Commit e5c5dc82 authored by 张彦钊's avatar 张彦钊

add

parent 80373604
......@@ -8,8 +8,8 @@ url="http://doris.paas-test.env/v1/once"
header_dict={'Content-Type': 'application/x-www-form-urlencoded'}
param_dict={}
param_dict["method"]="doris/recommend/ai_faces"
param_detail = {"device_id":"xx"}
param_dict["method"]="doris/recommend/ai_similar_service"
param_detail = {"device_id":"xx","user_city_tag_id":350,"new_tag_ids":[[1068,2288],[912,385],[283,2599]]}
# param_dict["method"]="doris/search/doctor_officer"
# param_detail = {"device_id": '1',"size": 10,"offset":0, "query": "双眼皮","user_city_tag_id": 328,
......
# -*- coding: utf-8 -*-
import redis
import re
import json
import pymysql
import pandas as pd
# 抽取医院名字简称
def name_short():
db = pymysql.connect(host='172.16.30.143', port=3306, user='work', passwd='BJQaT9VzDcuPBqkd', db='zhengxing')
cursor = db.cursor()
sql_active = "select name from api_hospital;"
cursor.execute(sql_active)
result = cursor.fetchall()
name_list = pd.DataFrame(list(result))[0].values.tolist()
print(name_list[:10])
# number = list()
# for i in cover:
# sql = "select count(cid) from data_feed_exposure " \
# "where cid_type = 'diary'" \
# "and stat_date = '{}' and device_id = '{}';".format(date,i)
# cursor.execute(sql)
# result = cursor.fetchone()[0]
# cid.append(i)
# number.append(result)
# df = pd.DataFrame()
# df['id'] = cid
# df['number'] = number
# df = df.sort_values(by = "number",ascending=False)
# df.to_csv(DIRECTORY_PATH+"exp.csv",index=None)
def name_process(name):
project_tags = ["口腔","植发","牙","皮肤","眼","外科","美容","整形","烧伤","胸","丰胸","美胸","祛痘","祛斑","脱毛",
"创伤","除疤","半永久","纹绣","纹眉"]
names = ["医疗","门诊","研究所","有限","公司","医学","诊所","中心","医美","集团","卫生","机构","专业",
"光学","国际","连锁","综合","专科",""]
location = ["街道","社区",]
stop_words = project_tags + names + location
for word in stop_words:
name = re.sub(word, '', name)
# 去除 中文括号( )
name = re.sub(r'\(.*?\)', '', name)
# 去除 英文括号( )
name = re.sub(r'\(.*?\)', '', name)
# 去除 左英文括号,右中文括号
name = re.sub(r'\(.*?\)', '', name)
# 去除数字
name = re.sub(r'\d', '', name)
# 去除\t
name = re.sub(r'\t', "", name)
return name
if __name__ == '__main__':
name_short()
Markdown is supported
0% or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment