简单线性回归(最小二乘法)

引入依赖

import numpy as np
import matplotlib.pyplot as plt

导入数据

points = np.genfromtxt("data.csv",delimiter=",")
#points
#提取points中的两列数据,分别作为x,y
x=points[:,0];
y=points[:,1];

#用plt画出散点图
plt.scatter(x,y)
plt.show()

定义损失函数

# 损失函数是系数的函数,另外还要传入数据的x,y
def compute_cost(w,b,points):
    total_cost=0
    M =len(points)
    for i in range(M):
        x=points[i,0]
        y=points[i,1]
        total_cost += (y-w*x-b)**2
    return total_cost/M #一除都是浮点 两个除号是地板除,整型。 如 3 // 4

定义核心算法拟合函数

# 先定义一个求均值的函数 问题 求均值是不是可以直接用np.mean(data)来实现?
# def average(data):
#     sum=0
#     num=len(data)
#     for i in range(num):
#         sum += data[i]
#     return sum/num
# print(average(x))
# print(np.mean(x))
#打印出来结果一样,可以通用。

#定义核心拟合函数
def fit(points):
    M = len(points)
    x_bar=np.mean(points[:,0])
    sum_yx= 0
    sum_x2=0
    sum_delta =0
    for i in range(M):
        x=points[i,0]
        y=points[i,1]
        sum_yx += y*(x-x_bar)
        sum_x2 += x**2
    #根据公式计算w
    w = sum_yx/(sum_x2-M*(x_bar**2))
    
    for i in range(M):
        x=points[i,0]
        y=points[i,1] 
        sum_delta += (y-w*x)
    b = sum_delta / M
    return w,b

测试

w,b =fit(points)
w,b
print ("w is :",w)
print ("b is :",b)
cost = compute_cost(w,b,points)
print("cost is :" ,cost)
w is : 1.9842918093406656
b is : 1.299369117112415
cost is : 16659.08147458056

画出拟合曲线

plt.scatter(x,y)

pred_y= w*x+b

plt.plot(x,pred_y,c='r')

参考:

https://www.cnblogs.com/arli/p/11428205.html

0 0 投票数
Article Rating
订阅评论
提醒
guest
0 评论
内联反馈
查看所有评论
0
希望看到您的想法,请您发表评论x