稿 Spark-MLlib的快速使用之十六（ 时间序列）

（1）描述

（2）代码

public static void main(String[] args) {

 

SparkConf sparkConf = new SparkConf().setAppName("JavaPrefixSpanExample").setMaster("local");

JavaSparkContext sc = new JavaSparkContext(sparkConf);

 

// $example on$

JavaRDD<List<List<Integer>>> sequences = sc.parallelize(Arrays.asList(

Arrays.asList(Arrays.asList(1, 2), Arrays.asList(3)),

Arrays.asList(Arrays.asList(1), Arrays.asList(3, 2), Arrays.asList(1, 2)),

Arrays.asList(Arrays.asList(1, 2), Arrays.asList(5)),

Arrays.asList(Arrays.asList(6))

), 2);

PrefixSpan prefixSpan = new PrefixSpan()

.setMinSupport(0.5)

.setMaxPatternLength(5);

PrefixSpanModel<Integer> model = prefixSpan.run(sequences);

for (PrefixSpan.FreqSequence<Integer> freqSeq: model.freqSequences().toJavaRDD().collect()) {

System.out.println(freqSeq.javaSequence() + ", " + freqSeq.freq());

}

// $example off$

}

（3）结果

[[2]], 3

[[3]], 2

[[1]], 3

[[2, 1]], 3

[[1], [3]], 2