线性回归学习

一元回归

案例

求解

多元线性回归

梯度下降法

梯度下降

一元

# y = theta0+theta1*x
X = [4, 8, 5, 10, 12]
y = [20, 50, 30, 70, 60]
# 初始化参数
theta0 = theta1 = 0
# 学习率
alpha = 0.001
# 迭代次数
cnt = 0
# 误差
error0 = error1 = 0
# 指定一个阈值，用于检查两次误差的差，以便停止迭代
threshold = 0.000001

while True:
    # 梯度，diff[0]是theta0的梯度，diff[1]是theta1的梯度
    diff = [0, 0]
    m = len(X)
    for i in range(m):
        diff[0] += y[i] - (theta0 + theta1 * X[i])
        diff[1] += (y[i] - (theta0 + theta1 * X[i])) * X[i]
    theta0 = theta0 + alpha/m * diff[0]
    theta1 = theta1 + alpha/m * diff[1]
    # 计算误差
    for i in range(m):
        error1 += (y[i] - (theta0 + theta1 * X[i])) ** 2
    error1 /= m
    if abs(error1 - error0) < threshold:
        break
    else:
        error0 = error1
    cnt += 1
print(theta0, theta1, cnt)


def predict(theta0, theta1, x_test):
    return theta0 + theta1 * x_test


print(predict(theta0, theta1, 15))

多元

# y = theta0 * x0 + theta1 * x1 + theta2 * x2
x_train = [[1,0.,3],[1,1.,3],[1,2.,3],[1,3.,2],[1,4.,4]]
y_train = [95.364,97.217205,75.195834,60.105519,49.342380]

theta0,theta1,theta2 = 0,0,0
alpha = 0.0001
cnt = 0
error0,error1 = 0,0
threshold = 0.00001

m = len(y_train)
while True:
    diff = [0,0,0]
    for i in range(m):
        diff[0] += (y_train[i] - (theta0 + theta1 * x_train[i][1] + theta2 * x_train[i][2])) * x_train[i][0]
        diff[1] += (y_train[i] - (theta0 + theta1 * x_train[i][1] + theta2 * x_train[i][2])) * x_train[i][1]
        diff[2] += (y_train[i] - (theta0 + theta1 * x_train[i][1] + theta2 * x_train[i][2])) * x_train[i][2]
    theta0 = theta0 + alpha / m * diff[0]
    theta1 = theta1 + alpha / m * diff[1]
    theta2 = theta2 + alpha / m * diff[2]

    for i in range(m):
        error1 += (y_train[i] - theta0 + theta1 * x_train[i][1] + theta2 * x_train[i][2])**2

    if abs(error1 - error0) < threshold:
        break
    else:
        error0 = error1
    cnt += 1
    print(theta0,theta1,theta2,cnt)

随机梯度下降

# y = theta0+theta1*x
X = [4, 8, 5, 10, 12]
y = [20, 50, 30, 70, 60]
# 初始化参数
theta0 = theta1 = 0
# 学习率
alpha = 0.001
# 迭代次数
cnt = 0
# 误差
error0 = error1 = 0
# 指定一个阈值，用于检查两次误差的差，以便停止迭代
threshold = 0.000001

while True:
    # 梯度，diff[0]是theta0的梯度，diff[1]是theta1的梯度
    diff = [0, 0]
    m = len(X)
    for i in range(m):
        diff[0] = y[i] - (theta0 + theta1 * X[i])
        diff[1] = (y[i] - (theta0 + theta1 * X[i])) * X[i]
        theta0 = theta0 + alpha * diff[0]
        theta1 = theta1 + alpha * diff[1]
    # 计算误差
    for i in range(m):
        error1 += (y[i] - (theta0 + theta1 * X[i])) ** 2
    error1 /= m
    if abs(error1 - error0) < threshold:
        break
    else:
        error0 = error1
    cnt += 1
print(theta0, theta1, cnt)


def predict(theta0, theta1, x_test):
    return theta0 + theta1 * x_test


print(predict(theta0, theta1, 15))

小批量梯度下降

总结

sklearn线性回归

from sklearn.linear_model import LinearRegression
X = [[4], [8], [5], [10], [12]]
y = [20, 50, 30, 70, 60]
model = LinearRegression()
model.fit(X,y)
print(model.coef_)
print(model.intercept_)
print(model.score(X,y))

from sklearn.linear_model.stochastic_gradient import SGDRegressor
X = [[4], [8], [5], [10], [12]]
y = [20, 50, 30, 70, 60]
model = SGDRegressor(max_iter=10000)
model.fit(X,y)
print(model.coef_)
print(model.intercept_)
print(model.score(X,y))