Github user dbtsai commented on a diff in the pull request:
https://github.com/apache/spark/pull/17078#discussion_r103342591
--- Diff:
mllib/src/test/scala/org/apache/spark/ml/classification/LogisticRegressionSuite.scala
---
@@ -456,6 +456,32 @@ class LogisticRegressionSuite
Github user dbtsai commented on a diff in the pull request:
https://github.com/apache/spark/pull/17078#discussion_r103342093
--- Diff:
mllib/src/main/scala/org/apache/spark/ml/classification/LogisticRegression.scala
---
@@ -1447,7 +1447,7 @@ private class LogisticAggregator
Github user dbtsai commented on a diff in the pull request:
https://github.com/apache/spark/pull/17078#discussion_r103342317
--- Diff:
mllib/src/main/scala/org/apache/spark/ml/classification/LogisticRegression.scala
---
@@ -1431,7 +1431,12 @@ private class LogisticAggregator
Github user dbtsai commented on a diff in the pull request:
https://github.com/apache/spark/pull/17078#discussion_r103154658
--- Diff:
mllib/src/main/scala/org/apache/spark/ml/classification/LogisticRegression.scala
---
@@ -1447,7 +1447,7 @@ private class LogisticAggregator
Github user dbtsai commented on the issue:
https://github.com/apache/spark/pull/16037
Sorry for late review. Just come back to US. LGTM too! Thanks.
---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does
Github user dbtsai commented on the issue:
https://github.com/apache/spark/pull/15893
LGTM. Since this doesn't have impact on performance, and make the codebase
cleaner, I merged this PR into master and branch 2.1. Thanks.
---
If your project is set up for it, you can reply
Github user dbtsai commented on a diff in the pull request:
https://github.com/apache/spark/pull/15893#discussion_r88767607
--- Diff:
mllib/src/main/scala/org/apache/spark/ml/classification/LogisticRegression.scala
---
@@ -586,15 +577,24 @@ class LogisticRegression @Since("
Github user dbtsai commented on the issue:
https://github.com/apache/spark/pull/15893
Only minor naming. LGTM. My interest can not access ssh to merge the code,
will merge later tonight. Thanks.
---
If your project is set up for it, you can reply to this email and have your
reply
Github user dbtsai commented on the issue:
https://github.com/apache/spark/pull/15876
LGTM. Thanks. Merged into master and 2.1 branch.
@srowen Are you referring the MLOR PR which has many followup PRs? If so,
the changes in the main MLOR PR is very big, and many of the issues
Github user dbtsai commented on the issue:
https://github.com/apache/spark/pull/15593
Thanks all for working on this PR. I merged this into master, and I'll
create a followup task and PR to handle the abstraction together with handling
the smoothing in the initialization
Github user dbtsai commented on the issue:
https://github.com/apache/spark/pull/15593
@MLnick I'm hoping that we could abstract out the the implementation of
using column major format as much as possible; as a result, in the future, new
developers can understand the code without
Github user dbtsai commented on a diff in the pull request:
https://github.com/apache/spark/pull/15593#discussion_r87518789
--- Diff:
mllib/src/main/scala/org/apache/spark/ml/classification/LogisticRegression.scala
---
@@ -1486,57 +1504,65 @@ private class LogisticAggregator
Github user dbtsai commented on a diff in the pull request:
https://github.com/apache/spark/pull/15593#discussion_r87516339
--- Diff:
mllib/src/main/scala/org/apache/spark/ml/classification/LogisticRegression.scala
---
@@ -489,13 +485,14 @@ class LogisticRegression @Since("
Github user dbtsai commented on a diff in the pull request:
https://github.com/apache/spark/pull/15593#discussion_r87501621
--- Diff:
mllib/src/main/scala/org/apache/spark/ml/classification/LogisticRegression.scala
---
@@ -489,13 +485,14 @@ class LogisticRegression @Since("
Github user dbtsai commented on the issue:
https://github.com/apache/spark/pull/15593
@sethah I'm recently busy on company work. Will start to work on open
source code review soon this week.
