples include:
- phone numbers
- US social security numbers
- names
The full list of current unit test cases can be found here: https://github.com/LexPredict/lexpredict-lexnlp/tree/master/test_data/lexnlp/extract/en/tests/test_pii
Extracting PII¶
-
lexnlp.extract.en.pii.
get_pii
(text: str, return_sources=False) → Generator¶ Find possible PII references in the text. :param text: :param return_sources: :return:
Example
>>> import lexnlp.extract.en.pii
>>> text = "John Doe (999-12-3456)"
>>> print(list(lexnlp.extract.en.pii.get_pii(text)))
[('ssn', '999-12-3456')]
>>> text = "Mary Doe (212-123-4567)"
>>> print(list(lexnlp.extract.en.pii.get_pii(text)))
[('us_phone', '(212) 123-4567')]
-
lexnlp.extract.en.pii.
get_ssns
(text, return_sources=False) → Generator¶ Find possible SSN references in the text.
-
lexnlp.extract.en.pii.
get_us_phones
(text: str, return_sources=False) → Generator¶ Find possible telephone numbers in the text.