void validateDataFrameWithBeans(Bean bean, DataFrame df) {
StructType schema = df.schema();
Assert.assertEquals(
new StructField("a", DoubleType$.MODULE$, false, Metadata.empty()), schema.apply("a"));
Assert.assertEquals(
new StructField("b", new ArrayType(IntegerType$.MODULE$, true), true, Metadata.empty()),
schema.apply("b"));
ArrayType valueType = new ArrayType(DataTypes.IntegerType, false);
MapType mapType = new MapType(DataTypes.StringType, valueType, true);
Assert.assertEquals(new StructField("c", mapType, true, Metadata.empty()), schema.apply("c"));
Assert.assertEquals(
new StructField("d", new ArrayType(DataTypes.StringType, true), true, Metadata.empty()),
schema.apply("d"));
Row first = df.select("a", "b", "c", "d").first();
Assert.assertEquals(bean.getA(), first.getDouble(0), 0.0);
// Now Java lists and maps are converted to Scala Seq's and Map's. Once we get a Seq below,
// verify that it has the expected length, and contains expected elements.
Seq<Integer> result = first.getAs(1);
Assert.assertEquals(bean.getB().length, result.length());
for (int i = 0; i < result.length(); i++) {
Assert.assertEquals(bean.getB()[i], result.apply(i));
}
@SuppressWarnings("unchecked")
Seq<Integer> outputBuffer = (Seq<Integer>) first.getJavaMap(2).get("hello");
Assert.assertArrayEquals(
bean.getC().get("hello"),
Ints.toArray(JavaConverters.seqAsJavaListConverter(outputBuffer).asJava()));
Seq<String> d = first.getAs(3);
Assert.assertEquals(bean.getD().size(), d.length());
for (int i = 0; i < d.length(); i++) {
Assert.assertEquals(bean.getD().get(i), d.apply(i));
}
}
@Test
public void testSampleBy() {
DataFrame df = context.range(0, 100, 1, 2).select(col("id").mod(3).as("key"));
DataFrame sampled = df.stat().<Integer>sampleBy("key", ImmutableMap.of(0, 0.1, 1, 0.2), 0L);
Row[] actual = sampled.groupBy("key").count().orderBy("key").collect();
Row[] expected = {RowFactory.create(0, 5), RowFactory.create(1, 8)};
Assert.assertArrayEquals(expected, actual);
}