梯度下降原理见下图
代码如下:
import numpy as np
def compute_error_for_line_given_points(w, b, points):
totalError = 0
for i in range(len(points)):
x = points[i, 0]
y = points[i, 1]
totalError = totalError + (y - (w * x + b)) ** 2
return totalError / float(len(points))
def step_gradient(b_current, w_current, points, learningRate):
b_gradient = 0
w_gradient = 0
N = float(len(points))
for i in range(0, len(points)):
x = points[i, 0]
y = points[i, 1]
b_gradient += -(2 / N) * (y - ((w_current * x) + b_current))
w_gradient += -(2 / N) * x * (y - ((w_current * x) + b_current))
new_b = b_current - (learningRate * b_gradient)
new_w = w_current - (learningRate * b_gradient)
return [new_b, new_w]
def gradient_descent_runner(points, starting_b, starting_m,
learning_rate, num_iterating):
b = starting_b
m = starting_m
for i in range(num_iterating):
b, m = step_gradient(b, m, np.array(points), learning_rate)
return [b, m]
def run():
points = np.genfromtxt("data.csv", delimiter=',')
learning_rate = 0.0001
initial_b = 0
initial_m = 0
num_iterating = 1000
print(f"Staring gradient descent at b={initial_b}, m={initial_m}, "
f"error={compute_error_for_line_given_points(initial_b, initial_m, points)}")
print("Running>>>>>>>>>>>>>>>>>>>>>>")
[b, m] = gradient_descent_runner(points, initial_b, initial_m, learning_rate, num_iterating)
print(f"After {num_iterating} iterations b={b}, m={m}, error={compute_error_for_line_given_points(b, m, points)}")
if __name__ == "__main__":
run()