Class/Object

ai.catboost.spark

CatBoostClassifier

Related Docs: object CatBoostClassifier | package spark

Permalink

class CatBoostClassifier extends ProbabilisticClassifier[Vector, CatBoostClassifier, CatBoostClassificationModel] with CatBoostPredictorTrait[CatBoostClassifier, CatBoostClassificationModel] with ClassifierTrainingParamsTrait

Class to train CatBoostClassificationModel

The default optimized loss function depends on various conditions:

Examples

Binary classification.

val spark = SparkSession.builder()
  .master("local[*]")
  .appName("ClassifierTest")
  .getOrCreate();

val srcDataSchema = Seq(
  StructField("features", SQLDataTypes.VectorType),
  StructField("label", StringType)
)

val trainData = Seq(
  Row(Vectors.dense(0.1, 0.2, 0.11), "0"),
  Row(Vectors.dense(0.97, 0.82, 0.33), "1"),
  Row(Vectors.dense(0.13, 0.22, 0.23), "1"),
  Row(Vectors.dense(0.8, 0.62, 0.0), "0")
)

val trainDf = spark.createDataFrame(spark.sparkContext.parallelize(trainData), StructType(srcDataSchema))
val trainPool = new Pool(trainDf)

val evalData = Seq(
  Row(Vectors.dense(0.22, 0.33, 0.9), "1"),
  Row(Vectors.dense(0.11, 0.1, 0.21), "0"),
  Row(Vectors.dense(0.77, 0.0, 0.0), "1")
)

val evalDf = spark.createDataFrame(spark.sparkContext.parallelize(evalData), StructType(srcDataSchema))
val evalPool = new Pool(evalDf)

val classifier = new CatBoostClassifier
val model = classifier.fit(trainPool, Array[Pool](evalPool))
val predictions = model.transform(evalPool.data)
predictions.show()

Multiclassification.

val spark = SparkSession.builder()
  .master("local[*]")
  .appName("ClassifierTest")
  .getOrCreate();

val srcDataSchema = Seq(
  StructField("features", SQLDataTypes.VectorType),
  StructField("label", StringType)
)

val trainData = Seq(
  Row(Vectors.dense(0.1, 0.2, 0.11), "1"),
  Row(Vectors.dense(0.97, 0.82, 0.33), "2"),
  Row(Vectors.dense(0.13, 0.22, 0.23), "1"),
  Row(Vectors.dense(0.8, 0.62, 0.0), "0")
)

val trainDf = spark.createDataFrame(spark.sparkContext.parallelize(trainData), StructType(srcDataSchema))
val trainPool = new Pool(trainDf)

val evalData = Seq(
  Row(Vectors.dense(0.22, 0.33, 0.9), "2"),
  Row(Vectors.dense(0.11, 0.1, 0.21), "0"),
  Row(Vectors.dense(0.77, 0.0, 0.0), "1")
)

val evalDf = spark.createDataFrame(spark.sparkContext.parallelize(evalData), StructType(srcDataSchema))
val evalPool = new Pool(evalDf)

val classifier = new CatBoostClassifier
val model = classifier.fit(trainPool, Array[Pool](evalPool))
val predictions = model.transform(evalPool.data)
predictions.show()

Serialization

Supports standard Spark MLLib serialization. Data can be saved to distributed filesystem like HDFS or local files.

