diff options
Diffstat (limited to 'hadoop/streaming/mapper/mapper_test1.sh')
-rwxr-xr-x | hadoop/streaming/mapper/mapper_test1.sh | 24 |
1 files changed, 24 insertions, 0 deletions
diff --git a/hadoop/streaming/mapper/mapper_test1.sh b/hadoop/streaming/mapper/mapper_test1.sh new file mode 100755 index 0000000..475699f --- /dev/null +++ b/hadoop/streaming/mapper/mapper_test1.sh @@ -0,0 +1,24 @@ +#!/bin/sh + + +hadoop dfs -put input input + +HADOOP_HOME=/usr/lib/hadoop +HADOOP_VERSION=0.20.2-cdh3u1 +JAR=contrib/streaming/hadoop-streaming-$HADOOP_VERSION.jar +HSTREAMING="$HADOOP_HOME/bin/hadoop jar $HADOOP_HOME/$JAR" + +OUT=mapper_test1_out + +$HSTREAMING \ + -input input \ + -output $OUT \ + -mapper "python mapper1.py" \ + -file mapper_test1.py \ + -reducer org.apache.hadoop.mapred.lib.IdentityReducer \ + -jobconf mapred.reduce.tasks=3 + +hadoop dfs -get $OUT . +hadoop dfs -rmr $OUT +hadoop dfs -rm input + |