zhengruifeng commented on pull request #28471:
URL: https://github.com/apache/spark/pull/28471#issuecomment-625599005
testCode:
```
import org.apache.spark.ml.regression._
import org.apache.spark.storage.StorageLevel
val df = spark.read.option("numFeatures",
"2000").format("libsvm").load("/data1/Datasets/epsilon/epsilon_normalized.t")
df.persist(StorageLevel.MEMORY_AND_DISK)
df.count
// Default SquaredError
val lir = new LinearRegression().setMaxIter(50).setSolver("l-bfgs")
lr.fit(df)
val results = Seq(1, 4, 16, 64, 256, 1024, 4096).map { size => val start =
System.currentTimeMillis; val model = lir.setBlockSize(size).fit(df); val end =
System.currentTimeMillis; (size, model, end - start) }
// Huber
val lir = new
LinearRegression().setMaxIter(50).setSolver("l-bfgs").setLoss("huber")
val results = Seq(1, 4, 16, 64, 256, 1024, 4096).map { size => val start =
System.currentTimeMillis; val model = lir.setBlockSize(size).fit(df); val end =
System.currentTimeMillis; (size, model, end - start) }
```
Result:
**Huber**
```
scala> results.foreach(t => println(t._2.coefficients.toString.take(100)))
[0.6424729506929868,-1.2292544634895406,1.7757284244387601,0.2974549255492886,0.935593736145218,-0.7
[0.6425694454021473,-1.22927248948364,1.7757268011427252,0.2974675136619897,0.9357357899375097,-0.77
[0.6424853073405433,-1.2292568932224641,1.775728104037945,0.29745659508182537,0.9356121907344618,-0.
[0.6429959531002037,-1.229354196708174,1.7757175326389232,0.29752415047198205,0.9363681130113419,-0.
[0.6424842544336862,-1.2292566837366543,1.775728142782258,0.29745645263402737,0.9356106116206417,-0.
[0.6430623639968113,-1.2293667308116527,1.7757163246117786,0.29753287650971944,0.9364661504709426,-0
[0.6421067597074761,-1.229184819802838,1.7757358482626238,0.2974067609553463,0.9350521980706877,-0.7
scala>
scala> results.map(_._2.summary.totalIterations)
res22: Seq[Int] = List(51, 51, 51, 51, 51, 51, 51)
scala> results.map(_._3)
res23: Seq[Long] = List(135189, 12046, 11783, 14307, 14399, 14026, 14329)
```
Up to 11X speedup
**SquaredError**
```
scala> results.foreach(t => println(t._2.coefficients.toString.take(100)))
[-0.2652587613623121,-0.0707048016667831,0.420750805149307,0.09194452205365045,0.05059855709172461,0
[-0.26525865677193483,-0.07070480422610806,0.42075057109293873,0.09194450660409814,0.050598582385999
[-0.26526635878841553,-0.07070459501522909,0.42076764197826116,0.09194564264821924,0.050596757952969
[-0.26525612879310023,-0.07070486362689087,0.42074489424648864,0.09194413298339,0.050599198284442995
[-0.2652611612036013,-0.07070474076806575,0.42075615827182555,0.09194487637000792,0.0505979807182646
[-0.26526190169346425,-0.07070472114668785,0.42075780340712315,0.0919449856303737,0.0505978044045689
[-0.265262317030222,-0.07070470997227678,0.42075872481615506,0.09194504690071631,0.05059770582212817
scala> results.map(_._2.summary.totalIterations)
res26: Seq[Int] = List(51, 51, 51, 51, 51, 51, 51)
scala> results.map(_._3)
res27: Seq[Long] = List(71269, 11828, 12254, 15331, 14963, 14420, 14022)
```
Up to 6X speedup
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
us...@infra.apache.org
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional commands, e-mail: reviews-h...@spark.apache.org
