cross validation:交叉验证

dev数据集是用来做交叉验证的，为了评估不同算法的表现
而测试数据集是为了计算所选算法的正确度的

def crossValidation(xArr,yArr,numVal = 10):
    """numVal：交叉验证的次数"""
    m = len(yArr)
    indexList = range(m)
    errorMat = np.zeros((numVal,30))
    for i in range(numVal):
        trainX = []
        trainY = []
        testX = []
        testY = []
        random.shuffle(indexList)   #实现训练和测试数据的随机抽取
        #分为训练集和测试集
        for j in range(m):
            if j < m*0.9:
                trainX.append(xArr[indexList[j]])
                trainY.append(yArr[indexList[j]])
            else:
                testX.append(xArr[indexList[j]])
                testY.append(yArr[indexList[j]])
        wMat = ridgeTest(trainX,trainY)
        for k in range(30):
            #用训练时的参数将测试数据标准化
            matTestX = np.mat(testX)
            matTrainX = np.mat(trainX)
            meanTrain = np.mean(matTrainX,0)
            varTrain = np.var(matTrainX,0)
            matTestX = (matTestX - meanTrain)/varTrain
            yEst = matTestX*np.mat(wMat[k,:]).T+np.mean(trainY)
            errorMat[i,k] = rssError(yEst.T.A,np.array(testY))
    meanErrors = np.mean(errorMat,0)
    minMean = float(min(meanErrors))
    bestWeights = wMat[np.nonzero(meanErrors==minMean)]
    print("the best regression params :",bestWeights)
    xMat = np.mat(xArr)
    yMat = np.mat(yArr).T
    meanX = np.mean(xMat,0)
    varX = np.var(xMat,0)
    #数据还原-便于与其他的算法模型拟合结果进行比较
    unReg = bestWeights/varX
    print('the best model from Ridge Regression is:\n',unReg)
    print('with constant term',-1*sum(np.multiply(meanX,unReg))+np.mean(yMat))