クラスタリング - RDDベースのAPI

import org.apache.spark.mllib.clustering.{KMeans, KMeansModel}
import org.apache.spark.mllib.linalg.Vectors

// Load and parse the data
val data = sc.textFile("data/mllib/kmeans_data.txt")
val parsedData = data.map(s => Vectors.dense(s.split(' ').map(_.toDouble))).cache()

// Cluster the data into two classes using KMeans
val numClusters = 2
val numIterations = 20
val clusters = KMeans.train(parsedData, numClusters, numIterations)

// Evaluate clustering by computing Within Set Sum of Squared Errors
val WSSSE = clusters.computeCost(parsedData)
println("Within Set Sum of Squared Errors = " + WSSSE)

// Save and load model
clusters.save(sc, "target/org/apache/spark/KMeansExample/KMeansModel")
val sameModel = KMeansModel.load(sc, "target/org/apache/spark/KMeansExample/KMeansModel")

import org.apache.spark.api.java.JavaRDD;
import org.apache.spark.api.java.function.Function;
import org.apache.spark.mllib.clustering.KMeans;
import org.apache.spark.mllib.clustering.KMeansModel;
import org.apache.spark.mllib.linalg.Vector;
import org.apache.spark.mllib.linalg.Vectors;

// Load and parse data
String path = "data/mllib/kmeans_data.txt";
JavaRDD<String> data = jsc.textFile(path);
JavaRDD<Vector> parsedData = data.map(
  new Function<String, Vector>() {
    public Vector call(String s) {
      String[] sarray = s.split(" ");
      double[] values = new double[sarray.length];
      for (int i = 0; i < sarray.length; i++) {
        values[i] = Double.parseDouble(sarray[i]);
      }
      return Vectors.dense(values);
    }
  }
);
parsedData.cache();

// Cluster the data into two classes using KMeans
int numClusters = 2;
int numIterations = 20;
KMeansModel clusters = KMeans.train(parsedData.rdd(), numClusters, numIterations);

System.out.println("Cluster centers:");
for (Vector center: clusters.clusterCenters()) {
  System.out.println(" " + center);
}
double cost = clusters.computeCost(parsedData.rdd());
System.out.println("Cost: " + cost);

// Evaluate clustering by computing Within Set Sum of Squared Errors
double WSSSE = clusters.computeCost(parsedData.rdd());
System.out.println("Within Set Sum of Squared Errors = " + WSSSE);

// Save and load model
clusters.save(jsc.sc(), "target/org/apache/spark/JavaKMeansExample/KMeansModel");
KMeansModel sameModel = KMeansModel.load(jsc.sc(),
  "target/org/apache/spark/JavaKMeansExample/KMeansModel");

from numpy import array
from math import sqrt

from pyspark.mllib.clustering import KMeans, KMeansModel

# Load and parse the data
data = sc.textFile("data/mllib/kmeans_data.txt")
parsedData = data.map(lambda line: array([float(x) for x in line.split(' ')]))

# Build the model (cluster the data)
clusters = KMeans.train(parsedData, 2, maxIterations=10, initializationMode="random")

# Evaluate clustering by computing Within Set Sum of Squared Errors
def error(point):
    center = clusters.centers[clusters.predict(point)]
    return sqrt(sum([x**2 for x in (point - center)]))

WSSSE = parsedData.map(lambda point: error(point)).reduce(lambda x, y: x + y)
print("Within Set Sum of Squared Error = " + str(WSSSE))

# Save and load model
clusters.save(sc, "target/org/apache/spark/PythonKMeansExample/KMeansModel")
sameModel = KMeansModel.load(sc, "target/org/apache/spark/PythonKMeansExample/KMeansModel")

import org.apache.spark.mllib.clustering.{GaussianMixture, GaussianMixtureModel}
import org.apache.spark.mllib.linalg.Vectors

