Permalink
Browse files

Added an elephantbird option

  • Loading branch information...
1 parent d1cae82 commit 46a289798ae6aeab602b34653856071ea72ced77 Gabor Szabo committed Mar 4, 2013
Showing with 3 additions and 0 deletions.
  1. +3 −0 java/src/com/twitter/pycascading/Util.java
@@ -110,6 +110,9 @@ public static void run(int numReducers, Map<String, Object> config, Map<String,
+ "com.twitter.pycascading.pythonserialization.PythonSerialization");
properties.put("mapred.jobtracker.completeuserjobs.maximum", "50000");
properties.put("mapred.input.dir.recursive", "true");
+ // This is the number of bad records that the elephantbird LzoRecordReader
+ // uses to decide about when to throw an exception
+// properties.put("elephantbird.mapred.input.bad.record.threshold", "0.05");
properties.put("elephantbird.mapred.input.bad.record.min", "8");
// Set the running mode in the jobconf so that the mappers/reducers can

0 comments on commit 46a2897

Please sign in to comment.