Skip to content

Commit 240dbd6

Browse files
author
James Lee
committed
add JoinOperations
1 parent 4941d26 commit 240dbd6

2 files changed

Lines changed: 44 additions & 1 deletion

File tree

Lines changed: 43 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,43 @@
1+
package com.sparkTutorial.pairRdd.join;
2+
3+
import org.apache.spark.SparkConf;
4+
import org.apache.spark.api.java.JavaPairRDD;
5+
import org.apache.spark.api.java.JavaSparkContext;
6+
import org.apache.spark.api.java.Optional;
7+
import scala.Tuple2;
8+
9+
import java.util.Arrays;
10+
11+
public class JoinOperations {
12+
13+
public static void main(String[] args) throws Exception {
14+
15+
SparkConf conf = new SparkConf().setAppName("JoinOperations").setMaster("local[1]");
16+
17+
JavaSparkContext sc = new JavaSparkContext(conf);
18+
19+
JavaPairRDD<String, Integer> ages = sc.parallelizePairs(Arrays.asList(new Tuple2<>("Tom", 29),
20+
new Tuple2<>("John", 22)));
21+
22+
JavaPairRDD<String, String> addresses = sc.parallelizePairs(Arrays.asList(new Tuple2<>("James", "USA"),
23+
new Tuple2<>("John", "UK")));
24+
25+
JavaPairRDD<String, Tuple2<Integer, String>> join = ages.join(addresses);
26+
27+
join.saveAsTextFile("out/age_address_join.text");
28+
29+
JavaPairRDD<String, Tuple2<Integer, Optional<String>>> leftOuterJoin = ages.leftOuterJoin(addresses);
30+
31+
leftOuterJoin.saveAsTextFile("out/age_address_left_out_join.text");
32+
33+
JavaPairRDD<String, Tuple2<Optional<Integer>, String>> rightOuterJoin = ages.rightOuterJoin(addresses);
34+
35+
rightOuterJoin.saveAsTextFile("out/age_address_right_out_join.text");
36+
37+
JavaPairRDD<String, Tuple2<Optional<Integer>, Optional<String>>> fullOuterJoin = ages.fullOuterJoin(addresses);
38+
39+
fullOuterJoin.saveAsTextFile("out/age_address_full_out_join.text");
40+
41+
42+
}
43+
}

src/main/java/com/sparkTutorial/rdd/nasaApacheWebLogs/NasaApacheWebLogsSolution.java

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -21,7 +21,7 @@ public static void main(String[] args) throws Exception {
2121

2222
JavaRDD<String> sample = cleanLogLines.sample(true, 0.1);
2323

24-
sample.saveAsTextFile("out/sample_nasa_logs.tsv");
24+
sample.saveAsTextFile("out/sample_nasa_logs.csv");
2525
}
2626

2727
private static boolean isNotHeader(String line) {

0 commit comments

Comments
 (0)