Version 2 (modified by jazz, 14 years ago) (diff) |
---|
Hadoop Streaming with commands
jazz@hadoop:~$ echo "sed -e \"s/ /\n/g\" | grep ." > streamingMapper.sh jazz@hadoop:~$ echo "uniq -c | awk '{print $2 \"\t\" $1}'" > streamingReducer.sh jazz@hadoop:~$ hadoop fs -rmr input output jazz@hadoop:~$ hadoop fs -put /etc/hadoop/conf input jazz@hadoop:~$ hadoop jar hadoop-streaming.jar -input input -output output -mapper `pwd`/streamingMapper.sh -reducer `pwd`/streamingReducer.sh