---
If your project is set up for it, you can reply to this email and have your
reply appear
Github user dbtsai commented on the issue:
https://github.com/apache/spark/pull/9
I was also thinking that most of people will use this for daily retraining
by passing in the previous model which will cause the model larger and larger
due to the model chain which is unnecessary
Github user dbtsai commented on a diff in the pull request:
https://github.com/apache/spark/pull/9#discussion_r83703876
--- Diff: mllib/src/main/scala/org/apache/spark/ml/util/ReadWrite.scala ---
@@ -446,6 +459,11 @@ private[ml] object DefaultParamsReader {
val cls
Github user dbtsai commented on a diff in the pull request:
https://github.com/apache/spark/pull/9#discussion_r83600176
--- Diff: mllib/src/main/scala/org/apache/spark/ml/clustering/KMeans.scala
---
@@ -303,6 +312,20 @@ class KMeans @Since("1.5.0") (
@Si
Github user dbtsai commented on the issue:
https://github.com/apache/spark/pull/12761
I'm benchmarking LOR with 14M features of internal company dataset
(unfortunately, it's not public).
Regrading using sparse data structure for aggregation, I'm not so sure how
much
Github user dbtsai commented on the issue:
https://github.com/apache/spark/pull/9
Please remove `WIP` in the description.
---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does not have this feature
Github user dbtsai commented on the issue:
https://github.com/apache/spark/pull/15488
Merged into master. Thanks.
---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does not have this feature
enabled
Github user dbtsai commented on the issue:
https://github.com/apache/spark/pull/15488
LGTM.
---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does not have this feature
enabled and wishes so
Github user dbtsai commented on the issue:
https://github.com/apache/spark/pull/9
+1 on what @sethah proposed. We can log with warn when k is modified by
setting the initial model. Thanks.
---
If your project is set up for it, you can reply to this email and have your
reply
Github user dbtsai commented on a diff in the pull request:
https://github.com/apache/spark/pull/9#discussion_r82497437
--- Diff:
mllib/src/test/scala/org/apache/spark/ml/clustering/KMeansSuite.scala ---
@@ -137,18 +143,64 @@ class KMeansSuite extends SparkFunSuite
Github user dbtsai commented on a diff in the pull request:
https://github.com/apache/spark/pull/9#discussion_r82489783
--- Diff:
mllib/src/test/scala/org/apache/spark/ml/clustering/KMeansSuite.scala ---
@@ -137,18 +143,64 @@ class KMeansSuite extends SparkFunSuite
Github user dbtsai commented on a diff in the pull request:
https://github.com/apache/spark/pull/15074#discussion_r82461977
--- Diff: python/pyspark/mllib/linalg/__init__.py ---
@@ -1296,9 +1296,19 @@ def asML(self):
return newlinalg.SparseMatrix(self.numRows
Github user dbtsai commented on a diff in the pull request:
https://github.com/apache/spark/pull/9#discussion_r82230001
--- Diff: mllib/src/main/scala/org/apache/spark/ml/clustering/KMeans.scala
---
@@ -303,6 +312,10 @@ class KMeans @Since("1.5.0") (
@Si
Github user dbtsai commented on a diff in the pull request:
https://github.com/apache/spark/pull/9#discussion_r82229991
--- Diff: mllib/src/main/scala/org/apache/spark/ml/clustering/KMeans.scala
---
@@ -303,6 +312,10 @@ class KMeans @Since("1.5.0") (
@Si
Github user dbtsai commented on a diff in the pull request:
https://github.com/apache/spark/pull/9#discussion_r82105944
--- Diff:
mllib/src/test/scala/org/apache/spark/ml/clustering/KMeansSuite.scala ---
@@ -137,18 +142,53 @@ class KMeansSuite extends SparkFunSuite
Github user dbtsai commented on a diff in the pull request:
https://github.com/apache/spark/pull/9#discussion_r82105608
--- Diff: mllib/src/main/scala/org/apache/spark/ml/clustering/KMeans.scala
---
@@ -303,6 +312,10 @@ class KMeans @Since("1.5.0") (
@Si
Github user dbtsai commented on the issue:
https://github.com/apache/spark/pull/15349
LGTM. Merged into master. Thanks.
