Hendrik/xgboost
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

[FLINK] remove nWorker from API

Browse Source
This commit is contained in:
tqchen 2016-03-14 16:18:04 -07:00
parent 084ed6224d
commit 90f7220736
4 changed files with 6 additions and 8 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
doc/jvm/xgboost4j-intro.md
View File

@ -147,7 +147,7 @@ val trainData = MLUtils.readLibSVM(env, "/path/to/data/agaricus.txt.train")
Model Training can be done as follows
```scala
val xgboostModel = XGBoost.train(trainData, paramMap, round, nWorkers)
val xgboostModel = XGBoost.train(trainData, paramMap, round)
```

5
jvm-packages/README.md
View File

@ -72,7 +72,7 @@ object DistTrainWithSpark {
"eta" -> 0.1f,
"max_depth" -> 2,
"objective" -> "binary:logistic").toMap
// use 5 distributed workers to train the model
// use 5 distributed workers to train the model
val model = XGBoost.train(trainRDD, paramMap, numRound, nWorkers = 5)
// save model to HDFS path
model.saveModelToHadoop(outputModelPath)
@ -100,9 +100,8 @@ object DistTrainWithFlink {
"objective" -> "binary:logistic").toMap
// number of iterations
val round = 2
val nWorkers = 5
// train the model
val model = XGBoost.train(trainData, paramMap, round, nWorkers)
val model = XGBoost.train(trainData, paramMap, round)
val predTrain = model.predict(trainData.map{x => x.vector})
model.saveModelToHadoop("file:///path/to/xgboost.model")
}

3
jvm-packages/xgboost4j-example/src/main/scala/ml/dmlc/xgboost4j/scala/example/flink/DistTrainWithFlink.scala
View File

@ -33,9 +33,8 @@ object DistTrainWithFlink {
"objective" -> "binary:logistic").toMap
// number of iterations
val round = 2
val nWorkers = 5
// train the model
val model = XGBoost.train(trainData, paramMap, round, 5)
val model = XGBoost.train(trainData, paramMap, round)
val predTest = model.predict(testData.map{x => x.vector})
model.saveModelAsHadoopFile("file:///path/to/xgboost.model")
}

4
jvm-packages/xgboost4j-flink/src/main/scala/ml/dmlc/xgboost4j/scala/flink/XGBoost.scala
View File

@ -82,9 +82,9 @@ object XGBoost {
* @param params The parameters to XGBoost.
* @param round Number of rounds to train.
*/
def train(dtrain: DataSet[LabeledVector], params: Map[String, Any], round: Int, nWorkers: Int):
def train(dtrain: DataSet[LabeledVector], params: Map[String, Any], round: Int):
XGBoostModel = {
val tracker = new RabitTracker(nWorkers)
val tracker = new RabitTracker(dtrain.getExecutionEnvironment.getParallelism)
if (tracker.start()) {
dtrain
.mapPartition(new MapFunction(params, round, tracker.getWorkerEnvs))