I am implementing a test class in Java with the library Algebird to compute HyperLogLog. This library is in scala but I want to use it in Java. In some point I have to translate a list of int into a list of array of bytes, then I have to use the Java lambda approach. There I am receiving the error Missing return statement
. What am I doing wrong here? This is the java code:
import com.twitter.algebird.Approximate;
import com.twitter.algebird.HLL;
import com.twitter.algebird.HyperLogLogMonoid;
import scala.collection.TraversableOnce;
import java.io.ByteArrayOutputStream;
import java.nio.ByteBuffer;
import java.util.ArrayList;
import java.util.Arrays;
import java.util.List;
// import com.twitter.algebird.HyperLogLog.int2Bytes;
public class AlgebirdHLLAppJ {
public static void main(String[] args) {
System.out.println("This is the Spark test of the Algebird HyperLogLog application");
HyperLogLogMonoid hll = new HyperLogLogMonoid(4);
List<Integer> data = new ArrayList<Integer>(Arrays.asList(1, 1, 2, 2, 3, 3, 4, 4, 5, 5));
ByteArrayOutputStream baos = new ByteArrayOutputStream();
baos.toByteArray();
hll.create(baos.toByteArray());
TraversableOnce<HLL> seqHll = data.stream().map(d -> {
ByteBuffer bb = ByteBuffer.allocate(4);
bb.putInt(d);
hll.create(bb.array());
}); // ERROR: Missing return statement
HLL sumHll = hll.sum(seqHll);
Approximate<Object> approxSizeOf = hll.sizeOf(sumHll);
Integer actualSize = data.size();
Integer estimate = (Integer) approxSizeOf.estimate();
System.out.println("Actual size: " + actualSize);
System.out.println("Estimate size: " + estimate);
}
}
this is the scala code
import com.twitter.algebird.HyperLogLogMonoid
import com.twitter.algebird.HyperLogLog.int2Bytes
object AlgebirdHLLApp {
def main(args: Array[String]): Unit = {
println("This is the Spark test of the Algebird HyperLogLog application")
val hll = new HyperLogLogMonoid(4)
val data = List(1, 1, 2, 2, 3, 3, 4, 4, 5, 5)
val seqHll = data.map { hll.create(_) }
val sumHll = hll.sum(seqHll)
val approxSizeOf = hll.sizeOf(sumHll)
val actualSize = data.toSet.size
val estimate = approxSizeOf.estimate
println("Actual size: " + actualSize)
println("Estimate size: " + estimate)
}
}
Try
import com.twitter.algebird.Approximate;
import com.twitter.algebird.HLL;
import com.twitter.algebird.HyperLogLog;
import com.twitter.algebird.HyperLogLogMonoid;
import java.util.ArrayList;
import java.util.Arrays;
import java.util.HashSet;
import java.util.List;
import java.util.stream.Collectors;
import scala.collection.JavaConverters;
public class AlgebirdHLLAppJ {
public static void main(String[] args) {
System.out.println("This is the Spark test of the Algebird HyperLogLog application");
HyperLogLogMonoid hll = new HyperLogLogMonoid(4);
List<Integer> data = new ArrayList<>(Arrays.asList(1, 1, 2, 2, 3, 3, 4, 4, 5, 5));
List<HLL> seqHll = data.stream().map(i -> hll.create(HyperLogLog.int2Bytes(i))).collect(Collectors.toList());
HLL sumHll = (HLL) hll.sum(JavaConverters.collectionAsScalaIterable(seqHll));
Approximate<Object> approxSizeOf = hll.sizeOf(sumHll);
int actualSize = new HashSet<>(data).size();
long estimate = (long) approxSizeOf.estimate();
System.out.println("Actual size: " + actualSize);
System.out.println("Estimate size: " + estimate);
}
}
The technical post webpages of this site follow the CC BY-SA 4.0 protocol. If you need to reprint, please indicate the site URL or the original address.Any question please contact:yoyou2525@163.com.