---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does not have this feature
enabled
Github user dbtsai commented on the issue:
https://github.com/apache/spark/pull/15293
+1 on just having the note. For y = 0/1, just more confusing to have
complicated formulation in the doc.
---
If your project is set up for it, you can reply to this email and have your
reply appear
Github user dbtsai commented on the issue:
https://github.com/apache/spark/pull/9
Ping @yinxusen on update. Would like to have it merged soon so we can work
on LiR and LoR parts. Thanks.
---
If your project is set up for it, you can reply to this email and have your
reply appear
Github user dbtsai commented on a diff in the pull request:
https://github.com/apache/spark/pull/9#discussion_r79936136
--- Diff: mllib/src/main/scala/org/apache/spark/ml/clustering/KMeans.scala
---
@@ -81,11 +81,23 @@ private[clustering] trait KMeansParams extends Params
Github user dbtsai commented on the issue:
https://github.com/apache/spark/pull/15177
LGTM. Merged into master. Thanks.
---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does not have this feature
enabled
Github user dbtsai commented on the issue:
https://github.com/apache/spark/pull/14834
Merged into master. Thanks.
---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does not have this feature
enabled
Github user dbtsai commented on the issue:
https://github.com/apache/spark/pull/14834
LGTM. Wait for the test.
---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does not have this feature
enabled and wishes
Github user dbtsai commented on a diff in the pull request:
https://github.com/apache/spark/pull/14834#discussion_r79517559
--- Diff:
mllib/src/main/scala/org/apache/spark/ml/classification/LogisticRegression.scala
---
@@ -508,11 +680,51 @@ object LogisticRegression extends
Github user dbtsai commented on a diff in the pull request:
https://github.com/apache/spark/pull/14834#discussion_r79509186
--- Diff:
mllib/src/main/scala/org/apache/spark/ml/classification/LogisticRegression.scala
---
@@ -676,39 +941,53 @@ object LogisticRegressionModel extends
Github user dbtsai commented on a diff in the pull request:
https://github.com/apache/spark/pull/14834#discussion_r79507627
--- Diff:
mllib/src/main/scala/org/apache/spark/ml/classification/LogisticRegression.scala
---
@@ -508,11 +680,51 @@ object LogisticRegression extends
Github user dbtsai commented on a diff in the pull request:
https://github.com/apache/spark/pull/14834#discussion_r79510132
--- Diff:
mllib/src/test/scala/org/apache/spark/ml/classification/OneVsRestSuite.scala ---
@@ -60,7 +60,8 @@ class OneVsRestSuite extends SparkFunSuite
Github user dbtsai commented on a diff in the pull request:
https://github.com/apache/spark/pull/14834#discussion_r79510068
--- Diff:
mllib/src/test/scala/org/apache/spark/ml/tuning/CrossValidatorSuite.scala ---
@@ -244,7 +244,8 @@ class CrossValidatorSuite
test("read/
Github user dbtsai commented on a diff in the pull request:
https://github.com/apache/spark/pull/14834#discussion_r79509747
--- Diff:
mllib/src/test/scala/org/apache/spark/ml/classification/LogisticRegressionSuite.scala
---
@@ -67,11 +105,15 @@ class LogisticRegressionSuite
Github user dbtsai commented on a diff in the pull request:
https://github.com/apache/spark/pull/14834#discussion_r79510095
