机器学习采用线性回归模型实现波士顿的房价

最新推荐文章于 2024-09-21 15:43:02 发布

原创最新推荐文章于 2024-09-21 15:43:02 发布

· 1.7k 阅读

9 ·

版权

python 同时被 2 个专栏收录

12 篇文章

订阅专栏

机器学习

3 篇文章

订阅专栏

需要数据集见文章最下方
数据说明在文末
背景介绍
波士顿房地产市场竞争激烈，而你想成为该地区最好的房地产经纪人。为了更好地与同行竞争，你决定运用机器学习的一些基本概念，帮助客户为自己的房产定下最佳售价。幸运的是，你找到了波士顿房价的数据集，里面聚合了波士顿郊区包含多个特征维度的房价数据。你的任务是用可用的工具进行统计分析，并基于分析建立优化模型。这个模型将用来为你的客户评估房产的最佳售价。
1.导入模块

from sklearn.linear_model import SGDRegressor
from sklearn.linear_model import LinearRegression
import pandas as pd
import numpy as np
from sklearn.model_selection import  train_test_split
from sklearn.preprocessing import StandardScaler
from sklearn.metrics import mean_squared_error
import matplotlib.pyplot as plt
plt.rcParams['font.sans-serif']=['SimHei']
#⽤来正常显示中⽂标签
plt.rcParams['axes.unicode_minus']=False 
#⽤来正常显示负号 #有中⽂出现的情况，需要u'内容'

2.分割数据集为训练集和测试集

#分割数据集为训练集和测试集
data = pd.read_csv('E:\Desktop\housing.csv')
x =data[['CRIM','ZN','INDUS','CHAS','NOX','RM','AGE','DIS','RAD','TAX','PIRATIO','B','LSTAT']]
y = data['MEDV']
x_train,x_test,y_train,y_test = train_test_split(x,y,train_size=0.25)

3.标准化处理

# 进行标准化处理
# 特征值和目标值进行标准化
std_x = StandardScaler()
x_train = std_x.fit_transform(x_train)
x_test = std_x.transform(x_test)
std_y = StandardScaler()
y_train = std_y.fit_transform(y_train.values.reshape(-1,1))
y_test = std_y.transform(y_test.values.reshape(-1,1))

4.用正规方程和梯度下降进行房价预测

lr = LinearRegression()
lr.fit(x_train,y_train)
print('正规方程预测回归系数',lr.coef_)
y_lr_pre = std_y.inverse_transform(lr.predict(x_test))
print('正规方程预测结果',y_lr_pre)
#SGD预测结果
ld = SGDRegressor()
ld.fit(x_train,y_train)
print('SGD预测回归系数',ld.coef_)
y_sgd_pre = std_y.inverse_transform(ld.predict(x_test))
print('SGD预测结果',y_sgd_pre)
result_lr = mean_squared_error(std_y.inverse_transform(y_test),y_lr_pre)
result_sgd = mean_squared_error(std_y.inverse_transform(y_test),y_sgd_pre)
print('lr均方误差',result_lr,'sgd均方误差',result_sgd)
print(lr.score(x_test,y_test))
print(ld.score(x_test,y_test))

5.完整代码

from sklearn.linear_model import SGDRegressor
from sklearn.linear_model import LinearRegression
import pandas as pd
from sklearn.model_selection import  train_test_split
from sklearn.preprocessing import StandardScaler
from sklearn.metrics import mean_squared_error
def My_Linear():
    #分割数据集为训练集和测试集
    data = pd.read_csv('E:\Desktop\housing.csv')
    x = data[['CRIM','ZN','INDUS','CHAS','NOX','RM','AGE','DIS','RAD','TAX','PIRATIO','B','LSTAT']]
    y = data['MEDV']
    x_train,x_test,y_train,y_test = train_test_split(x,y,train_size=0.25)
    # 进行标准化处理
    # 特征值和目标值进行标准化
    std_x = StandardScaler()
    x_train = std_x.fit_transform(x_train)
    x_test = std_x.transform(x_test)
    std_y = StandardScaler()
    y_train = std_y.fit_transform(y_train.values.reshape(-1,1))
    y_test = std_y.transform(y_test.values.reshape(-1,1))
    #正规方程预测结果
    lr = LinearRegression()
    lr.fit(x_train,y_train)
    print('正规方程预测回归系数',lr.coef_)
    y_lr_pre = std_y.inverse_transform(lr.predict(x_test))
    print('正规方程预测结果',y_lr_pre)
    #SGD预测结果
    ld = SGDRegressor()
    ld.fit(x_train,y_train)
    print('SGD预测回归系数',ld.coef_)
    y_sgd_pre = std_y.inverse_transform(ld.predict(x_test))
    print('SGD预测结果',y_sgd_pre)
    result_lr = mean_squared_error(std_y.inverse_transform(y_test),y_lr_pre)
    result_sgd = mean_squared_error(std_y.inverse_transform(y_test),y_sgd_pre)
    print('lr均方误差',result_lr,'sgd均方误差',result_sgd)
    print(lr.score(x_test,y_test))
    print(ld.score(x_test,y_test))
    return None
if __name__=='__main__':
    My_Linear()