add group by value example

James Lee · James Lee · commit f18ce7e29a0d · 2017-02-05T17:15:46.000Z
diff --git a/src/main/java/com/sparkTutorial/pairRdd/groupbykey/AirportsProblem.java b/src/main/java/com/sparkTutorial/pairRdd/groupbykey/AirportsProblem.java
@@ -0,0 +1,21 @@
+package com.sparkTutorial.pairRdd.groupbykey;
+
+public class AirportsProblem {
+
+    public static void main(String[] args) throws Exception {
+
+        /* TODO: Create a Spark program to read the airport data from in/airports.text, output the the list of the names of the airports located in each country.
+
+           Each row of the input file contains the following columns:
+
+           Airport ID, Name of airport, Main city served by airport, Country where airport is located, IATA/FAA code, ICAO Code, Latitude, Longitude, Altitude, Timezone, DST, Timezone in Olson format
+
+           Sample output:
+
+           "Canada", ["Bagotville", "Montreal", "Coronation", ...]
+           "Norway" : ["Vigra", "Andenes", "Alta", "Bomoen", "Bronnoy",..]
+           "Papua New Guinea",  ["Goroka", "Madang", ...]
+           ...
+         */
+    }
+}
diff --git a/src/main/java/com/sparkTutorial/pairRdd/groupbykey/AirportsSolution.java b/src/main/java/com/sparkTutorial/pairRdd/groupbykey/AirportsSolution.java
@@ -0,0 +1,32 @@
+package com.sparkTutorial.pairRdd.groupbykey;
+
+import org.apache.spark.SparkConf;
+import org.apache.spark.api.java.JavaPairRDD;
+import org.apache.spark.api.java.JavaRDD;
+import org.apache.spark.api.java.JavaSparkContext;
+import org.apache.spark.api.java.function.PairFunction;
+import scala.Tuple2;
+
+public class AirportsSolution {
+
+    public static void main(String[] args) throws Exception {
+
+        SparkConf conf = new SparkConf().setAppName("airports").setMaster("local[*]");
+
+        JavaSparkContext sc = new JavaSparkContext(conf);
+
+        JavaRDD<String> lines = sc.textFile("in/airports.text");
+
+        JavaPairRDD<String, String> CountryAndAirportNameAndPair = lines.mapToPair((PairFunction<String, String, String>) airport -> new Tuple2<>(airport.split(",")[3], airport.split(",")[1]));
+
+        JavaPairRDD<String, Iterable<String>> AirportsByCountry = CountryAndAirportNameAndPair.groupByKey();
+
+        for (Tuple2<String, Iterable<String>> airports : AirportsByCountry.collect()) {
+            System.out.print(airports._1() + " : [");
+            for (String s : airports._2()) {
+                System.out.print(s + ", ");
+            }
+            System.out.println("]");
+        }
+    }
+}
