[Spark Core] Spark Shell 实现 Word Count

# step 1 加载文档
val rdd1 = sc.textFile("file:///home/centos/wc1.txt")

# step 2 压扁
val rdd2 = rdd1.flatMap(line=>{line.split(" ")})

# step 3 标1成对
val rdd3 = rdd2.map(word=>{(word , 1)})

# step 4 聚合
val rdd4 = rdd3.reduceByKey((a:Int,b:Int)=>{a + b})

# step 5
rdd4.collect()

sc.textFile("file:///home/centos/wc1.txt").flatMap(_.split(" ")).map((_,1)).reduceByKey(_+_).collect()

sc.textFile("file:///home/centos/wc1.txt").flatMap(_.split(" ")).map((_,1)).groupByKey().mapValues(_.size).collect()