! pip3 install nltk pywsd symspellpy

import nltk
nltk.download('treebank')
nltk.download('wordnet')
nltk.download('stopwords')
nltk.download('averaged_perceptron_tagger')
nltk.download('punkt')

# 촘스키 CGF 문법규칙
from nltk.grammar import toy_pcfg2
grammar = toy_pcfg2
print(grammar)

# WordNet 데이터를 활용한 의미관계 분석
from nltk.corpus import wordnet as wn
word = 'bank'

print("Synset list : \n{}\n\nbank.n.02 뜻과 예제 : \n{}\n{}\n\ntrust.v.01 뜻과 예제 :\n{}\n{}".format(
    wn.synsets(word),
    wn.synset('bank.n.02').definition(), wn.synset('bank.n.02').examples(),
    wn.synset('trust.v.01').definition(), wn.synset('trust.v.01').examples()))

# pywsd 를 사용한 문장 내 의미분석
sent = 'I went to the bank to deposit my money'
# sent    = 'I bank my money'
ambiguous = 'bank'

from pywsd.lesk import simple_lesk
answer = simple_lesk(sent, ambiguous)
answer.definition()

from symspellpy.symspellpy import SymSpell

def spellCheck(dict_file, sentence):
    max_edit_dist, prefix_length = 0, 7
    term_index, count_index      = 0, 1
    
    sym_spell = SymSpell(max_edit_dist, prefix_length)
    if not sym_spell.load_dictionary(dict_file, term_index, count_index):
        print("사전파일을 정의하지 않았습니다"); return
    
    result = sym_spell.word_segmentation(sentence)
    print("오타 수정결과: {}\n편집거리 총합: {}".format(
        result.corrected_string, 
        result.distance_sum))
    
text = "thequickbrownfoxjumpsoverthelazydog"
spellCheck("frequency_dictionary_en_82_765.txt", sentence=text)