LinearRegression--python

本系列所有代码实现均参考https://github.com/lawlite19/MachineLearning_Python

import numpy as np
from matplotlib import pyplot as plt
# 线性回归
# X是矩阵，每一行是一组输入数据；theta是列向量；y也是列向量
def ComputeCost(X, y, theta):
    m = len(y)
    J = 0
    t = np.dot(X, theta)-y
    J = np.dot(t.T, t)/(2*m)
    return J

# 计算代价函数
# alpaa是学习率；num_iters是迭代次数
def GradientDescent(X, y, theta, alpha, num_iters):
    m = len(y)
    n = len(theta)
    temp = np.matrix(np.zeros((n, num_iters)))   # 暂存每次迭代计算的theta，转化为矩阵形式
    J_history = np.zeros((num_iters, 1))  # 记录每次迭代计算的代价值

    for i in range(num_iters):  # 遍历迭代次数
        h = np.dot(X, theta)     # 计算内积，matrix可以直接乘
        temp[:, i] = theta-((alpha/m)*(np.dot(X.T, h-y)))  # 梯度的计算
        theta = temp[:, i]
        J_history[i] = ComputeCost(X, y, theta)  # 调用计算代价函数
        # print(J_history[i])
    return theta, J_history

def featureNormaliza(X):
    X_norm = np.array(X)  # 将X转化为numpy数组对象，才可以进行矩阵的运算
    # 定义所需变量
    mu = np.zeros((1, X.shape[1]))
    sigma = np.zeros((1, X.shape[1]))
    mu = np.mean(X_norm, 0)          # 求每一列的平均值（0指定为列，1代表行）
    sigma = np.std(X_norm, 0)        # 求每一列的标准差
    for i in range(X.shape[1]):     # 遍历列
        X_norm[:, i] = (X_norm[:, i]-mu[i])/sigma[i]  # 归一化
    return X_norm, mu, sigma

# 逻辑回归
if __name__ == "__main__":
    alpha = 0.01
    num_iters = 400

    # 取消归一化需要的参数
    #alpha = 0.0000001
    #num_iters = 4000

    data = np.loadtxt('data.txt', delimiter=',', dtype=np.float64)
    X = data[:, 0:-1]
    y = data[:, -1].reshape(-1, 1)
    X, mu, s = featureNormaliza(X)
    #plt.scatter(X_norm[:, 0], X_norm[:, 1])
    # plt.show()
    X = np.hstack((np.ones((X.shape[0], 1)), X))
    theta = np.zeros((X.shape[1], 1))
    theta, J_history = GradientDescent(X, y, theta, alpha, num_iters)

    x = np.arange(1, num_iters+1)
    plt.plot(x, J_history)
    plt.show()

虽然算法理解起来不算很难，等到了自己动手是实现的时候还是有很多问题的。