--- Diff:
mllib/src/test/scala/org/apache/spark/ml/tuning/TrainValidationSplitSuite.scala
---
@@ -133,7 +133,8 @@ class TrainValidationSplitSuite
Github user dbtsai commented on a diff in the pull request:
https://github.com/apache/spark/pull/14834#discussion_r79509600
--- Diff:
mllib/src/test/scala/org/apache/spark/ml/classification/LogisticRegressionSuite.scala
---
@@ -22,28 +22,49 @@ import scala.language.existentials
Github user dbtsai commented on a diff in the pull request:
https://github.com/apache/spark/pull/14834#discussion_r79507486
--- Diff:
mllib/src/main/scala/org/apache/spark/ml/classification/LogisticRegression.scala
---
@@ -508,11 +680,51 @@ object LogisticRegression extends
Github user dbtsai commented on a diff in the pull request:
https://github.com/apache/spark/pull/14834#discussion_r79508998
--- Diff:
mllib/src/main/scala/org/apache/spark/ml/classification/LogisticRegression.scala
---
@@ -1103,6 +1382,7 @@ class BinaryLogisticRegressionSummary
Github user dbtsai commented on a diff in the pull request:
https://github.com/apache/spark/pull/14834#discussion_r79506294
--- Diff:
mllib/src/main/scala/org/apache/spark/ml/classification/LogisticRegression.scala
---
@@ -66,11 +69,37 @@ private[classification] trait
Github user dbtsai commented on a diff in the pull request:
https://github.com/apache/spark/pull/14834#discussion_r79509539
--- Diff:
mllib/src/main/scala/org/apache/spark/mllib/classification/LogisticRegression.scala
---
@@ -430,8 +431,9 @@ class LogisticRegressionWithLBFGS
Github user dbtsai commented on a diff in the pull request:
https://github.com/apache/spark/pull/14834#discussion_r79507775
--- Diff:
mllib/src/main/scala/org/apache/spark/ml/classification/LogisticRegression.scala
---
@@ -508,11 +680,51 @@ object LogisticRegression extends
Github user dbtsai commented on a diff in the pull request:
https://github.com/apache/spark/pull/9#discussion_r78682701
--- Diff: mllib/src/main/scala/org/apache/spark/ml/clustering/KMeans.scala
---
@@ -303,6 +322,29 @@ class KMeans @Since("1.5.0") (
@Si
Github user dbtsai commented on the issue:
https://github.com/apache/spark/pull/14834
Only couple minor issues; otherwise, LGTM.
---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does not have this feature
Github user dbtsai commented on a diff in the pull request:
https://github.com/apache/spark/pull/14834#discussion_r78674556
--- Diff:
mllib/src/main/scala/org/apache/spark/ml/classification/ProbabilisticClassifier.scala
---
@@ -201,11 +201,24 @@ abstract class
Github user dbtsai commented on a diff in the pull request:
https://github.com/apache/spark/pull/14834#discussion_r7867
--- Diff:
mllib/src/main/scala/org/apache/spark/ml/classification/LogisticRegression.scala
---
@@ -676,39 +936,54 @@ object LogisticRegressionModel extends
Github user dbtsai commented on a diff in the pull request:
https://github.com/apache/spark/pull/14834#discussion_r78674092
--- Diff:
mllib/src/main/scala/org/apache/spark/ml/classification/LogisticRegression.scala
---
@@ -595,55 +831,104 @@ class LogisticRegressionModel private
Github user dbtsai commented on a diff in the pull request:
https://github.com/apache/spark/pull/14834#discussion_r78673689
--- Diff:
mllib/src/main/scala/org/apache/spark/ml/classification/LogisticRegression.scala
---
