Python实现adaboost 算法+简单的注释

from numpy import  *

def loadSimpData():
    datMat = matrix([[1., 2.1],
                     [2., 1.1],
                     [1.3, 1.],
                     [1.1, 1.1],
                     [2., 1.]
                     ])
    classLabels = [1.0, 1.0, -1.0, -1.0, 1.0]
    return datMat, classLabels


def stumpClassify(dataMatrix, dimen, threshVal, threshIneq):  # 单层决策树模型
    retArray = ones((shape(dataMatrix)[0], 1))
    if threshIneq == 'lt':    # 若threshVal == 'lt' 并且dataMatirx <= threshVal 则 labels 改为 -1
        retArray[dataMatrix[:, dimen] <= threshVal] = -1.0
    else:
        retArray[dataMatrix[:, dimen] > threshVal] = -1.0
    return retArray


def buildStump(dataArr, classLabels, D):  # 遍历所有的数据，通过单层决策数对其进行分类
    dataMatrix = mat(dataArr)
    labelMat = mat(classLabels).T
    m,n  = shape(dataMatrix)
    numSteps = 10.0; bestStump = {}; bestClasEst = mat(zeros((m, 1