def __init__(self):
self.WORDS = dump_dict.getWORDS(self.pWORDSPATH)
from collections import Counter
TEXTSPATH = "/home/dicle/Documents/data/tr/tr_gazete_siir/tr_text_compilation.txt"
#def words(text): return re.findall(r'\w+', text.lower())
def words(text): return re.findall(r'\w+', text)
#def words(text): return text.split()
WORDS = Counter(words(open(TEXTSPATH).read()))
'''
import re
import string
from time import time
from language_tools.spellchecker import dump_dict
WORDS = dump_dict.getWORDS()
def P(word, N=sum(WORDS.values())):
"Probability of `word`."
return WORDS[word] / N
def correction(word):
"Most probable spelling correction for word."
return max(candidates(word), key=P)
def candidates(word):
"Generate possible spelling corrections for word."
return (known([word]) or known(edits1(word)) or known(edits2(word))