Examples== Save:
val classifier = new CatBoostClassifier().setIterations(100)
val path = "/home/user/catboost_classifiers/classifier0"
classifier.write.save(path)

Load:

val path = "/home/user/catboost_classifiers/classifier0"
val classifier = CatBoostClassifier.load(path)
val trainPool : Pool = ... init Pool ...
val model = classifier.fit(trainPool)
Linear Supertypes
ClassifierTrainingParamsTrait, TrainingParamsTrait, QuantizationParamsTrait, ThreadCountParams, IgnoredFeaturesParams, CatBoostPredictorTrait[CatBoostClassifier, CatBoostClassificationModel], DefaultParamsWritable, MLWritable, DatasetParamsTrait, HasWeightCol, ProbabilisticClassifier[Vector, CatBoostClassifier, CatBoostClassificationModel], ProbabilisticClassifierParams, HasThresholds, HasProbabilityCol, Classifier[Vector, CatBoostClassifier, CatBoostClassificationModel], ClassifierParams, HasRawPredictionCol, Predictor[Vector, CatBoostClassifier, CatBoostClassificationModel], PredictorParams, HasPredictionCol, HasFeaturesCol, HasLabelCol, Estimator[CatBoostClassificationModel], PipelineStage, Logging, Params, Serializable, Serializable, Identifiable, AnyRef, Any
Ordering
  1. Alphabetic
  2. By Inheritance
Inherited
  1. CatBoostClassifier
  2. ClassifierTrainingParamsTrait
  3. TrainingParamsTrait
  4. QuantizationParamsTrait
  5. ThreadCountParams
  6. IgnoredFeaturesParams
  7. CatBoostPredictorTrait
  8. DefaultParamsWritable
  9. MLWritable
  10. DatasetParamsTrait
  11. HasWeightCol
  12. ProbabilisticClassifier
  13. ProbabilisticClassifierParams
  14. HasThresholds
  15. HasProbabilityCol
  16. Classifier
  17. ClassifierParams
  18. HasRawPredictionCol
  19. Predictor
  20. PredictorParams
  21. HasPredictionCol
  22. HasFeaturesCol
  23. HasLabelCol
  24. Estimator
  25. PipelineStage
  26. Logging
  27. Params
  28. Serializable
  29. Serializable
  30. Identifiable
  31. AnyRef
  32. Any
  1. Hide All
  2. Show All
Visibility
  1. Public
  2. All

Instance Constructors

  1. new CatBoostClassifier()

    Permalink
  2. new CatBoostClassifier(uid: String)

    Permalink

Value Members

  1. final def !=(arg0: Any): Boolean

    Permalink
    Definition Classes
    AnyRef → Any
  2. final def ##(): Int

    Permalink
    Definition Classes
    AnyRef → Any
  3. final def $[T](param: Param[T]): T

    Permalink
    Attributes
    protected
    Definition Classes
    Params
  4. final def ==(arg0: Any): Boolean

    Permalink
    Definition Classes
    AnyRef → Any
  5. def addEstimatedCtrFeatures(quantizedTrainPool: Pool, quantizedEvalPools: Array[Pool], catBoostJsonParams: JObject): (Pool, Array[Pool], CtrsContext)

    Permalink

    returns

    (preprocessedTrainPool, preprocessedEvalPools, ctrsContext)

    Attributes
    protected
    Definition Classes
    CatBoostPredictorTrait
  6. final val allowConstLabel: BooleanParam

    Permalink
    Definition Classes
    TrainingParamsTrait
  7. final val allowWritingFiles: BooleanParam

    Permalink
    Definition Classes
    TrainingParamsTrait
  8. final val approxOnFullHistory: BooleanParam

    Permalink
    Definition Classes
    TrainingParamsTrait
  9. final def asInstanceOf[T0]: T0

    Permalink
    Definition Classes
    Any
  10. final val autoClassWeights: EnumParam[EAutoClassWeightsType]

    Permalink
  11. final val baggingTemperature: FloatParam

    Permalink
    Definition Classes
    TrainingParamsTrait
  12. final val bestModelMinTrees: IntParam

    Permalink
    Definition Classes
    TrainingParamsTrait
  13. final val bootstrapType: EnumParam[EBootstrapType]

    Permalink
    Definition Classes
    TrainingParamsTrait
  14. final val borderCount: IntParam

    Permalink
    Definition Classes
    QuantizationParamsTrait
  15. final val classNames: StringArrayParam