// Load and parse the data
val data = sc.textFile("data/mllib/gmm_data.txt")
val parsedData = data.map(s => Vectors.dense(s.trim.split(' ').map(_.toDouble))).cache()

// Cluster the data into two classes using GaussianMixture
val gmm = new GaussianMixture().setK(2).run(parsedData)

// Save and load model
gmm.save(sc, "target/org/apache/spark/GaussianMixtureExample/GaussianMixtureModel")
val sameModel = GaussianMixtureModel.load(sc,
  "target/org/apache/spark/GaussianMixtureExample/GaussianMixtureModel")

// output parameters of max-likelihood model
for (i <- 0 until gmm.k) {
  println("weight=%f\nmu=%s\nsigma=\n%s\n" format
    (gmm.weights(i), gmm.gaussians(i).mu, gmm.gaussians(i).sigma))
}

import org.apache.spark.api.java.JavaRDD;
import org.apache.spark.api.java.function.Function;
import org.apache.spark.mllib.clustering.GaussianMixture;
import org.apache.spark.mllib.clustering.GaussianMixtureModel;
import org.apache.spark.mllib.linalg.Vector;
import org.apache.spark.mllib.linalg.Vectors;

// Load and parse data
String path = "data/mllib/gmm_data.txt";
JavaRDD<String> data = jsc.textFile(path);
JavaRDD<Vector> parsedData = data.map(
  new Function<String, Vector>() {
    public Vector call(String s) {
      String[] sarray = s.trim().split(" ");
      double[] values = new double[sarray.length];
      for (int i = 0; i < sarray.length; i++) {
        values[i] = Double.parseDouble(sarray[i]);
      }
      return Vectors.dense(values);
    }
  }
);
parsedData.cache();

// Cluster the data into two classes using GaussianMixture
GaussianMixtureModel gmm = new GaussianMixture().setK(2).run(parsedData.rdd());

// Save and load GaussianMixtureModel
gmm.save(jsc.sc(), "target/org/apache/spark/JavaGaussianMixtureExample/GaussianMixtureModel");
GaussianMixtureModel sameModel = GaussianMixtureModel.load(jsc.sc(),
  "target/org.apache.spark.JavaGaussianMixtureExample/GaussianMixtureModel");

// Output the parameters of the mixture model
for (int j = 0; j < gmm.k(); j++) {
  System.out.printf("weight=%f\nmu=%s\nsigma=\n%s\n",
    gmm.weights()[j], gmm.gaussians()[j].mu(), gmm.gaussians()[j].sigma());
}

from numpy import array

from pyspark.mllib.clustering import GaussianMixture, GaussianMixtureModel

# Load and parse the data
data = sc.textFile("data/mllib/gmm_data.txt")
parsedData = data.map(lambda line: array([float(x) for x in line.strip().split(' ')]))

# Build the model (cluster the data)
gmm = GaussianMixture.train(parsedData, 2)

# Save and load model
gmm.save(sc, "target/org/apache/spark/PythonGaussianMixtureExample/GaussianMixtureModel")
sameModel = GaussianMixtureModel\
    .load(sc, "target/org/apache/spark/PythonGaussianMixtureExample/GaussianMixtureModel")

# output parameters of model
for i in range(2):
    print("weight = ", gmm.weights[i], "mu = ", gmm.gaussians[i].mu,
          "sigma = ", gmm.gaussians[i].sigma.toArray())

import org.apache.spark.mllib.clustering.PowerIterationClustering

val circlesRdd = generateCirclesRdd(sc, params.k, params.numPoints)
val model = new PowerIterationClustering()
  .setK(params.k)
  .setMaxIterations(params.maxIterations)
  .setInitializationMode("degree")
  .run(circlesRdd)

val clusters = model.assignments.collect().groupBy(_.cluster).mapValues(_.map(_.id))
val assignments = clusters.toList.sortBy { case (k, v) => v.length }
val assignmentsStr = assignments
  .map { case (k, v) =>
    s"$k -> ${v.sorted.mkString("[", ",", "]")}"
  }.mkString(", ")
val sizesStr = assignments.map {
  _._2.length
}.sorted.mkString("(", ",", ")")
println(s"Cluster assignments: $assignmentsStr\ncluster sizes: $sizesStr")

import org.apache.spark.mllib.clustering.PowerIterationClustering;
import org.apache.spark.mllib.clustering.PowerIterationClusteringModel;

