ml-original-data.py 文件源码

def predict_dt():
    data_with_idx=data_dt.zipWithIndex().map(lambda k,v : (v,k))
    test=data_with_idx.sample(False, 0.2, 42)
    train=data_with_idx.subtractByKey(test)
    test_data=test.map(lambda idx,p:p)
    train_data=train.map(lambda idx,p:p)
    maxDepths=[1,2,3,4,5,10,20]
    maxBins=[2,4,8,16,32,64,100]
    m={}
    for maxDepth in maxDepths:
        for maxBin in maxBins:
            metrics=evaluate_dt(train_data, test_data, maxDepth, maxBin)
            print( "metrics in maxDepth: %d; maxBins: %d" % (maxDepth, maxBin))
            print( metrics)
            m["maxDepth:%d;maxBins:%d" % (maxDepth, maxBin)]=metrics[2]
    mSort=sorted(m.iteritems(), key=operator.itemgetter(1), reverse=True)
    print( mSort)