Hi,大家好,这里是丹成学长的毕设系列文章!
对毕设有任何疑问都可以问学长哦!
这两年开始,各个学校对毕设的要求越来越高,难度也越来越大… 毕业设计耗费时间,耗费精力,甚至有些题目即使是专业的老师或者硕士生也需要很长时间,所以一旦发现问题,一定要提前准备,避免到后面措手不及,草草了事。
为了大家能够顺利以及最少的精力通过毕设,学长分享优质毕业设计项目,今天要分享的新项目是
基于python/大数据的疫情分析与可视化系统
学长这里给一个题目综合评分(每项满分5分)
选题指导, 项目分享:
https://blog.csdn.net/Mr_DC_IT/article/details/126460477
全球Covid-19大危机影响我们的生活,我们的出行、交流、教育、经济等都发生了巨大的变化,全球疫情大数据可视化分析与展示,可用于社会各界接入疫情数据,感知疫情相关情况的实时交互式态势,是重要的疫情分析、防控决策依据。
我国爆发的疫情,对我们的日常生活带来了极大的影响,疫情严重期间,大家都谈“疫”色变,大家对于了解疫情的情况具有巨大的需求;并且,目前来看我国仍然存在疫情二次爆发的可能,大家对于疫情的情况跟踪也急于了解。
基于这个情况,学长对疫情的数据进行了爬取和可视化的展示和疫情的追踪, 也就是学长设计的作品。
PS:篇幅有限,学长仅展示部分关键代码
疫情数据爬虫,就是给网站发起请求,并从响应中提取需要的数据
1、发起请求,获取响应
2、解析内容
3、保存数据
import pymysql
import time
import json
import traceback #追踪异常
import requests
def get_tencent_data():
"""
:return: 返回历史数据和当日详细数据
"""
url = ''
url_his=''
#最基本的反爬虫
headers = {
'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/79.0.3945.88 Safari/537.36',
}
r = requests.get(url, headers) #使用requests请求
res = json.loads(r.text) # json字符串转字典
data_all = json.loads(res['data'])
#再加上history的配套东西
r_his=requests.get(url_his,headers)
res_his=json.loads(r_his.text)
data_his=json.loads(res_his['data'])
history = {} # 历史数据
for i in data_his["chinaDayList"]:
ds = "2020." + i["date"]
tup = time.strptime(ds, "%Y.%m.%d")
ds = time.strftime("%Y-%m-%d", tup) # 改变时间格式,不然插入数据库会报错,数据库是datetime类型
confirm = i["confirm"]
suspect = i["suspect"]
heal = i["heal"]
dead = i["dead"]
history[ds] = {"confirm": confirm, "suspect": suspect, "heal": heal, "dead": dead}
for i in data_his["chinaDayAddList"]:
ds = "2020." + i["date"]
tup = time.strptime(ds, "%Y.%m.%d")
ds = time.strftime("%Y-%m-%d", tup)
confirm = i["confirm"]
suspect = i["suspect"]
heal = i["heal"]
dead = i["dead"]
history[ds].update({"confirm_add": confirm, "suspect_add": suspect, "heal_add": heal, "dead_add": dead})
details = [] # 当日详细数据
update_time = data_all["lastUpdateTime"]
data_country = data_all["areaTree"] # list 25个国家
data_province = data_country[0]["children"] # 中国各省
for pro_infos in data_province:
province = pro_infos["name"] # 省名
for city_infos in pro_infos["children"]:
city = city_infos["name"]
confirm = city_infos["total"]["confirm"]
confirm_add = city_infos["today"]["confirm"]
heal = city_infos["total"]["heal"]
dead = city_infos["total"]["dead"]
details.append([update_time, province, city, confirm, confirm_add, heal, dead])
return history, details
数据表结构
history表存储每日的总数据
CREATE TABLE history (
ds datetime NOT NULL COMMENT ‘日期’,
confirm int(11) DEFAULT NULL COMMENT ‘累计确诊’,
confirm_add int(11) DEFAULT NULL COMMENT ‘当日新增确诊’,
suspect int(11) DEFAULT NULL COMMENT ‘剩余疑似’,
suspect_add int(11) DEFAULT NULL COMMENT ‘当日新增疑似’,
heal int(11) DEFAULT NULL COMMENT ‘累计治愈’,
heal_add int(11) DEFAULT NULL COMMENT ‘当日新增治愈’,
dead int(11) DEFAULT NULL COMMENT ‘累计死亡’,
dead_add int(11) DEFAULT NULL COMMENT ‘当日新增死亡’,
PRIMARY KEY (ds) USING BTREE ) ENGINE=InnoDB DEFAULT CHARSET=utf8mb4;
details表存储每日的详细数据
CREATE TABLE details (
id int(11) NOT NULL AUTO_INCREMENT,
update_time datetime DEFAULT NULL COMMENT ‘数据最后更新时间’,
province varchar(50) DEFAULT NULL COMMENT ‘省’,
city varchar(50) DEFAULT NULL COMMENT ‘市’,
confirm int(11) DEFAULT NULL COMMENT ‘累计确诊’,
confirm_add int(11) DEFAULT NULL COMMENT ‘新增确诊’,
heal int(11) DEFAULT NULL COMMENT ‘累计治愈’,
dead int(11) DEFAULT NULL COMMENT ‘累计死亡’,
PRIMARY KEY (id) ) ENGINE=InnoDB DEFAULT CHARSET=utf8mb4;
整体的数据库图表:
echarts绘制图表
def get_c1_data():
"""
:return: 返回大屏div id=c1 的数据
"""
# 因为会更新多次数据,取时间戳最新的那组数据
sql = "select sum(confirm)," \
"(select suspect from history order by ds desc limit 1)," \
"sum(heal)," \
"sum(dead) " \
"from details " \
"where update_time=(select update_time from details order by update_time desc limit 1) "
res = query(sql)
res_list = [str(i) for i in res[0]]
res_tuple=tuple(res_list)
return res_tuple
中国疫情地图实现
def get_c2_data():
"""
:return: 返回各省数据
"""
# 因为会更新多次数据,取时间戳最新的那组数据
sql = "select province,sum(confirm) from details " \
"where update_time=(select update_time from details " \
"order by update_time desc limit 1) " \
"group by province"
res = query(sql)
return res
全国累计趋势
def get_l1_data():
"""
:return:返回每天历史累计数据
"""
sql = "select ds,confirm,suspect,heal,dead from history"
res = query(sql)
return res
def get_l2_data():
"""
:return:返回每天新增确诊和疑似数据
"""
sql = "select ds,confirm_add,suspect_add from history"
res = query(sql)
return res
def get_r1_data():
"""
:return: 返回非湖北地区城市确诊人数前5名
"""
sql = 'SELECT city,confirm FROM ' \
'(select city,confirm from details ' \
'where update_time=(select update_time from details order by update_time desc limit 1) ' \
'and province not in ("湖北","北京","上海","天津","重庆") ' \
'union all ' \
'select province as city,sum(confirm) as confirm from details ' \
'where update_time=(select update_time from details order by update_time desc limit 1) ' \
'and province in ("北京","上海","天津","重庆") group by province) as a ' \
'ORDER BY confirm DESC LIMIT 5'
res = query(sql)
return res
疫情热搜
def get_r2_data():
"""
:return: 返回最近的20条热搜
"""
sql = 'select content from hotsearch order by id desc limit 20'
res = query(sql) # 格式 (('民警抗疫一线奋战16天牺牲1037364',), ('四川再派两批医疗队1537382',)
return res
选题指导, 项目分享:
https://blog.csdn.net/Mr_DC_IT/article/details/126460477