JavaRDD<Tuple3<Long, Long, Double>> similarities = sc.parallelize(Lists.newArrayList(
  new Tuple3<>(0L, 1L, 0.9),
  new Tuple3<>(1L, 2L, 0.9),
  new Tuple3<>(2L, 3L, 0.9),
  new Tuple3<>(3L, 4L, 0.1),
  new Tuple3<>(4L, 5L, 0.9)));

PowerIterationClustering pic = new PowerIterationClustering()
  .setK(2)
  .setMaxIterations(10);
PowerIterationClusteringModel model = pic.run(similarities);

for (PowerIterationClustering.Assignment a: model.assignments().toJavaRDD().collect()) {
  System.out.println(a.id() + " -> " + a.cluster());
}

from pyspark.mllib.clustering import PowerIterationClustering, PowerIterationClusteringModel

# Load and parse the data
data = sc.textFile("data/mllib/pic_data.txt")
similarities = data.map(lambda line: tuple([float(x) for x in line.split(' ')]))

# Cluster the data into two classes using PowerIterationClustering
model = PowerIterationClustering.train(similarities, 2, 10)

model.assignments().foreach(lambda x: print(str(x.id) + " -> " + str(x.cluster)))

# Save and load model
model.save(sc, "target/org/apache/spark/PythonPowerIterationClusteringExample/PICModel")
sameModel = PowerIterationClusteringModel\
    .load(sc, "target/org/apache/spark/PythonPowerIterationClusteringExample/PICModel")

import org.apache.spark.mllib.clustering.{DistributedLDAModel, LDA}
import org.apache.spark.mllib.linalg.Vectors

// Load and parse the data
val data = sc.textFile("data/mllib/sample_lda_data.txt")
val parsedData = data.map(s => Vectors.dense(s.trim.split(' ').map(_.toDouble)))
// Index documents with unique IDs
val corpus = parsedData.zipWithIndex.map(_.swap).cache()

// Cluster the documents into three topics using LDA
val ldaModel = new LDA().setK(3).run(corpus)

// Output topics. Each is a distribution over words (matching word count vectors)
println("Learned topics (as distributions over vocab of " + ldaModel.vocabSize + " words):")
val topics = ldaModel.topicsMatrix
for (topic <- Range(0, 3)) {
  print("Topic " + topic + ":")
  for (word <- Range(0, ldaModel.vocabSize)) { print(" " + topics(word, topic)); }
  println()
}

// Save and load model.
ldaModel.save(sc, "target/org/apache/spark/LatentDirichletAllocationExample/LDAModel")
val sameModel = DistributedLDAModel.load(sc,
  "target/org/apache/spark/LatentDirichletAllocationExample/LDAModel")

import scala.Tuple2;

import org.apache.spark.api.java.JavaPairRDD;
import org.apache.spark.api.java.JavaRDD;
import org.apache.spark.api.java.function.Function;
import org.apache.spark.mllib.clustering.DistributedLDAModel;
import org.apache.spark.mllib.clustering.LDA;
import org.apache.spark.mllib.clustering.LDAModel;
import org.apache.spark.mllib.linalg.Matrix;
import org.apache.spark.mllib.linalg.Vector;
import org.apache.spark.mllib.linalg.Vectors;

