chrislit/abydos

TODO ( ^ |

TODO feat2: int, ^ |

TODO word_transform: Optional[Callable[[str], str]] = None, ^ |

Used in order to highlight an unnecessary block of code following an if containing a return statement. As such, it will warn when it encounters an else following a chain of ifs, all of them containing a return statement.

Indicates that a set of similar lines has been detected among multiple file. This usually means that the code should be refactored to avoid this duplication. ==abydos.phonetic.lein:61 ==abydos.phonetic.phonix:190 self.zeropad = zero_pad

def encode_alpha(self, word: str) -> str: ```Return the alphabetic LEIN code for a word.

Parameters

word : str The word to transform

Returns

str The alphabetic LEIN code

Examples

pe = LEIN() pe.encodealpha('Christopher') 'CLKT' pe.encodealpha('Niall') 'NL' pe.encodealpha('Smith') 'SNT' pe.encodealpha('Schmidt') 'SKNT'

.. versionadded:: 0.4.0

code = self.encode(word).rstrip('0')
 return code[:1] + code[1:].translate(self._alphabetic)

 def encode(self, word: str) -> str:
 ```Return the LEIN code for a word.

 Parameters
 ----------
 word : str
 The word to transform

 Returns
 -------
 str
 The LEIN code

 Examples
 --------
 >>> pe = LEIN()
 >>> pe.encode('Christopher')
 'C351'
 >>> pe.encode('Niall')
 'N300'
 >>> pe.encode('Smith')
 'S210'
 >>> pe.encode('Schmidt')
 'S521'


 .. versionadded:: 0.3.0
 .. versionchanged:: 0.3.6
 Encapsulated in class

# uppercase, normalize, decompose, and filter non-A-Z out

Indicates that a set of similar lines has been detected among multiple file. This usually means that the code should be refactored to avoid this duplication. ==abydos.distance.levenshtein:323 ==abydos.distance.phoneticeditdistance:253 dmat = cast( np.ndarray, self.alignment_matrix(src, tar, backtrace=False) )

if int(dmat[srclen, tarlen]) == dmat[srclen, tarlen]: return int(dmat[srclen, tarlen]) else: return cast(float, dmat[srclen, tarlen])

def dist(self, src: str, tar: str) -> float: ```Return the normalized phonetic edit distance between two strings.

The edit distance is normalized by dividing the edit distance (calculated by either of the two supported methods) by the greater of the number of characters in src times the cost of a delete and the number of characters in tar times the cost of an insert. For the case in which all operations have :math:cost = 1, this is equivalent to the greater of the length of the two strings src & tar.

Parameters

src : str Source string for comparison tar : str Target string for comparison

Returns

float The normalized Levenshtein distance between src & tar

Examples

cmp = PhoneticEditDistance() round(cmp.dist('cat', 'hat'), 12) 0.059139784946 round(cmp.dist('Niall', 'Neil'), 12) 0.232258064516 cmp.dist('aluminum', 'Catalan') 0.3084677419354839 cmp.dist('ATCG', 'TAGC') 0.2983870967741935

.. versionadded:: 0.4.1

Indicates that a set of similar lines has been detected among multiple file. This usually means that the code should be refactored to avoid this duplication. ==abydos.distance.prefix:32 ==abydos.distance.suffix:32 def sim(self, src: str, tar: str) -> float: ```Return the prefix similarity of two strings.

Prefix similarity is the ratio of the length of the shorter term that exactly matches the longer term to the length of the shorter term, beginning at the start of both terms.

Parameters

src : str Source string for comparison tar : str Target string for comparison

Returns

float Prefix similarity

Examples

cmp = Prefix() cmp.sim('cat', 'hat') 0.0 cmp.sim('Niall', 'Neil') 0.25 cmp.sim('aluminum', 'Catalan') 0.0 cmp.sim('ATCG', 'TAGC') 0.0

.. versionadded:: 0.1.0 .. versionchanged:: 0.3.6 Encapsulated in class

if src == tar:
 return 1.0
 if not src or not tar:
 return 0.0