    Permalink
  16. final val classWeightsList: DoubleArrayParam

    Permalink
  17. final val classWeightsMap: OrderedStringMapParam[Double]

    Permalink
  18. final val classesCount: IntParam

    Permalink
  19. final def clear(param: Param[_]): CatBoostClassifier.this.type

    Permalink
    Definition Classes
    Params
  20. def clone(): AnyRef

    Permalink
    Attributes
    protected[java.lang]
    Definition Classes
    AnyRef
    Annotations
    @throws( ... )
  21. def copy(extra: ParamMap): CatBoostClassifier

    Permalink
    Definition Classes
    CatBoostClassifier → Predictor → Estimator → PipelineStage → Params
  22. def copyValues[T <: Params](to: T, extra: ParamMap): T

    Permalink
    Attributes
    protected
    Definition Classes
    Params
  23. def createModel(nativeModel: TFullModel): CatBoostClassificationModel

    Permalink
    Attributes
    protected
    Definition Classes
    CatBoostClassifierCatBoostPredictorTrait
  24. final val customMetric: StringArrayParam

    Permalink
    Definition Classes
    TrainingParamsTrait
  25. final def defaultCopy[T <: Params](extra: ParamMap): T

    Permalink
    Attributes
    protected
    Definition Classes
    Params
  26. final val depth: IntParam

    Permalink
    Definition Classes
    TrainingParamsTrait
  27. final val diffusionTemperature: FloatParam

    Permalink
    Definition Classes
    TrainingParamsTrait
  28. final val earlyStoppingRounds: IntParam

    Permalink
    Definition Classes
    TrainingParamsTrait
  29. final def eq(arg0: AnyRef): Boolean

    Permalink
    Definition Classes
    AnyRef
  30. def equals(arg0: Any): Boolean

    Permalink
    Definition Classes
    AnyRef → Any
  31. final val evalMetric: Param[String]

    Permalink
    Definition Classes
    TrainingParamsTrait
  32. def explainParam(param: Param[_]): String

    Permalink
    Definition Classes
    Params
  33. def explainParams(): String

    Permalink
    Definition Classes
    Params
  34. def extractLabeledPoints(dataset: Dataset[_], numClasses: Int): RDD[LabeledPoint]

    Permalink
    Attributes
    protected
    Definition Classes
    Classifier
  35. def extractLabeledPoints(dataset: Dataset[_]): RDD[LabeledPoint]

    Permalink
    Attributes
    protected
    Definition Classes
    Predictor
  36. final def extractParamMap(): ParamMap

    Permalink
    Definition Classes
    Params
  37. final def extractParamMap(extra: ParamMap): ParamMap

    Permalink
    Definition Classes
    Params
  38. final val featureBorderType: EnumParam[EBorderSelectionType]

    Permalink
    Definition Classes
    QuantizationParamsTrait
  39. final val featureWeightsList: DoubleArrayParam

    Permalink
    Definition Classes
    TrainingParamsTrait
  40. final val featureWeightsMap: OrderedStringMapParam[Double]

    Permalink
    Definition Classes
    TrainingParamsTrait
  41. final val featuresCol: Param[String]

    Permalink
    Definition Classes
    HasFeaturesCol
  42. def finalize(): Unit

    Permalink
    Attributes
    protected[java.lang]
    Definition Classes
    AnyRef
    Annotations
    @throws( classOf[java.lang.Throwable] )
  43. final val firstFeatureUsePenaltiesList: DoubleArrayParam

    Permalink
    Definition Classes
    TrainingParamsTrait
  44. final val firstFeatureUsePenaltiesMap: OrderedStringMapParam[Double]

    Permalink
    Definition Classes
    TrainingParamsTrait
  45. def fit(trainPool: Pool, evalPools: Array[Pool] = Array[Pool]()): CatBoostClassificationModel

    Permalink

    Additional variant of fit method that accepts CatBoost's Pool s and allows to specify additional datasets for computing evaluation metrics and overfitting detection similarily to CatBoost's other APIs.

