Kmean pyspark'str'对象没有属性'map'

Question

我想运行此代码，但显示“ str对象没有属性“ map””错误：

我不知道如何解决

clusters = KMeans.train(data, K, maxIterations=10, runs=10, initializationMode="random")

C:\opt\spark\spark-2.3.3-bin-hadoop2.6\python\pyspark\mllib\clustering.py 

in train(cls, rdd, k, maxIterations, runs, initializationMode, seed, initializationSteps, epsilon, initialModel) 352 "to be of <type 'KMeansModel'>") 353 clusterInitialModel = [_convert_to_vector(c) for c in initialModel.clusterCenters] --> 354 model = callMLlibFunc("trainKMeansModel", rdd.map(_convert_to_vector), k, maxIterations, 355 runs, initializationMode, seed, initializationSteps, epsilon,