[jira] [Created] (MAHOUT-1929) Add Generalized Linear Models

Discussion:

Trevor Grant (JIRA)

2017-02-01 03:45:51 UTC

Trevor Grant created MAHOUT-1929:
------------------------------------

Summary: Add Generalized Linear Models
Key: MAHOUT-1929
URL: https://issues.apache.org/jira/browse/MAHOUT-1929
Project: Mahout
Issue Type: Wish
Components: Algorithms
Affects Versions: 0.13.1
Reporter: Trevor Grant

Implement generalize Linear Models (GLM)

https://en.wikipedia.org/wiki/Generalized_linear_model

--
This message was sent by Atlassian JIRA
(v6.3.15#6346)

Saikat Kanjilal (JIRA)

2017-02-27 21:08:45 UTC

Permalink

[ https://issues.apache.org/jira/browse/MAHOUT-1929?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15886533#comment-15886533 ]

Saikat Kanjilal commented on MAHOUT-1929:
-----------------------------------------

[~rawkintrevo] I was going to start working on this along with ALS, here's my thinking of the overall approach:

1) Put up an API for this to the mahout dev list
2) Start working on unit tests and then the code
3) I browsed through the web and found this implementation, I figured it may give us some inspirational ideas: https://github.com/BIDData/BIDMach/blob/master/src/main/scala/BIDMach/models/GLM.scala, this implementation has a similar theme where they derive from a model and regressionModel and then use options for all the hyper parameters. One thought I had was to take the gist of this and replace all the matrix operations with samsara functions instead

What do you think of the above plan?

Post by Trevor Grant (JIRA)
Add Generalized Linear Models
-----------------------------
Key: MAHOUT-1929
URL: https://issues.apache.org/jira/browse/MAHOUT-1929
Project: Mahout
Issue Type: Wish
Components: Algorithms
Affects Versions: 0.13.1
Reporter: Trevor Grant
Implement generalize Linear Models (GLM)
https://en.wikipedia.org/wiki/Generalized_linear_model

--
This message was sent by Atlassian JIRA
(v6.3.15#6346)

Andrew Musselman (JIRA)

2017-02-27 21:22:45 UTC

Permalink

[ https://issues.apache.org/jira/browse/MAHOUT-1929?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15886554#comment-15886554 ]

Andrew Musselman commented on MAHOUT-1929:
------------------------------------------

Sounds good; let's shoot for a point release soon if you can, or definitely for 0.14.

Thanks!

--
This message was sent by Atlassian JIRA
(v6.3.15#6346)

Saikat Kanjilal (JIRA)

2017-03-04 23:11:46 UTC

Permalink

[ https://issues.apache.org/jira/browse/MAHOUT-1929?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15895934#comment-15895934 ]

Saikat Kanjilal commented on MAHOUT-1929:
-----------------------------------------

Ok time to get down to business, [~jimjag] and Aditya I've started the implementation here:

https://github.com/skanjila/mahout/blob/mahout-1929/math-scala/src/main/scala/org/apache/mahout/math/algorithms/regression/GlmModel.scala

I've brought over the GLM implementation from https://github.com/BIDData/BIDMach/blob/master/src/main/scala/BIDMach/models/GLM.scala and I've merged that with implementing the methods for the traits RegressorModel and RegressorFitter.

Next steps:
1) Take a look at the methods that I've commented out and come up with a way to incorporate them into the object model established by [~rawkintrevo]
2) Propose some ideas on the devlist or JIRA or all the different types of regression we want to support, to get this off the ground I would propose we just stick to linear and logistic regression
3) Start stubbing out unit tests and check that into my branch so that we can collaborate

[~andrew.musselman][~rawkintrevo] would love some feedback on the general approach as well.
Thanks

--
This message was sent by Atlassian JIRA
(v6.3.15#6346)

Trevor Grant

2017-03-05 02:12:06 UTC

Permalink

Nice- in the middle of some other stuff, but on first glance I'd recommend
extending LinearRegressorModel, (instead of RegressorModel) (sames goes for
fitters) you'll get a lot of the calculateStandardError type of stuff for
free.

