Python字符串模糊匹配工具TheFuzz的用法详解

from fuzzywuzzy import fuzz

string1 = "Python is great"
string2 = "Python is awesome"
similarity_ratio = fuzz.ratio(string1, string2)
print(f"相似度：{similarity_ratio}%")

choices = ["Python is amazing", "Python is incredible", "Java is cool", "C++ is fast"]
target = "Python is astonishing"
best_match, score = fuzz.process.extractOne(target, choices)
print(f"最相似的字符串：{best_match}, 相似度：{score}")

from fuzzywuzzy import fuzz

# 示例数据：包含非精确匹配的姓名
customer_names = ["John Doe", "Jon D.", "Jane Smith", "j. smith", "J. Doe", "Alice Johnson"]

# 对顾客姓名进行清洗与规范化
unique_names = set()  # 存储规范化后的唯一姓名

for name in customer_names:
    # 使用 TheFuzz 库找到最相似的姓名并规范化
    most_similar_name = max(unique_names, key=lambda x: fuzz.ratio(x, name), default=None)

    # 若找到最相似的姓名并且相似度高于阈值，则认定为同一个姓名
    if most_similar_name and fuzz.ratio(most_similar_name, name) > 80:
        unique_names.remove(most_similar_name)
        unique_names.add(name)
    else:
        unique_names.add(name)

print(unique_names)

from fuzzywuzzy import process

# 假设这是搜索引擎的内容列表
content_list = [
    "Python Tutorials for Beginners",
    "Intermediate Python Topics",
    "Advanced Python Programming"
]

# 用户输入的搜索项
user_query = "Python Tutorils"

# 使用 TheFuzz 库找到与用户查询最相似的内容
best_match = process.extractOne(user_query, content_list)
print(best_match)

from fuzzywuzzy import process

# 假设用户喜欢的内容
user_likes = "The Lord of the Rings"

# 假设这是推荐系统的内容列表
content_list = [
    "The Lord of the Flies",
    "The Hobbit",
    "Game of Thrones",
    "Harry Potter"
]

# 使用 TheFuzz 库找到与用户喜欢内容相似的其他内容
similar_content = process.extract(user_likes, content_list)
print(similar_content)

from fuzzywuzzy import fuzz

# 示例短语
phrase1 = "Natural Language Processing is interesting"
phrase2 = "Naturall Langauge Process is interestng"

# 比较两个短语的相似度
similarity_ratio = fuzz.ratio(phrase1, phrase2)
print(f"短语相似度：{similarity_ratio}%")

from fuzzywuzzy import fuzz

# 示例句子
sentence1 = "The cat is on the mat."
sentence2 = "A cat sits on the mat."

# 比较两个句子的相似度
similarity_ratio = fuzz.ratio(sentence1, sentence2)
print(f"句子相似度：{similarity_ratio}%")

from fuzzywuzzy import fuzz

string1 = "apple pie with ice cream"
string2 = "I like apple pie"
partial_similarity = fuzz.partial_ratio(string1, string2)
print(f"部分字符串相似度：{partial_similarity}%")

from fuzzywuzzy import process

choices = ["apple", "ape", "apples", "mango", "banana"]
target = "app"

sorted_matches = process.extract(target, choices)
print(sorted_matches)