org.apache.spark.examples.ml.MinHashLSHExample.scala Maven / Gradle / Ivy

Go to download

Show more of this group Show more artifacts with this name
Show all versions of snappy-spark-examples_2.11 Show documentation

SnappyData distributed data store and execution engine

There is a newer version: 2.1.3.2

Show newest version

/*
 * Licensed to the Apache Software Foundation (ASF) under one or more
 * contributor license agreements.  See the NOTICE file distributed with
 * this work for additional information regarding copyright ownership.
 * The ASF licenses this file to You under the Apache License, Version 2.0
 * (the "License"); you may not use this file except in compliance with
 * the License.  You may obtain a copy of the License at
 *
 *    http://www.apache.org/licenses/LICENSE-2.0
 *
 * Unless required by applicable law or agreed to in writing, software
 * distributed under the License is distributed on an "AS IS" BASIS,
 * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 * See the License for the specific language governing permissions and
 * limitations under the License.
 */

// scalastyle:off println
package org.apache.spark.examples.ml

// $example on$
import org.apache.spark.ml.feature.MinHashLSH
import org.apache.spark.ml.linalg.Vectors
// $example off$
import org.apache.spark.sql.SparkSession

object MinHashLSHExample {
  def main(args: Array[String]): Unit = {
    // Creates a SparkSession
    val spark = SparkSession
      .builder
      .appName("MinHashLSHExample")
      .getOrCreate()

    // $example on$
    val dfA = spark.createDataFrame(Seq(
      (0, Vectors.sparse(6, Seq((0, 1.0), (1, 1.0), (2, 1.0)))),
      (1, Vectors.sparse(6, Seq((2, 1.0), (3, 1.0), (4, 1.0)))),
      (2, Vectors.sparse(6, Seq((0, 1.0), (2, 1.0), (4, 1.0))))
    )).toDF("id", "keys")

    val dfB = spark.createDataFrame(Seq(
      (3, Vectors.sparse(6, Seq((1, 1.0), (3, 1.0), (5, 1.0)))),
      (4, Vectors.sparse(6, Seq((2, 1.0), (3, 1.0), (5, 1.0)))),
      (5, Vectors.sparse(6, Seq((1, 1.0), (2, 1.0), (4, 1.0))))
    )).toDF("id", "keys")

    val key = Vectors.sparse(6, Seq((1, 1.0), (3, 1.0)))

    val mh = new MinHashLSH()
      .setNumHashTables(3)
      .setInputCol("keys")
      .setOutputCol("values")

    val model = mh.fit(dfA)

    // Feature Transformation
    model.transform(dfA).show()
    // Cache the transformed columns
    val transformedA = model.transform(dfA).cache()
    val transformedB = model.transform(dfB).cache()

    // Approximate similarity join
    model.approxSimilarityJoin(dfA, dfB, 0.6).show()
    model.approxSimilarityJoin(transformedA, transformedB, 0.6).show()
    // Self Join
    model.approxSimilarityJoin(dfA, dfA, 0.6).filter("datasetA.id < datasetB.id").show()

    // Approximate nearest neighbor search
    model.approxNearestNeighbors(dfA, key, 2).show()
    model.approxNearestNeighbors(transformedA, key, 2).show()
    // $example off$

    spark.stop()
  }
}
// scalastyle:on println