使用python统计新冠病毒新增人数并绘图

本文档仅供参考和个人娱乐分享，请勿用作其他场合和其他用途

工作环境：windows/anaconda3 + python 3.5
python IDE：pycharm
数据来源：https://news.qq.com/zt2020/page/feiyan.htm#/
分析工具：Fidder
实际url: https://view.inews.qq.com/g2/getOnsInfo?name=disease_other&callback=jQuery3410801068472621489_1583674003060&_=1583674003061
程序结构：
主程序：

from num_process import downloader
from pic_process import pic_process

def main_fx():
    target = 'https://view.inews.qq.com/g2/getOnsInfo?name=disease_other&callback=jQuery3410801068472621489_1583674003060&_=1583674003061'
    downloader_fx = downloader(target)
    new_confirm_np, new_dead_np = downloader_fx.get_contents()
    pic_process_fx = pic_process(downloader_fx.date_num_list, new_confirm_np, new_dead_np)
    pic_process_fx.pic_plot()
    max_num, max_day, min_day, min_num, mean_num, median_num = downloader_fx.num_feature()
    print('最大值是%d,日期是%s'%(max_num, max_day) +'\n')
    print('最小值是%d,日期是%s'%(min_num, min_day)+'\n')
    print('中位数是%d,众数是%d'%(mean_num, median_num))

if __name__ == '__main__':
    main_fx()

数据获取处理：

import requests
import json
import numpy as np
import operator

class downloader():
    def __init__(self,target):
        self.target = target
        self.date_num_list = []
        self.confirm_list = []
        self.dead_list = []

    def get_download_url(self):
        req = requests.get(url = self.target)
        html = req.text
        return html

    def get_contents(self):
        html = self.get_download_url()
        data = json.loads(html.split('(')[-1][:-1])
        data_str_2_json = json.loads(data["data"])
        chinaDayList = data_str_2_json["chinaDayList"]
        for num in range(len(chinaDayList)):
            data_every_day = chinaDayList[num]
            month = int(data_every_day['date'].split('.')[0])
            day = int(data_every_day['date'].split('.')[1])
            if (month == 2) or (month == 1 and day == 31):
                self.date_num_list.append(data_every_day['date'])
                self.confirm_list.append(data_every_day['confirm'])
                self.dead_list.append(data_every_day['dead'])
        confirm_np = np.array(self.confirm_list)
        dead_np = np.array(self.dead_list)
        new_confirm_np = confirm_np[1:]-confirm_np[:-1]
        new_dead_np = dead_np[1:]-dead_np[:-1]

        return new_confirm_np, new_dead_np

    def num_feature(self):
        new_confirm_np, new_dead_np = self.get_contents()
        new_confirm_num = np.max(new_confirm_np)
        max_num = np.max(new_confirm_np)
        max_day = self.date_num_list[((np.where(new_confirm_np == np.max(new_confirm_np)))[0][0])+1]
        # 两种方式找到最大最小值，实际上有很多种方法可以实现这个目的
        min_index, min_num = min(enumerate(new_confirm_np), key=operator.itemgetter(1))
        min_day = self.date_num_list[min_index+1]
        mean_num = np.mean(new_confirm_np)
        median_num = np.median(new_confirm_np)
        return max_num, max_day, min_day, min_num, mean_num, median_num

绘图

import matplotlib.pyplot as plt
import seaborn as sns
import matplotlib
import numpy as np

class pic_process():
    def __init__(self,date_num_list,new_confirm_np,new_dead_np):
        self.date_num_list = date_num_list
        self.new_confirm_np = new_confirm_np
        self.new_dead_np = new_dead_np

    def pic_plot(self):
        sns.set(style="darkgrid")
        myfont = matplotlib.font_manager.FontProperties(fname=r'C:/Windows/Fonts/STKAITI.TTF')  # 这一行
        fig = plt.figure(figsize=(10, 5))
        plt.xticks(np.arange(len(self.new_confirm_np)), self.date_num_list[1:], rotation=90)
        plt.title(u'2月份每日新增人数', fontproperties=myfont, fontsize=10)
        plt.xlabel(u'日期', fontproperties=myfont, fontsize=10)
        plt.ylabel(u'人数', fontproperties=myfont, fontsize=10)
        plt.plot(self.date_num_list[1:], self.new_confirm_np, color='darkslategray', linewidth=0.9, label='全国每日新增确认人数')
        plt.ylabel(u'人数', fontproperties=myfont, fontsize=10)
        plt.legend(loc='best', prop=myfont)
        plt.show()

结果示意