// Load and parse the data
String path = "data/mllib/sample_lda_data.txt";
JavaRDD<String> data = jsc.textFile(path);
JavaRDD<Vector> parsedData = data.map(
  new Function<String, Vector>() {
    public Vector call(String s) {
      String[] sarray = s.trim().split(" ");
      double[] values = new double[sarray.length];
      for (int i = 0; i < sarray.length; i++) {
        values[i] = Double.parseDouble(sarray[i]);
      }
      return Vectors.dense(values);
    }
  }
);
// Index documents with unique IDs
JavaPairRDD<Long, Vector> corpus =
  JavaPairRDD.fromJavaRDD(parsedData.zipWithIndex().map(
    new Function<Tuple2<Vector, Long>, Tuple2<Long, Vector>>() {
      public Tuple2<Long, Vector> call(Tuple2<Vector, Long> doc_id) {
        return doc_id.swap();
      }
    }
  )
);
corpus.cache();

// Cluster the documents into three topics using LDA
LDAModel ldaModel = new LDA().setK(3).run(corpus);

// Output topics. Each is a distribution over words (matching word count vectors)
System.out.println("Learned topics (as distributions over vocab of " + ldaModel.vocabSize()
  + " words):");
Matrix topics = ldaModel.topicsMatrix();
for (int topic = 0; topic < 3; topic++) {
  System.out.print("Topic " + topic + ":");
  for (int word = 0; word < ldaModel.vocabSize(); word++) {
    System.out.print(" " + topics.apply(word, topic));
  }
  System.out.println();
}

ldaModel.save(jsc.sc(),
  "target/org/apache/spark/JavaLatentDirichletAllocationExample/LDAModel");
DistributedLDAModel sameModel = DistributedLDAModel.load(jsc.sc(),
  "target/org/apache/spark/JavaLatentDirichletAllocationExample/LDAModel");

from pyspark.mllib.clustering import LDA, LDAModel
from pyspark.mllib.linalg import Vectors

# Load and parse the data
data = sc.textFile("data/mllib/sample_lda_data.txt")
parsedData = data.map(lambda line: Vectors.dense([float(x) for x in line.strip().split(' ')]))
# Index documents with unique IDs
corpus = parsedData.zipWithIndex().map(lambda x: [x[1], x[0]]).cache()

# Cluster the documents into three topics using LDA
ldaModel = LDA.train(corpus, k=3)

# Output topics. Each is a distribution over words (matching word count vectors)
print("Learned topics (as distributions over vocab of " + str(ldaModel.vocabSize())
      + " words):")
topics = ldaModel.topicsMatrix()
for topic in range(3):
    print("Topic " + str(topic) + ":")
    for word in range(0, ldaModel.vocabSize()):
        print(" " + str(topics[word][topic]))

# Save and load model
ldaModel.save(sc, "target/org/apache/spark/PythonLatentDirichletAllocationExample/LDAModel")
sameModel = LDAModel\
    .load(sc, "target/org/apache/spark/PythonLatentDirichletAllocationExample/LDAModel")

import org.apache.spark.mllib.clustering.BisectingKMeans
import org.apache.spark.mllib.linalg.{Vector, Vectors}

// Loads and parses data
def parse(line: String): Vector = Vectors.dense(line.split(" ").map(_.toDouble))
val data = sc.textFile("data/mllib/kmeans_data.txt").map(parse).cache()

// Clustering the data into 6 clusters by BisectingKMeans.
val bkm = new BisectingKMeans().setK(6)
val model = bkm.run(data)

// Show the compute cost and the cluster centers
println(s"Compute Cost: ${model.computeCost(data)}")
model.clusterCenters.zipWithIndex.foreach { case (center, idx) =>
  println(s"Cluster Center ${idx}: ${center}")
}

import com.google.common.collect.Lists;

import org.apache.spark.api.java.JavaRDD;
import org.apache.spark.mllib.clustering.BisectingKMeans;
import org.apache.spark.mllib.clustering.BisectingKMeansModel;
import org.apache.spark.mllib.linalg.Vector;
import org.apache.spark.mllib.linalg.Vectors;

