【数据可视化】pyecharts实现全国和全球疫情可视化

您所在的位置：网站首页 › 吉林市现有确诊人数 › 【数据可视化】pyecharts实现全国和全球疫情可视化

【数据可视化】pyecharts实现全国和全球疫情可视化

2024-07-14 14:45| 来源: 网络整理| 查看: 265

实验目的和要求在本次实验中基于当前的疫情数据完成各种可视化的构建：

（1）对全国总数据绘制饼图；

（2）对全国各地数据进行地图的绘制

（3）对全国的确诊人数做词云图

（4）对山东（湖北）的确诊人数做词云图

（5）进行更复杂的全国（全球）疫情地图的绘制

博客链接：https://www.iamzlt.com/?p=251

前导内容安装pyecharts

1、进入官网或点击这里下载安装包Pyecharts 下载最新版本

2、将Pyecharts 文件放到Anaconda3 的pkgs 目录下

3、打开Anaconda Prompt,输入cd anaconda3/pkgs 进入文件夹

5 继续安装插件

$ pip install echarts-countries-pypkg 全球国家地图 $ pip install echarts-china-provinces-pypkg 中国省份地图 $ pip install echarts-china-cities-pypkg 中国城市地图 $ pip install wordcloud 词云图包实验内容一对全国数据绘制饼图，keshihua.py文件

1.获取数据

import json import requests def catch_data(): url = 'https://view.inews.qq.com/g2/getOnsInfo?name=disease_h5' reponse = requests.get(url=url).json() data = json.loads(reponse['data']) return data if __name__ == '__main__': data = catch_data() print(data.keys()) lastUpdateTime = data['lastUpdateTime'] chinaTotal= data['chinaTotal'] chinaAdd = data['chinaAdd'] print(chinaTotal) print(chinaAdd)

运行结果：

dict_keys(['lastUpdateTime', 'chinaTotal', 'chinaAdd', 'isShowAdd', 'showAddSwitch', 'areaTree']) {'confirm': 84407, 'heal': 79209, 'dead': 4643, 'nowConfirm': 555, 'suspect': 5, 'nowSevere': 26, 'importedCase': 1678, 'noInfect': 903} {'confirm': 3, 'heal': 83, 'dead': 0, 'nowConfirm': -80, 'suspect': 3, 'nowSevere': -3, 'importedCase': 2, 'noInfect': 20}

2.对总数据进行饼图绘制

import json import requests def catch_data(): url = 'https://view.inews.qq.com/g2/getOnsInfo?name=disease_h5' reponse = requests.get(url=url).json() data = json.loads(reponse['data']) return data from pyecharts.charts import Pie from pyecharts import options as opts def create_pie(): data = catch_data() lastUpdateTime = data['lastUpdateTime'] chinaTotal= data['chinaTotal'] #创建实例对象 pie = Pie(init_opts=opts.InitOpts(width='1000px',height='600px')) #添加数据 pie.add(series_name='腾讯数据', data_pair=[list(z) for z in zip(chinaTotal.keys(), chinaTotal.values())]) #设置全局项 pie.set_global_opts(title_opts=opts.TitleOpts(title='全国总数据',pos_left='center',pos_top=20)) #设置每项数据战机 pie.set_series_opts(tooltip_opts=opts.TooltipOpts(trigger='item', formatter="{a} {b}:{c}")) pie.render(path="Bing1.html") if __name__ == '__main__': create_pie() ''' data = catch_data() print(data.keys()) lastUpdateTime = data['lastUpdateTime'] chinaTotal= data['chinaTotal'] chinaAdd = data['chinaAdd'] print(chinaTotal) print(chinaAdd) '''

