机器学习 AdaBoost算法

AdaBoost算法

算法原理

数学原理

#!/usr/bin/env python
# encoding: utf-8

from __future__ import print_function
from numpy import *
import matplotlib.pyplot as plt


def loadSimData():
    '''
        加载数据集
    :return:
        dataMat :数据集
        labelMat : 标签集
    '''
    datMat = matrix([[1., 2.1],
                     [2., 1.1],
                     [1.3, 1.],
                     [1., 1.],
                     [2., 1.]])
    classLabels = [1.0, 1.0, -1.0, -1.0, 1.0]
    return datMat, classLabels

def loadDataSet(fileName):
    # get number of fields
    numFeat = len(open(fileName).readline().split('\t'))
    dataArr = []
    labelArr = []
    fr = open(fileName)
    for line in fr.readlines():
        lineArr = []
        curLine = line.strip().split('\t')
        for i in range(numFeat-1):
            lineArr.append(float(curLine[i]))
        dataArr.append(lineArr)
        labelArr.append(float(curLine[-1]))
    return dataArr, labelArr


def stumpClassify(dataMatrix, dimen, threshVal, threshIneq):
    '''

    :param dataMatrix:
    :param dimen: 维数
    :param threshVal: 比较值
    :param threshIneq:  表示比较大小符号
    :return:
        retArray 结果集
    '''
    # 形成一个m*1的向量
    retArray = ones((shape(dataMatrix)[0], 1