 min_word, max_word = (src, tar) if len(src) < len(tar) else (tar, src)
 min_len = len(min_word)
 for i in range(min_len, 0, -1):

Indicates that a set of similar lines has been detected among multiple file. This usually means that the code should be refactored to avoid this duplication. ==abydos.distance.gotoh:67 ==abydos.distance.needlemanwunsch:150 ==abydos.distance.smithwaterman:65 self.simfunc = cast( Callable[[str, str], float], NeedlemanWunsch.simmatrix if simfunc is None else simfunc, ) # type: Callable[[str, str], float]

def sim_score(self, src: str, tar: str) -> float: ```Return the Gotoh score of two strings.

Parameters

src : str Source string for comparison tar : str Target string for comparison

Returns

float Gotoh score

Examples

cmp = Gotoh() cmp.simscore('cat', 'hat') 2.0 cmp.simscore('Niall', 'Neil') 1.0 round(cmp.simscore('aluminum', 'Catalan'), 12) -0.4 cmp.simscore('cat', 'hat') 2.0

.. versionadded:: 0.1.0 .. versionchanged:: 0.3.6 Encapsulated in class

d_mat = np_zeros((len(src) + 1, len(tar) + 1), dtype=np_float)

Indicates that a set of similar lines has been detected among multiple file. This usually means that the code should be refactored to avoid this duplication. ==abydos.phonetic.pshpsoundexfirst:41 ==abydos.phonetic.pshpsoundexlast:41 trans = dict( zip( (ord() for _ in 'ABCDEFGHIJKLMNOPQRSTUVWXYZ'), '01230120022455012523010202', ) )

alphabetic = dict(zip((ord() for _ in '12345'), 'PKTLN'))

def init(self, max_length: int = 4, german: bool = False) -> None: ```Initialize PSHPSoundexFirst instance.

Parameters

max_length : int The length of the code returned (defaults to 4) german : bool Set to True if the name is German (different rules apply)

.. versionadded:: 0.4.0

self._max_length = max_length
 self._german = german

Indicates that a set of similar lines has been detected among multiple file. This usually means that the code should be refactored to avoid this duplication. ==abydos.distance.blocklevenshtein:40 ==abydos.distance.dameraulevenshtein:43 def init( self, cost: Tuple[float, float, float, float] = (1, 1, 1, 1), normalizer: Callable[[List[float]], float] = max, **kwargs: Any ): ```Initialize BlockLevenshtein instance.

Parameters

**kwargs Arbitrary keyword arguments

.. versionadded:: 0.4.0

Indicates that a set of similar lines has been detected among multiple file. This usually means that the code should be refactored to avoid this duplication. ==abydos.tokenizer.legalipy:136 ==abydos.tokenizer.sonoripy:101 if not self.orderedtokens: self.orderedtokens = [self._string]

self.scaleand_counterize() return self

if name == 'main': import doctest

doctest.testmod()

Indicates that a set of similar lines has been detected among multiple file. This usually means that the code should be refactored to avoid this duplication. ==abydos.distance.ncdbwtrle:80 ==abydos.distance.ncdbz2:103 ==abydos.distance.ncdlzma:102 ==abydos.distance.ncdlzss:90 ==abydos.distance.ncdrle:80 return ( min(len(concatcomp), len(concatcomp2)) - min(len(srccomp), len(tarcomp)) ) / max(len(srccomp), len(tarcomp))

if name == 'main': import doctest

doctest.testmod()

Indicates that a set of similar lines has been detected among multiple file. This usually means that the code should be refactored to avoid this duplication. ==abydos.distance.chebyshev:21 ==abydos.distance.unknown_f:22 from typing import ( Any, Counter as TCounter, NoReturn, Optional, Sequence, Set, Union, )

TODO self, scaler: Optional[Union[str, Callable[[float], float]]] = None, ^ |

TODO and 'nltk.tokenize' in nltktokenizer.module_ ^ |

TODO consonants: Optional[Set[str]] = None, ^ |

TODO self, scaler: Optional[Union[str, Callable[[float], float]]] = None, ^ |

TODO weights: Optional[ ^ |

TODO and token[0] not in self._vowels ^ |

TODO nltk_tokenizer: Optional[object] = None, ^ |