如何更正文本文档中的拼写错误(适用于单个单词)
How can I correct spelling mistakes in a text document (it works for single words)
我有这个代码。它只能用于单词。我需要类似的字符串或文本文档。
import re
from collections import Counter
def words(text): return re.findall(r'\w+', text.lower())
WORDS = Counter(words(open('big.txt').read()))
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)) or [word])
def known(words):
"The subset of `words` that appear in the dictionary of WORDS."
return set(w for w in words if w in WORDS)
def edits1(word):
"All edits that are one edit away from `word`."
letters = 'abcdefghijklmnopqrstuvwxyz'
splits = [(word[:i], word[i:]) for i in range(len(word) + 1)]
deletes = [L + R[1:] for L, R in splits if R]
transposes = [L + R[1] + R[0] + R[2:] for L, R in splits if len(R)>1]
replaces = [L + c + R[1:] for L, R in splits if R for c in letters]
inserts = [L + c + R for L, R in splits for c in letters]
return set(deletes + transposes + replaces + inserts)
def edits2(word):
"All edits that are two edits away from `word`."
return (e2 for e1 in edits1(word) for e2 in edits1(e1))
使用此代码遍历文本中的所有单词,大功告成!
text = "This is an exmple"
result = ""
for word in text.split():
result += correction(word) + " "
print(result)
您唯一需要做的就是用词典填充 'big.txt'
文本文件。
标记文本是一项 well-studied 任务。简单地按 space 个字符拆分单词并不总能按预期工作。您可以使用像 https://github.com/cbaziotis/ekphrasis and https://github.com/mammothb/symspellpy 这样的库。
我有这个代码。它只能用于单词。我需要类似的字符串或文本文档。
import re
from collections import Counter
def words(text): return re.findall(r'\w+', text.lower())
WORDS = Counter(words(open('big.txt').read()))
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)) or [word])
def known(words):
"The subset of `words` that appear in the dictionary of WORDS."
return set(w for w in words if w in WORDS)
def edits1(word):
"All edits that are one edit away from `word`."
letters = 'abcdefghijklmnopqrstuvwxyz'
splits = [(word[:i], word[i:]) for i in range(len(word) + 1)]
deletes = [L + R[1:] for L, R in splits if R]
transposes = [L + R[1] + R[0] + R[2:] for L, R in splits if len(R)>1]
replaces = [L + c + R[1:] for L, R in splits if R for c in letters]
inserts = [L + c + R for L, R in splits for c in letters]
return set(deletes + transposes + replaces + inserts)
def edits2(word):
"All edits that are two edits away from `word`."
return (e2 for e1 in edits1(word) for e2 in edits1(e1))
使用此代码遍历文本中的所有单词,大功告成!
text = "This is an exmple"
result = ""
for word in text.split():
result += correction(word) + " "
print(result)
您唯一需要做的就是用词典填充 'big.txt'
文本文件。
标记文本是一项 well-studied 任务。简单地按 space 个字符拆分单词并不总能按预期工作。您可以使用像 https://github.com/cbaziotis/ekphrasis and https://github.com/mammothb/symspellpy 这样的库。