@@ -508,11 +680,42 @@ object LogisticRegression extends
Github user dbtsai commented on a diff in the pull request:
https://github.com/apache/spark/pull/14834#discussion_r78483816
--- Diff:
mllib/src/main/scala/org/apache/spark/ml/classification/LogisticRegression.scala
---
@@ -460,33 +577,74 @@ class LogisticRegression @Since("
Github user dbtsai commented on a diff in the pull request:
https://github.com/apache/spark/pull/14834#discussion_r78420053
--- Diff:
mllib/src/main/scala/org/apache/spark/ml/classification/LogisticRegression.scala
---
@@ -460,33 +577,74 @@ class LogisticRegression @Since("
Github user dbtsai commented on a diff in the pull request:
https://github.com/apache/spark/pull/14834#discussion_r78419383
--- Diff:
mllib/src/main/scala/org/apache/spark/ml/classification/LogisticRegression.scala
---
@@ -311,8 +350,28 @@ class LogisticRegression @Since("
Github user dbtsai commented on a diff in the pull request:
https://github.com/apache/spark/pull/14834#discussion_r78321887
--- Diff:
mllib/src/main/scala/org/apache/spark/ml/classification/LogisticRegression.scala
---
@@ -460,33 +577,74 @@ class LogisticRegression @Since("
Github user dbtsai commented on a diff in the pull request:
https://github.com/apache/spark/pull/14834#discussion_r78321247
--- Diff:
mllib/src/main/scala/org/apache/spark/ml/classification/LogisticRegression.scala
---
@@ -323,32 +382,33 @@ class LogisticRegression @Since("
Github user dbtsai commented on a diff in the pull request:
https://github.com/apache/spark/pull/14834#discussion_r78321146
--- Diff:
mllib/src/main/scala/org/apache/spark/ml/classification/LogisticRegression.scala
---
@@ -311,8 +350,28 @@ class LogisticRegression @Since("
Github user dbtsai commented on a diff in the pull request:
https://github.com/apache/spark/pull/14834#discussion_r78316060
--- Diff:
mllib/src/main/scala/org/apache/spark/ml/classification/LogisticRegression.scala
---
@@ -311,8 +350,28 @@ class LogisticRegression @Since("
Github user dbtsai commented on a diff in the pull request:
https://github.com/apache/spark/pull/14834#discussion_r78315600
--- Diff:
mllib/src/main/scala/org/apache/spark/ml/classification/LogisticRegression.scala
---
@@ -261,6 +299,7 @@ class LogisticRegression @Since("
Github user dbtsai commented on the issue:
https://github.com/apache/spark/pull/14998
Merged into master. Great work! Thanks.
---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does not have this feature
Github user dbtsai commented on the issue:
https://github.com/apache/spark/pull/14998
Jenkins, retest this please
---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does not have this feature
enabled
Github user dbtsai commented on the issue:
https://github.com/apache/spark/pull/14834
@sethah Could you create another JIRA to track the issue that when there is
a class which is not in training, centering the intercepts doesn't make any
sense at all. The intercepts should be just
Github user dbtsai commented on a diff in the pull request:
https://github.com/apache/spark/pull/14834#discussion_r78128581
--- Diff:
mllib/src/main/scala/org/apache/spark/ml/classification/LogisticRegression.scala
---
@@ -460,33 +564,74 @@ class LogisticRegression @Since("
Github user dbtsai commented on a diff in the pull request:
https://github.com/apache/spark/pull/14834#discussion_r78128374
