PySpark：属性错误：“管道模型”对象没有属性“群集中心”

Question

我用Pypsark创建了一个kmeans算法。现在，我还想提取集群中心。如何将其包含在管道中？这是我到目前为止拥有的代码，但它给我带来了一个错误“AttributeError：'PipelineModel'对象没有属性'clusterCenters'。如何修复？#### model K-Means ###from pyspark.ml.clustering import KMeans, KMeansModelkmeans = KMeans() \          .setK(3) \          .setFeaturesCol("scaledFeatures")\          .setPredictionCol("cluster")# Chain indexer and tree in a Pipelinepipeline = Pipeline(stages=[kmeans])model = pipeline.fit(matrix_normalized)cluster = model.transform(matrix_normalized)#get cluster centerscenters = model.clusterCenters()

Answer 1

虚拟数据

from pyspark.ml.linalg import Vectors

from pyspark.ml.clustering import KMeans, KMeansModel

from pyspark.ml.pipeline import Pipeline

data = [(Vectors.dense([0.0, 0.0]),), (Vectors.dense([1.0, 1.0]),),

        (Vectors.dense([9.0, 8.0]),), (Vectors.dense([8.0, 9.0]),)]

matrix_normalized = spark.createDataFrame(data, ["scaledFeatures"])

您的代码

kmeans = KMeans() \

          .setK(3) \

          .setFeaturesCol("scaledFeatures")\

          .setPredictionCol("cluster")

# Chain indexer and tree in a Pipeline

pipeline = Pipeline(stages=[kmeans])

model = pipeline.fit(matrix_normalized)

cluster = model.transform(matrix_normalized)

只需更改最后一行

model.stages[0].clusterCenters()

[array([0.5, 0.5]), array([8., 9.]), array([9., 8.])]