在python / pyspark中获取k-means质心和异常值

from pyspark.ml.clustering import KMeans
from pyspark.ml.feature import VectorAssembler
from pyspark.sql import SparkSession

spark = SparkSession.builder.appName("KMeansExample").getOrCreate()

data = spark.read.format("csv").option("header", "true").load("data.csv")
assembler = VectorAssembler(inputCols=data.columns, outputCol="features")
data = assembler.transform(data)

kmeans = KMeans(k=3, seed=1)
model = kmeans.fit(data)

centers = model.clusterCenters()

predictions = model.transform(data)
outliers = predictions.filter(predictions["prediction"] == -1)

print("K-means质心:")
for center in centers:
    print(center)

print("异常值:")
outliers.show()