地区数据统计

# -*- coding:utf-8 -*-
import numpy as np
import pandas as pd
from datetime import datetime
from pandas.core.frame import DataFrame
import matplotlib.pyplot as plt
import time
import ast
import json

df = pd.read_csv('data.csv')
#s = {'四川省绵阳中学':0, '四川省绵阳实验高级中学':0, '四川省绵阳市实验高级中学':0, '绵阳普明中学':0, '四川省绵阳南山中学双语学校':0, '绵阳南山中学实验学校':0, '四川省绵阳市丰谷中学':0, '四川省科学城第一中学':0, '三台中学校':0, '三台县芦溪中学':0, '三台一中':0, '四川省盐亭中学':0, '四川省绵阳市安州中学':0, '绵阳市秀水中学':0, '四川省梓潼中学校':0, '四川省北川中学':0, '江油中学':0, '四川省江油市第一中学':0, '江油市太白中学':0, '江油外国语学校':0, '南山中学':0, '绵阳中学实验学校':0, '三台中学实验学校':0}
#k = {'四川省绵阳中学':0, '四川省绵阳实验高级中学':0, '四川省绵阳市实验高级中学':0, '绵阳普明中学':0, '四川省绵阳南山中学双语学校':0, '绵阳南山中学实验学校':0, '四川省绵阳市丰谷中学':0, '四川省科学城第一中学':0, '三台中学校':0, '三台县芦溪中学':0, '三台一中':0, '四川省盐亭中学':0, '四川省绵阳市安州中学':0, '绵阳市秀水中学':0, '四川省梓潼中学校':0, '四川省北川中学':0, '江油中学':0, '四川省江油市第一中学':0, '江油市太白中学':0, '江油外国语学校':0, '南山中学':0, '绵阳中学实验学校':0, '三台中学实验学校':0}
total = []
for index in range(0, 26124):
    row_data = df.loc[index, :]
    dt = "2055-01-01 01:01:01"
#    dl = '2021-07-17 20:30:00'
#    dm = '2021-07-18 00:00:00'
#    ds = '2021-07-17 00:00:00'
    d1 = datetime.strptime(dt, "%Y-%m-%d %H:%M:%S")
#    d2 = datetime.strptime(dl, "%Y-%m-%d %H:%M:%S")
#    dstop = datetime.strptime(dm, "%Y-%m-%d %H:%M:%S")
#    dstart = datetime.strptime(ds, "%Y-%m-%d %H:%M:%S")
    #时间的处理
    start_time = row_data['start_time']
    if str(start_time)!='nan':
        start_time = datetime.strptime(start_time, "%Y-%m-%dT%H:%M:%S+08:00")
    else:
        start_time = d1
    stop_time = row_data['stop_time']
    if str(stop_time)!='nan':
        stop_time = datetime.strptime(stop_time, "%Y-%m-%dT%H:%M:%S+08:00")
    else:
        stop_time = d1
    #时间计算
    if stop_time==d1 or start_time==d1:
        total_sec = 0
        total.append(total_sec)
    else:
        tot = (stop_time - start_time).seconds
        total.append(tot)
    '''#统计人数
    if start_time>=dstart and stop_time <= dstop:
        if total_sec<=600:
            for i in s:
                if i == row_data['school']:
                    s[i]+=1
    if stop_time<=d2:
        if total_sec<=600:
            for i in k:
                if i == row_data['school']:
                    k[i]+=1

print(s)
print(k)
'''

total = pd.DataFrame(total)
total.to_excel('E:/桌面/暑期实习/train.xlsx')
'''       
print('科学小于10min:',mq10," 科学小于20min:", mq20, " 科学小于30min:", mq30)
print('问题小于10min:',ms10," 问题小于20min:", ms20, " 问题小于30min:", ms30)

values = [mq10, mq20 , mq30, mq40, mq50, mq60, mq]
labels = ['less than 10min', 'less than 20min', 'less than 30min', 'less than 40min', 'less than 50min', 'less than 60min', 'more than 60min']

def make_autopct(values):
    def my_autopct(pct):
        total = sum(values)
        val = int(round(pct*total/100.0))
        # 同时显示数值和占比的饼图
        return '{p:.2f}%  ({v:d})'.format(p=pct,v=val)
    return my_autopct

plt.pie(values, labels=labels, autopct=make_autopct(values))
plt.show()


values = [ms10, ms20 , ms30, ms40, ms50, ms60, ms]
labels = ['less than 10min', 'less than 20min', 'less than 30min', 'less than 40min', 'less than 50min', 'less than 60min', 'more than 60min']

def make_autopct(values):
    def my_autopct(pct):
        total = sum(values)
        val = int(round(pct*total/100.0))
        # 同时显示数值和占比的饼图
        return '{p:.2f}%  ({v:d})'.format(p=pct,v=val)
    return my_autopct

plt.pie(values, labels=labels, autopct=make_autopct(values))
plt.show()'''