# -*- coding: utf-8 -*-"""
Created on Sun May 26 13:06:39 2019
@author: sun
"""from sklearn.feature_selection import SelectKBest,f_regression
from sklearn.linear_model import LinearRegression
from sklearn.svm import SVR
from sklearn.ensemble import RandomForestRegressor
import pandas as pd
import matplotlib.pyplot as plt
from matplotlib import font_manager
my_font = font_manager.FontProperties(fname="\Windows\Fonts\simhei.ttf")# 获取数据
data = pd.read_csv(r"C:\Users\sun\Desktop\论文\算法代码\线性回归\波士顿原数据.csv",engine='python')# 处理数据,找出特征值和目标值
x = data[['crim','zn','indus','chas','nox','rm','age','dis','rad','tax','ptratto','b','lstat']]
y = data ['medv']#找出影响最大的特征值 k = 1
SelectKBest = SelectKBest(f_regression, k=1)
bestFeature = SelectKBest.fit_transform(x,y.values.ravel())
SelectKBest.get_support
七、(2)线性回归——正规方程(基础的线性回归)、SVM、随机森林对比。本文主要探讨一下线性回归、SVM、随机森林三种模型预测波士顿房价数据集的特点,即准确率。第一步:可视化三种线性模型完整代码如下:# -*- coding: utf-8 -*-"""Created on Sun May 26 13:06:39 2019@author: sun"""from sklearn.f...