iSharkFly-Docs
/
java-tutorials
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Bael 1166 intro apache spark (#2875) 

* Changes for BAEL-1166

* Changes for BAEL_1166

* Changes for BAEL 1166

* Changes for BAEL 1166

* Changes for BAEL_1166
This commit is contained in:
Nikhil Khatwani 2017-10-26 23:16:35 +05:30 committed by Grzegorz Piwowarek
parent 814aff3031
commit c389f56da5
1 changed files with 18 additions and 31 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

23
apache-spark/src/main/java/com/baeldung/WordCount.java
View File

@ -23,28 +23,15 @@ public class WordCount {
System.err.println("Usage: JavaWordCount <file>"); System.err.println("Usage: JavaWordCount <file>");
System.exit(1); System.exit(1);
} }
SparkConf sparkConf = new SparkConf().setAppName("JavaWordCount").setMaster("local"); SparkConf sparkConf = new SparkConf().setAppName("JavaWordCount")
.setMaster("local");
JavaSparkContext ctx = new JavaSparkContext(sparkConf); JavaSparkContext ctx = new JavaSparkContext(sparkConf);
JavaRDD<String> lines = ctx.textFile(args[0], 1); JavaRDD<String> lines = ctx.textFile(args[0], 1);
JavaRDD<String> words = lines.flatMap(s -> Arrays.asList(SPACE.split(s)).iterator()); JavaRDD<String> words = lines.flatMap(s -> Arrays.asList(SPACE.split(s)).iterator());
JavaPairRDD<String, Integer> ones = words.mapToPair( JavaPairRDD<String, Integer> wordAsTuple = words.mapToPair(word -> new Tuple2<>(word, 1));
new PairFunction<String, String, Integer>() { JavaPairRDD<String, Integer> wordWithCount = wordAsTuple.reduceByKey((Integer i1, Integer i2)->i1 + i2);
@Override List<Tuple2<String, Integer>> output = wordWithCount.collect();
public Tuple2<String, Integer> call(String s) {
return new Tuple2<>(s, 1);
}
});
JavaPairRDD<String, Integer> counts = ones.reduceByKey(
new Function2<Integer, Integer, Integer>() {
@Override
public Integer call(Integer i1, Integer i2) {
return i1 + i2;
}
});
List<Tuple2<String, Integer>> output = counts.collect();
for (Tuple2<?, ?> tuple : output) { for (Tuple2<?, ?> tuple : output) {
System.out.println(tuple._1() + ": " + tuple._2()); System.out.println(tuple._1() + ": " + tuple._2());
} }