    Additional variant of fit method that accepts CatBoost's Pool s and allows to specify additional datasets for computing evaluation metrics and overfitting detection similarily to CatBoost's other APIs.

    trainPool

    The input training dataset.

    evalPools

    The validation datasets used for the following processes:

    • overfitting detector
    • best iteration selection
    • monitoring metrics' changes
    returns

    trained model

    Definition Classes
    CatBoostPredictorTrait
  46. def fit(dataset: Dataset[_]): CatBoostClassificationModel

    Permalink
    Definition Classes
    Predictor → Estimator
  47. def fit(dataset: Dataset[_], paramMaps: Array[ParamMap]): Seq[CatBoostClassificationModel]

    Permalink
    Definition Classes
    Estimator
    Annotations
    @Since( "2.0.0" )
  48. def fit(dataset: Dataset[_], paramMap: ParamMap): CatBoostClassificationModel

    Permalink
    Definition Classes
    Estimator
    Annotations
    @Since( "2.0.0" )
  49. def fit(dataset: Dataset[_], firstParamPair: ParamPair[_], otherParamPairs: ParamPair[_]*): CatBoostClassificationModel

    Permalink
    Definition Classes
    Estimator
    Annotations
    @Since( "2.0.0" ) @varargs()
  50. final val foldLenMultiplier: FloatParam

    Permalink
    Definition Classes
    TrainingParamsTrait
  51. final val foldPermutationBlock: IntParam

    Permalink
    Definition Classes
    TrainingParamsTrait
  52. final def get[T](param: Param[T]): Option[T]

    Permalink
    Definition Classes
    Params
  53. final def getAllowConstLabel: Boolean

    Permalink
    Definition Classes
    TrainingParamsTrait
  54. final def getAllowWritingFiles: Boolean

    Permalink
    Definition Classes
    TrainingParamsTrait
  55. final def getApproxOnFullHistory: Boolean

    Permalink
    Definition Classes
    TrainingParamsTrait
  56. final def getAutoClassWeights: EAutoClassWeightsType

    Permalink
  57. final def getBaggingTemperature: Float

    Permalink
    Definition Classes
    TrainingParamsTrait
  58. final def getBestModelMinTrees: Int

    Permalink
    Definition Classes
    TrainingParamsTrait
  59. final def getBootstrapType: EBootstrapType

    Permalink
    Definition Classes
    TrainingParamsTrait
  60. final def getBorderCount: Int

    Permalink
    Definition Classes
    QuantizationParamsTrait
  61. final def getClass(): Class[_]

    Permalink
    Definition Classes
    AnyRef → Any
  62. final def getClassNames: Array[String]

    Permalink
  63. final def getClassWeightsList: Array[Double]

    Permalink
  64. final def getClassWeightsMap: LinkedHashMap[String, Double]

    Permalink
  65. final def getClassesCount: Int

    Permalink
  66. final def getCustomMetric: Array[String]

    Permalink
    Definition Classes
    TrainingParamsTrait
  67. final def getDefault[T](param: Param[T]): Option[T]

    Permalink
    Definition Classes
    Params
  68. final def getDepth: Int

    Permalink
    Definition Classes
    TrainingParamsTrait
  69. final def getDiffusionTemperature: Float

    Permalink
    Definition Classes
    TrainingParamsTrait
  70. final def getEarlyStoppingRounds: Int

    Permalink
    Definition Classes
    TrainingParamsTrait
  71. final def getEvalMetric: String

    Permalink
    Definition Classes
    TrainingParamsTrait
  72. final def getFeatureBorderType: EBorderSelectionType

    Permalink
    Definition Classes
    QuantizationParamsTrait
  73. final def getFeatureWeightsList: Array[Double]

    Permalink
    Definition Classes
    TrainingParamsTrait
  74. final def getFeatureWeightsMap: LinkedHashMap[String, Double]

