kzinmr

import regex
from typing import List, Tuple


def fuzzy_match_spans(annotation: str, text: str, max_num_errors: int = 5) -> List[Tuple[int, int]]:
    r = regex.compile('(%s)' % re.escape(annotation))
    matches = [m.span() for m in r.finditer(text)]
    num_errors = 1
    while not matches and num_errors <= max_num_errors:
        r = regex.compile('(%s){e<=%d}' % (re.escape(annotation), num_errors))

kzinmr

from itertools import groupby
from operator import itemgetter
data = [ 1, 4,5,6, 10, 15,16,17,18, 22, 25,26,27,28]
consecutive_ints = [map(itemgetter(1), g) for k, g in groupby(enumerate(data), lambda (i, x): i-x)]
# [[1],
# [4, 5, 6],
# [10],
# [15, 16, 17, 18],
# [22],
# [25, 26, 27, 28]]

kzinmr

from typing import List
from itertools import tee, combinations
from collections import Counter


# def count_cooccurrence_in_window(context_window, delimiter=' '):
#     return Counter([delimiter.join(bi) for bi in combinations(context_window, 2)])


def window_cooccurrence(sentence: List[str], window: int = 5) -> Counter:

kzinmr

from typing import List, Dict, Set, Optional
from nltk.lm import MLE
from nltk.util import ngrams


class InvalidOrderException(Exception):
    pass

class InvalidContextSizeException(Exception):
    pass

kzinmr

from collections import OrderedDict
from html.parser import HTMLParser
import json


class MyHTMLParser(HTMLParser):
    
    debug = False
    
    def __init__(self):

kzinmr

from collections import defaultdict, Counter
from operator import add
from functools import reduce
import numpy as np

from sklearn.cluster import KMeans


def dict_of_list(keys, values):
    assert(len(keys) == len(values))

kzinmr

from collections import defaultdict
from functools import reduce, partial
import numpy as np
from itertools import chain


def flatten(l):
    return list(chain.from_iterable(l))

kzinmr

a

kzinmr

"calculate PMI(A,B)=P(A,B)/P(A)P(B) for every token A and B in a window"
from itertools import tee, combinations
from collections import Counter


def count_bigram(sentence, window=5):
    # ['A','B','C','D', 'E', 'F', 'G'], 4  ->
    # [['A', 'B', 'C', 'D'],
    #  ['B', 'C', 'D', 'E'],
    #  ['C', 'D', 'E', 'F'],

kzinmr

try:
    from xml.etree.cElementTree import XML
except ImportError:
    from xml.etree.ElementTree import XML
import zipfile


"""
Module that extract text from MS XML Word document (.docx).
(Inspired by python-docx <https://github.com/mikemaccana/python-docx>)