运行结果：Bing1

Todo 工作：

（1）把上面饼图的 confirm 等字样改成中文

import json import requests def catch_data(): url = 'https://view.inews.qq.com/g2/getOnsInfo?name=disease_h5' reponse = requests.get(url=url).json() data = json.loads(reponse['data']) return data from pyecharts.charts import Pie from pyecharts import options as opts def create_pie(): data = catch_data() lastUpdateTime = data['lastUpdateTime'] chinaTotal= data['chinaTotal'] print(chinaTotal.keys()) chinaTotal_en = {} key_en = ['确诊','治愈','死亡','现有确诊','疑似感染','现有重症','重症','无症状感染者'] i = 0 for key, value in zip(chinaTotal.keys(), chinaTotal.values()): chinaTotal_en[key_en[i]] = value i+=1; #创建实例对象 pie = Pie(init_opts=opts.InitOpts(width='1000px',height='600px')) #添加数据 pie.add(series_name='腾讯数据', data_pair=[list(z) for z in zip(chinaTotal_en.keys(), chinaTotal.values())]) #设置全局项 pie.set_global_opts(title_opts=opts.TitleOpts(title='全国总数据',pos_left='center',pos_top=20)) #设置每项数据战机 pie.set_series_opts(tooltip_opts=opts.TooltipOpts(trigger='item', formatter="{a} {b}:{c}")) pie.render(path="Bing1.html") if __name__ == '__main__': create_pie() #data.keys()=['上次更新','总和','增加','','','',''] #data = catch_data() #print(data.keys()) #lastUpdateTime = data['lastUpdateTime'] #chinaTotal= data['chinaTotal'] #chinaAdd = data['chinaAdd'] #print(chinaTotal) #print(chinaAdd)

运行结果：Bing1

（2）再编写函数对chinaAdd（新增数据）进行绘制，并去掉其中的某个项目，比如heal

运行结果：Bing2

（3）从其他网站下载全球疫情数据，并将其绘制成饼图

# -*- coding: utf-8 -*- """ Created on Wed May 6 16:55:30 2020 @author: ZLT """ import json import requests import pandas as pd import time def time_c(timeNum): timeTemp = float(timeNum/1000) tupTime = time.localtime(timeTemp) stadardTime = time.strftime("%Y-%m-%d %H:%M:%S", tupTime) return stadardTime def catch_data(): url = 'https://lab.isaaclin.cn/nCoV/api/area?latest=0' data = requests.get(url=url).json() res = data['results'] df = pd.DataFrame(res) for i in range(len(df)): df.iloc[i,16] = time_c(df.iloc[i,16]) for i in range(len(df)): df.iloc[i,15] = df.iloc[i,16][5:10] df1 = df df2 = df1.drop_duplicates(['updateTime'],keep='last') date = [] for i in range(len(df2)): date.append(df2.iloc[i,16]) #print(date) tem = df1[df1['updateTime'] == '05-14'] tem = tem.drop_duplicates(['provinceShortName'], keep='last') for i in date[1:41]: tem1 = df1[df1['updateTime'] == i] tem1= tem1.drop_duplicates(['provinceShortName'],keep='last') tem = tem.append(tem1) tem = tem.reset_index(drop=True) #print(tem) tem = tem[tem['cities'] == '05-14'] print(tem) world_dict={} keys = ['currentConfirmedCount','confirmedCount','suspectedCount','curedCount','deadCount'] for i in range(len(keys)): world_dict[keys[i]]=0 print(world_dict) for i in range(len(keys)): #print(tem[keys[i]]) world_dict[keys[i]] = sum(tem[keys[i]]) print(world_dict) return world_dict from pyecharts.charts import Pie from pyecharts import options as opts def create_pie(): data = catch_data() #创建实例对象 pie = Pie(init_opts=opts.InitOpts(width='1000px',height='600px')) #添加数据 pie.add(series_name='数据', data_pair=[list(z) for z in zip(data.keys(), data.values())]) #设置全局项 pie.set_global_opts(title_opts=opts.TitleOpts(title='全球总数据',pos_left='center',pos_top=20)) #设置每项数据战机 pie.set_series_opts(tooltip_opts=opts.TooltipOpts(trigger='item', formatter="{a} {b}:{c}")) pie.render(path="Bing3.html") if __name__ == '__main__': #data = catch_data() create_pie()

