机器学习线性归回实战（单因子和多音字分别建立预测房价模型）

以面积为输入变量，建立单因子模型，评估模型表现，预测合理房价

import pandas as pd
import numpy as np

data = pd.read_csv('usa_housing_price.csv')
data.head()

from matplotlib import pyplot as plt

fig = plt.figure(figsize=(10,10)) #图的尺寸
fig1 = plt.subplot(231) #2行3列第一个图
plt.scatter(data.loc[:,'Avg.Area Income'],data.loc[:,'Price'])
plt.title('Price VS Income')

fig2 = plt.subplot(232) 
plt.scatter(data.loc[:,'Avg.Area House Age'],data.loc[:,'Price'])
plt.title('Price VS House Age')

fig3 = plt.subplot(233) 
plt.scatter(data.loc[:,'Avg.Area Number of Rooms'],data.loc[:,'Price'])
plt.title('Price VS Number of Rooms')

fig4 = plt.subplot(234) 
plt.scatter(data.loc[:,'Area Population'],data.loc[:,'Price'])
plt.title('Price VS Area Population')

fig5 = plt.subplot(235) 
plt.scatter(data.loc[:,'size'],data.loc[:,'Price'])
plt.title('Price VS size')

plt.show()

# 定义X，Y
X = data.loc(:,'size') # 面积
Y = data.loc(:,'Price') # 价格

X = np.array(X).reshape(-1,1) #维度转换 print(X.shape)

import sklearn.linear_model import LineearRegression
LR1 = LinearRegression()
LR1.fit(X,y) #模型训练

y_predict_1 = LR1.predict(X)
print(y_predict_1) #计算预测的价格和面积

from sklean.metrics import mean_squared_error,r2_score # 评估模型
mean_squared_error_1 = mean_squared_error(y,y_predict_1)
r2_score_1 = r2_score(y,y_predict_1) 
print(mean_squared_error_1,r2_score_1) #r2_score_1越接近1越好

fig6 = plt.figure(figsize=(8,5))
plt.scatter(X,y)
plt.plot(X,y_predict_1,'r') #红色方式可视化

多因子模型

#重新定义X
X_multi = data.drop(['Price'],axis=1)
x_Multi 

# 建立线性回归的模型
LR_multi = LinearRegression()
LR_multi.fit(X_multi,y)

# 模型预测
y_predict_multi = LR_multi.predict(X_multi)
print(y_predict_multi)

mean_squared_error_multi = mean_squared_error(y,y_predict_multi)
r2_score_multi = r2_score(y,y_predict_multi)
print(mean_squared_error_multi,r2_score_multi)

# 可视化
fig7 = plt.figure(figsize=(8,5))
plt.scatter(y,y_predict_multi)
plt.show()

预测Income=65000,House Age=5,Number of Rooms=5,Population=30000,size=200合理房价

X_test = [65000,5,5,30000,200]

X_test =  [65000,5,5,30000,200]
X_test = np.array(X_test).reshape(1,-1) #转换成数组，维度转化为一行若干列

y_test_predict = LR_multi.predict(X_test) #调用模型进行预测
print(y_test_predict)