[大数据]【spark使用】3.java和scala转换算子使用区别

map

String转为Tuple2<String, Integer>

public class test {
    public static void main(String[] args) {
        SparkConf conf = new SparkConf().setAppName("jiangtao_demo").setMaster("local");
        JavaSparkContext jsc = new JavaSparkContext(conf);
        //并行集合生成JavaRDD
        JavaRDD lines = jsc.parallelize(Arrays.asList("pandas pip", "numpy", "pip", "pip", "pip"));
        //map 输出包含newTail的元素
        //这个是给每个元素尾部加newTail
        JavaRDD<String> mapResult = lines.map(new Function<String, String>() {
            @Override
            public String call(String o) throws Exception {
                return o.concat("newTail");
            }
        });



        //下面这个是给每个元素String转为Tuple2<String, Integer>元组类型的
        //map算子输入与输出一对一，输出结果为
        // [(pandas, 1),(pip, 1)]
        // [(numpy, 1)]
        // [(pip, 1)]
        // [(pip, 1)]
        // [(pip, 1)]
        JavaRDD<Iterable<Tuple2<String, Integer>>> maprdd = lines.map(new Function<String, Iterable<Tuple2<String, Integer>>>() {

            public Iterable<Tuple2<String, Integer>> call(String line) throws Exception {
                String[] fields = line.split(" ");
                ArrayList<Tuple2<String, Integer>> al = new ArrayList<Tuple2<String, Integer>>();
                for (int i = 0; i < fields.length; i++) {
                    al.add(new Tuple2(fields[i], 1));
                }
                return al;
            }
        });
        maprdd.foreach(s -> {
            System.out.println(s);
        });
     }
}

flatMap

<String>类型的转为<String> 这里比如一行元素有两个单词，使用这个方法可以将这一行元素拆为两行元素，每行元素一个单词

public class test {
    public static void main(String[] args) {
        SparkConf conf = new SparkConf().setAppName("jiangtao_demo").setMaster("local");
        JavaSparkContext jsc = new JavaSparkContext(conf);
        JavaRDD lines = jsc.parallelize(Arrays.asList("pandas pip", "numpy", "pip", "pip", "pip"));

        // flatMap
        // 与输入是一对多的关系，返回的是可迭代的List
        // pandas
        // pip
        // numpy
        // pip
        // pip
        // pip
        JavaRDD<String> flatMapResult = lines.flatMap(new FlatMapFunction<String, String>() {
            @Override
            public Iterator<String> call(String line) throws Exception {
                return Arrays.asList(line.toString().split(" ")).iterator();
            }
        });

        flatMapResult.foreach(s -> {
            System.out.println(s);
        });
    }
}

flatMapToPair

<String>类型的转为<String, Integer> 将每一行的元素拆分后再转为键值对类型的RDD

public class test {
    public static void main(String[] args) {
        SparkConf conf = new SparkConf().setAppName("jiangtao_demo").setMaster("local");
        JavaSparkContext jsc = new JavaSparkContext(conf);
        JavaRDD lines = jsc.parallelize(Arrays.asList("pandas pip", "numpy", "pip", "pip", "pip"));

        // flatMapToPair
        // 注意返回值，返回的是list，里面封装了tuple2
        // (pandas,1)
        // (pip,1)
        // (numpy,1)
        // (pip,1)
        // (pip,1)
        // (pip,1)
        JavaPairRDD<String, Integer> result1 = lines.flatMapToPair(new PairFlatMapFunction<String, String, Integer>() {
            @Override
            public Iterator<Tuple2<String, Integer>> call(String line) throws Exception {
                String[] fields = line.split(" ");
                ArrayList<Tuple2<String, Integer>> al = new ArrayList<Tuple2<String, Integer>>();
                for (int i = 0; i < fields.length; i++) {
                    al.add(new Tuple2<String, Integer>(fields[i], 1));
                }
                return al.iterator();
            }
        });
        result1.foreach(s -> {
            System.out.println(s);
        });

    }
}