1、简单线性回归模型举例:
汽车卖家做电视广告数量与卖出的汽车数量:
如何训练适合简单线性回归模型的最佳回归线?
使sum of squares最小
计算
分子 = (1-2)(14-20)+(3-2)(24-20)+(2-2)(18-20)+(1-2)(17-20)+(3-2)(27-20)=6+4+0+3+7=20
分母 = (1-2)^2+(3-2)^2+(2-2)^2+(1-2)^2+(3-2)^2 = 1+1+0+1+1=4
b1 = 20/4 = 5
b0 = 20 - 5*2 = 20 - 10 =10
预测:假设有一周广告数量为6,预测的汽车销售量是多少?
x_given = 6
Y_hat = 5*6+10=40
import numpy as np
def fitSLR(x,y):
n = len(x)
dinominator = 0#分子
numerator = 0#分母
for i in range(0,n):
numerator += (x[i] - np.mean(x))*(y[i] - np.mean(y))
dinominator += (x[i] - np.mean(x))**2
print "numerator: ",numerator
print "dinominaytor: ",dinominator
b1 = numerator/float(dinominator)
b0 = np.mean(y)/float(np.mean(x))
return b0,b1
def predict(x,b0,b1):
return b0 + x*b1
x = [1,3,2,1,3]
y = [14,24,18,17,27]
b0,b1 = fitSLR(x,y)
print "intercept:",b0,"slope:",b1
x_test = 6
y_test = predict(6,b0,b1)
print "y_test:",y_test