【Python】python批量模糊匹配技术解决用户-配变匹配问题

from fuzzywuzzy import fuzzfrom fuzzywuzzy import process
print("简单匹配")print(fuzz.ratio("四川省","四川省"))print(fuzz.ratio("四川省","四川"))print(fuzz.ratio("四川省","西川"))
print("非完全匹配")print(fuzz.partial_ratio("四川省","四川省"))print(fuzz.partial_ratio("四川省","四川"))print(fuzz.partial_ratio("四川省","西川"))
choices = ["四川省", "成都市", "西川", "四川"]print(process.extract("四川", choices, limit=3))print(process.extractOne("四川", choices))

from fuzzywuzzy import processimport pandas as pd
# 通用模糊匹配函数def fuzzy_merge(df_1, df_2, key1, key2, threshold=90, limit=2):    """    :param df_1: the left table to join    :param df_2: the right table to join    :param key1: key column of the left table    :param key2: key column of the right table    :param threshold: how close the matches should be to return a match, based on Levenshtein distance    :param limit: the amount of matches that will get returned, these are sorted high to low    :return: dataframe with boths keys and matches    """    # 匹配参考表    s = df_2[key2].tolist()
    # 待匹配结果表    m = df_1[key1].apply(lambda x: process.extract(x, s, limit=limit))
    # 把算出来的结果放到了df_1的matches列    df_1['matches'] = m
    # 对extractOne方法的完善，提取到的最大匹配度的结果并不一定是我们需要的，所以需要设定一个阈值来评判，这个值可以是90    # 第一个‘matches'字段返回的数据类型，参考一下这个格式：[('四川省', 90), ('成都市', 0)]    m2 = df_1['matches'].apply(        lambda x: [i[0] for i in x if i[1] >= threshold][0] if len([i[0] for i in x if i[1] >= threshold]) > 0 else '')
    # 把最佳的符合条件的匹配信息处理到df_1的matches列    df_1['matches'] = m2
    return df_1
user_values = pd.read_excel('用户名.xlsx')PB_values = pd.read_excel('配变.xls')
df = fuzzy_merge(user_values, PB_values, 'user', 'PBname', threshold=80)
df.to_excel('结果.xlsx')

from fuzzywuzzy import processimport pandas as pd
data = pd.read_csv("配变.csv", encoding="gbk").astype(str)find = pd.read_csv("用户名.csv", encoding="gbk").astype(str)
users = data.name.to_list()result = find.name.apply(lambda x: next(    zip(*process.extract(x, users, limit=3)))).apply(pd.Series)result.rename(columns=lambda i: f"匹配{i + 1}", inplace=True)result = pd.concat([find, result], axis=1)
result.to_excel('结果.xlsx')

import pandas as pdimport jiebafrom gensim import corpora,similarities,models
data = pd.read_csv("配变.csv", encoding="gbk").astype(str)find = pd.read_csv("用户名.csv", encoding="gbk").astype(str)
# 对原始的文本进行jieba分词，得到用户名称的特征列表data_split_word = data.name.apply(jieba.lcut)
# 建立语料特征的索引字典，并将文本特征的原始表达转化成词袋模型对应的稀疏向量的表达# 这样得到了每一个用户名称对应的稀疏向量（这里是bow向量），向量的每一个元素代表了一个词在这个名称中出现的次数。dictionary = corpora.Dictionary(data_split_word.values)data_corpus = data_split_word.apply(dictionary.doc2bow)
# 将被查找的数据统一由小写数字转换为大写数字（保持与数据库一致）后，作相同的处理，即可进行相似度批量匹配trantab = str.maketrans("0123456789", "零一二三四五六七八九")find_corpus = find.name.apply(    lambda x: dictionary.doc2bow(jieba.lcut(x.translate(trantab))))
# 构建相似度矩阵tfidf = models.TfidfModel(data_corpus.to_list())index = similarities.SparseMatrixSimilarity(    tfidf[data_corpus], num_features=len(dictionary))
# 同时获取最大的3个结果result = []for corpus in find_corpus.values:    sim = pd.Series(index[corpus])    result.append(data.name[sim.nlargest(3).index].values)result = pd.DataFrame(result)result.rename(columns=lambda i: f"匹配{i + 1}", inplace=True)result = pd.concat([find, result], axis=1)
result.to_excel('结果.xlsx')