Q7

[SHELL]
echo "Old MACDONALD had a farm E-I-E-I-O And on his farm he had
a cow E-I-E-I-O With a moo moo here And a moo moo there Here a
moo there a moo Everywhere a moo moo Old MacDonald had a farm
E-I-E-I-O" > doc01.txt
echo "Old MACDONALD had a farm E-I-E-I-O And on his farm he had a
pig E-I-E-I-O With a oink oink here And a oink oink there Here
a oink there a oink Everywhere a oink oink Old MacDonald had a
farm E-I-E-I-O" > doc02.txt
echo "Old MACDONALD had a farm E-I-E-I-O And on his farm he had a
duck E-I-E-I-O With a quack quack here And a quack quack there
Here a quack there a quack Everywhere a quack quack Old
MacDonald had a farm E-I-E-I-O" > doc03.txt
echo "Old MACDONALD had a farm E-I-E-I-O And on his farm he had a
horse E-I-E-I-O With a neigh neigh here And a neigh neigh there
Here a neigh there a neigh Everywhere a neigh neigh Old
MacDonald had a farm E-I-E-I-O" > doc04.txt
echo "Old MACDONALD had a farm E-I-E-I-O And on his farm he had a
lamb E-I-E-I-O With a baa baa here And a baa baa there Here a
baa there a baa Everywhere a baa baa Old MacDonald had a farm
E-I-E-I-O" > doc05.txt

hdfs dfs -mkdir /Q7_dir
hdfs dfs -put doc*.txt /Q7_dir
hdfs dfs -ls /Q7_dir


[CODE]
val Q7Data=sc.wholeTextFiles("hdfs://127.0.0.1:9000/Q7_dir/")

val invIndex = Q7Data.map{case (fname,content) =>
    val contSplited=content.toLowerCase.split("\\s+").groupBy(x=>x).mapValues(x=>x.length)
    val result=contSplited.map(x=>(x._1,
(fname.takeRight(9))))
    result
}.flatMap(x=>x).groupByKey().sortByKey(true)

invIndex.foreach(println)

[截圖]
https://imgur.com/a/gHN2VB5.jpg