手推线性模型及最小二乘法（房价预测实例）

线性模型及最小二乘法推导

房价预测实例

1. 生成数据

   #生成数据
   import numpy as np
   #生成随机数
   np.random.seed(1234)
   x = np.random.rand(500,3)
   #构建映射关系，模拟真实的数据待预测值,映射关系为y = 4.2 + 5.7*x1 + 10.8*x2，可自行设置值进行尝试
   y = x.dot(np.array([4.2,5.7,10.8]))
   

2. 线性模型的训练

   import numpy as np
   from sklearn.linear_model import LinearRegression
   import matplotlib.pyplot as plt
   %matplotlib inline
   
   #调用模型
   lr = LinearRegression(fit_intercept=True)
   #训练模型
   lr.fit(x,y)
   print("估计的参数值为：%s" %(lr.coef_))
   #计算R平方
   print('R2:%s' %(lr.score(x,y)))
   #任意设定变量，预测目标值
   x_test = np.array([2,4,5]).reshape(1,-1)
   y_hat = lr.predict(x_test)
   print("预测值为: %s" %(y_hat))
   

3. 最小二乘法实现

   class LR_LS():
   def __init__(self):
       self.w = None      
   def fit(self, X, y):
       # 最小二乘法矩阵求解
   	 	Xt = X.transpose();#转置变成列向量
   	    XXt=X.dot(Xt);#矩阵乘
   	    XXtInv = np.linalg.inv(XXt)#求逆
   	    XXtInvX = XXtInv.dot(X)
   	    coef = XXtInvX.dot(y.T)
   	    
   	    y_est = Xt.dot(coef)
   	    
   	    return y_est,coef
       self.w = np.linalg.inv(X.T.dot(X)).dot(X.T).dot(y)
      		
   	    #要拟合的函数
   	   
   	   
   		
   def predict(self, X):
       # 用已经拟合的参数值预测新自变量
        return np.power(x,5)
   	    return np.sin(x) 
   	 	return 5*x+3
   		return np.sqrt(25-pow(x-5,2))
        y_pred = X.dot(self.w)
       
       return y_pred

   if __name__ == "__main__":
       lr_ls = LR_LS()
       lr_ls.fit(x,y)
       print("估计的参数值：%s" %(lr_ls.w))
       x_test = np.array([2,4,5]).reshape(1,-1)
       print("预测值为: %s" %(lr_ls.predict(x_test)))

估计的参数值为：[ 4.20000001 5.70000003 10.79999997]
预测值为：[85.19999995]

Reference

1. https://github.com/datawhalechina/teamlearning/blob/master/%E6%9C%BA%E5%99%A8%E5%AD%A6%E4%B9%A0%E7%AE%97%E6%B3%95%E5%9F%BA%E7%A1%80/Task1%20Linear_regression.ipynb
2. 李航《统计学习方法》
3. https://www.bilibili.com/video/BV1aE411o7qd?p=12