java - Lanczsos-Eigenvector in Mahout -


i attempting machine learning in mahout, java. have downloaded data want mysql. point stuck when variable of type "sparserowmatrix" has computations , rearrangements done. not understand how call of 2 methods can see fit:

1) org.apache.mahout.math.decomposer.lanczos.lanczossolver

2) org.apache.mahout.math.hadoop.decomposer.distributedlanczossolver

any advice helpful @ point!

distributedlanczossolver implements tool interface, can run regular hadoop job, example:

hadoop jar $mahout_home/mahout-examples-0.5-job.jar org.apache.mahout.math.hadoop.decomposer.distributedlanczossolver --input /path/to/input --output /path/to/output --numcols 42 --numrows 42 --cleansvd "true" --rank 5 

you call directly java using:

toolrunner.run(new distributedlanczossolver().job(), args); 

alternatively if don't need in distributed fashion, lanczossolver.solve method looking for, have pass matrix, eigen vectors , eigen values. complicated stuff behind hood using lanczos algorithm wouldn't able explain, recommend directly more clarity in source code.


Comments

Popular posts from this blog

user interface - Python attempting to create a simple gui, getting "AttributeError: 'MainMenu' object has no attribute 'intro_screen'" -

jquery - Common JavaScript snippet to share files on Google Drive, Dropbox, Box.net or SkyDrive -

Android Gson.fromJson error -