[jira] Updated: (MAHOUT-85) Perceptron/Winnow Trainer

[Isabel Drost (JIRA)]

 [ 
https://issues.apache.org/jira/browse/MAHOUT-85?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
 ]

Isabel Drost updated MAHOUT-85:
---

Attachment: MAHOUT-85.patch

The patch has tests added to the implementation. The additional abstraction 
proposed earlier is integrated. Distance measure is not configurable but 
corresponds to what was defined in the original algorithm formulations.

The implementation currently is sequential-only. Still evaluating, if and how 
is might be possible to parallelize.

Missing so far: An example showing how to use training, how to store the 
resulting model and how to apply the model. Probably should be done in a new 
issue to keep this one focused on the algorithm itself. In addition I still 
have to at least add links from our wiki to the wikipedia pages on both 
algorithms.

(Had some time left during the past few days: Screws in my knee are out now ;) )

> Perceptron/Winnow Trainer
> -
>
> Key: MAHOUT-85
> URL: https://issues.apache.org/jira/browse/MAHOUT-85
> Project: Mahout
>  Issue Type: New Feature
>  Components: Classification
>Affects Versions: 0.1
>Reporter: Isabel Drost
>Assignee: Isabel Drost
> Fix For: 0.3
>
> Attachments: MAHOUT-85.patch, MAHOUT-85.patch, 
> perceptronWinnowTrainer.diff
>
>
> Please find attached a first sketch for perceptron and winnow training. 
> Please look very, very carefully at the patch, as I added the heart of the 
> algorithms in the emergency room at Charite Berlin (after I broke my leg when 
> cycling to the Hadoop Get Together ;) ). 
> The patch does not yet feature unit tests nor is it parallelised. Currently 
> my plan is to set up an example with the webKb dataset, add unit tests to the 
> code and after that go parallel. I would like to get some feedback early on, 
> in addition I would feel a lot better, if a second and third pair of eyes had 
> a look at the code to make sure all obvious mistakes are out as early as 
> possible.

-- 
This message is automatically generated by JIRA.
-
You can reply to this email to add a comment to the issue online.

[jira] Updated: (MAHOUT-85) Perceptron/Winnow Trainer

[Isabel Drost (JIRA)]

 [ 
https://issues.apache.org/jira/browse/MAHOUT-85?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
 ]

Isabel Drost updated MAHOUT-85:
---

Attachment: MAHOUT-85.patch

The patch has tests added to the implementation. The additional abstraction 
proposed earlier is integrated. Distance measure is not configurable but 
corresponds to what was defined in the original algorithm formulations.

The implementation currently is sequential-only. Still evaluating, if and how 
is might be possible to parallelize.

Missing so far: An example showing how to use training, how to store the 
resulting model and how to apply the model. Probably should be done in a new 
issue to keep this one focused on the algorithm itself. In addition I still 
have to at least add links from our wiki to the wikipedia pages on both 
algorithms.

(Had some time left during the past few days: Screws in my knee are out now ;) )

> Perceptron/Winnow Trainer
> -
>
> Key: MAHOUT-85
> URL: https://issues.apache.org/jira/browse/MAHOUT-85
> Project: Mahout
>  Issue Type: New Feature
>  Components: Classification
>Affects Versions: 0.1
>Reporter: Isabel Drost
>Assignee: Isabel Drost
> Fix For: 0.3
>
> Attachments: MAHOUT-85.patch, perceptronWinnowTrainer.diff
>
>
> Please find attached a first sketch for perceptron and winnow training. 
> Please look very, very carefully at the patch, as I added the heart of the 
> algorithms in the emergency room at Charite Berlin (after I broke my leg when 
> cycling to the Hadoop Get Together ;) ). 
> The patch does not yet feature unit tests nor is it parallelised. Currently 
> my plan is to set up an example with the webKb dataset, add unit tests to the 
> code and after that go parallel. I would like to get some feedback early on, 
> in addition I would feel a lot better, if a second and third pair of eyes had 
> a look at the code to make sure all obvious mistakes are out as early as 
> possible.

-- 
This message is automatically generated by JIRA.
-
You can reply to this email to add a comment to the issue online.

[jira] Updated: (MAHOUT-85) Perceptron/Winnow Trainer

[Sean Owen (JIRA)]

 [ 
https://issues.apache.org/jira/browse/MAHOUT-85?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
 ]

Sean Owen updated MAHOUT-85:


Affects Version/s: 0.1
Fix Version/s: 0.3

More housekeeping for 0.3. Is this still pretty commitable? I'd go for it if 
you think it's basically sound.

