机器学习算法之Logistic Regression算法实现

最新推荐文章于 2025-06-30 10:16:26 发布

原创

最新推荐文章于 2025-06-30 10:16:26 发布 · 1.9k 阅读

0 ·

CC 4.0 BY-SA版权

文章标签：

#机器学习 #逻辑回归

本文介绍了Logistic Regression算法的实现过程，参考了zouxy09的专栏，通过改进的随机梯度下降进行训练，最终得出分类结果。在数据挖掘的道路上，作者鼓励继续努力。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

该代码基本上参考了zouxy09的专栏中的逻辑回归代码，他对于ML一些经典的算法都写得很不错，读后受益匪浅。

直接上代码：

#-*- coding:utf8 -*-

'''
逻辑回归1.0
Author:Stephen
2016.10.6
'''

from numpy import *
import matplotlib.pyplot as plt
import time

def sigmoid(inX):
    return 1.0 / (1 + exp(-inX))

# input: train_x is a mat datatype, each row stands for one sample
#        train_y is mat datatype too, each row is the corresponding label
#        opts is optimize option include step and maximum number of iterations
def trainLogRegres(train_x, train_y, opts):
    '训练逻辑分类器'
    startTime = time.time()  # calculate training time

    numSamples, numFeatures = shape(train_x)
    weights = ones((numFeatures, 1))

    alpha = opts['alpha']
    maxIter = opts['maxIter']

    # optimize through gradient descent algorilthm
    for k in range(maxIter):
        if opts['optimizeType'] == 'GradDescent':  # 梯度下降   梯度上升算法计算最佳回归系数
            output = sigmoid(train_x * weights)
            error = train_y - output
            weights = weights + alpha * train_x.transpose() * error
        elif opts['optimizeType'] == 'StoGradDescent':  # 随机梯度下降
            for i in range(numSamples):
                output = sigmoid(train_x[i, :] * weights)
                error = train_y[i