MinHashForJaccard.java

package com.topsec.ti.patronus;

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.SparkSession;
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;

/**
 * Created by hhy on 2017/09/07.
 */
public class MinHashForJaccard {
    public static void main(String[] args){
        SparkSession spark= SparkSession.builder().master("local").appName("").getOrCreate();
        List<Row> 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<Row> dataFrame = spark.createDataFrame(data, schema);
        dataFrame.show();

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

        MinHashLSHModel model = mh.fit(dataFrame);
        model.transform(dataFrame).show();
    }
}