python根据项目标签匹配人员-优快云博客

本文链接：https://blog.youkuaiyun.com/qq_45396577/article/details/125621075

import random
import pandas as pd
import numpy as np

df1 = pd.read_excel(r'C:\Users\Administrator\Desktop\项目标签_人员.xlsx')
df1['人员id'] = df1['人员id'].astype('str')
gp = df1.groupby("项目标签")["人员id"].apply(lambda x:x.str.cat(sep=",")).reset_index()
gp.head()

	项目标签	人员id
0	C10祛斑	518,517,514,509,498,567,573,5502,5593,5594,559...
1	E光嫩肤	518,517,514,509,498,567,573,5502,5593,5594,559...
2	E光祛斑	518,517,514,509,498,567,573,5502,5593,5594,559...
3	Fotona4DPro	518,517,514,509,498,567,573,5502,5593,5594,559...
4	G点注射	5599,5596,5502

df2 = pd.read_excel(r'C:\Users\Administrator\Desktop\合并.xlsx')
df2.head()

在这里插入图片描述

flag = []
for bq in df2["项目标签"]:
    tags =set()
    for i,value in gp.iterrows(): 
        word = value["项目标签"]
        if bq == word:
            doc_id = random.choice(value["人员id"].split(",") ) 
            tags.add(doc_id)
    tag ="".join(tags)
    
    if tag:
        flag.append(tag)
    else:                    
        flag.append(None)
df2["人员id匹配"] = flag
df2.to_excel(r'C:\Users\Administrator\Desktop\out_put.xlsx',index=False)

在这里插入图片描述

flag = []
for row in df2["项目标签"].values:
    if row in df1['项目标签'].tolist() :    
        flag.append(row)
    else:
        flag.append(None)
df2["flag"] = flag
df2.head()

在这里插入图片描述