代碼:
object WordCount {
def main(args: Array[String]): Unit = {
val spark: SparkSession = SparkSession.builder().appName("SimpleApp").master("local[1]").getOrCreate()
val data = Array("hello world", "simple app is good", "good world")
val result: Array[(String, Int)] = spark.sparkContext.parallelize(data)
.flatMap(_.split(" "))
.map((_, 1))
.reduceByKey(_ + _)
.collect()
result.foreach(println)
}
}
輸出:
(is,1)
(app,1)
(simple,1)
(hello,1)
(good,2)
(world,2)