百度深度学习CV7日-Day01-新冠疫情可视化

若该文为原创文章，未经允许不得转载
QQ: 627833006
Email: [email protected]
微信：Abner程
CSDN博客地址：https://blog.csdn.net/weixin_46718879
Gitee代码存储：https://gitee.com/abnerwork/python.git

1.概述

今天是百度深度学习课程的第一天，目的在于掌握基本的python使用，以及爬虫操作，和数据的可视化操作。
实际操作共分为5部分。
a : 使用爬虫操作，获取当日全国范围内，各地区疫情数据。
b : 绘制全国实时确诊数据地图，保存为html，网页查看。
c : 绘制湖北实时确诊数据地图，保存为html，网页查看。
d : 绘制新增确诊确诊趋势图，保存为html，网页查看。
e : 绘制全国实时确诊数据，以饼图的方式显示，保存为html，网页查看。

2.示例代码解析

2.1.爬取当日疫情数据

import json
import re
import requests
import datetime

today = datetime.date.today().strftime('%Y%m%d')   #20200315

def crawl_dxy_data():
    """
    爬取丁香园实时统计数据，保存到data目录下，以当前日期作为文件名，存JSON文件
    """
    response = requests.get('https://ncov.dxy.cn/ncovh5/view/pneumonia') #request.get()用于请求目标网站
    print(response.status_code)                                          # 打印状态码


    try:
        url_text = response.content.decode()                             #更推荐使用response.content.deocde()的方式获取响应的html页面
        #print(url_text)
        url_content = re.search(r'window.getAreaStat = (.*?)}]}catch',   #re.search():扫描字符串以查找正则表达式模式产生匹配项的第一个位置 ，然后返回相应的match对象。
                                url_text, re.S)                          #在字符串a中，包含换行符\n，在这种情况下：如果不使用re.S参数，则只在每一行内进行匹配，如果一行没有，就换下一行重新开始;
                                                                         #而使用re.S参数以后，正则表达式会将这个字符串作为一个整体，在整体中进行匹配。
        texts = url_content.group()                                      #获取匹配正则表达式的整体结果
        content = texts.replace('window.getAreaStat = ', '').replace('}catch', '') #去除多余的字符
        json_data = json.loads(content)
        with open('C:/chengyang/workspace/python/Day01/data/' + today + '.json', 'w', encoding='UTF-8') as f:
            json.dump(json_data, f, ensure_ascii=False)
    except:
        print('' % response.status_code)


def crawl_statistics_data():
    """
    获取各个省份历史统计数据，保存到data目录下，存JSON文件
    """
    with open('C:/chengyang/workspace/python/Day01/data/'+ today + '.json', 'r', encoding='UTF-8') as file:
        json_array = json.loads(file.read())

    statistics_data = {}
    for province in json_array:
        response = requests.get(province['statisticsData'])
        try:
            statistics_data[province['provinceShortName']] = json.loads(response.content.decode())['data']
        except:
            print(' for url: [%s]' % (response.status_code, province['statisticsData']))

    with open("C:/chengyang/workspace/python/Day01/data/statistics_data.json", "w", encoding='UTF-8') as f:
        json.dump(statistics_data, f, ensure_ascii=False)


if __name__ == '__main__':
    crawl_dxy_data()
    crawl_statistics_data()

2.2.绘制全国实时确诊数据地图

import json
import datetime
from pyecharts.charts import Map
from pyecharts import options as opts

# 读原始数据文件
today = datetime.date.today().strftime('%Y%m%d')   #20200315
datafile = 'C:/chengyang/workspace/python/Day01/data/'+ today + '.json'
with open(datafile, 'r', encoding='UTF-8') as file:
    json_array = json.loads(file.read())

# 分析全国实时确诊数据：'confirmedCount'字段
china_data = []
for province in json_array:
    china_data.append((province['provinceShortName'], province['confirmedCount']))
china_data = sorted(china_data, key=lambda x: x[1], reverse=True)                 #reverse=True,表示降序，反之升序

print(china_data)
# 全国疫情地图
# 自定义的每一段的范围，以及每一段的特别的样式。
pieces = [
    {'min': 10000, 'color': '#540d0d'},
    {'max': 9999, 'min': 1000, 'color': '#9c1414'},
    {'max': 999, 'min': 500, 'color': '#d92727'},
    {'max': 499, 'min': 100, 'color': '#ed3232'},
    {'max': 99, 'min': 10, 'color': '#f27777'},
    {'max': 9, 'min': 1, 'color': '#f7adad'},
    {'max': 0, 'color': '#f7e4e4'},
]
labels = [data[0] for data in china_data]
counts = [data[1] for data in china_data]

m = Map()
m.add("累计确诊", [list(z) for z in zip(labels, counts)], 'china')