ArrayList<Vector> localData = Lists.newArrayList(
  Vectors.dense(0.1, 0.1),   Vectors.dense(0.3, 0.3),
  Vectors.dense(10.1, 10.1), Vectors.dense(10.3, 10.3),
  Vectors.dense(20.1, 20.1), Vectors.dense(20.3, 20.3),
  Vectors.dense(30.1, 30.1), Vectors.dense(30.3, 30.3)
);
JavaRDD<Vector> data = sc.parallelize(localData, 2);

BisectingKMeans bkm = new BisectingKMeans()
  .setK(4);
BisectingKMeansModel model = bkm.run(data);

System.out.println("Compute Cost: " + model.computeCost(data));

Vector[] clusterCenters = model.clusterCenters();
for (int i = 0; i < clusterCenters.length; i++) {
  Vector clusterCenter = clusterCenters[i];
  System.out.println("Cluster Center " + i + ": " + clusterCenter);
}

from numpy import array

from pyspark.mllib.clustering import BisectingKMeans, BisectingKMeansModel

# Load and parse the data
data = sc.textFile("data/mllib/kmeans_data.txt")
parsedData = data.map(lambda line: array([float(x) for x in line.split(' ')]))

# Build the model (cluster the data)
model = BisectingKMeans.train(parsedData, 2, maxIterations=5)

# Evaluate clustering
cost = model.computeCost(parsedData)
print("Bisecting K-means Cost = " + str(cost))

# Save and load model
path = "target/org/apache/spark/PythonBisectingKMeansExample/BisectingKMeansModel"
model.save(sc, path)
sameModel = BisectingKMeansModel.load(sc, path)

import org.apache.spark.mllib.clustering.StreamingKMeans
import org.apache.spark.mllib.linalg.Vectors
import org.apache.spark.mllib.regression.LabeledPoint
import org.apache.spark.streaming.{Seconds, StreamingContext}

val conf = new SparkConf().setAppName("StreamingKMeansExample")
val ssc = new StreamingContext(conf, Seconds(args(2).toLong))

val trainingData = ssc.textFileStream(args(0)).map(Vectors.parse)
val testData = ssc.textFileStream(args(1)).map(LabeledPoint.parse)

val model = new StreamingKMeans()
  .setK(args(3).toInt)
  .setDecayFactor(1.0)
  .setRandomCenters(args(4).toInt, 0.0)

model.trainOn(trainingData)
model.predictOnValues(testData.map(lp => (lp.label, lp.features))).print()

ssc.start()
ssc.awaitTermination()

from pyspark.mllib.linalg import Vectors
from pyspark.mllib.regression import LabeledPoint
from pyspark.mllib.clustering import StreamingKMeans

# we make an input stream of vectors for training,
# as well as a stream of vectors for testing
def parse(lp):
    label = float(lp[lp.find('(') + 1: lp.find(')')])
    vec = Vectors.dense(lp[lp.find('[') + 1: lp.find(']')].split(','))

    return LabeledPoint(label, vec)

trainingData = sc.textFile("data/mllib/kmeans_data.txt")\
    .map(lambda line: Vectors.dense([float(x) for x in line.strip().split(' ')]))

testingData = sc.textFile("data/mllib/streaming_kmeans_data_test.txt").map(parse)

trainingQueue = [trainingData]
testingQueue = [testingData]

trainingStream = ssc.queueStream(trainingQueue)
testingStream = ssc.queueStream(testingQueue)

# We create a model with random clusters and specify the number of clusters to find
model = StreamingKMeans(k=2, decayFactor=1.0).setRandomCenters(3, 1.0, 0)

# Now register the streams for training and testing and start the job,
# printing the predicted cluster assignments on new data points as they arrive.
model.trainOn(trainingStream)

result = model.predictOnValues(testingStream.map(lambda lp: (lp.label, lp.features)))
result.pprint()

ssc.start()
ssc.stop(stopSparkContext=True, stopGraceFully=True)