From 26c490f404731d053a6205719b6246502c07b449 Mon Sep 17 00:00:00 2001 From: Patrick Simianer Date: Sat, 14 Jun 2014 16:46:27 +0200 Subject: init --- overlapping_rules/merge_rules_mapred.sh | 12 ++++++++++++ 1 file changed, 12 insertions(+) create mode 100755 overlapping_rules/merge_rules_mapred.sh (limited to 'overlapping_rules/merge_rules_mapred.sh') diff --git a/overlapping_rules/merge_rules_mapred.sh b/overlapping_rules/merge_rules_mapred.sh new file mode 100755 index 0000000..e1329f4 --- /dev/null +++ b/overlapping_rules/merge_rules_mapred.sh @@ -0,0 +1,12 @@ +#!/bin/sh + +hadoop jar /usr/lib/hadoop-0.20-mapreduce/contrib/streaming/hadoop-streaming-2.0.0-mr1-cdh4.1.2.jar \ + -D mapred.reduce.tasks=23 \ + -D mapred.task.timeout=120000000 \ + -input overlap/g120+index-16mb \ + -cacheFile 'hdfs://10.0.0.1:8020/user/simianer/overlap/g120+index#g120+index' \ + -output overlap/test-g120 \ + -mapper merge_rules.rb \ + -reducer /usr/bin/uniq \ + -file merge_rules.rb \ + -- cgit v1.2.3