AdaBoost算法（AdbBoost Algorithm）—有监督学习方法、非概率模型、判别模型、非线性模型、非参数化模型、批量学习

定义

输入:训练数据集 $T=\{ (x_1,y_1),(x_2,y_2),\cdots,(x_N,y_N)\}$ ,其中， $x_i \in \chi\subseteq R^n, y_i \in {\tt y}=\{ -1,+1 \}$ ;弱学习算法;

输出:最终分类器 $G (x) 。$

(1)初始化训练数据的权值分布
$D_1=\big( \omega_{11},\cdots,\omega_{1i},\cdots,\omega_{1N} \big),\omega_{1i}=\frac{1}{N},i=1,2,\cdots,N$
(2)对 $m=1,2,\cdots,M$

(a)使用具有权值分布 $D_m$ 的训练数据集学习，得到基本分类器
$G_m(x): \chi \rightarrow \{ -1,+1 \}$

(b)计算 $G_m(x)$ 在训练数据集上的分类误差率
$e_m=\sum_{i=1}^N P(G_m(x_i) \ne y_i) = \sum_{i=1}^N \omega_{mi}I(G_m(x_i) \ne y_i )$

©计算 $G_m(x)$ 的系数
$\alpha_m = \frac{1}{2} log \frac{1-e_m}{e_m},此处的对数是自然对数$

(d)更新训练数据集的权值分布
$D_{m+1} = ( \omega_{m+1,1},\cdots,\omega_{m+1,i},\cdots,\omega_{m+1,N} )$
$\omega_{m+1,i} = \frac{\omega_{mi}}{Z_m} exp(-\alpha_m y_i G_m(x_i)),i=1,2,\cdots,N$
$其中Z_m是规范化因子, Z_m = \sum_{i=1}^N \omega_{mi} exp(-\alpha_m y_i G_m(x_i)),它使D_{m+1}成为一个概率分布$
(3)构建基本分类器的线性组合
$\sum_{m=1}^M \alpha_m G_m(x)$
      得到最终分类器
$sign\bigg( \sum_{m=1}^M \alpha_m G_m(x) \bigg)$

输入空间

T= $\left\{(x_1,y_1),(x_2,y_2),\dots,(x_N,y_N)\right\}$

import time
import numpy as np

def loadData(fileName):
    '''
    加载Mnist数据集 下载地址：https://download.csdn.net/download/nanxiaotao/89720991）
    :param fileName:要加载的文件路径
    :return: 数据集和标签集
    '''
    #存放数据及标记
    dataArr = []; labelArr = []
    #读取文件
    fr = open(fileName)
    #遍历文件中的每一行
    for line in fr.readlines():
        curLine = line.strip().split(',')
        dataArr.append([int(int(num) > 128) for num in curLine[1:]])
        if int(curLine[0]) == 0:
            labelArr.append(1)
        else:
            labelArr.append(-1)
    #返回数据集和标记
    return dataArr, labelArr

trainDataList, trainLabelList = loadData('../Mnist/mnist_train.csv')

np.shape(trainDataList)

特征空间（Feature Space）

trainDataList[0][0:784]

统计学习方法

模型

$sign\bigg( \sum_{m=1}^M \alpha_m G_m(x) \bigg)$

策略

$\omega_{m+1,i} = \frac{\omega_{mi}}{Z_m} exp(-\alpha_m y_i G_m(x_i)),i=1,2,\cdots,N$
$(\alpha_m , G_m(x)) = arg * \mathop{min}\limits_{\alpha,G}\sum_{i=1}^N exp\bigg[ -y_i ( f_{m-1}(x_i) + \alpha G(x_i)) \bigg],其中 f(x) = \sum_{m=1}^M \alpha_m G_m(x)$

算法

trainDataList = trainDataList[:10000]
trainLabelList = trainLabelList[:10000]
treeNum = 40 #树的层数

$e_m = \sum_{i=1}^N P(G_m(x_i) \neq y_i ) = \sum_{i=1}^N \omega_{mi} I(G_m(x_i) \neq y_i )$

def calc_e_Gx(trainDataArr, trainLabelArr, n, div, rule, D):
    '''
    计算分类错误率
    :param trainDataArr:训练数据集数字
    :param trainLabelArr: 训练标签集数组
    :param n: 要操作的特征
    :param div:划分点
    :param rule:正反例标签
    :param D:权值分布D
    :return:预测结果， 分类误差率
    '''
    #初始化分类误差率为0
    e = 0
    x = trainDataArr[:, n]
    y = trainLabelArr
    predict = []

    if rule == 'LisOne':    L = 1; H = -1
    else:                   L = -1; H = 1

    #遍历所有样本的特征m
    for i in range(trainDataArr.shape[0]):
        if x[i] < div:
            predict.append(L)
            if y[i] != L: e += D[i]
        elif x[i] >= div:
            predict.append(H)
            if y[i] != H: e += D[i]
    return np.array(predict), e

