利用Pyecharts可视化事件-第二步

2022年8月4日 507点热度 4人点赞 0条评论

提出问题

之前的《给定语句提取含有地理信息的省份》一节提出对给定事件提取到了省份，那么如果我们要对其可视化并且做一些统计分析，应该怎么办？

解决思路

利用Pyecharts强大的可视化功能实现简单的前端可视化展示和统计分析

方法

之前已通过相关算法提取到省市级别对应的事件发生详情，但是是随机分布的，现在需要对其按省份顺序排列，并且输出为csv表格格式。处理操作如下：

import json
import csv

content = json.load(open("./class.json"))
with open('test.csv', 'a', newline='',encoding='utf-8-sig') as f:
    header = ['事件名称', '类型', '发生地', '详情']
    writer = csv.DictWriter(f, fieldnames=header)
    writer.writeheader()  # 写入列名
    for item in content:
        datas = []
        datas.append(item)
        writer.writerows(datas)  # 写入数据

处理结果如下：

进一步将上述结果按省市级别分割成单个csv存储。处理操作如下：

import numpy as np
import pandas as pd
import csv
from collections import defaultdict

path = "./test.csv"
df = pd.read_csv(path, header=0, usecols = [2])
data_array = np.array(df.stack()) # 首先将pandas读取的数据转化为array
data_list = data_array.tolist() # 然后转化为list形式

dd = defaultdict(list)
for k, va in [(v,i) for i, v in enumerate(data_list)]:
    dd[k].append(va)

df1 = pd.read_csv(path,header=0)
for i,j in dd.items():
    #print (i,j)
    if len(j) == 1:
        cont_part = df1[j[0]:j[0]+1]
    else:
        cont_part = df1[j[0]:j[-1]]
    cont_part.to_csv("./pro_csv/{}.csv".format(i), index_label = 'ID', encoding='utf-8-sig')

处理结果如下：

对以上各个省份发生的事件类型进行统计分析。处理操作如下：

# 导入必要的包
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
import seaborn as sns
from pyecharts.charts import *
from pyecharts.components import Table
from pyecharts import options as opts
from pyecharts.commons.utils import JsCode
import random
import datetime
import warnings
warnings.filterwarnings("ignore")
import os
from collections import defaultdict

def make_html(cate, data, file_name):
    pie = (Pie()
       .add('', [list(z) for z in zip(cate, data)])
       .set_global_opts(tooltip_opts=opts.TooltipOpts(is_show=True,
                                                     # 鼠标移动或者点击时触发
                                                      trigger_on="mousemove|click",
                                                      formatter='{b} :{d}%',
                                                      background_color="green",
                                                      textstyle_opts=opts.TextStyleOpts(color='red')
                                                     ))
       )

    pie.render(file_name + ".html")

files = './pro_csv'
files_html = "./type_html/"
file_list = os.listdir(files)
#type_thing = ["爆炸事故",'车辆事故','电气事故','高处坠落','']
for item in file_list:
    df = pd.read_csv(os.path.join(files, item), header=0, usecols = [2])
    data_array = np.array(df.stack()) # 首先将pandas读取的数据转化为array
    data_list = data_array.tolist() # 然后转化为list形式
    dd = defaultdict(list)

    for k, va in [(v,i) for i, v in enumerate(data_list)]:
        dd[k].append(va)

    type_thing = []
    count_thing = []
    for i, j in dd.items():
        count_i = j[-1] - j[0] + 1
        type_thing.append(i)
        count_thing.append(count_i)
    print (item)
    print (type_thing)
    print (count_thing)
    make_html(type_thing, count_thing, files_html + item[:-4])

处理结果如下：

再以每个省市级构建全国地图显示，通过地图选择显示相关详细信息。处理操作如下：

#coding=utf-8
import pandas as pd
from pyecharts.charts import Map
from pyecharts import options as opts
from pyecharts.charts import *
from pyecharts.components import Table
from pyecharts.commons.utils import JsCode
from pyecharts.faker import Faker
import os
import numpy as np
from collections import defaultdict
import re

def visulization(list_item):

