用python写单层决策树

好的，以下是用Python实现单层决策树的示例代码：

from numpy import *

def loadSimpData():
    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 stumpClassify(dataMatrix, dimen, threshVal, threshIneq):
    retArray = ones((shape(dataMatrix)[0], 1))
    if threshIneq == 'lt':
        retArray[dataMatrix[:, dimen] <= threshVal] = -1.0
    else:
        retArray[dataMatrix[:, dimen] > threshVal] = -1.0
    return retArray

def buildStump(dataArr, classLabels, D):
    dataMatrix = mat(dataArr)
    labelMat = mat(classLabels).T
    m, n = shape(dataMatrix)
    numSteps = 10.0
    bestStump = {}
    bestClasEst = mat(zeros((m, 1)))
    minError = inf 
    for i in range(n):
        rangeMin = dataMatrix[:, i].min()
        rangeMax = dataMatrix[:, i].max()
        stepSize = (rangeMax - rangeMin) / numSteps
        for j in range(-1, int(numSteps) + 1):
            for inequal in ['lt', 'gt']:
                threshVal = (rangeMin + float(j) * stepSize)
                predictedVals = stumpClassify(dataMatrix, i, threshVal, inequal)
                errArr = mat(ones((m, 1)))
                errArr[predictedVals == labelMat] = 0
                weightedError = D.T * errArr
                if weightedError < minError:
                    minError = weightedError
                    bestClasEst = predictedVals.copy()
                    bestStump['dim'] = i
                    bestStump['thresh'] = threshVal
                    bestStump['ineq'] = inequal
    return bestStump, minError, bestClasEst

def adaBoostTrainDS(dataArr, classLabels, numIt=40):
    weakClassArr = []
    m = shape(dataArr)[0]
    D = mat(ones((m, 1)) / m)
    aggClassEst = mat(zeros((m, 1)))
    for i in range(numIt):
        bestStump, error, classEst = buildStump(dataArr, classLabels, D)
        alpha = float(0.5 * log((1.0 - error) / max(error, 1e-16)))
        bestStump['alpha'] = alpha
        weakClassArr.append(bestStump)
        expon = multiply(-1 * alpha * mat(classLabels).T, classEst)
        D = multiply(D, exp(expon))
        D = D / D.sum()
        aggClassEst += alpha * classEst
        aggErrors = multiply(sign(aggClassEst) != mat(classLabels).T, ones((m, 1)))
        errorRate = aggErrors.sum() / m
        if errorRate == 0.0:
            break
    return weakClassArr

datArr, classLabels = loadSimpData()
classifierArray = adaBoostTrainDS(datArr, classLabels, 9)

print(classifierArray)

以上是一个简单的单层决策树的AdaBoost实现，其模型根据样本数据的特征生成分类阈值，并通过AdaBoost算法不断加强分类器的准确性。具体来说，`stumpClassify()`函数实现了单层决策树的分类过程，而`buildStump()`函数根据样本数据特征选择出最佳的单层决策树分类器及其分类阈值。`adaBoostTrainDS()`函数则使用AdaBoost算法在训练数据上训练多个单层决策树分类器，并将其组合成一个强分类器。最后输出的`classifierArray`为一个包含多个单层决策树分类器及其权重的数组。