$\alpha_m = \frac{1}{2} log \frac{1-e_m}{e_m}$
$\omega_{m+1,i} = \frac{\omega_{mi}}{Z_m} exp(-\alpha_m y_i G_m(x_i)),i=1,2,\cdots,N$
$D_{m+1} = ( \omega_{m+1,1},\cdots,\omega_{m+1,i},\cdots,\omega_{m+1,N} )$

def createSigleBoostingTree(trainDataArr, trainLabelArr, D):
    '''
    创建单层提升树
    :param trainDataArr:训练数据集数组
    :param trainLabelArr: 训练标签集数组
    :param D: 
    :return: 创建的单层提升树
    '''

    #获得样本数目及特征数量
    m, n = np.shape(trainDataArr)

    sigleBoostTree = {}
    #误差率最高也只能100%，因此初始化为1
    sigleBoostTree['e'] = 1

    #对每一个特征进行遍历，寻找用于划分的最合适的特征
    for i in range(n):
        #因为特征已经经过二值化，只能为0和1，因此分切分时分为-0.5， 0.5， 1.5三挡进行切割
        for div in [-0.5, 0.5, 1.5]:
            for rule in ['LisOne', 'HisOne']:
                #按照第i个特征，以值div进行切割，进行当前设置得到的预测和分类错误率
                Gx, e = calc_e_Gx(trainDataArr, trainLabelArr, i, div, rule, D)
                #如果分类错误率e小于当前最小的e，那么将它作为最小的分类错误率保存
                if e < sigleBoostTree['e']:
                    sigleBoostTree['e'] = e
                    #同时也需要存储最优划分点、划分规则、预测结果、特征索引
                    #以便进行D更新和后续预测使用
                    sigleBoostTree['div'] = div
                    sigleBoostTree['rule'] = rule
                    sigleBoostTree['Gx'] = Gx
                    sigleBoostTree['feature'] = i
    #返回单层的提升树
    return sigleBoostTree

def createBosstingTree(trainDataList, trainLabelList, treeNum = 50):
    '''
    创建提升树
    :param trainDataList:训练数据集
    :param trainLabelList: 训练测试集
    :param treeNum: 树的层数
    :return: 提升树
    '''
    #将数据和标签转化为数组形式
    trainDataArr = np.array(trainDataList)
    trainLabelArr = np.array(trainLabelList)
    #没增加一层数后，当前最终预测结果列表
    finallpredict = [0] * len(trainLabelArr)
    #获得训练集数量以及特征个数
    m, n = np.shape(trainDataArr)
    D = [1 / m] * m
    #初始化提升树列表，每个位置为一层
    tree = []
    #循环创建提升树
    for i in range(treeNum):
        curTree = createSigleBoostingTree(trainDataArr, trainLabelArr, D)
        alpha = 1/2 * np.log((1 - curTree['e']) / curTree['e'])
        Gx = curTree['Gx']
        D = np.multiply(D, np.exp(-1 * alpha * np.multiply(trainLabelArr, Gx))) / sum(D)
        curTree['alpha'] = alpha
        tree.append(curTree)
        finallpredict += alpha * Gx
        error = sum([1 for i in range(len(trainDataList)) if np.sign(finallpredict[i]) != trainLabelArr[i]])
        finallError = error / len(trainDataList)
        if finallError == 0:    return tree
        print('iter:%d:%d, sigle error:%.4f, finall error:%.4f'%(i, treeNum, curTree['e'], finallError ))
    #返回整个提升树
    return tree

tree = createBosstingTree(trainDataList,trainLabelList,treeNum)

假设空间（Hypothesis Space）

$\left\{f|f(x) = sign\bigg( \sum_{m=1}^M \alpha_m G_m(x) \bigg) \right\}$

输出空间

$\in \{ -1,1 \}$

模型评估

训练误差

testDataList, testLabelList = loadData('../Mnist/mnist_test.csv')
testDataList = testDataList[:1000]
testLabelList = testLabelList[:1000]

def predict(x, div, rule, feature):
    '''
    输出单独层预测结果
    :param x: 预测样本
    :param div: 划分点
    :param rule: 划分规则
    :param feature: 进行操作的特征
    :return:
    '''
    #依据划分规则定义小于及大于划分点的标签
    if rule == 'LisOne':    L = 1; H = -1
    else:                   L = -1; H = 1

    #判断预测结果
    if x[feature] < div: return L
    else:   return H

def model_test(testDataList, testLabelList, tree):
    '''
    测试
    :param testDataList:测试数据集
    :param testLabelList: 测试标签集
    :param tree: 提升树
    :return: 准确率
    '''
    #错误率计数值
    errorCnt = 0
    #遍历每一个测试样本
    for i in range(len(testDataList)):
        #预测结果值，初始为0
        result = 0
        #遍历每层的树
        for curTree in tree:
            #获取该层参数
            div = curTree['div']
            rule = curTree['rule']
            feature = curTree['feature']
            alpha = curTree['alpha']
            #将当前层结果加入预测中
            result += alpha * predict(testDataList[i], div, rule, feature)
        #预测结果取sign值，如果大于0 sign为1，反之为0
        if np.sign(result) != testLabelList[i]: errorCnt += 1
    #返回准确率
    return 1 - errorCnt / len(testDataList)

accuracy = model_test(testDataList[:1000], testLabelList[:1000], tree)
print('the accuracy is:%d' % (accuracy * 100), '%')