Knn算法对天气数据进行分类代码_天气分类算法

数据的准备工作
下载数据

import time
import requests
from bs4 import BeautifulSoup

headers = {
   
    'User-Agent':'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/63.0.3239.132 Safari/537.36'
}
for i in range(1, 13):
    time.sleep(5)
    # 把1转换为01
    url = 'http://www.tianqihoubao.com/aqi/tianjin-2019' + str("%02d" % i) + '.html'
    response = requests.get(url=url, headers=headers)
    soup = BeautifulSoup(response.text, 'html.parser')
    tr = soup.find_all('tr')
    # 去除标签栏
    for j in tr[1:]:
        td = j.find_all('td')
        Date = td[0].get_text().strip()
        Quality_grade = td[1].get_text().strip()
        AQI = td[2].get_text().strip()
        AQI_rank = td[3].get_text().strip()
        PM = td[4].get_text()
        with open('air_tianjin_2019.csv', 'a+', encoding='utf-8-sig') as f:
            f.write(Date + ',' + Quality_grade + ',' + AQI + ',' + AQI_rank + ',' + PM + '\n')

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26

首先读入数据，并将其转换为列表。
将空气质量转换为数字

import numpy as np
import pandas as pd
import math
import os

# 文件的名字
FILENAME1 = 
1
2
3
4
5
6