国内疫情分析

利用Python获取国内疫情数据并进行数据可视化

数据收集

• 利用request获取国内疫情相关数据
• 利用josn模块获取解析HTML数据，并保存为json格式文件

import requests
import json
# 获取疫情数据链接
china_url = 'https://view.inews.qq.com/g2/getOnsInfo?name=disease_h5'
headers = {
    'referer':
    'https://news.qq.com/zt2020/page/feiyan.htm'
    'user-agent: Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/78.0.3904.108 Safari/537.36'
}
# 获取疫情json数据
response = requests.get(url=china_url, headers=headers).json()
# print(response)
print(type(response))
# 把json格式数据转化为Python的数据格式
data = json.loads(response['data'])

with open('./国内疫情数据.json', 'w', encoding='utf-8') as f:
    #把Python数据格式data转化为json数据格式，然后在写入文件进行保存
    f.write(json.dumps(data, ensure_ascii=False, indent=2))  #indent 格式化字符串后输出

<class 'dict'>

获取我们需要的数据

• 分别获取国家、省、市名称及其相应的数据
• 利用pandas转化为dateframe数据格式
• 拆解today和total两个字段
• 保存为Excel格式文件

import pandas as pd
from openpyxl import load_workbook

with open('./国内疫情数据.json', 'r', encoding='utf-8') as f:
    data = f.read()
type(data)
data = json.loads(data)
type(data)
# print(data)
# 获取China数据
ChinaArea = data["areaTree"][0]
# print(ChinaArea)
# 获取各省名字province
provincearea = ChinaArea['children']
# print(provincearea)
city_list = []  # Y用于存放城市的数据
for x in range(len(provincearea)):
    province = provincearea[x]['name']
    # 获取各省下的城市
    cityarea = provincearea[x]['children']
    for y in range(len(cityarea)):
        city = cityarea[y]['name']
        today = cityarea[y]['today']
        total = cityarea[y]['total']
        # print(city,today,total)
        city_dict = {'province': province, 'city': city,
                     'today': today, 'total': total}
        city_list.append(city_dict)
# print(city_list)
# 转为dateframe格式
df = pd.DataFrame(city_list)
# print(df)
# 拆解today和total列
confirmlist = []  # 确诊人数
suspectlist = []  # 嫌疑人数
deadlist = []  # 死亡人数
deadratelist = []  # 死亡率
heallist = []  # 治愈人数
healratelist = []  # 治愈率
for value in df['total'].values.tolist():
    confirmlist.append(value['confirm'])
    suspectlist.append(value['suspect'])
    deadlist.append(value['dead'])
    deadratelist.append(value['deadRate'])
    heallist.append(value['heal'])
    healratelist.append(value['healRate'])
df['confirm'] = confirmlist
df['suspect'] = suspectlist
df['dead'] = deadlist
df['deadrate'] = deadratelist
df['heal'] = heallist
df['healrate'] = healratelist


# 拆解today列字段
today_confirmlist = []  # 今日确诊
today_confirmcutslist = []  # 今日隔离
for value in df['today'].values.tolist():
    today_confirmlist.append(value['confirm'])
    today_confirmcutslist.append(value['confirmCuts'])
df['today_confirm'] = today_confirmlist
df['today_confirmCuts'] = today_confirmcutslist


# 删除total字段列
df.drop(['total', 'today'], axis=1, inplace=True)
df

# 将df保存到Excel文件中
# 将df保存到Excel文件中
book = load_workbook('国内疫情.xlsx')
writer = pd.ExcelWriter('国内疫情.xlsx', engine='openpyxl')
writer.book = book
'''writer.sheets语句主要是确保每次运行时把数据写到已有的相应sheets表格中，如果原有表格没有就创建新的
表格，如果取消此语句就会导致每次运行都会生成一个新的sheet表格来存放数据 '''
writer.sheets = dict((ws.title, ws) for ws in book.worksheets)
# 增加sheet_name方便于把一段时间内收集获取的数据放到同一个Excel文件中的不同表格
lastUpdateTime = data['lastUpdateTime']  # 获取数据更新日期
sheet_name = lastUpdateTime[:lastUpdateTime.find(' ')]  # 只获取日期，不需要后面的时间
# 保存到Excel文件
df.to_excel(writer, index=False,
            sheet_name=sheet_name)
writer.save()  # 文件保存
writer.close()  # 关闭

数据分析和可视化

import matplotlib.pyplot as plt
import numpy as np
%matplotlib inline
plt.rcParams['font.family'] = 'SimHei'
# 各省份累计确诊人数和治愈人数
plt.figure(figsize=(12, 15), dpi=80)
province_confirm = df.groupby(by='province')['confirm'].sum().sort_values()
province_heal = df.groupby(by='province')['heal'].sum().sort_values()
index=np.arange(len(province_heal))
bar_width=0.4
plt.barh(index,province_confirm.values.tolist(), height=bar_width, color='b',label='累计确诊人数')
plt.barh(index+bar_width+0.1,province_heal.values.tolist(), height=bar_width, color='r',label='累计治愈人数')
plt.yticks(index+(bar_width+0.1)/2,province_heal.index) 
plt.title('国内疫情累计确诊和治愈人数')
plt.xlabel('人数') 
plt.ylabel('省份') 
plt.ylim(0,34)
plt.legend(loc='best') 
plt.show() 

使用pyecharts数据可视化-map

from pyecharts import options as opts
import pandas as pd
from pyecharts.charts import Map

data = pd.read_excel('./国内疫情.xlsx', sheet_name=sheet_name)
#根据国内省份进行分组汇总，绘制各省确诊人数地图
data_groupby = data.groupby(by=['province'], as_index=False).sum()
data_groupby
#获取各省确诊人数
data_groupby_list = list(
    zip(data_groupby['province'].values.tolist(),
        data_groupby['confirm'].values.tolist()))
data_groupby_list
def china_map():
    c=(
        Map()
        .add(series_name='确诊病例',data_pair=data_groupby_list,maptype='china')
        .set_global_opts(
            title_opts=opts.TitleOpts(title='疫情地图'),visualmap_opts=opts.VisualMapOpts(is_piecewise=True,
                    pieces=[{'max':9,'min':0,'label':'0-9','color':'#FFE4E1'},
                           {'max':99,'min':10,'label':'10-99','color':'#FF7F50'},
                           {'max':499,'min':100,'label':'100-499','color':'#F08080'},
                           {'max':999,'min':500,'label':'500-999','color':'#CD5C5C'},
                           {'max':9999,'min':1000,'label':'1000-9999','color':'#990000'},
                           {'max':99999,'min':10000,'label':'>10000','color':'#660000'},
                           ])      
        )  
    )
    return c 
d_map =china_map()
d_map.render('国内疫情确诊地图.html')
d_map.render_notebook() 

    <div id="99085df893a346e1973efbeca526ce2d" style="width:900px; height:500px;"></div>