Trevor Grant
Data Scientist
https://github.com/rawkintrevo
http://stackexchange.com/users/3002022/rawkintrevo
http://trevorgrant.org

*"Fortunate is he, who is able to know the causes of things." -Virgil*

Post by Saikat Kanjilal (JIRA)
[ https://issues.apache.org/jira/browse/MAHOUT-1929?page=
com.atlassian.jira.plugin.system.issuetabpanels:comment-
tabpanel&focusedCommentId=15895934#comment-15895934 ]
-----------------------------------------
https://github.com/skanjila/mahout/blob/mahout-1929/math-
scala/src/main/scala/org/apache/mahout/math/algorithms/
regression/GlmModel.scala
I've brought over the GLM implementation from https://github.com/BIDData/
BIDMach/blob/master/src/main/scala/BIDMach/models/GLM.scala and I've
merged that with implementing the methods for the traits RegressorModel and
RegressorFitter.
1) Take a look at the methods that I've commented out and come up with a
way to incorporate them into the object model established by [~rawkintrevo]
2) Propose some ideas on the devlist or JIRA or all the different types of
regression we want to support, to get this off the ground I would propose
we just stick to linear and logistic regression
3) Start stubbing out unit tests and check that into my branch so that we can collaborate
[~andrew.musselman][~rawkintrevo] would love some feedback on the general approach as well.
Thanks

--
This message was sent by Atlassian JIRA
(v6.3.15#6346)

Saikat Kanjilal (JIRA)

2017-03-05 23:57:32 UTC

Permalink

[ https://issues.apache.org/jira/browse/MAHOUT-1929?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15896616#comment-15896616 ]

Saikat Kanjilal commented on MAHOUT-1929:
-----------------------------------------

[~rawkintrevo] for simplicity's sake lets keep all work/conversations for GLM inside only this JIRA, mahout-1941 is linked to this and will be indirectly fixed when glm is in place, that being said I spent some time thinking about what you proposed and GLM seems like a superclass for linear as well as possion as well as logistic regression, this was the reason that I had GLM derive from Regressor as opposed to linear regressor, at the end of thie implementation linear regression will be one of the choices of glm but not necessarily the only end result, if it makes sense to reuse the functionality from linearregressor what do you think about creating a separate glmregressor that all the other regressors can derive from.

Thoughts?

--
This message was sent by Atlassian JIRA
(v6.3.15#6346)

Saikat Kanjilal (JIRA)

2017-03-05 23:58:32 UTC

Permalink

[ https://issues.apache.org/jira/browse/MAHOUT-1929?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15896616#comment-15896616 ]

Saikat Kanjilal edited comment on MAHOUT-1929 at 3/5/17 11:57 PM:
------------------------------------------------------------------

[~rawkintrevo] for simplicity's sake lets keep all work/conversations for GLM inside only this JIRA, mahout-1941 is linked to this and will be indirectly fixed when glm is in place, that being said I spent some time thinking about what you proposed and GLM seems like a superclass for linear as well as possion as well as logistic regression, this was the reason that I had GLM derive from Regressor as opposed to linear regressor, at the end of thie implementation linear regression will be one of the choices of glm but not necessarily the only end result, if it makes sense to reuse the functionality from linearregressor what do you think about creating a separate glmregressor that all the other regressors can derive from. I also added a stubbed out unit test here: https://github.com/skanjila/mahout/blob/mahout-1929/math-scala/src/test/scala/org/apache/mahout/math/algorithms/GlmSuiteBase.scala

Thoughts?

was (Author: kanjilal):
[~rawkintrevo] for simplicity's sake lets keep all work/conversations for GLM inside only this JIRA, mahout-1941 is linked to this and will be indirectly fixed when glm is in place, that being said I spent some time thinking about what you proposed and GLM seems like a superclass for linear as well as possion as well as logistic regression, this was the reason that I had GLM derive from Regressor as opposed to linear regressor, at the end of thie implementation linear regression will be one of the choices of glm but not necessarily the only end result, if it makes sense to reuse the functionality from linearregressor what do you think about creating a separate glmregressor that all the other regressors can derive from.

Thoughts?

--
This message was sent by Atlassian JIRA
(v6.3.15#6346)

Saikat Kanjilal (JIRA)

2017-03-11 15:26:04 UTC

Permalink

[ https://issues.apache.org/jira/browse/MAHOUT-1929?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15906225#comment-15906225 ]

Saikat Kanjilal commented on MAHOUT-1929:
-----------------------------------------

[~rawkintrevo] I've spent the past few days looking at already existing GLM implementations that would fit cleanly into the current architecture inside mahout (namely the LinearRegressorFitter and LienarRegressorModel etc), between this implementation that I already brought across https://github.com/BIDData/BIDMach/blob/master/src/main/scala/BIDMach/models/GLM.scala and this one https://github.com/scalation/scalation/blob/master/src/main/scala/scalation/analytics/par/GLM.scala I am leaning towards the latter, effectively we can mimic the structure of having apply functions inside GLM and keep our other infrastructure inside each of the Regression classes, this way we can reuse the functions already created inside RegressorFitter and RegressorModel, one idea to go along with this is to move these functions into GLMFitter and GLMModel and then have each of the derived regressor classes derive from this.

