KMeans聚类算法

from pyspark.ml.clustering import KMeans, KMeansModel

from pyspark import SparkContext

from pyspark.sql import SparkSession, Row

from pyspark.ml.linalg import Vector, Vectors

sc = SparkContext('local','KMeans聚类算法')

spark = SparkSession.builder.master('local').appName('KMeans聚类算法').getOrCreate()

def f(x):

rel={}

rel['features'] = Vectors.dense(float(x[0]), float(x[1]), float(x[2]), float(x[3]))

return rel

df = sc.textFile("file:///usr/local/spark/mycode/exercise/iris.txt").map(lambda line: line.split(",")).map(lambda p: Row(**f(p))).toDF()

kmeansmodel = KMeans().setFeaturesCol('features').setPredictionCol('prediction').fit(df)

results = kmeansmodel.transform(df).collect()

# for item in results:

# print(str(item[0])+' is predcted as cluster'+ str(item[1]))

results2 = kmeansmodel.clusterCenters()

# for item in results2:

# print(item)

kemdata=kmeansmodel.computeCost(df)

print(kemdata)