lexnlp.extract.en.addresses package¶
Subpackages¶
Submodules¶
lexnlp.extract.en.addresses.address_features module¶
Features extraction for addresses detecting classifier.
-
lexnlp.extract.en.addresses.address_features.
build_country_words
()¶
-
lexnlp.extract.en.addresses.address_features.
build_provinces_words
()¶
-
lexnlp.extract.en.addresses.address_features.
get_word_features
(word: str, part_of_speech: str) → List[int]¶
-
lexnlp.extract.en.addresses.address_features.
is_datetime
(word: str) → bool¶
-
lexnlp.extract.en.addresses.address_features.
is_email
(word: str) → bool¶
-
lexnlp.extract.en.addresses.address_features.
is_lowercase_char
(word: str) → bool¶
-
lexnlp.extract.en.addresses.address_features.
is_single_initial
(word: str) → bool¶
-
lexnlp.extract.en.addresses.address_features.
is_uppercase_char
(word: str) → bool¶
-
lexnlp.extract.en.addresses.address_features.
is_url
(word: str) → bool¶
-
lexnlp.extract.en.addresses.address_features.
is_zip_code
(s: str) → bool¶
lexnlp.extract.en.addresses.addresses module¶
Addresses extraction for English language.
-
class
lexnlp.extract.en.addresses.addresses.
Address
(zip_code: str, country: str, state: str, city: str, addr1: str, addr2: str)¶ Bases:
object
-
members
()¶
-
-
class
lexnlp.extract.en.addresses.addresses.
NGramType
¶ Bases:
object
-
ADDR_END
= 3¶
-
ADDR_MIDDLE
= 2¶
-
ADDR_START
= 1¶
-
OTHER
= 0¶
-
-
lexnlp.extract.en.addresses.addresses.
align_tokens
(tokens, sentence)¶ Copy of the same function from nltk fixing processing of double quotes. :param tokens: :param sentence: :return:
-
lexnlp.extract.en.addresses.addresses.
cleanup
(address: str) → str¶
-
lexnlp.extract.en.addresses.addresses.
get_address_spans
(text: str) → Generator[[Tuple[str, int, int], None], None]¶
-
lexnlp.extract.en.addresses.addresses.
get_addresses
(text: str) → Generator[[str, None], None]¶
-
lexnlp.extract.en.addresses.addresses.
load_classifier
()¶
-
lexnlp.extract.en.addresses.addresses.
prepare_ngrams_in_text
(text: str, window_half_width: int, window_step: int) → Generator[[Tuple[List[int], List[str], int, int], None], None]¶