Would like to get a general brainstorm input from you, [~andrew.musselman] and [~jimjag] to avoid designing by 1 person syndrome :)

--
This message was sent by Atlassian JIRA
(v6.3.15#6346)

Saikat Kanjilal (JIRA)

2017-03-12 01:25:04 UTC

Permalink

[ https://issues.apache.org/jira/browse/MAHOUT-1929?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15906388#comment-15906388 ]

Saikat Kanjilal commented on MAHOUT-1929:
-----------------------------------------

Ok more progress, I decided to take the strategy that scalation is taking in implementing GLM (https://github.com/scalation/scalation/blob/master/src/main/scala/scalation/analytics/par/GLM.scala), I have:
1) Added a set of apply functions that reuse our existing infrastructure to compute the models that already exist, namely for Linear Regression and Ordinary Least Squares
2) I have placed this code inside GLMModel for now

Code is here: https://github.com/skanjila/mahout/blob/mahout-1929/math-scala/src/main/scala/org/apache/mahout/math/algorithms/regression/GlmModel.scala

Would really appreciate a looksy from all interested parties identified in the above comments before I get too much farther :), next steps include:
1) unit tests for the apply functions
2) figure out a creative way to tie in the other functions into the apply API infrastructure:

def fit(drmX: DrmLike[K],
drmTarget: DrmLike[K],
hyperparameters: (Symbol, Any)*): GlmModel[K]

def setStandardHyperparameters(hyperparameters: Map[Symbol, Any] = Map('foo -> None)): Unit

def calculateStandardError[M[K] <: GlmModel[K]](X: DrmLike[K],
drmTarget: DrmLike[K],
drmXtXinv: Matrix,
model: M[K]): M[K]

def modelPostprocessing[M[K] <: GlmModel[K]](model: M[K],
X: DrmLike[K],
drmTarget: DrmLike[K],
drmXtXinv: Matrix): M[K]

Here are my thoughts on the above, my philosophy is that we keep around as much of the existing infrastructure that [~rawkintrevo] has put in place and therefore these may need to just be implemented inside each of the derived classes, I would like to see the apply function eventually do the following: 1) compute the model 2) train the model 3) do the prediction 4) build quality measures around each of the models

Thoughts ?

--
This message was sent by Atlassian JIRA
(v6.3.15#6346)

Saikat Kanjilal (JIRA)

2017-03-13 22:33:41 UTC

Permalink

[ https://issues.apache.org/jira/browse/MAHOUT-1929?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15923098#comment-15923098 ]

Saikat Kanjilal commented on MAHOUT-1929:
-----------------------------------------

More progress, added a successful unit test using the new GlmModel here: https://github.com/skanjila/mahout/blob/mahout-1929/math-scala/src/test/scala/org/apache/mahout/math/algorithms/GlmSuiteBase.scala

Refactored the GlmModel code to leverage LinearRegressorModel instead: https://github.com/skanjila/mahout/blob/mahout-1929/math-scala/src/main/scala/org/apache/mahout/math/algorithms/regression/GlmModel.scala to make things a bit easier given the current architecture

[~rawkintrevo] any chance we could do a quick google hangout to discuss design before I get too far ahead? Would love some feedback to make sure this goes smoothly, I know you are busy with 0.13 so let me know what works

--
This message was sent by Atlassian JIRA
(v6.3.15#6346)

Saikat Kanjilal

2017-03-15 15:13:21 UTC

Permalink

@Trevor, I know you're busy with 0.13, when you have a moment I would really appreciate some input before I forge further ahead or a quick google hangout design review of what I've put into place. Just wanting to make sure this gets into the next release.
Thanks in advance for your time.