--- Diff:
mllib/src/main/scala/org/apache/spark/ml/classification/LogisticRegression.scala
---
@@ -460,33 +564,74 @@ class LogisticRegression @Since("
Github user dbtsai commented on a diff in the pull request:
https://github.com/apache/spark/pull/14834#discussion_r78128102
--- Diff:
mllib/src/main/scala/org/apache/spark/ml/classification/LogisticRegression.scala
---
@@ -452,6 +555,7 @@ class LogisticRegression @Since("
Github user dbtsai commented on a diff in the pull request:
https://github.com/apache/spark/pull/14834#discussion_r78127943
--- Diff:
mllib/src/main/scala/org/apache/spark/ml/classification/LogisticRegression.scala
---
@@ -370,49 +420,102 @@ class LogisticRegression @Since("
Github user dbtsai commented on a diff in the pull request:
https://github.com/apache/spark/pull/14834#discussion_r78127321
--- Diff:
mllib/src/main/scala/org/apache/spark/ml/classification/LogisticRegression.scala
---
@@ -370,49 +420,102 @@ class LogisticRegression @Since("
Github user dbtsai commented on a diff in the pull request:
https://github.com/apache/spark/pull/14834#discussion_r78126776
--- Diff:
mllib/src/main/scala/org/apache/spark/ml/classification/LogisticRegression.scala
---
@@ -370,49 +420,102 @@ class LogisticRegression @Since("
Github user dbtsai commented on a diff in the pull request:
https://github.com/apache/spark/pull/14834#discussion_r78111319
--- Diff:
mllib/src/main/scala/org/apache/spark/ml/classification/LogisticRegression.scala
---
@@ -370,49 +420,102 @@ class LogisticRegression @Since("
Github user dbtsai commented on a diff in the pull request:
https://github.com/apache/spark/pull/14834#discussion_r78111049
--- Diff:
mllib/src/main/scala/org/apache/spark/ml/classification/LogisticRegression.scala
---
@@ -370,49 +420,102 @@ class LogisticRegression @Since("
Github user dbtsai commented on a diff in the pull request:
https://github.com/apache/spark/pull/14834#discussion_r78109655
--- Diff:
mllib/src/main/scala/org/apache/spark/ml/classification/LogisticRegression.scala
---
@@ -333,22 +387,18 @@ class LogisticRegression @Since("
Github user dbtsai commented on a diff in the pull request:
https://github.com/apache/spark/pull/14834#discussion_r78101965
--- Diff:
mllib/src/main/scala/org/apache/spark/ml/classification/LogisticRegression.scala
---
@@ -333,22 +387,18 @@ class LogisticRegression @Since("
Github user dbtsai commented on a diff in the pull request:
https://github.com/apache/spark/pull/14834#discussion_r78101327
--- Diff:
mllib/src/main/scala/org/apache/spark/ml/classification/LogisticRegression.scala
---
@@ -311,8 +348,25 @@ class LogisticRegression @Since("
Github user dbtsai commented on a diff in the pull request:
https://github.com/apache/spark/pull/14834#discussion_r78093424
--- Diff:
mllib/src/main/scala/org/apache/spark/ml/classification/LogisticRegression.scala
---
@@ -50,6 +50,8 @@ private[classification] trait
Github user dbtsai commented on the issue:
https://github.com/apache/spark/pull/14834
@sethah For sparse MLOR problems with L1, the models will be sparse in row.
As a result, in the sparse, we need to store the models in CSR format, and CSR
models can be used for model prediction
Github user dbtsai commented on the issue:
https://github.com/apache/spark/pull/14998
Some minor issues, and LGTM. Thanks.
