You are viewing a plain text version of this content. The canonical link for it is here.
Posted to issues@mahout.apache.org by "ASF GitHub Bot (JIRA)" <ji...@apache.org> on 2017/09/21 20:41:00 UTC
[jira] [Commented] (MAHOUT-2015) Expose OLS in Spark ML Pipelines
[ https://issues.apache.org/jira/browse/MAHOUT-2015?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=16175434#comment-16175434 ]
ASF GitHub Bot commented on MAHOUT-2015:
----------------------------------------
GitHub user holdenk opened a pull request:
https://github.com/apache/mahout/pull/340
MAHOUT-2015 [WIP]: Expose Mahout's OLS algorithm in the Spark ML API
### Purpose of PR:
Expose Mahout's OLS algorithm in the Spark ML API
### Important ToDos
Please mark each with an "x"
- [ X] A JIRA ticket exists (if not, please create this first)[https://issues.apache.org/jira/browse/ZEPPELIN/]
- [ X ] Title of PR is "MAHOUT-XXXX Brief Description of Changes" where XXXX is the JIRA number.
- [ X ] Created unit tests where appropriate
- [ X ] Added licenses correct on newly added files
- [ X ] Assigned JIRA to self
- [ ] Added documentation in scala docs/java docs, and to website
- [ ] Successfully built and ran all unit tests, verified that all tests pass locally.
If all of these things aren't complete, but you still feel it is
appropriate to open a PR, please add [WIP] after MAHOUT-XXXX before the
descriptions- e.g. "MAHOUT-XXXX [WIP] Description of Change"
Does this change break earlier versions?
No
Is this the beginning of a larger project for which a feature branch should be made?
No
You can merge this pull request into a Git repository by running:
$ git pull https://github.com/holdenk/mahout add-pipelinesupport-magic
Alternatively you can review and apply these changes as the patch at:
https://github.com/apache/mahout/pull/340.patch
To close this pull request, make a commit to your master/trunk branch
with (at least) the following in the commit message:
This closes #340
----
commit 0e3a9f935cf35bd2fe3b913dc18c374ac409baaa
Author: Holden Karau <ho...@us.ibm.com>
Date: 2017-07-17T02:51:20Z
Start working on porting the first algorithm by hand
commit e52f11b991d420d5f618d755d1d1a1dbccc9a7d9
Author: Holden Karau <ho...@us.ibm.com>
Date: 2017-07-26T00:32:41Z
Start thinking about how to do Spark pipelines for only 2+
commit 29cd357f97ea85a59a6b228219d0de8407be7bf1
Author: Holden Karau <ho...@us.ibm.com>
Date: 2017-07-26T00:33:08Z
Allow us to construct instances of OrderedIntDoubleMapping for making sparse vectors
commit bb57010809e9cf28e50dc2a3c06e2453ec2ddc37
Author: Holden Karau <ho...@us.ibm.com>
Date: 2017-07-26T00:33:40Z
Work on the Spark Estimator
commit 4f03eb664a42b5df9c7c1c93df395e26ff068d23
Author: Holden Karau <ho...@us.ibm.com>
Date: 2017-07-26T00:34:02Z
Continue working on base classes and converters
commit e7f428350d226e15434f0b6d7b6529a1a19f071c
Author: Holden Karau <ho...@us.ibm.com>
Date: 2017-07-26T00:41:27Z
Change the type params so we can extend the predictor class correctly
commit 82a6d144df42e252855005d9a250b2031274bc48
Author: Holden Karau <ho...@us.ibm.com>
Date: 2017-07-30T23:01:40Z
Ok build successful now lets make it reasonable[ish]:
commit c17fdc1c95f5805b111c59bf527b1dc08af6258f
Author: Holden Karau <ho...@us.ibm.com>
Date: 2017-07-30T23:14:55Z
Ok don't specify the return model type in the type params since it seems to make the compiler confused.
commit 20a58863ff2eba2597253cd202f8ad0fc66e7cb5
Author: Holden Karau <ho...@us.ibm.com>
Date: 2017-07-30T23:16:47Z
We already have good enough testing basics
commit 788de480f4b72afb1d1b2b453dabf1eb18686ba6
Author: Holden Karau <ho...@us.ibm.com>
Date: 2017-07-30T23:17:22Z
Testing with local[1] is going to hide a whole class of bugs
commit 73b3669346c17e55945910d07ade90aa72006e3f
Author: Holden Karau <ho...@us.ibm.com>
Date: 2017-09-20T20:49:30Z
Add pipeline tests
commit 632ffd80c956d2faa640dde8bfec506fcebea621
Author: Holden Karau <ho...@us.ibm.com>
Date: 2017-09-20T20:54:56Z
Remove unecessary SuperVisedSparkEstimator in sparkbindings
commit 699bd68d66cc97aed8fc82aa20aa6381262e656e
Author: Holden Karau <ho...@us.ibm.com>
Date: 2017-09-20T22:15:00Z
Remove serializable and switch to Kyro
commit 9ee28233e41a62aa4c89ece4a803aff2c8f76d50
Author: Holden Karau <ho...@us.ibm.com>
Date: 2017-09-20T22:19:45Z
Remove unused/broken import
commit 4f2c1fde8cf8959cb091577640c738b9a6287f5e
Author: Holden Karau <ho...@us.ibm.com>
Date: 2017-09-21T16:08:07Z
Use the built in test framework for now (eventuall want to test withou mahout ctx for bootstrapping but this is a good first step) -- fix reflection used to convert the DRM back to piepline stage
commit 7b4fd3dc79e099610e37d7434afefd8918f134ad
Author: Holden Karau <ho...@us.ibm.com>
Date: 2017-09-21T20:05:53Z
Switch back to 1.6.3
commit 7f45935cd567ae0c0d0e40c228c91417ec5b94b4
Author: Holden Karau <ho...@us.ibm.com>
Date: 2017-09-21T20:07:26Z
Remove repo since not using different test lib
----
> Expose OLS in Spark ML Pipelines
> --------------------------------
>
> Key: MAHOUT-2015
> URL: https://issues.apache.org/jira/browse/MAHOUT-2015
> Project: Mahout
> Issue Type: Sub-task
> Reporter: holdenk
> Assignee: holdenk
>
--
This message was sent by Atlassian JIRA
(v6.4.14#64029)