    Permalink
    Definition Classes
    TrainingParamsTrait
  75. final def getFeaturesCol: String

    Permalink
    Definition Classes
    HasFeaturesCol
  76. final def getFirstFeatureUsePenaltiesList: Array[Double]

    Permalink
    Definition Classes
    TrainingParamsTrait
  77. final def getFirstFeatureUsePenaltiesMap: LinkedHashMap[String, Double]

    Permalink
    Definition Classes
    TrainingParamsTrait
  78. final def getFoldLenMultiplier: Float

    Permalink
    Definition Classes
    TrainingParamsTrait
  79. final def getFoldPermutationBlock: Int

    Permalink
    Definition Classes
    TrainingParamsTrait
  80. final def getHasTime: Boolean

    Permalink
    Definition Classes
    TrainingParamsTrait
  81. final def getIgnoredFeaturesIndices: Array[Int]

    Permalink
    Definition Classes
    IgnoredFeaturesParams
  82. final def getIgnoredFeaturesNames: Array[String]

    Permalink
    Definition Classes
    IgnoredFeaturesParams
  83. final def getInputBorders: String

    Permalink
    Definition Classes
    QuantizationParamsTrait
  84. final def getIterations: Int

    Permalink
    Definition Classes
    TrainingParamsTrait
  85. final def getL2LeafReg: Float

    Permalink
    Definition Classes
    TrainingParamsTrait
  86. final def getLabelCol: String

    Permalink
    Definition Classes
    HasLabelCol
  87. final def getLeafEstimationBacktracking: ELeavesEstimationStepBacktracking

    Permalink
    Definition Classes
    TrainingParamsTrait
  88. final def getLeafEstimationIterations: Int

    Permalink
    Definition Classes
    TrainingParamsTrait
  89. final def getLeafEstimationMethod: ELeavesEstimation

    Permalink
    Definition Classes
    TrainingParamsTrait
  90. final def getLearningRate: Float

    Permalink
    Definition Classes
    TrainingParamsTrait
  91. final def getLoggingLevel: ELoggingLevel

    Permalink
    Definition Classes
    TrainingParamsTrait
  92. final def getLossFunction: String

    Permalink
    Definition Classes
    TrainingParamsTrait
  93. final def getMetricPeriod: Int

    Permalink
    Definition Classes
    TrainingParamsTrait
  94. final def getModelShrinkMode: EModelShrinkMode

    Permalink
    Definition Classes
    TrainingParamsTrait
  95. final def getModelShrinkRate: Float

    Permalink
    Definition Classes
    TrainingParamsTrait
  96. final def getMvsReg: Float

    Permalink
    Definition Classes
    TrainingParamsTrait
  97. final def getNanMode: ENanMode

    Permalink
    Definition Classes
    QuantizationParamsTrait
  98. def getNumClasses(dataset: Dataset[_], maxNumClasses: Int): Int

    Permalink
    Attributes
    protected
    Definition Classes
    Classifier
  99. final def getOdPval: Float

    Permalink
    Definition Classes
    TrainingParamsTrait
  100. final def getOdType: EOverfittingDetectorType

    Permalink
    Definition Classes
    TrainingParamsTrait
  101. final def getOdWait: Int

    Permalink
    Definition Classes
    TrainingParamsTrait
  102. final def getOneHotMaxSize: Int

    Permalink
    Definition Classes
    TrainingParamsTrait
  103. final def getOrDefault[T](param: Param[T]): T

    Permalink
    Definition Classes
    Params
  104. def getParam(paramName: String): Param[Any]

    Permalink
    Definition Classes
    Params
  105. final def getPenaltiesCoefficient: Float

    Permalink
    Definition Classes
    TrainingParamsTrait
  106. final def getPerFloatFeatureQuantizaton: Array[String]

