Python Pandas两个表格内容模糊匹配的实现

import pandas as pd
import numpy as np
import re

#关键词数据
df_keyWord = pd.DataFrame({
    "keyid" : np.arange(5),
    "keyword" : ["numpy", "pandas", "matplotlib", "sklearn", "Tensorflow"]
})
df_keyword

df_sentence = pd.DataFrame({
    "senid" : np.arange(10,17),
    "sentence" : [
        "怎样用pandas实现merge？",
        "python之Numpy详细教程",
        "怎么使用Pandas批量拆分与合并excel文件？",
        "怎样使用pandas的map和apply函数？",
        "深度学习之tensorflow简介",
        "tensorflow和numpy的关系",
        "基于sklearn的一些机器学习的代码"
    ]
})
df_sentence

df_keyword['match'] = 1
df_sentence['match'] = 1

df_merge = pd.merge(df_keyword, df_sentence)
df_merge

def match_func(row):
    return re.search(row["keyword"], row["sentence"], re.IGNORECASE) is not None
df_merge[df_merge.apply(match_func, axis = 1)]

key_word_dict = {
    row.keyword : row.keyid
    for row in df_keyword.itertuples()
}
key_word_dict

def merge_func(row):
    #新增一列，表示可以匹配的keyid
    row["keyids"] = [
        keyid
        for key_word, keyid in key_word_dict.items()
        if re.search(key_word, row["sentence"], re.IGNORECASE)
    ]
    return row
df_merge = df_sentence.apply(merge_func, axis = 1)

df_merge

df_result = pd.merge(
left = df_merge.explode("keyids"),
right = df_keyword,
left_on = "keyids",
right_on = "keyid")
df_result