> Perceptron/Winnow Trainer
> -
>
> Key: MAHOUT-85
> URL: https://issues.apache.org/jira/browse/MAHOUT-85
> Project: Mahout
>  Issue Type: New Feature
>  Components: Classification
>Affects Versions: 0.1
>Reporter: Isabel Drost
>Assignee: Isabel Drost
> Fix For: 0.3
>
> Attachments: perceptronWinnowTrainer.diff
>
>
> Please find attached a first sketch for perceptron and winnow training. 
> Please look very, very carefully at the patch, as I added the heart of the 
> algorithms in the emergency room at Charite Berlin (after I broke my leg when 
> cycling to the Hadoop Get Together ;) ). 
> The patch does not yet feature unit tests nor is it parallelised. Currently 
> my plan is to set up an example with the webKb dataset, add unit tests to the 
> code and after that go parallel. I would like to get some feedback early on, 
> in addition I would feel a lot better, if a second and third pair of eyes had 
> a look at the code to make sure all obvious mistakes are out as early as 
> possible.

-- 
This message is automatically generated by JIRA.
-
You can reply to this email to add a comment to the issue online.

Re: [jira] Updated: (MAHOUT-85) Perceptron/Winnow Trainer

[Isabel Drost]

On Friday 31 October 2008, Grant Ingersoll wrote:
> I hope to get to these sometime in the next week or so

:) 

> (maybe will actually have some time at ApacheCon this year) Is there any
> examples I could try out? 

I am currently about to set up an example for text classification. I wanted to 
use the WebKB dataset. My plan was to read and parse the texts into vectors 
with UIMA, store them to disk and feed them into the classifier. Currently I 
am still working on the UIMA part.


> Would also be good if you could write up on the Wiki 
> some intro/background. 

About to do that. Will add a links to relevant documentation as well - the 
wikipedia article on the perceptron isn't too bad for instance.


Isabel

-- 
One Bell System - it used to work before they installed the Dimension!
  |\  _,,,---,,_   Web:   
  /,`.-'`'-.  ;-;;,_
 |,4-  ) )-,_..;\ (  `'-'
'---''(_/--'  `-'\_) (fL)  IM:  


signature.asc
Description: This is a digitally signed message part.

Re: [jira] Updated: (MAHOUT-85) Perceptron/Winnow Trainer

[Grant Ingersoll]

Hey Isabel,

I hope to get to these sometime in the next week or so (maybe will  
actually have some time at ApacheCon this year)  Is there any examples  
I could try out?  Would also be good if you could write up on the Wiki  
some intro/background.  I'd love to be able to add info on it to my  
talk on Wednesday.


Thanks,
Grant


On Oct 16, 2008, at 7:42 AM, Isabel Drost (JIRA) wrote:



[ https://issues.apache.org/jira/browse/MAHOUT-85?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel 
 ]


Isabel Drost updated MAHOUT-85:
---

   Attachment: perceptronWinnowTrainer.diff

The attachment mentioned above.


Perceptron/Winnow Trainer
-

   Key: MAHOUT-85
   URL: https://issues.apache.org/jira/browse/MAHOUT-85
   Project: Mahout
Issue Type: New Feature
Components: Classification
  Reporter: Isabel Drost
   Attachments: perceptronWinnowTrainer.diff


Please find attached a first sketch for perceptron and winnow  
training. Please look very, very carefully at the patch, as I added  
the heart of the algorithms in the emergency room at Charite Berlin  
(after I broke my leg when cycling to the Hadoop Get Together ;) ).
The patch does not yet feature unit tests nor is it parallelised.  
Currently my plan is to set up an example with the webKb dataset,  
add unit tests to the code and after that go parallel. I would like  
to get some feedback early on, in addition I would feel a lot  
better, if a second and third pair of eyes had a look at the code  
to make sure all obvious mistakes are out as early as possible.


--
This message is automatically generated by JIRA.
-
You can reply to this email to add a comment to the issue online.

[jira] Updated: (MAHOUT-85) Perceptron/Winnow Trainer

[Isabel Drost (JIRA)]

 [ 
https://issues.apache.org/jira/browse/MAHOUT-85?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
 ]

Isabel Drost updated MAHOUT-85:
---

Attachment: perceptronWinnowTrainer.diff

The attachment mentioned above.

> Perceptron/Winnow Trainer
> -
>
> Key: MAHOUT-85
> URL: https://issues.apache.org/jira/browse/MAHOUT-85
> Project: Mahout
>  Issue Type: New Feature
>  Components: Classification
>Reporter: Isabel Drost
> Attachments: perceptronWinnowTrainer.diff
>
>
> Please find attached a first sketch for perceptron and winnow training. 
> Please look very, very carefully at the patch, as I added the heart of the 
> algorithms in the emergency room at Charite Berlin (after I broke my leg when 
> cycling to the Hadoop Get Together ;) ). 
> The patch does not yet feature unit tests nor is it parallelised. Currently 
> my plan is to set up an example with the webKb dataset, add unit tests to the 
> code and after that go parallel. I would like to get some feedback early on, 
> in addition I would feel a lot better, if a second and third pair of eyes had 
> a look at the code to make sure all obvious mistakes are out as early as 
> possible.

-- 
This message is automatically generated by JIRA.
-
You can reply to this email to add a comment to the issue online.