    Permalink
    Definition Classes
    QuantizationParamsTrait
  107. final def getPerObjectFeaturePenaltiesList: Array[Double]

    Permalink
    Definition Classes
    TrainingParamsTrait
  108. final def getPerObjectFeaturePenaltiesMap: LinkedHashMap[String, Double]

    Permalink
    Definition Classes
    TrainingParamsTrait
  109. final def getPredictionCol: String

    Permalink
    Definition Classes
    HasPredictionCol
  110. final def getProbabilityCol: String

    Permalink
    Definition Classes
    HasProbabilityCol
  111. final def getRandomSeed: Int

    Permalink
    Definition Classes
    TrainingParamsTrait
  112. final def getRandomStrength: Float

    Permalink
    Definition Classes
    TrainingParamsTrait
  113. final def getRawPredictionCol: String

    Permalink
    Definition Classes
    HasRawPredictionCol
  114. final def getRsm: Float

    Permalink
    Definition Classes
    TrainingParamsTrait
  115. final def getSamplingFrequency: ESamplingFrequency

    Permalink
    Definition Classes
    TrainingParamsTrait
  116. final def getSamplingUnit: ESamplingUnit

    Permalink
    Definition Classes
    TrainingParamsTrait
  117. final def getSaveSnapshot: Boolean

    Permalink
    Definition Classes
    TrainingParamsTrait
  118. final def getScalePosWeight: Float

    Permalink
  119. final def getScoreFunction: EScoreFunction

    Permalink
    Definition Classes
    TrainingParamsTrait
  120. final def getSnapshotFile: String

    Permalink
    Definition Classes
    TrainingParamsTrait
  121. final def getSnapshotInterval: Duration

    Permalink
    Definition Classes
    TrainingParamsTrait
  122. final def getSparkPartitionCount: Int

    Permalink
    Definition Classes
    TrainingParamsTrait
  123. final def getSubsample: Float

    Permalink
    Definition Classes
    TrainingParamsTrait
  124. final def getTargetBorder: Float

    Permalink
  125. final def getThreadCount: Int

    Permalink
    Definition Classes
    ThreadCountParams
  126. def getThresholds: Array[Double]

    Permalink
    Definition Classes
    HasThresholds
  127. final def getTrainDir: String

    Permalink
    Definition Classes
    TrainingParamsTrait
  128. final def getUseBestModel: Boolean

    Permalink
    Definition Classes
    TrainingParamsTrait
  129. final def getWeightCol: String

    Permalink
    Definition Classes
    HasWeightCol
  130. final def getWorkerInitializationTimeout: Duration

    Permalink
    Definition Classes
    TrainingParamsTrait
  131. final def hasDefault[T](param: Param[T]): Boolean

    Permalink
    Definition Classes
    Params
  132. def hasParam(paramName: String): Boolean

    Permalink
    Definition Classes
    Params
  133. final val hasTime: BooleanParam

    Permalink
    Definition Classes
    TrainingParamsTrait
  134. def hashCode(): Int

    Permalink
    Definition Classes
    AnyRef → Any
  135. final val ignoredFeaturesIndices: IntArrayParam

    Permalink
    Definition Classes
    IgnoredFeaturesParams
  136. final val ignoredFeaturesNames: StringArrayParam

    Permalink
    Definition Classes
    IgnoredFeaturesParams
  137. def initializeLogIfNecessary(isInterpreter: Boolean, silent: Boolean): Boolean

    Permalink
    Attributes
    protected
    Definition Classes
    Logging
  138. def initializeLogIfNecessary(isInterpreter: Boolean): Unit

    Permalink
    Attributes
    protected
    Definition Classes
    Logging
  139. final val inputBorders: Param[String]

    Permalink
    Definition Classes
    QuantizationParamsTrait
  140. final def isDefined(param: Param[_]): Boolean

    Permalink
    Definition Classes
    Params
  141. final def isInstanceOf[T0]: Boolean

