public final class UnitVectorizerJob extends Object
Given a DistributedRowMatrix, this job normalizes each row to unit vector length. If the input is a matrix U, and the output is a matrix W, the job follows:
v_ij = u_ij / sqrt(sum_j(u_ij * u_ij))
| Modifier and Type | Class and Description |
|---|---|
static class |
UnitVectorizerJob.UnitVectorizerMapper |
| Modifier and Type | Method and Description |
|---|---|
static void |
runJob(org.apache.hadoop.fs.Path input,
org.apache.hadoop.fs.Path output) |
public static void runJob(org.apache.hadoop.fs.Path input,
org.apache.hadoop.fs.Path output)
throws IOException,
InterruptedException,
ClassNotFoundException
Copyright © 2008–2017 The Apache Software Foundation. All rights reserved.