class Booster extends Serializable with KryoSerializable
Booster for xgboost, this is a model API that support interactive build of a XGBoost Model
DEVELOPER WARNING: A Java Booster must not be shared by more than one Scala Booster
- Alphabetic
- By Inheritance
- Booster
- KryoSerializable
- Serializable
- AnyRef
- Any
- Hide All
- Show All
- Public
- Protected
Value Members
- final def !=(arg0: Any): Boolean
- Definition Classes
- AnyRef → Any
- final def ##: Int
- Definition Classes
- AnyRef → Any
- final def ==(arg0: Any): Boolean
- Definition Classes
- AnyRef → Any
- final def asInstanceOf[T0]: T0
- Definition Classes
- Any
- def boost(dtrain: DMatrix, grad: Array[Float], hess: Array[Float]): Unit
update with give grad and hess
update with give grad and hess
- dtrain
training data
- grad
first order of gradient
- hess
seconde order of gradient
- Annotations
- @throws(classOf[XGBoostError])
- def clone(): AnyRef
- Attributes
- protected[lang]
- Definition Classes
- AnyRef
- Annotations
- @throws(classOf[java.lang.CloneNotSupportedException]) @IntrinsicCandidate() @native()
- def dispose: Unit
Dispose the booster when it is no longer needed
- final def eq(arg0: AnyRef): Boolean
- Definition Classes
- AnyRef
- def equals(arg0: AnyRef): Boolean
- Definition Classes
- AnyRef → Any
- def evalSet(evalMatrixs: Array[DMatrix], evalNames: Array[String], eval: EvalTrait): String
evaluate with given customized Evaluation class
evaluate with given customized Evaluation class
- evalMatrixs
evaluation matrix
- evalNames
evaluation names
- eval
custom evaluator
- returns
eval information
- Annotations
- @throws(classOf[XGBoostError])
- def evalSet(evalMatrixs: Array[DMatrix], evalNames: Array[String], iter: Int): String
evaluate with given dmatrixs.
evaluate with given dmatrixs.
- evalMatrixs
dmatrixs for evaluation
- evalNames
name for eval dmatrixs, used for check results
- iter
current eval iteration
- returns
eval information
- Annotations
- @throws(classOf[XGBoostError])
- def finalize(): Unit
- Definition Classes
- Booster → AnyRef
- def getAttr(key: String): String
Get attribute from the Booster.
Get attribute from the Booster.
- key
attr name
- returns
attr value
- Annotations
- @throws(classOf[XGBoostError])
- def getAttrs: Map[String, String]
Get attributes stored in the Booster as a Map.
Get attributes stored in the Booster as a Map.
- returns
A map contain attribute pairs.
- Annotations
- @throws(classOf[XGBoostError])
- final def getClass(): Class[_ <: AnyRef]
- Definition Classes
- AnyRef → Any
- Annotations
- @IntrinsicCandidate() @native()
- def getFeatureScore(featureNames: Array[String]): Map[String, Integer]
Get importance of each feature based on weight only (number of splits), with specified feature names.
Get importance of each feature based on weight only (number of splits), with specified feature names.
- returns
featureScoreMap key: feature name, value: feature importance score
- Annotations
- @throws(classOf[XGBoostError])
- def getFeatureScore(featureMap: String = null): Map[String, Integer]
Get importance of each feature based on weight only (number of splits)
Get importance of each feature based on weight only (number of splits)
- returns
featureScoreMap key: feature index, value: feature importance score
- Annotations
- @throws(classOf[XGBoostError])
- def getModelDump(featureNames: Array[String], withStats: Boolean, format: String): Array[String]
- def getModelDump(featureNames: Array[String]): Array[String]
Dump model as Array of string with specified feature names.
Dump model as Array of string with specified feature names.
- featureNames
Names of features.
- Annotations
- @throws(classOf[XGBoostError])
- def getModelDump(featureMap: String = null, withStats: Boolean = false, format: String = "text"): Array[String]
Dump model as Array of string
Dump model as Array of string
- featureMap
featureMap file
- withStats
bool Controls whether the split statistics are output.
- Annotations
- @throws(classOf[XGBoostError])
- def getNumFeature: Long
Get the number of model features.
Get the number of model features.
- returns
number of features
- Annotations
- @throws(classOf[XGBoostError])
- def getScore(featureNames: Array[String], importanceType: String): Map[String, Double]
Get importance of each feature based on information gain or cover , with specified feature names.
