org.apache.spark.examples.ml.JavaMinHashLSHExample 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.
 */

package org.apache.spark.examples.ml;

import org.apache.spark.sql.SparkSession;

// $example on$
import java.util.Arrays;
import java.util.List;

import org.apache.spark.ml.feature.MinHashLSH;
import org.apache.spark.ml.feature.MinHashLSHModel;
import org.apache.spark.ml.linalg.VectorUDT;
import org.apache.spark.ml.linalg.Vectors;
import org.apache.spark.sql.Dataset;
import org.apache.spark.sql.Row;
import org.apache.spark.sql.RowFactory;
import org.apache.spark.sql.types.DataTypes;
import org.apache.spark.sql.types.Metadata;
import org.apache.spark.sql.types.StructField;
import org.apache.spark.sql.types.StructType;
// $example off$

public class JavaMinHashLSHExample {
  public static void main(String[] args) {
    SparkSession spark = SparkSession
      .builder()
      .appName("JavaMinHashLSHExample")
      .getOrCreate();

    // $example on$
    List data = Arrays.asList(
      RowFactory.create(0, Vectors.sparse(6, new int[]{0, 1, 2}, new double[]{1.0, 1.0, 1.0})),
      RowFactory.create(1, Vectors.sparse(6, new int[]{2, 3, 4}, new double[]{1.0, 1.0, 1.0})),
      RowFactory.create(2, Vectors.sparse(6, new int[]{0, 2, 4}, new double[]{1.0, 1.0, 1.0}))
    );

    StructType schema = new StructType(new StructField[]{
      new StructField("id", DataTypes.IntegerType, false, Metadata.empty()),
      new StructField("keys", new VectorUDT(), false, Metadata.empty())
    });
    Dataset dataFrame = spark.createDataFrame(data, schema);

    MinHashLSH mh = new MinHashLSH()
      .setNumHashTables(1)
      .setInputCol("keys")
      .setOutputCol("values");

    MinHashLSHModel model = mh.fit(dataFrame);
    model.transform(dataFrame).show();
    // $example off$

    spark.stop();
  }
}