    Permalink
    Definition Classes
    Any
  142. final def isSet(param: Param[_]): Boolean

    Permalink
    Definition Classes
    Params
  143. def isTraceEnabled(): Boolean

    Permalink
    Attributes
    protected
    Definition Classes
    Logging
  144. final val iterations: IntParam

    Permalink
    Definition Classes
    TrainingParamsTrait
  145. final val l2LeafReg: FloatParam

    Permalink
    Definition Classes
    TrainingParamsTrait
  146. final val labelCol: Param[String]

    Permalink
    Definition Classes
    HasLabelCol
  147. final val leafEstimationBacktracking: EnumParam[ELeavesEstimationStepBacktracking]

    Permalink
    Definition Classes
    TrainingParamsTrait
  148. final val leafEstimationIterations: IntParam

    Permalink
    Definition Classes
    TrainingParamsTrait
  149. final val leafEstimationMethod: EnumParam[ELeavesEstimation]

    Permalink
    Definition Classes
    TrainingParamsTrait
  150. final val learningRate: FloatParam

    Permalink
    Definition Classes
    TrainingParamsTrait
  151. def log: Logger

    Permalink
    Attributes
    protected
    Definition Classes
    Logging
  152. def logDebug(msg: ⇒ String, throwable: Throwable): Unit

    Permalink
    Attributes
    protected
    Definition Classes
    Logging
  153. def logDebug(msg: ⇒ String): Unit

    Permalink
    Attributes
    protected
    Definition Classes
    Logging
  154. def logError(msg: ⇒ String, throwable: Throwable): Unit

    Permalink
    Attributes
    protected
    Definition Classes
    Logging
  155. def logError(msg: ⇒ String): Unit

    Permalink
    Attributes
    protected
    Definition Classes
    Logging
  156. def logInfo(msg: ⇒ String, throwable: Throwable): Unit

    Permalink
    Attributes
    protected
    Definition Classes
    Logging
  157. def logInfo(msg: ⇒ String): Unit

    Permalink
    Attributes
    protected
    Definition Classes
    Logging
  158. def logName: String

    Permalink
    Attributes
    protected
    Definition Classes
    Logging
  159. def logTrace(msg: ⇒ String, throwable: Throwable): Unit

    Permalink
    Attributes
    protected
    Definition Classes
    Logging
  160. def logTrace(msg: ⇒ String): Unit

    Permalink
    Attributes
    protected
    Definition Classes
    Logging
  161. def logWarning(msg: ⇒ String, throwable: Throwable): Unit

    Permalink
    Attributes
    protected
    Definition Classes
    Logging
  162. def logWarning(msg: ⇒ String): Unit

    Permalink
    Attributes
    protected
    Definition Classes
    Logging
  163. final val loggingLevel: EnumParam[ELoggingLevel]

    Permalink
    Definition Classes
    TrainingParamsTrait
  164. final val lossFunction: Param[String]

    Permalink
    Definition Classes
    TrainingParamsTrait
  165. final val metricPeriod: IntParam

    Permalink
    Definition Classes
    TrainingParamsTrait
  166. final val modelShrinkMode: EnumParam[EModelShrinkMode]

    Permalink
    Definition Classes
    TrainingParamsTrait
  167. final val modelShrinkRate: FloatParam

    Permalink
    Definition Classes
    TrainingParamsTrait
  168. final val mvsReg: FloatParam

    Permalink
    Definition Classes
    TrainingParamsTrait
  169. final val nanMode: EnumParam[ENanMode]

    Permalink
    Definition Classes
    QuantizationParamsTrait
  170. final def ne(arg0: AnyRef): Boolean

    Permalink
    Definition Classes
    AnyRef
  171. final def notify(): Unit

    Permalink
    Definition Classes
    AnyRef
  172. final def notifyAll(): Unit

    Permalink
    Definition Classes
    AnyRef
  173. final val odPval: FloatParam

    Permalink
    Definition Classes
    TrainingParamsTrait
  174. final val odType: EnumParam[EOverfittingDetectorType]