Sent from my iPhone

Begin forwarded message:

From: "Saikat Kanjilal (JIRA)" <***@apache.org<mailto:***@apache.org>>
Date: March 13, 2017 at 3:33:41 PM PDT
To: <***@mahout.apache.org<mailto:***@mahout.apache.org>>
Subject: [jira] [Commented] (MAHOUT-1929) Add Generalized Linear Models
Reply-To: <***@mahout.apache.org<mailto:***@mahout.apache.org>>

[ https://issues.apache.org/jira/browse/MAHOUT-1929?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15923098#comment-15923098 ]

Saikat Kanjilal commented on MAHOUT-1929:
-----------------------------------------

More progress, added a successful unit test using the new GlmModel here: https://github.com/skanjila/mahout/blob/mahout-1929/math-scala/src/test/scala/org/apache/mahout/math/algorithms/GlmSuiteBase.scala

Refactored the GlmModel code to leverage LinearRegressorModel instead: https://github.com/skanjila/mahout/blob/mahout-1929/math-scala/src/main/scala/org/apache/mahout/math/algorithms/regression/GlmModel.scala to make things a bit easier given the current architecture

[~rawkintrevo] any chance we could do a quick google hangout to discuss design before I get too far ahead? Would love some feedback to make sure this goes smoothly, I know you are busy with 0.13 so let me know what works

Add Generalized Linear Models
-----------------------------

Key: MAHOUT-1929
URL: https://issues.apache.org/jira/browse/MAHOUT-1929
Project: Mahout
Issue Type: Wish
Components: Algorithms
Affects Versions: 0.13.1
Reporter: Trevor Grant

Implement generalize Linear Models (GLM)
https://en.wikipedia.org/wiki/Generalized_linear_model

--
This message was sent by Atlassian JIRA
(v6.3.15#6346)

Trevor Grant

2017-03-16 14:41:51 UTC

Permalink

Also at Strata- thanks for reaching out a second time- totally missed your
first message.

I'll check this out tomorrow on the flight home. We can set something up
from there. Thanks for the contribution!!

tg

Trevor Grant
Data Scientist
https://github.com/rawkintrevo
http://stackexchange.com/users/3002022/rawkintrevo
http://trevorgrant.org

*"Fortunate is he, who is able to know the causes of things." -Virgil*

Post by Saikat Kanjilal
@Trevor, I know you're busy with 0.13, when you have a moment I would
really appreciate some input before I forge further ahead or a quick google
hangout design review of what I've put into place. Just wanting to make
sure this gets into the next release.
Thanks in advance for your time.
Sent from my iPhone
Date: March 13, 2017 at 3:33:41 PM PDT
Subject: [jira] [Commented] (MAHOUT-1929) Add Generalized Linear Models
[ https://issues.apache.org/jira/browse/MAHOUT-1929?page=
com.atlassian.jira.plugin.system.issuetabpanels:comment-
tabpanel&focusedCommentId=15923098#comment-15923098 ]
-----------------------------------------
https://github.com/skanjila/mahout/blob/mahout-1929/math-
scala/src/test/scala/org/apache/mahout/math/algorithms/GlmSuiteBase.scala
https://github.com/skanjila/mahout/blob/mahout-1929/math-
scala/src/main/scala/org/apache/mahout/math/algorithms/
regression/GlmModel.scala to make things a bit easier given the current
architecture
[~rawkintrevo] any chance we could do a quick google hangout to discuss
design before I get too far ahead? Would love some feedback to make sure
this goes smoothly, I know you are busy with 0.13 so let me know what works
Add Generalized Linear Models
-----------------------------
Key: MAHOUT-1929
URL: https://issues.apache.org/jira/browse/MAHOUT-1929
Project: Mahout
Issue Type: Wish
Components: Algorithms
Affects Versions: 0.13.1
Reporter: Trevor Grant
Implement generalize Linear Models (GLM)
https://en.wikipedia.org/wiki/Generalized_linear_model
--
This message was sent by Atlassian JIRA
(v6.3.15#6346)

Saikat Kanjilal

2017-03-18 20:04:38 UTC

Permalink

Sounds good, looking forward to collaborating on this. Let me know next steps.

Sent from my iPhone

Post by Trevor Grant
Also at Strata- thanks for reaching out a second time- totally missed your
first message.
I'll check this out tomorrow on the flight home. We can set something up
from there. Thanks for the contribution!!
tg
Trevor Grant
Data Scientist
https://github.com/rawkintrevo
http://stackexchange.com/users/3002022/rawkintrevo
http://trevorgrant.org
*"Fortunate is he, who is able to know the causes of things." -Virgil*

Saikat Kanjilal

2017-03-24 16:23:15 UTC

Permalink

@Trevor

Its been a week and haven't heard back on this, guessing you are buried with 0.13 release at this point and that you have not had time to check this in detail, what do you think should I keep progressing on the design, I want to make sure I am making timely progress to a deliverable for GLM for 0.14, otoh would hate to do throw away work before a design review in detail, let me know your thoughts.

