Tree classifiers in MLib

[Charles Earl]

In the latest API docs off of the web page

http://spark.incubator.apache.org/docs/latest/api/mllib/index.html#org.apache.spark.mllib.package

I had not seen tree classifiers included.

Are there plans to include decision trees etc at some point. Is there an interest?

--
- Charles

[Evan R. Sparks]

Yes - Manish Amde and Hirakendu Das have been working on a distributed tree classifier. We are taking the current version through large scale testing and expect to merge it into the master branch soon. I expect that ensembled tree learned (random forests, GBDTs) will follow shortly. 

On Dec 29, 2013, at 10:35 AM, Charles Earl <[hidden email]> wrote:

In the latest API docs off of the web page

http://spark.incubator.apache.org/docs/latest/api/mllib/index.html#org.apache.spark.mllib.package

I had not seen tree classifiers included.

Are there plans to include decision trees etc at some point. Is there an interest?

--
- Charles

[Debasish Das]

Hi Evan,

Could you please point to the git repo for the decision tree classifier or the enhancement JIRA ?

Thanks.
Deb

On Dec 29, 2013 8:55 AM, "Evan Sparks" <[hidden email]> wrote:

Yes - Manish Amde and Hirakendu Das have been working on a distributed tree classifier. We are taking the current version through large scale testing and expect to merge it into the master branch soon. I expect that ensembled tree learned (random forests, GBDTs) will follow shortly. 

On Dec 29, 2013, at 10:35 AM, Charles Earl <[hidden email]> wrote:

In the latest API docs off of the web page

http://spark.incubator.apache.org/docs/latest/api/mllib/index.html#org.apache.spark.mllib.package

I had not seen tree classifiers included.

Are there plans to include decision trees etc at some point. Is there an interest?

--
- Charles

[Charles Earl]

Evan,

As a follow up to Deb's request, is there a wiki page that might contain rough status of algorithm implementations that are under development or even relevant JIRAs? 

Charles

On Dec 29, 2013, at 3:34 PM, Debasish Das <[hidden email]> wrote:

Hi Evan,

Could you please point to the git repo for the decision tree classifier or the enhancement JIRA ?

Thanks.
Deb

On Dec 29, 2013 8:55 AM, "Evan Sparks" <[hidden email]> wrote:

Yes - Manish Amde and Hirakendu Das have been working on a distributed tree classifier. We are taking the current version through large scale testing and expect to merge it into the master branch soon. I expect that ensembled tree learned (random forests, GBDTs) will follow shortly. 

On Dec 29, 2013, at 10:35 AM, Charles Earl <[hidden email]> wrote:

In the latest API docs off of the web page

http://spark.incubator.apache.org/docs/latest/api/mllib/index.html#org.apache.spark.mllib.package

I had not seen tree classifiers included.

Are there plans to include decision trees etc at some point. Is there an interest?

--
- Charles

[Evan R. Sparks]

Hi there,

The current status of improvements planned to MLlib/MLI are here: https://spark-project.atlassian.net/browse/MLI - we've not done a great job of maintaining this JIRA, but we'll plan to update soon.

The tree work is mostly happening here: https://github.com/manishamde/incubator-spark/tree/tree - we're currently working on large scale testing of the code for a single decision tree, and once that looks ready a PR into spark master will follow.

- Evan

On Sun, Dec 29, 2013 at 3:44 PM, Charles Earl <[hidden email]> wrote:

Evan,

As a follow up to Deb's request, is there a wiki page that might contain rough status of algorithm implementations that are under development or even relevant JIRAs? 

Charles

On Dec 29, 2013, at 3:34 PM, Debasish Das <[hidden email]> wrote:

Hi Evan,

Could you please point to the git repo for the decision tree classifier or the enhancement JIRA ?

Thanks.
Deb

On Dec 29, 2013 8:55 AM, "Evan Sparks" <[hidden email]> wrote:

Yes - Manish Amde and Hirakendu Das have been working on a distributed tree classifier. We are taking the current version through large scale testing and expect to merge it into the master branch soon. I expect that ensembled tree learned (random forests, GBDTs) will follow shortly. 

On Dec 29, 2013, at 10:35 AM, Charles Earl <[hidden email]> wrote:

In the latest API docs off of the web page

http://spark.incubator.apache.org/docs/latest/api/mllib/index.html#org.apache.spark.mllib.package

I had not seen tree classifiers included.

Are there plans to include decision trees etc at some point. Is there an interest?

--
- Charles