本文拟采用随机森林实现空气质量的预测。
实现环境:python3.5
所需包:pandas 、numpy、matplotlib、csv等。引入包如下:
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import matplotlib
import csv
import random
from sklearn.ensemble import RandomForestClassifier
from sklearn.ensemble import RandomForestRegressor
from sklearn.preprocessing import LabelEncoder
from sklearn.metrics import confusion_matrix
from sklearn.metrics import classification_report
from sklearn.model_selection import train_test_split
实现过程:
1.数据获取。
本文数据来源:天气后报网:http://www.tianqihoubao.com。通过python的requests库爬取2018年绵阳历史空气质量信息,并将数据存入csv文件。
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
# 获取2018年空气质量数据
url = 'http://www.tianqihoubao.com/aqi/mianyang-2018' + 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_t