Regards

________________________________
From: Trevor Grant <***@gmail.com>
Sent: Thursday, March 16, 2017 7:41 AM
To: ***@mahout.apache.org
Subject: Re: [jira] [Commented] (MAHOUT-1929) Add Generalized Linear Models

Also at Strata- thanks for reaching out a second time- totally missed your
first message.

I'll check this out tomorrow on the flight home. We can set something up
from there. Thanks for the contribution!!

tg

Trevor Grant
Data Scientist
https://github.com/rawkintrevo
[https://avatars3.githubusercontent.com/u/5852441?v=3&s=400]<https://github.com/rawkintrevo>

rawkintrevo (Trevor Grant) · GitHub<https://github.com/rawkintrevo>
github.com
rawkintrevo has 22 repositories available. Follow their code on GitHub.

http://stackexchange.com/users/3002022/rawkintrevo
User rawkintrevo - Stack Exchange<http://stackexchange.com/users/3002022/rawkintrevo>
stackexchange.com
Fortuna Audaces Iuvat ~Chance Favors the Bold. top accounts reputation activity favorites subscriptions. Top Questions

http://trevorgrant.org

*"Fortunate is he, who is able to know the causes of things." -Virgil*

Saikat Kanjilal

2017-03-29 23:24:59 UTC

Permalink

@Trevor politely re-pinging again on this, thoughts on next steps :). I'm in a holding pattern at the moment.

________________________________
From: Saikat Kanjilal <***@hotmail.com>
Sent: Friday, March 24, 2017 9:23 AM
To: ***@mahout.apache.org
Subject: Re: [jira] [Commented] (MAHOUT-1929) Add Generalized Linear Models

@Trevor

Its been a week and haven't heard back on this, guessing you are buried with 0.13 release at this point and that you have not had time to check this in detail, what do you think should I keep progressing on the design, I want to make sure I am making timely progress to a deliverable for GLM for 0.14, otoh would hate to do throw away work before a design review in detail, let me know your thoughts.

Regards

________________________________
From: Trevor Grant <***@gmail.com>
Sent: Thursday, March 16, 2017 7:41 AM
To: ***@mahout.apache.org
Subject: Re: [jira] [Commented] (MAHOUT-1929) Add Generalized Linear Models

Also at Strata- thanks for reaching out a second time- totally missed your
first message.

I'll check this out tomorrow on the flight home. We can set something up
from there. Thanks for the contribution!!

tg

Trevor Grant
Data Scientist
https://github.com/rawkintrevo
[https://avatars3.githubusercontent.com/u/5852441?v=3&s=400]<https://github.com/rawkintrevo>

rawkintrevo (Trevor Grant) · GitHub<https://github.com/rawkintrevo>
github.com
rawkintrevo has 24 repositories available. Follow their code on GitHub.

[https://avatars3.githubusercontent.com/u/5852441?v=3&s=400]<https://github.com/rawkintrevo>

rawkintrevo (Trevor Grant) · GitHub<https://github.com/rawkintrevo>
github.com
rawkintrevo has 22 repositories available. Follow their code on GitHub.

http://stackexchange.com/users/3002022/rawkintrevo
User rawkintrevo - Stack Exchange<http://stackexchange.com/users/3002022/rawkintrevo>
stackexchange.com
Fortuna Audaces Iuvat ~Chance Favors the Bold. top accounts reputation activity favorites subscriptions. Top Questions

http://trevorgrant.org

*"Fortunate is he, who is able to know the causes of things." -Virgil*

Saikat Kanjilal

2017-03-29 23:44:17 UTC

Permalink

Andy,

Thanks for the update, the non licensed code was a starting point which I was emulating to kick this effort off, I was not intending to use that code, I mimiced part of the code setup in the pull request, ping me further after more review.

Thanks

________________________________
From: Andrew Palumbo <***@outlook.com>
Sent: Wednesday, March 29, 2017 4:37 PM
To: ***@mahout.apache.org
Subject: Re: [jira] [Commented] (MAHOUT-1929) Add Generalized Linear Models

Hi Saikat,

I closed the Jira because in it you pointed to some non ASF liscensed code, which I then saw in the pull request- I'm not sure of when I'll have a chance to review it further, but I will let you know if this is an effort that we can continue on.

