add

local/hospital_name_short.py

+# -*- coding: utf-8 -*-
+
+import redis
+import re
+import json
+import pymysql
+import pandas as pd
+
+# 抽取医院名字简称
+
+
+def get_city_names():
+    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_city;"
+    cursor.execute(sql_active)
+    result = cursor.fetchall()
+    name_list = pd.DataFrame(list(result))[0].values.tolist()
+    print(name_list[:10])
+    db.close()
+    return name_list
+
+
+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 where is_online = 1;"
+    cursor.execute(sql_active)
+    result = cursor.fetchall()
+    name_list = pd.DataFrame(list(result))[0].values.tolist()
+    db.close()
+    print(name_list[:10])
+    names = ["门诊部","医疗", "门诊", "研究所", "有限", "公司", "医学", "诊所", "中心","美容","医院","整形","外科",
+             "医美", "集团", "卫生", "机构", "专业","皮肤","管理",
+             "光学", "国际", "连锁", "综合", "专科",]
+    location = ["街道", "社区",]
+    city_list = get_city_names()
+    stop_words = names + location
+    new_names = []
+    third_names = []
+    for name in name_list:
+        city_tag = "flag"
+        for city in city_list:
+            if city in name:
+                city_tag = city
+            name = re.sub(city, '', name)
+        for word in stop_words:
+            name = re.sub(word, '', name)
+        # 去除\t
+        name = re.sub(r'\t', "", 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)
+        if city_tag != "flag":
+            third_names.append(city_tag+name)
+        else:
+            third_names.append("无")
+        new_names.append(name)
+    df = pd.DataFrame()
+    df['old_name'] = name_list
+    df['new_name'] = new_names
+    df['core_name'] = third_names
+
+    print(df.head(6))
+    df.to_csv("/home/gmuser/"+"hospital_name_21.csv",index=None)
+
+
+
+    # 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()
+
+
+