决策树 cart

区别在于cart采用基尼系数。

def CART_chooseBestFeatureToSplit(dataset):

    numFeatures = len(dataset[0]) - 1
    bestGini = 999999.0
    bestFeature = -1
    for i in range(numFeatures):
        featList = [example[i] for example in dataset]
        uniqueVals = set(featList)
        gini = 0.0
        for value in uniqueVals:
            subdataset=splitdataset(dataset,i,value)
            p=len(subdataset)/float(len(dataset))
            subp = len(splitdataset(subdataset, -1, '0')) / float(len(subdataset))
        gini += p * (1.0 - pow(subp, 2) - pow(1 - subp, 2))
        print(u"CART中第%d个特征的基尼值为：%.3f"%(i,gini))
        if (gini < bestGini):
            bestGini = gini
            bestFeature = i
    return bestFeature