Bare-bones usage of the Spark 2 Dataset API from Java 8

build.gradle

dependencies {
    compile group: 'org.apache.spark', name: 'spark-core_2.11', version: '2.1.0'
    compile group: 'org.apache.spark', name: 'spark-sql_2.11', version: '2.1.0'
}

Spark20Example.java

package com.example;

import org.apache.spark.sql.Dataset;
import org.apache.spark.sql.SparkSession;
import org.apache.spark.sql.catalyst.encoders.ExpressionEncoder;
import scala.runtime.AbstractFunction1;

import java.util.Arrays;
import java.util.function.Function;

/*
* The Dataset API does not yet have a proper Java version,
* so we wrap away the fact that we're using Scala's Function_ traits,
* and provide type evidences as arguments to every combinator.
*/
public class Spark20Example {

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

        Dataset<Integer> ints = spark.createDataset(
                Arrays.asList(1, 2, 3, 4, 5),
                ExpressionEncoder.javaBean(Integer.class)
        );

        Dataset<String> strings = ints.map(
                wrap(String::valueOf),
                ExpressionEncoder.javaBean(String.class));
    }

    private static <A, B> AbstractFunction1<A, B> wrap(Function<A, B> doThis) {
        return new AbstractFunction1<A, B>() {
            @Override
            public B apply(A v1) {
                return doThis.apply(v1);
            }
        };
    }
}