return features
def _extract_features(doc):
return [_doc2features(doc, i) for i in range(len(doc))]
crf = sklearn_crfsuite.CRF(
algorithm='pa',
#c1=0.1,
#c2=0.1,
max_iterations=450, #500,
all_possible_transitions=True,
model_filename=templates_file)
check = NorvigSpellChecker()
checking = ""
def spell(text, autocorrect=False, worddict=None):
global check, checking
word_cut = word_tokenize(text)
if worddict == "thai2fit" and checking == "":
from pythainlp.word_vector import get_model
words = get_model().index2word
w_rank = {}
for i, word in enumerate(words):
w_rank[word] = i
word = w_rank.items()
check = NorvigSpellChecker(custom_dict=word)
checking = "thai2fit"
def spell(text, autocorrect=False, worddict=None):
global check, checking
word_cut = word_tokenize(text)
if worddict == "thai2fit" and checking == "":
from pythainlp.word_vector import get_model
words = get_model().index2word
w_rank = {}
for i, word in enumerate(words):
w_rank[word] = i
word = w_rank.items()
check = NorvigSpellChecker(custom_dict=word)
checking = "thai2fit"
elif checking == "thai2fit" and worddict != None:
pass
else:
checking = ""
check = NorvigSpellChecker()
#print(word_cut)
X_test = _extract_features([(i, ) for i in word_cut])
#print(X_test)
y_ = crf.predict_single(X_test)
x = [(word_cut[i], data) for i, data in enumerate(y_)]
output = ""
temp = ''
#print(x)
for i, b in enumerate(x):
if i == len(x) - 1 and 'B' in b[1] and temp == 'B':
output += "</คำผิด><คำผิด>" + b[0] + "</คำผิด>"
temp = 'B'
elif i == len(x) - 1 and 'B' in b[1]:
output += "<คำผิด>" + b[0] + "</คำผิด>"
temp = 'B'
elif 'B-' in b[1] and temp == 'B':
output += "</คำผิด><คำผิด>" + b[0]
temp = 'B'
elif 'B-' in b[1]:
output += "<คำผิด>" + b[0]
temp = 'B'
elif 'O' in b[1] and temp == 'B':
output += "</คำผิด>" + b[0]
temp = 'O'
elif i == len(x) - 1 and 'I' in b[1] and temp == 'B':
output += b[0] + "</คำผิด>"
temp = 'O'
else:
output += b[0]
if autocorrect:
f = "(<คำผิด>)(.*)(</คำผิด>)"
output = output.replace("<คำผิด>", "|---|<คำผิด>|---|").replace(
"</คำผิด>", "|---|</คำผิด>|---|")
listall = output.split("|---|")
i = 0
output = ""
ii = len(listall)
while i < ii:
if listall[i] == "<คำผิด>":
output += check.correct(listall[i + 1])
i += 3
else:
output += listall[i]
i += 1
return output
# -*- coding: utf-8 -*-
"""
Spell checking and spelling correction.
"""
__all__ = [
"DEFAULT_SPELL_CHECKER",
"correct",
"spell",
"NorvigSpellChecker",
"spell_sent",
"correct_sent"
]
from pythainlp.spell.pn import NorvigSpellChecker
DEFAULT_SPELL_CHECKER = NorvigSpellChecker()
from pythainlp.spell.core import correct, spell, correct_sent, spell_sent