Andy

________________________________
From: Saikat Kanjilal <***@hotmail.com>
Sent: Wednesday, March 29, 2017 7:24:59 PM
To: ***@mahout.apache.org
Subject: Re: [jira] [Commented] (MAHOUT-1929) Add Generalized Linear Models

@Trevor politely re-pinging again on this, thoughts on next steps :). I'm in a holding pattern at the moment.

________________________________
From: Saikat Kanjilal <***@hotmail.com>
Sent: Friday, March 24, 2017 9:23 AM
To: ***@mahout.apache.org
Subject: Re: [jira] [Commented] (MAHOUT-1929) Add Generalized Linear Models

@Trevor

Its been a week and haven't heard back on this, guessing you are buried with 0.13 release at this point and that you have not had time to check this in detail, what do you think should I keep progressing on the design, I want to make sure I am making timely progress to a deliverable for GLM for 0.14, otoh would hate to do throw away work before a design review in detail, let me know your thoughts.

Regards

________________________________
From: Trevor Grant <***@gmail.com>
Sent: Thursday, March 16, 2017 7:41 AM
To: ***@mahout.apache.org
Subject: Re: [jira] [Commented] (MAHOUT-1929) Add Generalized Linear Models

Also at Strata- thanks for reaching out a second time- totally missed your
first message.

I'll check this out tomorrow on the flight home. We can set something up
from there. Thanks for the contribution!!

tg

Trevor Grant
Data Scientist
https://github.com/rawkintrevo
[https://avatars3.githubusercontent.com/u/5852441?v=3&s=400]<https://github.com/rawkintrevo>

rawkintrevo (Trevor Grant) · GitHub<https://github.com/rawkintrevo>
github.com
rawkintrevo has 24 repositories available. Follow their code on GitHub.

[https://avatars3.githubusercontent.com/u/5852441?v=3&s=400]<https://github.com/rawkintrevo>

rawkintrevo (Trevor Grant) · GitHub<https://github.com/rawkintrevo>
[https://avatars3.githubusercontent.com/u/5852441?v=3&s=400]<https://github.com/rawkintrevo>

rawkintrevo (Trevor Grant) · GitHub<https://github.com/rawkintrevo>
github.com
rawkintrevo has 24 repositories available. Follow their code on GitHub.

github.com
rawkintrevo has 24 repositories available. Follow their code on GitHub.

[https://avatars3.githubusercontent.com/u/5852441?v=3&s=400]<https://github.com/rawkintrevo>

rawkintrevo (Trevor Grant) · GitHub<https://github.com/rawkintrevo>
github.com
rawkintrevo has 22 repositories available. Follow their code on GitHub.

http://stackexchange.com/users/3002022/rawkintrevo
User rawkintrevo - Stack Exchange<http://stackexchange.com/users/3002022/rawkintrevo>
stackexchange.com
Fortuna Audaces Iuvat ~Chance Favors the Bold. top accounts reputation activity favorites subscriptions. Top Questions

http://trevorgrant.org

*"Fortunate is he, who is able to know the causes of things." -Virgil*

Saikat Kanjilal

2017-03-30 15:13:05 UTC

Permalink

Andy/Trevor,
I wanted to do an additional follow up on this as I'm running short on time, as I mentioned earlier I need to implement glm for work using samsara as this is something our data scientists need to use. Given that I have a deadline at the end of April I will be moving ahead with an implementation. When I finish I will send a pull request and you guys can decide how to proceed at that point, if it's ok with you I will reopen that JIRA again and add the pull request there.