#系列配置项,可配置图元样式、文字样式、标签样式、点线样式等
m.set_series_opts(label_opts=opts.LabelOpts(font_size=12),
                  is_show=False)
#全局配置项,可配置标题、动画、坐标轴、图例等
m.set_global_opts(title_opts=opts.TitleOpts(title='全国实时确诊数据',
                                            subtitle='数据来源：丁香园'),
                  legend_opts=opts.LegendOpts(is_show=False),
                  visualmap_opts=opts.VisualMapOpts(pieces=pieces,
                                                    is_piecewise=True,   #是否为分段型
                                                    is_show=True))       #是否显示视觉映射配置
#render（）会生成本地 HTML 文件，默认会在当前目录生成 render.html 文件，也可以传入路径参数，如 m.render("mycharts.html")
m.render(path='C:/chengyang/workspace/python/Day01/data/全国实时确诊数据.html')

2.3.绘制湖北实时确诊数据地图

import json
import datetime
from pyecharts.charts import Map
from pyecharts import options as opts

# 读原始数据文件
today = datetime.date.today().strftime('%Y%m%d')   #20200315
datafile = 'C:/chengyang/workspace/python/Day01/data/'+ today + '.json'
with open(datafile, 'r', encoding='UTF-8') as file:
    json_array = json.loads(file.read())

# 分析湖北省实时确诊数据
# 读入规范化的城市名称，用于规范化丁香园数据中的城市简称
with open('C:/chengyang/workspace/python/Day01/data/data24815/pycharts_city.txt', 'r', encoding='UTF-8') as f:
    defined_cities = [line.strip() for line in f.readlines()]


def format_city_name(name, defined_cities):
    for defined_city in defined_cities:
        if len((set(defined_city) & set(name))) == len(name):
            name = defined_city
            if name.endswith('市') or name.endswith('区') or name.endswith('县') or name.endswith('自治州'):
                return name
            return name + '市'
    return None


province_name = '湖北'
for province in json_array:
    if province['provinceName'] == province_name or province['provinceShortName'] == province_name:
        json_array_province = province['cities']
        hubei_data = [(format_city_name(city['cityName'], defined_cities), city['confirmedCount']) for city in
                      json_array_province]
        hubei_data = sorted(hubei_data, key=lambda x: x[1], reverse=True)

        print(hubei_data)

labels = [data[0] for data in hubei_data]
counts = [data[1] for data in hubei_data]
pieces = [
    {'min': 10000, 'color': '#540d0d'},
    {'max': 9999, 'min': 1000, 'color': '#9c1414'},
    {'max': 999, 'min': 500, 'color': '#d92727'},
    {'max': 499, 'min': 100, 'color': '#ed3232'},
    {'max': 99, 'min': 10, 'color': '#f27777'},
    {'max': 9, 'min': 1, 'color': '#f7adad'},
    {'max': 0, 'color': '#f7e4e4'},
]

m = Map()
m.add("累计确诊", [list(z) for z in zip(labels, counts)], '湖北')
m.set_series_opts(label_opts=opts.LabelOpts(font_size=12),
                  is_show=False)
m.set_global_opts(title_opts=opts.TitleOpts(title='湖北省实时确诊数据',
                                            subtitle='数据来源：丁香园'),
                  legend_opts=opts.LegendOpts(is_show=False),
                  visualmap_opts=opts.VisualMapOpts(pieces=pieces,
                                                    is_piecewise=True,
                                                    is_show=True))
m.render(path='C:/chengyang/workspace/python/Day01/data/湖北省实时确诊数据.html')

2.4.绘制新增确诊确诊趋势图

import numpy as np
import json
from pyecharts.charts import Line
from pyecharts import options as opts

# 读原始数据文件
datafile = 'C:/chengyang/workspace/python/Day01/data/statistics_data.json'
with open(datafile, 'r', encoding='UTF-8') as file:
    json_dict = json.loads(file.read())

