pyDeid.phi_types package

Submodules

pyDeid.phi_types.AddressPHIFinder module

class pyDeid.phi_types.AddressPHIFinder.AddressPHIFinder(local_places_unambig: list[str] = None)

Bases: PHITypeFinder

Concrete implementation of PHITypeFinder for detecting addresses.

apt_indicators = ['apt', 'suite']

find()

Find phand return all occurrences of the PHI type in the given text.

street_add_suff = ['park', 'drive', 'street', 'road', 'lane', 'boulevard', 'blvd', 'avenue', 'highway', 'circle', 'ave', 'place', 'rd', 'st']

strict_street_add_suff = ['Park', 'Drive', 'Street', 'Road', 'Lane', 'Boulevard', 'Blvd', 'Avenue', 'Highway', 'Ave', 'Rd', 'PARK', 'DRIVE', 'STREET', 'ROAD', 'LANE', 'BOULEVARD', 'BLVD', 'AVENUE', 'HIGHWAY', 'AVE', 'RD']

pyDeid.phi_types.AmericanPIIFinder module

pyDeid.phi_types.DatesPHIFinder module

class pyDeid.phi_types.DatesPHIFinder.Date(date_string, day, month, year)

Bases: tuple

date_string

Alias for field number 0

day

Alias for field number 1

month

Alias for field number 2

year

Alias for field number 3

class pyDeid.phi_types.DatesPHIFinder.DatesPHIFinder(two_digit_threshold=30, valid_year_low=1001, valid_year_high=2999, invalid_time_pre_words: List[str] = None, invalid_time_post_words: List[str] = None)

Bases: PHITypeFinder

Concrete implementation of PHITypeFinder for detecting dates, years, holidays, seasons.

date(text: str)

date_range(text: str)

date_with_context_check(text: str)

days = {'1': 31, '10': 31, '11': 30, '12': 31, '2': 28, '3': 31, '4': 30, '5': 31, '6': 30, '7': 31, '8': 31, '9': 30}

find()

Find phand return all occurrences of the PHI type in the given text.

find_time(text: str)

holiday(text: str)

monthly(text: str)

months = {'Apr': 4, 'April': 4, 'Aug': 8, 'August': 8, 'Dec': 12, 'December': 12, 'Feb': 2, 'February': 2, 'Jan': 1, 'January': 1, 'Jul': 7, 'July': 7, 'Jun': 6, 'June': 6, 'Mar': 3, 'March': 3, 'May': 5, 'Nov': 11, 'November': 11, 'Oct': 10, 'October': 10, 'Sep': 9, 'Sept': 9, 'September': 9}

property name

season_year(text)

seasons = ['winter', 'spring', 'summer', 'autumn', 'fall']

year_with_context_check(text: str)

class pyDeid.phi_types.DatesPHIFinder.Time(time_string, hours, minutes, seconds, meridiem)

Bases: tuple

hours

Alias for field number 1

meridiem

Alias for field number 4

minutes

Alias for field number 2

seconds

Alias for field number 3

time_string

Alias for field number 0

pyDeid.phi_types.EmailPHIFinder module

class pyDeid.phi_types.EmailPHIFinder.EmailPHIFinder

Bases: PHITypeFinder

Concrete implementation of PHITypeFinder for detecting email addresses.

find() → Dict[str, List[str]]

Find phand return all occurrences of the PHI type in the given text.

pyDeid.phi_types.HospitalNamePHIFinder module

class pyDeid.phi_types.HospitalNamePHIFinder.HospitalNamePHIFinder(hospitals: list[str], hospital_acronyms: list[str] = None)

Bases: PHITypeFinder

Concrete implementation of PHITypeFinder for detecting hospital names and their acronyms.

find() → Dict[str, List[str]]

Find phand return all occurrences of the PHI type in the given text.

pyDeid.phi_types.MrnPHIFinder module

class pyDeid.phi_types.MrnPHIFinder.MrnPHIFinder

Bases: PHITypeFinder

Concrete implementation of PHITypeFinder for detecting Medical Record Numbers (MRNs).

find() → Dict[str, List[str]]

Find phand return all occurrences of the PHI type in the given text.

pyDeid.phi_types.NamesPHIFinder module

class pyDeid.phi_types.NamesPHIFinder.NamesPHIFinder(config: Config = None)

Bases: PHITypeFinder

Concrete implementation of PHITypeFinder for detecting names.

class Config(female_names_unambig: List[str] = <factory>, male_names_unambig: List[str] = <factory>, all_first_names: List[str] = <factory>, last_names_unambig: List[str] = <factory>, all_last_names: List[str] = <factory>, doctor_first_names: List[str] = <factory>, doctor_last_names: List[str] = <factory>, female_names_ambig: List[str] = <factory>, male_names_ambig: List[str] = <factory>, last_names_ambig: List[str] = <factory>, female_names_popular: List[str] = <factory>, male_names_popular: List[str] = <factory>, last_names_popular: List[str] = <factory>, medical_phrases: List[str] = <factory>, custom_dr_first_names: List[str] = <factory>, custom_dr_last_names: List[str] = <factory>, custom_patient_first_names: List[str] = <factory>, custom_patient_last_names: List[str] = <factory>, prefixes_unambig: Set[str] = <factory>, last_name_prefixes: Set[str] = <factory>, ner_model: <built-in function any> = None, name_indicators: List[str] = <factory>, eponym_indicators: List[str] = <factory>)