Let me know your thoughts

Sent from my iPhone

Post by Saikat Kanjilal
Andy,
Thanks for the update, the non licensed code was a starting point which I was emulating to kick this effort off, I was not intending to use that code, I mimiced part of the code setup in the pull request, ping me further after more review.
Thanks
________________________________
Sent: Wednesday, March 29, 2017 4:37 PM
Subject: Re: [jira] [Commented] (MAHOUT-1929) Add Generalized Linear Models
Hi Saikat,
I closed the Jira because in it you pointed to some non ASF liscensed code, which I then saw in the pull request- I'm not sure of when I'll have a chance to review it further, but I will let you know if this is an effort that we can continue on.
Andy
________________________________
Sent: Wednesday, March 29, 2017 7:24:59 PM
Subject: Re: [jira] [Commented] (MAHOUT-1929) Add Generalized Linear Models
@Trevor politely re-pinging again on this, thoughts on next steps :). I'm in a holding pattern at the moment.
________________________________
Sent: Friday, March 24, 2017 9:23 AM
Subject: Re: [jira] [Commented] (MAHOUT-1929) Add Generalized Linear Models
@Trevor
Its been a week and haven't heard back on this, guessing you are buried with 0.13 release at this point and that you have not had time to check this in detail, what do you think should I keep progressing on the design, I want to make sure I am making timely progress to a deliverable for GLM for 0.14, otoh would hate to do throw away work before a design review in detail, let me know your thoughts.
Regards
________________________________
Sent: Thursday, March 16, 2017 7:41 AM
Subject: Re: [jira] [Commented] (MAHOUT-1929) Add Generalized Linear Models
Also at Strata- thanks for reaching out a second time- totally missed your
first message.
I'll check this out tomorrow on the flight home. We can set something up
from there. Thanks for the contribution!!
tg
Trevor Grant
Data Scientist
https://github.com/rawkintrevo
[https://avatars3.githubusercontent.com/u/5852441?v=3&s=400]<https://github.com/rawkintrevo>
rawkintrevo (Trevor Grant) · GitHub<https://github.com/rawkintrevo>
github.com
rawkintrevo has 24 repositories available. Follow their code on GitHub.
[https://avatars3.githubusercontent.com/u/5852441?v=3&s=400]<https://github.com/rawkintrevo>
rawkintrevo (Trevor Grant) · GitHub<https://github.com/rawkintrevo>
[https://avatars3.githubusercontent.com/u/5852441?v=3&s=400]<https://github.com/rawkintrevo>
rawkintrevo (Trevor Grant) · GitHub<https://github.com/rawkintrevo>
github.com
rawkintrevo has 24 repositories available. Follow their code on GitHub.
github.com
rawkintrevo has 24 repositories available. Follow their code on GitHub.
[https://avatars3.githubusercontent.com/u/5852441?v=3&s=400]<https://github.com/rawkintrevo>
rawkintrevo (Trevor Grant) · GitHub<https://github.com/rawkintrevo>
github.com
rawkintrevo has 22 repositories available. Follow their code on GitHub.
http://stackexchange.com/users/3002022/rawkintrevo
User rawkintrevo - Stack Exchange<http://stackexchange.com/users/3002022/rawkintrevo>
stackexchange.com
Fortuna Audaces Iuvat ~Chance Favors the Bold. top accounts reputation activity favorites subscriptions. Top Questions
http://trevorgrant.org
*"Fortunate is he, who is able to know the causes of things." -Virgil*

Saikat Kanjilal

2017-04-19 04:09:28 UTC

Permalink

Trevor/Andy,
Now that the release is out there I'd like to work with you guys to get glm into mahout, I've made a fair bit of progress in getting the code incorporated based on ideas that I had shared earlier from others who have done this, I've taken these ideas and modified them to use Samsara. I'm looking for a bit of guidance on logical next steps on this. We can start by reopening this JIRA or creating a new one.

Thoughts/interest?

Sent from my iPhone

Post by Saikat Kanjilal
Hi Saikat,
I closed the Jira because in it you pointed to some non ASF liscensed code, which I then saw in the pull request- I'm not sure of when I'll have a chance to review it further, but I will let you know if this is an effort that we can continue on.
Andy
________________________________
Sent: Wednesday, March 29, 2017 7:24:59 PM
Subject: Re: [jira] [Commented] (MAHOUT-1929) Add Generalized Linear Models
@Trevor politely re-pinging again on this, thoughts on next steps :). I'm in a holding pattern at the moment.
________________________________
Sent: Friday, March 24, 2017 9:23 AM
Subject: Re: [jira] [Commented] (MAHOUT-1929) Add Generalized Linear Models
@Trevor
Its been a week and haven't heard back on this, guessing you are buried with 0.13 release at this point and that you have not had time to check this in detail, what do you think should I keep progressing on the design, I want to make sure I am making timely progress to a deliverable for GLM for 0.14, otoh would hate to do throw away work before a design review in detail, let me know your thoughts.
Regards
________________________________
Sent: Thursday, March 16, 2017 7:41 AM
Subject: Re: [jira] [Commented] (MAHOUT-1929) Add Generalized Linear Models
Also at Strata- thanks for reaching out a second time- totally missed your
first message.
I'll check this out tomorrow on the flight home. We can set something up
from there. Thanks for the contribution!!
tg
Trevor Grant
Data Scientist
https://github.com/rawkintrevo
[https://avatars3.githubusercontent.com/u/5852441?v=3&s=400]<https://github.com/rawkintrevo>
rawkintrevo (Trevor Grant) · GitHub<https://github.com/rawkintrevo>
github.com
rawkintrevo has 24 repositories available. Follow their code on GitHub.
[https://avatars3.githubusercontent.com/u/5852441?v=3&s=400]<https://github.com/rawkintrevo>
rawkintrevo (Trevor Grant) · GitHub<https://github.com/rawkintrevo>
github.com
rawkintrevo has 22 repositories available. Follow their code on GitHub.
http://stackexchange.com/users/3002022/rawkintrevo
User rawkintrevo - Stack Exchange<http://stackexchange.com/users/3002022/rawkintrevo>
stackexchange.com
Fortuna Audaces Iuvat ~Chance Favors the Bold. top accounts reputation activity favorites subscriptions. Top Questions
http://trevorgrant.org
*"Fortunate is he, who is able to know the causes of things." -Virgil*