    c = (
    Map(init_opts=opts.InitOpts(width="1000px", height="600px"))  #初始化地图大小
    .set_global_opts(
        title_opts=opts.TitleOpts(title="全国事故类型可视化"),  #配置标题
        visualmap_opts=opts.VisualMapOpts(type_ = "scatter", is_piecewise=True,
        pieces=[
                    {"min":0,"max":3,"label":"0~3","color":"cyan"},
                    {"min":4,"max":7,"label":"4~7","color":"yellow"},
                    {"min":8,"max":11,"label":"8~11","color":"orange"},
                    {"min":12,"max":15,"label":"12~15","color":"coral"},
                    {"min":16,"max":17,"label":"16~17","color":"red"},
        ]
        )
    )
    .add("事故种类总数", list_item, maptype="china")  #将list传入，地图类型为中国地图
    .render("全国事故发生地图.html")
    )

files = './pro_csv'
file_list = os.listdir(files)

total_pro = []
total_type = []

for file in file_list:
    df1 = pd.read_csv(os.path.join(files, file), header=0, usecols = [2], encoding='utf-8-sig')
    df2 = pd.read_csv(os.path.join(files, file), header=0, usecols = [3], encoding='utf-8-sig')
    data_array1 = np.array(df1.stack()) # 首先将pandas读取的数据转化为array
    data_list1 = data_array1.tolist() # 然后转化为list形式
    #print (data_list1)
    len_type = len(set(data_list1))

    data_array2 = np.array(df2.stack()) # 首先将pandas读取的数据转化为array
    data_list2 = data_array2.tolist() # 然后转化为list形式
    data_list2 = list(set(data_list2))
    for item in data_list2:
        item = filter(lambda ch: ch not in '省市自治区回族壮族维吾尔', item) 
        item = list(item)
        item = "".join(item)
        total_pro.append(item)
    total_type.append(len_type)

#name_translate = dict(zip(Faker.provinces,total_pro))
list_ = [list(z) for z in zip(total_pro, total_type)]
print (list_)
visulization(list_)

处理结果如下：

将以省市级别单个存储的csv表格以html格式显示，从而实现点击地图可以跳转到html格式显示事件。并且实现了点击生成的事故详情页中的事故比例跳转到第3步生成的对应省市级统计分析图。处理操作如下：

import os

# 填充数据，参数为列表，全部居中显示，返回一个tr
def fill_data(locls1, locls2, locls3, locls4, href_):
    seg = '<tr><td align="center">{0}</td><td align="center">{1}</td><td align="center">{2}</td><td align="center">{3}</td><td align="center"><a href={4}>事故链接</a> </td></tr>\n'.format(locls1, locls2, locls3, locls4, href_)
    return seg

def csv2html(csv_path, filename):  
    # 将CSV文件转化为HTML文件
    # 标签头
    seg1 = '''<!DOCTYPE html><html lang="en"><head>
    <meta charset="GBK">
    <title>Title</title>
    </head>
    <body>
    <h2 align="center">事故详情</h2>\n
    <table border="1" align="center" width="70%">\n
    <tr bgcolor="orange">\n'''

    # 将数据存入<table>标签中
    # 结尾标签
    seg2 = "</tr>\n"
    seg3 = "</table>\n</body>\n</html>"

    seg4 = '<tr><td align="center"><a href={}>事故比例</a></td></tr>'.format('./type_html/' + filename + '.html')
    # 获取csv文件，存入列表中
    ls = []
    with open(csv_path, "r", encoding="utf-8") as fr:
        for line in fr:

            line = line.replace("\n", "")  # 每行去掉换行符
            lineout = line.split(",")
            ls.append(lineout)  # 按分隔符分割

    # 写入HTML中
    with open("./csv_html/{}.html".format(filename), "w", encoding = 'utf-8-sig') as fw:
        fw.write(seg4)
        fw.write(seg1)
        # 添加表头：ls[0]是表头
        fw.write('<th width="25%">{}</th>\n<th width="25%">{}</th>\n<th width="25%">{}</th>\n<th width="25%">{}</th>\n<th width="25%">{}</th>\n'.format(*ls[0]))

        fw.write(seg2)
        # 添加每一行
        for i in range(1, len(ls)):
            #print (ls[i])
            fw.write(fill_data(ls[i][0],ls[i][1],ls[i][2],ls[i][3],ls[i][4]))
        # 添加结尾标签
        fw.write(seg3)
        fw.close()

if __name__ == "__main__":
    files_floder = './pro_csv'
    files_path = os.listdir(files_floder)
    #print(files_path)
    for item in files_path:
        #print (os.path.join(files_floder, item))
        csv2html(os.path.join(files_floder, item), item[:-4])