【python】数据分析绘制疫情图(爬取数据+保存Excel+echart绘制地图)

数据分析师工作中常规流程一般是：数据获取、数据处理、数据分析展示等。
本篇通过国内疫情数据实现数据从爬取到展示的过程。

介绍

py版本：python 3.8
目标绘制全国疫情图。

思路

通过以下三个方法实现：

1. 爬取国内疫情数据。data_download()，引用包requests、json。1）访问网站获取数据；2）保存数据成json文件

2. 将数据转存到excel。cpdata_toexcel()，引用包openpyxl、json。
   1）从json文件中抽取所需数据，字段需求：省份、地市、总确诊人数、总疑似病例、总死亡人数。
   
   2）创建Excel表，数据保存。

3. 读取文件数据画疫情地图。show_data()，引用包pandas、pyecharts。

脚本

引用包

import requests
import json
import pandas as pd
import openpyxl
from pyecharts.charts import Bar
from pyecharts.charts import Map
from pyecharts import options as opts

方法一：爬取国内疫情数据

def data_download():
    "爬取国内疫情数据"
    china_url = 'https://view.inews.qq.com/g2/getOnsInfo?name=disease_h5'
    headers={
        'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/84.0.4147.125 Safari/537.36',
        'referer': 'https://news.qq.com/zt2020/page/feiyan.htm'
    }
    # 获取json数据
    response = requests.get(url=china_url,headers=headers).json()

    # 先把数据转成python中的字典
    data = json.loads(response['data'])

    # 保存数据
    with open('./国内疫情.json','w') as f:
        # 再把字典改成json字符串
        f.write(json.dumps(data,ensure_ascii=False,indent=2))

方法二：将数据转存到excel

def cpdata_toexcel():
    "将数据转存到excel"
    # 读取文件
    with open('./国内疫情.json','r',encoding='GBK') as f:
        data = f.read()
    data = json.loads(data)
    # 获取国内数据
    chinaAreaDict = data['areaTree'][0]
    # 获取省份数据
    provinceList = chinaAreaDict['children']
    # excel表头 省 市 ...
    china_citylist = [] #[{湖北,武汉},{湖北,襄阳}]
    for x in range(len(provinceList)):
        province = provinceList[x]['name']
        province_list = provinceList[x]['children']

        for y in range(len(province_list)):
            city = province_list[y]['name']
            today = province_list[y]['today']
            total = province_list[y]['total']

            city_dict = {'province':province,
                         'city':city,
                         'today':today,
                         'total':total
                         }
            china_citylist.append(city_dict)

    chinaTotalData = pd.DataFrame(china_citylist)

    # 将chinaTotalData的today和total数据添加dataFrame中
    confirmlist = []
    suspectlist = []
    deadlist = []

    for value in chinaTotalData['total'].values.tolist():
        confirmlist.append(value['confirm'])
        suspectlist.append(value['suspect'])
        deadlist.append(value['dead'])

    chinaTotalData['confirm'] = confirmlist
    chinaTotalData['suspect'] = suspectlist
    chinaTotalData['dead'] = deadlist

    # 删除total列
    chinaTotalData.drop(['total','today'],axis=1,inplace=True)
    print(chinaTotalData)

    # 创建excel
    wb = openpyxl.Workbook()
    wb.save('国内疫情.xlsx')

    #将其保存excel中
    book = openpyxl.load_workbook('国内疫情.xlsx')
    writer = pd.ExcelWriter('国内疫情.xlsx',engine='openpyxl')
    writer.book = book
    writer.sheet = dict((ws.title,ws) for ws in book.worksheets)
    chinaTotalData.to_excel(writer,index=False,sheet_name = '国内疫情')
    writer.save()
    writer.close()

方法三：读取文件数据画疫情地图

def show_data():
    "读取文件数据画疫情地图"
    df = pd.read_excel('./国内疫情.xlsx',sheet_name = 'Sheet1')
    # 1. 根据绘制国内总疫情图（确诊）
    data = df.groupby(by='province',as_index=False).sum()

    data_list = list(zip(data['province'].values.tolist(),data['confirm'].values.tolist()))
    # ------------------------中国地图
    c =(
        Map()
        .add(series_name="确诊病例",data_pair=data_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": 99999, "min": 1000, "label": ">=1000", "color": "#990000"}]
                                    )
            )
        .render("d_map.html")
    )

效果图：

相关文章：【python】自动化办公之excel常用操作实战详解(xlwings)