线性回归_最小二乘法

from numpy import *
import matplotlib.pyplot as plt

1.导入数据

# 1.导入数据
# 模型 y = wx + b
points = genfromtxt('linear_regress_lsm_data.csv', delimiter=',')
N = len(points)
print('point count %d'%N)
x = array(points[:, 0])
y = array(points[:, 1])
plt.scatter(x, y)
plt.show

point count 100





<function matplotlib.pyplot.show(close=None, block=None)>

2.损失函数

# 2.损失函数
def compute_cost(points, w, b):
    total_cost = 0
    length = len(points)
    for i in range(length):
        x = points[i, 0]
        y = points[i, 1]
        total_cost = (y - w * x - b) ** 2
    return total_cost / float (length)
    

3.训练

# 3.训练
def average(nums):
    sum = 0
    length = len(nums)
    for i in range(length):
        sum += nums[i]
    return sum / float(length)


def fit(points):
    length = len(points)
    x_bar = average(array(points[:, 0]))
    
    sum_y_x = 0
    sum_x_power = 0
    sum_b = 0
    
    # 求 w
    for i in range(length):
        x = points[i, 0]
        y = points[i, 1]
        sum_y_x += y * (x - x_bar)
        sum_x_power += x ** 2
    
    w = sum_y_x / (sum_x_power - x_bar ** 2 * float(length))
    
    # 求 b
    for i in range(length):
        x = points[i, 0]
        y = points[i, 1]
        sum_b += y - w * x
    b = sum_b / float(length)
    return w, b

4.测试

# 4.测试
w, b = fit(points)
print("w is : ", w)
print("b is : ", b)
cost = compute_cost(points, w, b)
print("cost is :", cost)

w is :  1.3224310227553846
b is :  7.991020982269173
cost is : 1.4963859648775966

5.画拟合曲线

# 5. 画拟合曲线
plt.scatter(x, y)
y_predict = w * x + b
plt.plot(x, y_predict, c = 'y')
plt.show

<function matplotlib.pyplot.show(close=None, block=None)>