Linear regression + fitting of the relationship between house price and house size

Linear regression + linear fitting of the relationship between house price and house size


(For the data in this section, please refer to the computer "F:\pythondata\test4" or the Tencent Weiyun file "python data\test4")

import  matplotlib.pyplot as plt
from sklearn import  linear_model #进行线性回归。
import numpy as np

#建立datasets_X和datasets_Y用来存储数据中的房屋尺寸和房屋成交价格。
datasets_X =[]
datasets_Y =[]

fr =open('F:/python数据/test4.txt','r')
lines =fr.readlines()
for line in lines:
    items =line.strip().split(',')
    datasets_X.append(int(items[0]))
    datasets_Y.append(int(items[1]))

#此时的datasets_X为[1000, 792, 1260,,,]样式的
#此时的datasets_Y为[168, 184, 197,,,,]样式的
    
length =len(datasets_X) #求得datasets_X的长度，即为数据的总数。
#将datasets_X转化为数组， 并变为二维，以符合线性回 归拟合函数输入参数要求
datasets_X= np.array(datasets_X).reshape([length,1])
#将datasets_Y转化为数组
datasets_Y=np.array(datasets_Y)

'''
此时的datasets_X为
[[1000]
 [ 792]
 [1260]
 ...
 ]
样式的

此时的datasets_Y为[168 184 197 220...]样式的(没了逗号了)
'''

linear =linear_model.LinearRegression()
linear.fit(datasets_X,datasets_Y)#调用线性回归模块，建立回归方程，拟合数据
#查看回归方程系数
print('Cofficients:',linear.coef_)
#查看回归方程截距
print('intercept',linear.intercept_)

minX =min(datasets_X)
maxX =max(datasets_X)
#以数据datasets_X的最大值4399和最小值792为范围，建立等差数列[ 792  793  794 ... 4397 4398 4399]，方便后续画图。
X=np.arange(minX,maxX).reshape([-1,1])
#使用reshape(-1,1)之后，数据集变成了一列。使用reshape(1,-1)数据集会变成一行。
plt.scatter(datasets_X,datasets_Y,color='red')
plt.plot(X,linear.predict(X),color='blue')
plt.xlabel('Area')
plt.ylabel('Price')
plt.show()

2.3. Polynomial regression + nonlinear fitting of the relationship between house price and house size

(For the data in this section, please refer to the computer "F:\pythondata\test4" or the Tencent Weiyun file "python data\test4")

import matplotlib.pyplot as plt
from sklearn import linear_model
import numpy as np
from sklearn.preprocessing import PolynomialFeatures


datasets_x = []
datasets_y = []
fr = open('F:/python数据/test4.txt','r')
lines = fr.readlines()
for line in lines:
    items = line.strip().split(',')
    datasets_x.append(int(items[0]))
    datasets_y.append(int(items[1]))
    
length = len(datasets_x)
datasets_X=np.array(datasets_x).reshape([length,1])#将datasets_x转化为数组，并变为二维，以符合线性回归拟合函数
datasets_Y=np.array(datasets_y)


poly_reg=PolynomialFeatures(degree=2) #degree=2表示建立datasets_X的二次多项式特征x_poly
x_poly = poly_reg.fit_transform(datasets_X) #使用线性模型学习x_poly和datasets_y之间的映射关系
lin_reg_2 = linear_model.LinearRegression()
lin_reg_2.fit(x_poly,datasets_Y)


minX=min(datasets_X)
maxX=max(datasets_X)
X=np.arange(minX,maxX).reshape([-1,1])

plt.scatter(datasets_X,datasets_Y,color='red')#scatter函数绘制数据点
plt.plot(X,lin_reg_2.predict(poly_reg.fit_transform(X)),color='blue')#plot函数用来绘制直线，这里表示绘制回归线
plt.xlabel("Area")
plt.ylabel("Price")
plt.show()