运行结果：Bing3

实验内容二对全国各地数据进行地图绘制 keshihua2.py import json import requests import pandas as pd import time from pyecharts.charts import Map import pyecharts.options as opts def catch_data(): url = 'https://view.inews.qq.com/g2/getOnsInfo?name=disease_h5' reponse = requests.get(url=url).json() data = json.loads(reponse['data']) return data data = catch_data() print(data.keys()) lastUpdateTime = data['lastUpdateTime'] areaTree = data['areaTree'] china_data = areaTree[0]['children'] china_list = [] for a in range(len(china_data)): province = china_data[a]['name'] province_list = china_data[a]['children'] for b in range(len(province_list)): city = province_list[b]['name'] total = province_list[b]['total'] today = province_list[b]['today'] china_dict = {} china_dict['province'] = province china_dict['city'] = city china_dict['total'] = total china_dict['today'] = today china_list.append(china_dict) china_data = pd.DataFrame(china_list) def confirm(x): confirm = eval(str(x))['confirm'] return confirm def dead(x): dead = eval(str(x))['dead'] return dead def heal(x): heal = eval(str(x))['heal'] return heal china_data['confirm'] = china_data['total'].map(confirm) china_data['dead'] = china_data['total'].map(dead) china_data['heal'] = china_data['total'].map(heal) china_data = china_data[["province","city","confirm","dead","heal"]] #print(china_data.head()) #print(china_data) area_data = china_data.groupby("province")["confirm"].sum().reset_index() area_data.columns = ["province", "confirm"] print(area_data) ( Map() .add("", [list(z) for z in zip(list(area_data["province"]), list(area_data["confirm"]))], "china", is_map_symbol_show=False) .set_global_opts(title_opts=opts.TitleOpts(title="2019_nCov中国各地总确诊人数地图"), visualmap_opts=opts.VisualMapOpts(is_piecewise=True, pieces=[ {"min": 5000, "label":';5000', "color":"#893448"}, {"min": 1000, "max": 4999, "label":'1000~4999', "color":"#ff585e"}, {"min": 500, "max":999, "label":'500~1000', "color":"#fb8146"}, {"min": 101, "max":499, "label":'101~499', "color":"#ffA500"}, {"min": 10, "max":99, "label":'10~100', "color":"#ffb248"}, {"min": 0, "max":9,"label":'0~9', "color":"#fff2d1"} ] )) ).render(path="Bing4.html")

运行结果：Bing4

实验内容三对全国确诊人数做词云图

1 保存csv 数据（还是keshihua2.py，在中间加入一行代码再运行生成csv）

area_data.to_csv('china.csv', index=False)

2 制作词云图（新建keshihua3.py）

import pandas as pd from wordcloud import WordCloud, ImageColorGenerator import matplotlib.pyplot as plt def draw_cloud(read_name): wc = WordCloud(font_path='simkai.ttf', background_color="white") fp = pd.read_csv(read_name, encoding='utf-8') name = list(fp.province) value = fp.confirm for i in range(len(name)): name[i] = str(name[i]) dic = dict(zip(name, value)) wc.generate_from_frequencies(dic) plt.imshow(wc) plt.axos("off") wc.to_file('china.png') if __name__ == '__main__': draw_cloud('china.csv')

运行结果：

Todo 工作：生成的 csv 文件虽然在词云图中没有问题，但是用execl 等程序打开后，省名确实乱码，请优化使之用excel 打开后仍然可读。

area_data.to_csv('china.csv', index=False, encoding='utf-8-sig') 实验内容四对山东（湖北）省确诊人数做词云图

1 保存csv 数据（还是keshihua2.py）

shandong_data=china_data.loc[china_data.province=='山东',['city','confirm']] shandong_data.to_csv('shandong.csv',index=False,encoding='utf-8-sig')

2 绘制词云图（todo 在keshihua2.py 基础上改动实现）

import pandas as pd from wordcloud import WordCloud, ImageColorGenerator import matplotlib.pyplot as plt def draw_cloud(read_name): wc = WordCloud(font_path='simkai.ttf', background_color="white") fp = pd.read_csv(read_name, encoding='utf-8') name = list(fp.city) value = fp.confirm for i in range(len(name)): name[i] = str(name[i]) dic = dict(zip(name, value)) wc.generate_from_frequencies(dic) plt.imshow(wc) plt.axis("off") wc.to_file('china.png') if __name__ == '__main__': draw_cloud('shandong.csv')

运行结果：

实验内容五在实验三的基础上生成一个动态的，显示所有信息的地图（keshihua4.py）

1 选定json 网址

https://ncportal.esrichina.com.cn/JKZX/yq_20200131.json 为了简单，直接使用２０２００１３１这一天的数据，该json 的结构请打开网页查看

