@Test public void testJoin() { List<Integer> data = Arrays.asList(1, 2, 3); Dataset<Integer> ds = spark.createDataset(data, Encoders.INT()).as("a"); List<Integer> data2 = Arrays.asList(2, 3, 4); Dataset<Integer> ds2 = spark.createDataset(data2, Encoders.INT()).as("b"); Dataset<Tuple2<Integer, Integer>> joined = ds.joinWith(ds2, col("a.value").equalTo(col("b.value"))); Assert.assertEquals( Arrays.asList(tuple2(2, 2), tuple2(3, 3)), joined.collectAsList()); }
@Test public void testJoin() { List<Integer> data = Arrays.asList(1, 2, 3); Dataset<Integer> ds = spark.createDataset(data, Encoders.INT()).as("a"); List<Integer> data2 = Arrays.asList(2, 3, 4); Dataset<Integer> ds2 = spark.createDataset(data2, Encoders.INT()).as("b"); Dataset<Tuple2<Integer, Integer>> joined = ds.joinWith(ds2, col("a.value").equalTo(col("b.value"))); Assert.assertEquals( Arrays.asList(tuple2(2, 2), tuple2(3, 3)), joined.collectAsList()); }
@Test public void testJoin() { List<Integer> data = Arrays.asList(1, 2, 3); Dataset<Integer> ds = spark.createDataset(data, Encoders.INT()).as("a"); List<Integer> data2 = Arrays.asList(2, 3, 4); Dataset<Integer> ds2 = spark.createDataset(data2, Encoders.INT()).as("b"); Dataset<Tuple2<Integer, Integer>> joined = ds.joinWith(ds2, col("a.value").equalTo(col("b.value"))); Assert.assertEquals( Arrays.asList(tuple2(2, 2), tuple2(3, 3)), joined.collectAsList()); }