Bases: object

all_first_names: List[str]

all_last_names: List[str]

custom_dr_first_names: List[str]

custom_dr_last_names: List[str]

custom_patient_first_names: List[str]

custom_patient_last_names: List[str]

doctor_first_names: List[str]

doctor_last_names: List[str]

eponym_indicators: List[str]

female_names_ambig: List[str]

female_names_popular: List[str]

female_names_unambig: List[str]

last_name_prefixes: Set[str]

last_names_ambig: List[str]

last_names_popular: List[str]

last_names_unambig: List[str]

male_names_ambig: List[str]

male_names_popular: List[str]

male_names_unambig: List[str]

medical_phrases: List[str]

name_indicators: List[str]

ner_model: any = None

prefixes_unambig: Set[str]

find() → Dict[str, List[str]]

Find phand return all occurrences of the PHI type in the given text.

pyDeid.phi_types.OhipPHIFinder module

class pyDeid.phi_types.OhipPHIFinder.OhipPHIFinder

Bases: PHITypeFinder

Concrete implementation of PHITypeFinder for detecting OHIP numbers.

find() → Dict[str, List[str]]

Find phand return all occurrences of the PHI type in the given text.

pyDeid.phi_types.PHITypeFinder module

class pyDeid.phi_types.PHITypeFinder.PHI(start, end, phi)

Bases: tuple

end

Alias for field number 1

phi

Alias for field number 2

start

Alias for field number 0

class pyDeid.phi_types.PHITypeFinder.PHITypeFinder

Bases: ABC

Abstract base class for Protected Health Information (PHI) finders.

abstract find() → Dict[str, List[str]]

Find phand return all occurrences of the PHI type in the given text.

set_note(new_note: str) → None

set_phis(new_phis) → None

pyDeid.phi_types.PostalCodePHIFinder module

class pyDeid.phi_types.PostalCodePHIFinder.PostalCodePHIFinder

Bases: PHITypeFinder

Concrete implementation of PHITypeFinder for detecting postal codes.

find() → Dict[str, List[str]]

Find phand return all occurrences of the PHI type in the given text.

pyDeid.phi_types.SinPHIFinder module

class pyDeid.phi_types.SinPHIFinder.SinPHIFinder

Bases: PHITypeFinder

Concrete implementation of PHITypeFinder for detecting Canadian Social Insurance Numbers (SIN).

find() → Dict[str, List[str]]

Find phand return all occurrences of the PHI type in the given text.

pyDeid.phi_types.TelephoneFaxPHIFinder module

class pyDeid.phi_types.TelephoneFaxPHIFinder.TelephoneFaxPHIFinder(area_codes: List[str] = None, disqualifiers: List[str] = None)

Bases: PHITypeFinder

Concrete implementation of PHITypeFinder for detecting telephone and fax numbers.

find() → Dict[str, List[str]]

Find phand return all occurrences of the PHI type in the given text.

pyDeid.phi_types.utils module

class pyDeid.phi_types.utils.CustomRegex(phi_type, pattern, surrogate_builder_fn, arguments)

Bases: tuple

arguments

Alias for field number 3

pattern

Alias for field number 1

phi_type

Alias for field number 0

surrogate_builder_fn

Alias for field number 2

class pyDeid.phi_types.utils.PHI(start, end, phi)

Bases: tuple

end

Alias for field number 1

phi

Alias for field number 2

start

Alias for field number 0

pyDeid.phi_types.utils.add_phi_list(phi_list, phitype, phi)

pyDeid.phi_types.utils.add_type(key, phitype, phi)

pyDeid.phi_types.utils.create_custom_regex(phi_type, pattern, surrogate_builder_fn, arguments=[])

pyDeid.phi_types.utils.is_ambig(key, phi)

pyDeid.phi_types.utils.is_common(x)

pyDeid.phi_types.utils.is_commonest(x)

pyDeid.phi_types.utils.is_medical_eponym(x)

pyDeid.phi_types.utils.is_name_indicator(x)

pyDeid.phi_types.utils.is_probably_measurement(x)

pyDeid.phi_types.utils.is_type(key: str, phitype: str, pattern: bool, phi)

pyDeid.phi_types.utils.is_unambig_common(x)

pyDeid.phi_types.utils.load_file(filename, optimization='lookup')

pyDeid.phi_types.utils.merge_phi_dicts(phi1, phi2, in_place=True)

Merge phi2 into phi1. If in_place is True, modify phi1 directly. Otherwise, return a new dict and leave phi1 unmodified.

pyDeid.phi_types.utils.phi_dict_to_list(x, phi)

Module contents