python线性回归预测pm2.5_pm2.5的预测

# coding:utf-8

'''利用 Linear Regression 线性回归预测 PM2.5date:2020-2-30author:xuanyun'''

# 导入必要的包 numpy、pandas以及scikit-learn归一化预处理

import numpy as np

import pandas as pd

from sklearn.preprocessing import StandardScaler

# 指定相对路径

path = r'G:\\jupyterNotebookNetwordFile\\李弘毅\\HW_1\\Dataset\\'

# 利用 pands 进行读取文件操作

train = pd.read_csv(path + 'train.csv', engine='python', encoding='utf-8')

test = pd.read_csv(path + 'test.csv', engine='python', encoding='gbk')

# print(train.head(20))

train = train[train['observation'] == 'PM2.5']

test = test[test['AMB_TEMP'] == 'PM2.5']

# 删除无关特征

train = train.drop(['Date', 'stations', 'observation'], ax