How big is your model when you are done training? Just curious.
At least in the M-9 case, the storage model is not optimized at all.
I think Karl used Lucene to store the model in a non-M/R version.
Maybe that would be useful.
On Jul 21, 2008, at 12:45 PM, Steven Handerson (JIRA) wrote:
[
https://issues.apache.org/jira/browse/MAHOUT-60?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=12615324#action_12615324
]
Steven Handerson commented on MAHOUT-60:
I'll add one more thing so you see where I'
[
https://issues.apache.org/jira/browse/MAHOUT-60?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=12615308#action_12615308
]
Steven Handerson commented on MAHOUT-60:
Hmm -- well, in a sense I agree that all yo
A reminder that the next user group meeting is scheduled for July 22nd
from 6 - 7:30 pm at Yahoo! Mission College, Building 1, Training Rooms 3
and 4.
Agenda:
Cascading - Chris Wensel
Performance Benchmarking on Hadoop (Terabyte Sort, Gridmix) - Sameer
Paranjpye, Owen O'Malley, Runping Qi
[
https://issues.apache.org/jira/browse/MAHOUT-60?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=12615302#action_12615302
]
Steven Handerson commented on MAHOUT-60:
Well, yes, I was thinking of batch classifi
[
https://issues.apache.org/jira/browse/MAHOUT-65?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=12615292#action_12615292
]
Karl Wettin commented on MAHOUT-65:
---
bq. That seems like shoe-horning two functions into o
