直接上代码:show you the codes
单词个数统计,首先将以行语句切分为每个单词,并标记为1,然后这个单词进行统计累加,最后算出每个单词的个数
3.2 编辑上面创建的对象“SparkWordCountTest”,然后编辑内容如下
import org.apache.spark.SparkConf
import org.apache.spark.SparkContext
object SparkWordCountTest {
def main(args: Array[String]) {
val conf = new SparkConf().setAppName("WordCount").setMaster("local[4]")
val sc = new SparkContext(conf)
val lines = sc.textFile("filePath", 1)
val words = lines.flatMap { line => line.split(" ") }
val pairs = words.map { word => (word, 1) }
val wordCounts = pairs.reduceByKey { _ + _ }
wordCounts.foreach(wordCount => println(wordCount._1 + "---->" + wordCount._2))
}
}