寒假学习进度

本文主要是介绍寒假学习进度，对大家解决编程问题具有一定的参考价值，需要的程序猿们随着小编来一起学习吧！

spark中wordcount的实现

（1）//aggregateByKey
def wordcount3(sc:SparkContext)={

val fileRDD: RDD[String] = sc.textFile("D:\\qq text\\1791028291\\FileRecv\\《飘》英文版.txt")
// 将文件中的数据进行分词
val wordRDD: RDD[String] = fileRDD.flatMap( _.split(" ") )
val wordmap: RDD[(String, Int)] = wordRDD.map((_, 1))
val group: RDD[(String, Int)] = wordmap.aggregateByKey(0)(_ + _,_ + _)

group.collect().foreach(println)
}

//foldByKey
def wordcount4(sc:SparkContext)={

val fileRDD: RDD[String] = sc.textFile("D:\\qq text\\1791028291\\FileRecv\\《飘》英文版.txt")
// 将文件中的数据进行分词
val wordRDD: RDD[String] = fileRDD.flatMap( _.split(" ") )
val wordmap: RDD[(String, Int)] = wordRDD.map((_, 1))
val group: RDD[(String, Int)] = wordmap.foldByKey(0)(_ + _)

group.collect().foreach(println)
}
//combineByKey
def wordcount5(sc:SparkContext)={

val fileRDD: RDD[String] = sc.textFile("D:\\qq text\\1791028291\\FileRecv\\《飘》英文版.txt")
// 将文件中的数据进行分词
val wordRDD: RDD[String] = fileRDD.flatMap( _.split(" ") )
val wordmap: RDD[(String, Int)] = wordRDD.map((_, 1))
val group: RDD[(String, Int)] = wordmap.combineByKey(
v => v,
(x: Int, y) => x + y,
(x: Int, y: Int) => x + y
)

group.collect().foreach(println)
}

//countByKey
def wordcount6(sc:SparkContext)={

val fileRDD: RDD[String] = sc.textFile("D:\\qq text\\1791028291\\FileRecv\\《飘》英文版.txt")
// 将文件中的数据进行分词
val wordRDD: RDD[String] = fileRDD.flatMap( _.split(" ") )
val wordmap: RDD[(String, Int)] = wordRDD.map((_, 1))
val group: collection.Map[String, Long] = wordmap.countByKey()
println(group)


}

//countByValue
def wordcount7(sc:SparkContext)={

val fileRDD: RDD[String] = sc.textFile("D:\\qq text\\1791028291\\FileRecv\\《飘》英文版.txt")
// 将文件中的数据进行分词
val wordRDD: RDD[String] = fileRDD.flatMap( _.split(" ") )

val group: collection.Map[String, Long] = wordRDD.countByValue()
println(group)


}

//reduce
def wordcount8(sc:SparkContext)={

val fileRDD: RDD[String] = sc.textFile("D:\\qq text\\1791028291\\FileRecv\\《飘》英文版.txt")
// 将文件中的数据进行分词
val wordRDD: RDD[String] = fileRDD.flatMap( _.split(" ") )
val wordmap: RDD[mutable.Map[String, Long]] = wordRDD.map(
word => {
mutable.Map[String, Long]((word, 1))
}
)

val stringToLong: mutable.Map[String, Long] = wordmap.reduce(
(map1, map2) => {
map2.foreach{
case (word,count)=>{
val newCount=map1.getOrElse(word,0L)+count
map1.update(word,newCount)
}
}
map1
}
)
println(stringToLong)
}

这篇关于寒假学习进度的文章就介绍到这儿，希望我们推荐的文章对大家有所帮助，也希望大家多多支持为之网！