逻辑回归python代码实现 迪哥

逻辑回归是一种机器学习算法，常用于二分类问题。下面是一个逻辑回归的Python代码实现的例子：

import numpy as np
import pandas as pd

# Sigmoid函数，用于将预测结果转化为概率值
def sigmoid(z):
    return 1 / (1 + np.exp(-z))
# 损失函数，用于评估模型的准确性
def cost(theta, X, y):
    theta = np.matrix(theta)
    X = np.matrix(X)
    y = np.matrix(y)
    first = np.multiply(-y, np.log(sigmoid(X * theta.T)))
    second = np.multiply((1-y), np.log(1 - sigmoid(X * theta.T)))
    return np.sum(first - second) / len(X)

# 梯度下降算法，用于最小化损失函数，得到最优参数
def gradientDescent(X, y, theta, alpha, iters):
    temp = np.matrix(np.zeros(theta.shape))
    parameters = int(theta.ravel().shape[1])
    cost = np.zeros(iters)
    
    for i in range(iters):
        error = sigmoid(X * theta.T) - y
        for j in range(parameters):
            term = np.multiply(error, X[:,j])
            temp[0,j] = theta[0,j] - (alpha / len(X)) * np.sum(term)
        theta = temp
        cost[i] = cost(theta, X, y)
        
    return theta, cost

# 读取数据
data = pd.read_csv('data.csv')

# 添加一列全为1的特征列
data.insert(0, 'Ones', 1)

# 将数据转化为矩阵
cols = data.shape[1]
X = data.iloc[:,0:cols-1]
y = data.iloc[:,cols-1:cols]
X = np.matrix(X.values)
y = np.matrix(y.values)
theta = np.zeros([1,3])

# 设置学习率和迭代次数
alpha = 0.01
iters = 1000

# 执行梯度下降算法，得到最优参数
theta, cost = gradientDescent(X, y, theta, alpha, iters)

# 输出最优参数和损失函数值
print("最优参数：", theta)
print("损失函数值：", cost[-1])