SpellCorrection
# 词典库
vocab = set([line.rstrip() for line in open('vocab.txt')])
# 需要生成所有候选集合
def generate_candidates(word):
"""
word: 给定的输入(错误的输入)
返回所有(valid)候选集合
"""
# 生成编辑距离为1的单词
# 1.insert 2. delete 3. replace
# appl: replace: bppl, cppl, aapl, abpl...
# insert: bappl, cappl, abppl, acppl....
# delete: ppl, apl, app
# 假设使用26个字符
letters = 'abcdefghijklmnopqrstuvwxyz'
splits = [(word[:i], word[i:]) for i in range(len(word)+1)]
# insert操作
inserts = [L+c+R for L, R in splits for c in letters]
# delete
deletes = [L+R[1:] for L,R in splits if R]
# replace
replaces = [L+c+R[1:] for L,R in splits if R for c in letters]
candidates = set(inserts+deletes+replaces)
# 过来掉不存在于词典库里面的单词
return [word for word in candidates if word in vocab]
generate_candidates("apple")
['ample', 'apples', 'apply', 'apple']
from nltk.corpus import reuters
# 读取语料库
categories = reuters.categories()
corpus = reuters.sents(categories=categories)
# 构建语言模型: bigram
term_count = {}
bigram_count = {}
for doc in corpus:
doc = ['<s>'] + doc
for i in range(0, len(doc)-1):
# bigram: [i,i+1]
term = doc[i]
bigram = doc[i:i+2]
if term in term_count:
term_count[term]+=1
else:
term_count[term]=1
bigram = ' '.join(bigram)
if bigram in bigram_count:
bigram_count[bigram]+=1
else:
bigram_count[bigram]=1
# sklearn里面有现成的包
# 用户打错的概率统计 - channel probability
channel_prob = {}
for line in open('spell-errors.txt'):
items = line.split(":")
correct = items[0].strip()
# EDIT START
# 数据中的*可能为词频
mistakes = [item.strip().split("*") for item in items[1].strip().split(",")]
mistakes = [[mis[0], 1] if len(mis) == 1 else [mis[0], int(mis[1])] for mis in mistakes]
mis_count = sum([mis[1] for mis in mistakes])
channel_prob[correct] = {}
for mis in mistakes:
channel_prob[correct][mis[0]] = mis[1] / mis_count
# EDIT END
print(channel_prob)
{'raining': {'rainning': 0.5, 'raning': 0.5}, 'writings': {'writtings': 1.0}, 'disparagingly': {'disparingly': 1.0}, 'yellow': {'yello': 1.0}, 'four': {'forer': 0.08333333333333333, 'fours': 0.08333333333333333, 'fuore': 0.08333333333333333, 'fore': 0.4166666666666667, 'for': 0.3333333333333333}, 'woods': {'woodes': 1.0}, 'hanging': {'haing': 1.0}, 'aggression': {'agression': 1.0}, 'looking': {'loking': 0.09090909090909091, 'begining': 0.09090909090909091, 'luing': 0.09090909090909091, 'look': 0.18181818181818182, 'locking': 0.09090909090909091, 'lucking': 0.09090909090909091, 'louk': 0.09090909090909091, 'looing': 0.09090909090909091, 'lookin': 0.09090909090909091, 'liking': 0.09090909090909091},
...
import numpy as np
V = len(term_count.keys())
file = open("testdata.txt", 'r')
for line in file:
items = line.rstrip().split('\t')
line = items[2].split()
# line = ["I", "like", "playing"]
for word in line:
if word not in vocab:
# 需要替换word成正确的单词
# Step1: 生成所有的(valid)候选集合
candidates = generate_candidates(word)
# 一种方式: if candidate = [], 多生成几个candidates, 比如生成编辑距离不大于2的
# TODO : 根据条件生成更多的候选集合
# EDIT START
# 获得编辑距离不大于2的candidates
for i in range(len(candidates)):
candidates += generate_candidates(candidates[i])
candidates = list(set(candidates))
# EDIT END
if len(candidates) < 1:
continue # 不建议这么做(这是不对的)
probs = []
# 对于每一个candidate, 计算它的score
# score = p(correct)*p(mistake|correct)
# = log p(correct) + log p(mistake|correct)
# 返回score最大的candidate
for candi in candidates:
prob = 0
# a. 计算channel probability
if candi in channel_prob and word in channel_prob[candi]:
prob += np.log(channel_prob[candi][word])
else:
prob += np.log(0.0001)
# b. 计算语言模型的概率
# EDIT START
idx = line.index(word)
bigram = ['<s>', candi] if idx == 0 else [line[idx - 1], candi]
if " ".join(bigram) in bigram_count:
prob += np.log((bigram_count[" ".join(bigram)] + 1.0) / (
term_count[bigram[0]] + V))
# EDIT END
# TODO: 也要考虑当前 [word, post_word]
# prob += np.log(bigram概率)
else:
prob += np.log(1.0 / V)
probs.append(prob)
# # EDIT START
# # 原代码存在错误:probs几乎只有一个数,求最大值实际无意义
# # 可解除该部分代码注释观察probs
# print(set(probs))
# # EDIT END
max_idx = probs.index(max(probs))
print (word, candidates[max_idx])
protectionst protectionist
products. products
long-run, longrun
gain. gain
17, 1
retaiation retaliation
...
P.S.
若读取nltk.corpus语料库时出现问题,尝试下载全部nltk_data
若遍历corpus过程中出现问题,尝试按照错误提示路径手动解压punkt并创建相应文件夹结构
# EDIT START
# EDIT START -> END: Edit by ziuno, for reference only.
# EDIT END