# 获取日期列表
dateId = [str(da['dateId'])[4:6] + '-' + str(da['dateId'])[6:8] for da in json_dict['湖北'] if
          da['dateId'] >= 20200201]

# 分析各省份2月1日至今的新增确诊数据：'confirmedIncr'
statistics__data = {}
for province in json_dict:
    statistics__data[province] = []
    for da in json_dict[province]:
        if da['dateId'] >= 20200201:
            statistics__data[province].append(da['confirmedIncr'])
    #若当天该省数据没有更新，则默认为0
    if(len(statistics__data[province])!=len(dateId)):
        statistics__data[province].append(0)


# 全国新增趋势
all_statis = np.array([0] * len(dateId))
for province in statistics__data:
    all_statis = all_statis + np.array(statistics__data[province])

all_statis = all_statis.tolist()
# 湖北新增趋势
hubei_statis = statistics__data['湖北']
# 湖北以外的新增趋势
other_statis = [all_statis[i] - hubei_statis[i] for i in range(len(dateId))]

line = Line()
line.add_xaxis(dateId)
line.add_yaxis("全国新增确诊病例",   #图例
                all_statis,       #数据
                is_smooth=True,   #是否平滑曲线
               linestyle_opts=opts.LineStyleOpts(width=4, color='#B44038'),#线样式配置项
               itemstyle_opts=opts.ItemStyleOpts(color='#B44038',          #图元样式配置项
                                                 border_color="#B44038",   #颜色
                                                 border_width=10))         #图元的大小
line.add_yaxis("湖北新增确诊病例", hubei_statis, is_smooth=True,
               linestyle_opts=opts.LineStyleOpts(width=2, color='#4E87ED'),
               label_opts=opts.LabelOpts(position='bottom'),              #标签在折线的底部
               itemstyle_opts=opts.ItemStyleOpts(color='#4E87ED',
                                                 border_color="#4E87ED",
                                                 border_width=3))
line.add_yaxis("其他省份新增病例", other_statis, is_smooth=True,
               linestyle_opts=opts.LineStyleOpts(width=2, color='#F1A846'),
               label_opts=opts.LabelOpts(position='bottom'),              #标签在折线的底部
               itemstyle_opts=opts.ItemStyleOpts(color='#F1A846',
                                                 border_color="#F1A846",
                                                 border_width=3))
line.set_global_opts(title_opts=opts.TitleOpts(title="新增确诊病例", subtitle='数据来源：丁香园'),
                     yaxis_opts=opts.AxisOpts(max_=16000, min_=1, type_="log",    #坐标轴配置项
                                              splitline_opts=opts.SplitLineOpts(is_show=True),#分割线配置项
                                              axisline_opts=opts.AxisLineOpts(is_show=True)))#坐标轴刻度线配置项
line.render(path='C:/chengyang/workspace/python/Day01/data/新增确诊趋势图.html')

2.5.绘制全国实时确诊数据饼图

from pyecharts import options as opts
from pyecharts.charts import Pie
from pyecharts.faker import Faker

import json
import datetime
from pyecharts.charts import Map
from pyecharts import options as opts

# 读原始数据文件
today = datetime.date.today().strftime('%Y%m%d')   #20200315
datafile = 'C:/chengyang/workspace/python/Paddle/Day01/data/'+ today + '.json'
with open(datafile, 'r', encoding='UTF-8') as file:
    json_array = json.loads(file.read())

# 分析全国实时确诊数据：'confirmedCount'字段
china_data = []
for province in json_array:
    china_data.append((province['provinceShortName'], province['confirmedCount']))
china_data = sorted(china_data, key=lambda x: x[1], reverse=True)                 #reverse=True,表示降序，反之升序


c = (
    Pie()
    .add("", [list(z) for z in china_data])
    # .set_colors(["blue", "green", "yellow", "red", "pink", "orange", "purple"])
    .set_global_opts(title_opts=opts.TitleOpts(title="Pie-分析"))
    .set_series_opts(label_opts=opts.LabelOpts(formatter="{b}: {c}"))
    .render("pie number.html")
)

3.后续

PS：今天是开课的第一天，从零基础到python入门，陆陆续续花了近一周，期间搭建环境各种折腾。当绘图显示成功的那一刻异常的兴奋~~