Andrew Musselman

2017-04-19 04:13:37 UTC

Permalink

My recollection is your original PR had some compliance issues and the JIRA
was closed out.

Post by Saikat Kanjilal
Trevor/Andy,
Now that the release is out there I'd like to work with you guys to get
glm into mahout, I've made a fair bit of progress in getting the code
incorporated based on ideas that I had shared earlier from others who have
done this, I've taken these ideas and modified them to use Samsara. I'm
looking for a bit of guidance on logical next steps on this. We can start
by reopening this JIRA or creating a new one.
Thoughts/interest?
Sent from my iPhone

Post by Saikat Kanjilal
Hi Saikat,
I closed the Jira because in it you pointed to some non ASF liscensed

code, which I then saw in the pull request- I'm not sure of when I'll have
a chance to review it further, but I will let you know if this is an effort
that we can continue on.

Post by Saikat Kanjilal
Andy
________________________________
Sent: Wednesday, March 29, 2017 7:24:59 PM
Subject: Re: [jira] [Commented] (MAHOUT-1929) Add Generalized Linear

Models

Post by Saikat Kanjilal
@Trevor politely re-pinging again on this, thoughts on next steps :).

I'm in a holding pattern at the moment.

Post by Saikat Kanjilal
________________________________
Sent: Friday, March 24, 2017 9:23 AM
Subject: Re: [jira] [Commented] (MAHOUT-1929) Add Generalized Linear

Models

Post by Saikat Kanjilal
@Trevor
Its been a week and haven't heard back on this, guessing you are buried

with 0.13 release at this point and that you have not had time to check
this in detail, what do you think should I keep progressing on the design,
I want to make sure I am making timely progress to a deliverable for GLM
for 0.14, otoh would hate to do throw away work before a design review in
detail, let me know your thoughts.

Post by Saikat Kanjilal
Regards
________________________________
Sent: Thursday, March 16, 2017 7:41 AM
Subject: Re: [jira] [Commented] (MAHOUT-1929) Add Generalized Linear

Models

Post by Saikat Kanjilal
Also at Strata- thanks for reaching out a second time- totally missed

your

Post by Saikat Kanjilal
first message.
I'll check this out tomorrow on the flight home. We can set something up
from there. Thanks for the contribution!!
tg
Trevor Grant
Data Scientist
https://github.com/rawkintrevo
[https://avatars3.githubusercontent.com/u/5852441?v=3&s=400]<https://

github.com/rawkintrevo>

Post by Saikat Kanjilal
rawkintrevo (Trevor Grant) Â· GitHub<https://github.com/rawkintrevo>
github.com
rawkintrevo has 24 repositories available. Follow their code on GitHub.
[https://avatars3.githubusercontent.com/u/5852441?v=3&s=400]<https://

github.com/rawkintrevo>

Post by Saikat Kanjilal
rawkintrevo (Trevor Grant) Â· GitHub<https://github.com/rawkintrevo>
github.com
rawkintrevo has 22 repositories available. Follow their code on GitHub.
http://stackexchange.com/users/3002022/rawkintrevo
User rawkintrevo - Stack Exchange<http://stackexchange.

com/users/3002022/rawkintrevo>

Post by Saikat Kanjilal
stackexchange.com
Fortuna Audaces Iuvat ~Chance Favors the Bold. top accounts reputation

activity favorites subscriptions. Top Questions

Post by Saikat Kanjilal
http://trevorgrant.org
*"Fortunate is he, who is able to know the causes of things." -Virgil*

Post by Saikat Kanjilal
@Trevor, I know you're busy with 0.13, when you have a moment I would
really appreciate some input before I forge further ahead or a quick

google