Get importance of each feature based on information gain or cover , with specified feature names. Supported: ["gain, "cover", "total_gain", "total_cover"]
- returns
featureScoreMap key: feature name, value: feature importance score
- Annotations
- @throws(classOf[XGBoostError])
- def getScore(featureMap: String, importanceType: String): Map[String, Double]
Get importance of each feature based on information gain or cover Supported: ["gain, "cover", "total_gain", "total_cover"]
Get importance of each feature based on information gain or cover Supported: ["gain, "cover", "total_gain", "total_cover"]
- returns
featureScoreMap key: feature index, value: feature importance score
- Annotations
- @throws(classOf[XGBoostError])
- def getVersion: Int
- def hashCode(): Int
- Definition Classes
- AnyRef → Any
- Annotations
- @IntrinsicCandidate() @native()
- final def isInstanceOf[T0]: Boolean
- Definition Classes
- Any
- final def ne(arg0: AnyRef): Boolean
- Definition Classes
- AnyRef
- final def notify(): Unit
- Definition Classes
- AnyRef
- Annotations
- @IntrinsicCandidate() @native()
- final def notifyAll(): Unit
- Definition Classes
- AnyRef
- Annotations
- @IntrinsicCandidate() @native()
- def predict(data: DMatrix, outPutMargin: Boolean = false, treeLimit: Int = 0): Array[Array[Float]]
Predict with data
Predict with data
- data
dmatrix storing the input
- outPutMargin
Whether to output the raw untransformed margin value.
- treeLimit
Limit number of trees in the prediction; defaults to 0 (use all trees).
- returns
predict result
- Annotations
- @throws(classOf[XGBoostError])
- def predictContrib(data: DMatrix, treeLimit: Int = 0): Array[Array[Float]]
Output feature contributions toward predictions of given data
Output feature contributions toward predictions of given data
- data
dmatrix storing the input
- treeLimit
Limit number of trees in the prediction; defaults to 0 (use all trees).
- returns
The feature contributions and bias.
- Annotations
- @throws(classOf[XGBoostError])
- Exceptions thrown
XGBoostError
native error
- def predictLeaf(data: DMatrix, treeLimit: Int = 0): Array[Array[Float]]
Predict the leaf indices
Predict the leaf indices
- data
dmatrix storing the input
- treeLimit
Limit number of trees in the prediction; defaults to 0 (use all trees).
- returns
predict result
- Annotations
- @throws(classOf[XGBoostError])
- Exceptions thrown
XGBoostError
native error
- def read(kryo: Kryo, input: Input): Unit
- Definition Classes
- Booster → KryoSerializable
- def saveModel(out: OutputStream, format: String): Unit
save model to Output stream
save model to Output stream
- out
output stream
- format
the supported model format, (json, ubj, deprecated)
- Annotations
- @throws(classOf[XGBoostError])
- Exceptions thrown
- def saveModel(out: OutputStream): Unit
save model to Output stream
save model to Output stream
- out
Output stream
- Annotations
- @throws(classOf[XGBoostError])
- def saveModel(modelPath: String): Unit
save model to modelPath
save model to modelPath
- modelPath
model path
- Annotations
- @throws(classOf[XGBoostError])
- def setAttr(key: String, value: String): Unit
Set attribute to the Booster.
Set attribute to the Booster.
- key
attr name
- value
attr value
- Annotations
- @throws(classOf[XGBoostError])
- def setAttrs(params: Map[String, String]): Unit
set attributes
set attributes
- params
attributes key-value map
- Annotations
- @throws(classOf[XGBoostError])
- def setParam(key: String, value: AnyRef): Unit
Set parameter to the Booster.
Set parameter to the Booster.
- key
param name
- value
param value
- Annotations
- @throws(classOf[XGBoostError])
- def setParams(params: Map[String, AnyRef]): Unit
set parameters
set parameters
- params
parameters key-value map
- Annotations
- @throws(classOf[XGBoostError])
- final def synchronized[T0](arg0: => T0): T0
- Definition Classes
- AnyRef
- def toByteArray: Array[Byte]
Save model into a raw byte array.
Save model into a raw byte array. Currently it's using the deprecated format as default, which will be changed into
ubj
in future releases.- Annotations
- @throws(classOf[XGBoostError])
- def toByteArray(format: String): Array[Byte]
Save model into a raw byte array.
Save model into a raw byte array. Available options are "json", "ubj" and "deprecated".
- Annotations
- @throws(classOf[XGBoostError])
- def toString(): String
- Definition Classes
- AnyRef → Any
- def update(dtrain: DMatrix, obj: ObjectiveTrait): Unit
update with customize obj func
update with customize obj func
- dtrain
training data
- obj
customized objective class
- Annotations
- @throws(classOf[XGBoostError])
- def update(dtrain: DMatrix, iter: Int): Unit
Update (one iteration)
Update (one iteration)
- dtrain
training data
- iter
current iteration number
- Annotations
- @throws(classOf[XGBoostError])
- final def wait(arg0: Long, arg1: Int): Unit
- Definition Classes
- AnyRef
- Annotations
- @throws(classOf[java.lang.InterruptedException])
- final def wait(arg0: Long): Unit
- Definition Classes
- AnyRef
- Annotations
- @throws(classOf[java.lang.InterruptedException])
- final def wait(): Unit
- Definition Classes
- AnyRef
- Annotations
- @throws(classOf[java.lang.InterruptedException])
- def write(kryo: Kryo, output: Output): Unit
- Definition Classes
- Booster → KryoSerializable