---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does not have this feature
Github user dbtsai commented on a diff in the pull request:
https://github.com/apache/spark/pull/14998#discussion_r78090880
--- Diff: graphx/src/main/scala/org/apache/spark/graphx/lib/PageRank.scala
---
@@ -163,6 +166,85 @@ object PageRank extends Logging
Github user dbtsai commented on a diff in the pull request:
https://github.com/apache/spark/pull/14998#discussion_r78090050
--- Diff: graphx/src/main/scala/org/apache/spark/graphx/lib/PageRank.scala
---
@@ -163,6 +166,85 @@ object PageRank extends Logging
Github user dbtsai commented on a diff in the pull request:
https://github.com/apache/spark/pull/14998#discussion_r78089652
--- Diff: graphx/src/main/scala/org/apache/spark/graphx/lib/PageRank.scala
---
@@ -163,6 +166,85 @@ object PageRank extends Logging
Github user dbtsai commented on the issue:
https://github.com/apache/spark/pull/14998
Jenkins, retest this please
---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does not have this feature
enabled
Github user dbtsai commented on the issue:
https://github.com/apache/spark/pull/14834
@sethah I remember that `compressed` method for `Matrix` is one of the todo
in the followup tasks. For sparse binary logistic regression, if we store the
models as `1 x numFeatures` compressed
Github user dbtsai commented on a diff in the pull request:
https://github.com/apache/spark/pull/14998#discussion_r77925377
--- Diff: graphx/src/main/scala/org/apache/spark/graphx/lib/PageRank.scala
---
@@ -19,8 +19,11 @@ package org.apache.spark.graphx.lib
import
Github user dbtsai commented on the issue:
https://github.com/apache/spark/pull/14834
@sethah +1 for this approach. Couple minor questions. With L1, the
coefficients can be very sparse. Currently, we will store them as sparse vector
and use sparse vector for prediction
Github user dbtsai commented on the issue:
https://github.com/apache/spark/pull/14834
@sethah Thank you for coming up with PR with detailed documentation. For
option 2, if a two class model is trained with multinomial family, how do you
store it? I was thinking about maybe we could
Github user dbtsai commented on the issue:
https://github.com/apache/spark/pull/9
Thanks @sethah for reviewing. @yinxusen once it's ready to merge, please
remove WIP and I will be more than happy to do a final pass, and help to merge
the code. Thanks.
---
If your project
Github user dbtsai commented on the issue:
https://github.com/apache/spark/pull/14785
LGTM. Merged into master. Thanks.
---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does not have this feature
enabled
Github user dbtsai commented on the issue:
https://github.com/apache/spark/pull/14785
Please also add test cases for matrices. Thanks.
---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does not have
Github user dbtsai commented on the issue:
https://github.com/apache/spark/pull/14785
Can you also fix
`https://github.com/apache/spark/blob/master/mllib-local/src/test/scala/org/apache/spark/ml/util/TestingUtils.scala`?
Please add tests showing the issue is addressed. Thanks
Github user dbtsai commented on the issue:
https://github.com/apache/spark/pull/14766
LGTM. Since I mostly work on scala part, wait for other vote. Thanks.
---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project
Github user dbtsai commented on the issue:
https://github.com/apache/spark/pull/13796
The solution of this overparameterized problem in the link is just adding
the regularization, and users may not want it. I think we need to optimize it
on (k-1) parameters, and then put the final
Github user dbtsai commented on the issue:
https://github.com/apache/spark/pull/13796
@WeichenXu123 Do you run into this potential issue with any dataset? If so,
we may need to consider optimize softmax with pivoting when `reg == 0`.
---
If your project is set up for it, you can
Github user dbtsai commented on a diff in the pull request:
https://github.com/apache/spark/pull/14717#discussion_r75588252
--- Diff:
mllib/src/main/scala/org/apache/spark/ml/param/shared/sharedParams.scala ---
@@ -389,4 +389,21 @@ private[ml] trait HasSolver extends Params
Github user dbtsai commented on the issue:
https://github.com/apache/spark/pull/14717
LGTM. Merge into master. Thanks.
---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does not have this feature
enabled
Github user dbtsai commented on a diff in the pull request:
https://github.com/apache/spark/pull/14717#discussion_r75587723
--- Diff:
mllib/src/main/scala/org/apache/spark/ml/classification/LogisticRegression.scala
---
@@ -256,6 +256,17 @@ class LogisticRegression @Since("
Github user dbtsai commented on a diff in the pull request:
https://github.com/apache/spark/pull/14717#discussion_r75587709
--- Diff:
mllib/src/main/scala/org/apache/spark/ml/classification/LogisticRegression.scala
---
@@ -48,7 +48,7 @@ import
501 - 600 of 1777 matches
Mail list logo