相关疑难解决方法(0)

我有以下Python测试代码(ALS.train其他地方定义的参数):

 r1 = (2, 1)
 r2 = (3, 1)
 test = sc.parallelize([r1, r2]) 
 model = ALS.train(ratings, rank, numIter, lmbda)
 predictions = model.predictAll(test)

 print test.take(1)     
 print predictions.count()
 print predictions

哪个有效,因为它对预测变量和输出的计数为1:

[(2, 1)]
1
ParallelCollectionRDD[2691] at parallelize at PythonRDD.scala:423

但是,当我尝试使用RDD我使用以下代码创建自己时,它似乎不再起作用了:

model = ALS.train(ratings, rank, numIter, lmbda)
validation_data = validation.map(lambda xs: tuple(int(x) for x in xs))
predictions = model.predictAll(validation_data)

print validation_data.take(1)
print predictions.count()
print validation_data

哪个输出:

[(61, 3864)]
0
PythonRDD[4018] at RDD at PythonRDD.scala:43

如您所见,predictAll传递映射后返回空RDD.进入的值都是相同的格式.我能看到的唯一明显的区别是第一个例子使用parallelize并产生一个 …

我在 Spark（推荐系统算法）中使用 ALS 算法（implicitPrefs = True）。通常，运行此算法后，预测值必须从 0 到 1。但我收到的值大于 1

    "usn" : 72164,
    "recommendations" : [ 
        {
            "item_code" : "C1346",
            "rating" : 0.756096363067627
        }, 
        {
            "item_code" : "C0117",
            "rating" : 0.966064214706421
        }, 
        {
            "item_code" : "I0009",
            "rating" : 1.00000607967377
        }, 
        {
            "item_code" : "C0102",
            "rating" : 0.974934458732605
        }, 
        {
            "item_code" : "I0853",
            "rating" : 1.03272235393524
        }, 
        {
            "item_code" : "C0103",
            "rating" : 0.928574025630951
        }
    ]