线性回归第一个机器学习算法 - 单变量线性回归

"""
使用sklearn实现线性回归
"""

import numpy as np
from sklearn.linear_model import LinearRegression

X = 2 * np.random.rand(100, 1)
y = 4 + 3 * X + np.random.randn(100, 1)

lin_reg = LinearRegression()
#fit方法就是训练模型的方法
lin_reg.fit(X, y)
#intercept 是截距 coef是参数
print(lin_reg.intercept_, lin_reg.coef_)

#预测
X_new = np.array([[0], [2]])
print(lin_reg.predict(X_new))

#encoding=utf-8
"""
线性回归实现梯度下降的批处理（batch_gradient_descent ）
"""
import numpy as np

X = 2 * np.random.rand(100, 1)
y = 4 + 3 * X + np.random.randn(100, 1)
X_b = np.c_[np.ones((100, 1)), X]
#print(X_b)

learning_rate = 0.1
#通常在做机器学习的时候，一般不会等到他收敛，因为太浪费时间，所以会设置一个收敛次数
n_iterations = 1000
m = 100

#1.初始化theta， w0...wn
theta = np.random.randn(2, 1)
count = 0

#4. 不会设置阈值，之间设置超参数，迭代次数，迭代次数到了，我们就认为收敛了
for iteration in range(n_iterations):
    count += 1
    #2. 接着求梯度gradient
    gradients = 1.0/m * X_b.T.dot(X_b.dot(theta)-y)
    #3. 应用公式调整theta值， theta_t + 1 = theta_t - grad * learning_rate
    theta = theta - learning_rate * gradients

print(count)
print(theta)

import numpy as np
import time

a = np.array([1,2,3,4])

a = np.random.rand(1000000)
b = np.random.rand(1000000)

tic = time.time()
c = np.dot(a,b)
toc = time.time()

print("Vectorized version:" + str(1000*(toc-tic)) + 'ms')

c = 0
tic = time.time()
for i in range(1000000):
    c += a[i]*b[i]
toc = time.time()

print("for loop:" + str(1000*(toc-tic)) + 'ms')