DistributedRowMatrix.transpose().transpose() = Exception

[Laszlo Dosa]

Hi,

As far as I know if I transpose a matrix twice I should get back the original 
matrix.

I tried to do this with DistributedRowMatrix (trunk version).  My sample matrix 
has 14 rows and 31 columns.

I got the following exception:
org.apache.mahout.math.IndexException: Index 31 is outside allowable range of 
[0,31]
                at 
org.apache.mahout.math.AbstractVector.set(AbstractVector.java:324)
                at 
org.apache.mahout.math.SequentialAccessSparseVector.<init>(SequentialAccessSparseVector.java:69)
                at 
org.apache.mahout.math.hadoop.TransposeJob$TransposeReducer.reduce(TransposeJob.java:144)
                at 
org.apache.mahout.math.hadoop.TransposeJob$TransposeReducer.reduce(TransposeJob.java:1)
                at 
org.apache.hadoop.mapred.ReduceTask.runOldReducer(ReduceTask.java:463)
                at org.apache.hadoop.mapred.ReduceTask.run(ReduceTask.java:411)
                at org.apache.hadoop.mapred.Child.main(Child.java:170)

Exception in thread "main" java.io.IOException: Job failed!
                at 
org.apache.hadoop.mapred.JobClient.runJob(JobClient.java:1293)
                at 
org.apache.mahout.math.hadoop.DistributedRowMatrix.transpose(DistributedRowMatrix.java:153)
                at 
com.fredhopper.MatrixTransposeJob.run(MatrixTransposeJob.java:46)
                at org.apache.hadoop.util.ToolRunner.run(ToolRunner.java:65)
                at 
com.fredhopper.MatrixTransposeJob.main(MatrixTransposeJob.java:52)
                at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
                at 
sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:39)
                at 
sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:25)
                at java.lang.reflect.Method.invoke(Method.java:597)
                at org.apache.hadoop.util.RunJar.main(RunJar.java:156)

Does anyone had the same issues or knows how to sole it?

Thanks,
Laszlo

I runned:
hadoop jar matrix-transpose.jar \
com.fredhopper.MatrixTransposeJob \
-i input/ \
-o output/ \
--numRows 14 \
--numCols 31

My code is:
package com.fredhopper;

import java.io.IOException;
import java.util.Map;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.mapred.JobConf;
import org.apache.hadoop.util.ToolRunner;
import org.apache.mahout.common.AbstractJob;
import org.apache.mahout.math.hadoop.DistributedRowMatrix;

public class MatrixTransposeJob extends AbstractJob {

                @SuppressWarnings("deprecation")
                @Override
                public int run(String[] args) throws IOException, 
ClassNotFoundException, InterruptedException {
                               addInputOption();
                               addOutputOption();

                               addOption("numRows", "nr", "Number of rows of 
the input matrix");
                               addOption("numCols", "nc", "Number of columns of 
the input matrix");

                               Configuration originalConfig = getConf();

                               Map<String,String> parsedArgs = 
parseArguments(args);
                               if (parsedArgs == null) {
                                               return -1;
                               }

                               Path inputPath = getInputPath();
                               Path outputPath =  getOutputPath();

                               int numRows = 
Integer.parseInt(parsedArgs.get("--numRows"));
                               int numCols = 
Integer.parseInt(parsedArgs.get("--numCols"));

                               DistributedRowMatrix matrix = new 
DistributedRowMatrix(inputPath,
                                                               outputPath,
                                                               numRows,
                                                               numCols);
                               
                               JobConf conf = new JobConf(originalConfig);
                               matrix.configure(conf);

                               DistributedRowMatrix t1 = matrix.transpose();
                               DistributedRowMatrix t2 = t1.transpose();

                               return 0;
                }

                public static void main(String[] args) throws Exception {
                               ToolRunner.run(new Configuration(), new 
MatrixTransposeJob(), args);
                }

}