import time import json import requests import datetime import pandas as pd import numpy as np from pyecharts.charts import Map from pyecharts import options as opts infoType = ['新增疑似', '累计疑似', '新增确诊', '累计确诊', '新增死亡', '累计死亡'] date = 0 def getInfo(types, results): #从字典中获取types信息（types in infoType） rDict = {} for item in results: rDict[item['name']] = item[types] return rDict def formatProvince(proName): if proName.endswith('省') or proName.endswith('市'): return proName[:-1] elif proName == '内蒙古自治区': return '内蒙古' elif proName.endswith('自治区'): return proName[:2] elif proName.endswith('行政区'): return proName[:2] def mapVisualmap(iType=infoType): #定义一个Map类 c = Map() #设置图例显示列表 pieces = [] #获取网页内容 result = getResult()[0] #返回时间信息 #遍历项目类型 for i in range(len(iType)): #将每一组数据添加到类c中 rDict = getInfo(iType[i], result) c.add('{}'.format(iType[i]), [list(z) for z in zip([formatProvince(i) for i in rDict.keys()], list(rDict.values()))], 'china') #将每一组数据中的最大最小值作为每一个图例区间 pieces.append({'min': min(rDict.values()), 'max': max(rDict.values())}) #设置类Map的全局属性，标题属性，visualmap属性，图例属性 c.set_global_opts( title_opts=opts.TitleOpts(title="全国各省份疫情感染情况(截止：{})".format(date), pos_top=15, pos_right='center'), visualmap_opts=opts.VisualMapOpts(is_piecewise=True, pieces=pieces, type_= 'color'), legend_opts=opts.LegendOpts(selected_mode='single', orient='vertical', pos_right=40, pos_top=40)) return c def formatProvince(proName): if proName.endswith('省') or proName.endswith('市'): return proName[:-1] elif proName == '内蒙古自治区': return '内蒙古' elif proName.endswith('自治区'): return proName[:2] elif proName.endswith('行政区'): return proName[:2] def getResult(): url = "https://ncportal.esrichina.com.cn/JKZX/yq_{}.json" headers = {'User-Agent': 'Mozilla/5.0 (windows NT 10.0; Win64; x64)'} global date date = 20200131 print(url.format(date)) req = requests.get(url.format(date), headers=headers) provinceInfo = [] for i in range(34): provinceInfo.append(req.json()['features'][i]['properties']) return provinceInfo, date #返回各省、自治区、直辖市及港澳台的全部数据 if __name__ == '__main__': c = mapVisualmap() c.render(path="全国各省份疫情感染情况.html")

运行结果：全国各省份疫情感染情况

项目实战：绘制世界动态疫情地图：生成如下所示的html 文件

import json import requests import pandas as pd import time from pyecharts.charts import Map from pyecharts import options as opts def time_c(timeNum): timeTemp = float(timeNum/1000) tupTime = time.localtime(timeTemp) stadardTime = time.strftime("%Y-%m-%d %H:%M:%S", tupTime) return stadardTime def catch_data(): url = 'https://lab.isaaclin.cn/nCoV/api/area?latest=0' data = requests.get(url=url).json() res = data['results'] df = pd.DataFrame(res) for i in range(len(df)): df.iloc[i,16] = time_c(df.iloc[i,16]) for i in range(len(df)): df.iloc[i,15] = df.iloc[i,16][5:10] df1 = df df2 = df1.drop_duplicates(['updateTime'],keep='last') date = [] for i in range(len(df2)): date.append(df2.iloc[i,16]) #print(date) tem = df1[df1['updateTime'] == '05-14'] tem = tem.drop_duplicates(['provinceShortName'], keep='last') for i in date[1:41]: tem1 = df1[df1['updateTime'] == i] tem1= tem1.drop_duplicates(['provinceShortName'],keep='last') tem = tem.append(tem1) tem = tem.reset_index(drop=True) #print(tem) tem = tem[tem['cities'] == '05-14'] print(tem) tem.to_csv('world_5_14.csv',index=False,encoding='utf-8-sig') return tem if __name__ == '__main__': area_data = catch_data() #create_pie() ( Map() .add("", [list(z) for z in zip(list(area_data["countryEnglishName"]), list(area_data["currentConfirmedCount"]))], "world", is_map_symbol_show=False) .set_global_opts(title_opts=opts.TitleOpts(title="2019_nCov世界各地现确诊人数地图"), visualmap_opts=opts.VisualMapOpts(is_piecewise=True, pieces=[ {"min": 5000, "label":'>5000', "color":"#893448"}, {"min": 1000, "max": 4999, "label":'1000~4999', "color":"#ff585e"}, {"min": 500, "max":999, "label":'500~1000', "color":"#fb8146"}, {"min": 101, "max":499, "label":'101~499', "color":"#ffA500"}, {"min": 10, "max":99, "label":'10~100', "color":"#ffb248"}, {"min": 0, "max":9,"label":'0~9', "color":"#fff2d1"} ] )) .set_series_opts(label_opts=opts.LabelOpts(is_show=False)) ).render(path="全球疫情.html")

运行结果：全球疫情

【本文地址】

【数据可视化】pyecharts实现全国和全球疫情可视化

【数据可视化】pyecharts实现全国和全球疫情可视化

今日新闻

推荐新闻