    Permalink
    Definition Classes
    TrainingParamsTrait
  175. final val odWait: IntParam

    Permalink
    Definition Classes
    TrainingParamsTrait
  176. final val oneHotMaxSize: IntParam

    Permalink
    Definition Classes
    TrainingParamsTrait
  177. lazy val params: Array[Param[_]]

    Permalink
    Definition Classes
    Params
  178. final val penaltiesCoefficient: FloatParam

    Permalink
    Definition Classes
    TrainingParamsTrait
  179. final val perFloatFeatureQuantizaton: StringArrayParam

    Permalink
    Definition Classes
    QuantizationParamsTrait
  180. final val perObjectFeaturePenaltiesList: DoubleArrayParam

    Permalink
    Definition Classes
    TrainingParamsTrait
  181. final val perObjectFeaturePenaltiesMap: OrderedStringMapParam[Double]

    Permalink
    Definition Classes
    TrainingParamsTrait
  182. final val predictionCol: Param[String]

    Permalink
    Definition Classes
    HasPredictionCol
  183. def preprocessBeforeTraining(quantizedTrainPool: Pool, quantizedEvalPools: Array[Pool]): (Pool, Array[Pool], JObject, CtrsContext)

    Permalink

    override in descendants if necessary

    override in descendants if necessary

    returns

    (preprocessedTrainPool, preprocessedEvalPools, catBoostJsonParams, ctrsContext)

    Attributes
    protected
    Definition Classes
    CatBoostClassifierCatBoostPredictorTrait
  184. final val probabilityCol: Param[String]

    Permalink
    Definition Classes
    HasProbabilityCol
  185. final val randomSeed: IntParam

    Permalink
    Definition Classes
    TrainingParamsTrait
  186. final val randomStrength: FloatParam

    Permalink
    Definition Classes
    TrainingParamsTrait
  187. final val rawPredictionCol: Param[String]

    Permalink
    Definition Classes
    HasRawPredictionCol
  188. final val rsm: FloatParam

    Permalink
    Definition Classes
    TrainingParamsTrait
  189. final val samplingFrequency: EnumParam[ESamplingFrequency]

    Permalink
    Definition Classes
    TrainingParamsTrait
  190. final val samplingUnit: EnumParam[ESamplingUnit]

    Permalink
    Definition Classes
    TrainingParamsTrait
  191. def save(path: String): Unit

    Permalink
    Definition Classes
    MLWritable
    Annotations
    @Since( "1.6.0" ) @throws( ... )
  192. final val saveSnapshot: BooleanParam

    Permalink
    Definition Classes
    TrainingParamsTrait
  193. final val scalePosWeight: FloatParam

    Permalink
  194. final val scoreFunction: EnumParam[EScoreFunction]

    Permalink
    Definition Classes
    TrainingParamsTrait
  195. final def set(paramPair: ParamPair[_]): CatBoostClassifier.this.type

    Permalink
    Attributes
    protected
    Definition Classes
    Params
  196. final def set(param: String, value: Any): CatBoostClassifier.this.type

    Permalink
    Attributes
    protected
    Definition Classes
    Params
  197. final def set[T](param: Param[T], value: T): CatBoostClassifier.this.type

    Permalink
    Definition Classes
    Params
  198. final def setAllowConstLabel(value: Boolean): CatBoostClassifier.this.type

    Permalink
    Definition Classes
    TrainingParamsTrait
  199. final def setAllowWritingFiles(value: Boolean): CatBoostClassifier.this.type

    Permalink
    Definition Classes
    TrainingParamsTrait
  200. final def setApproxOnFullHistory(value: Boolean): CatBoostClassifier.this.type

    Permalink
    Definition Classes
    TrainingParamsTrait
  201. final def setAutoClassWeights(value: EAutoClassWeightsType): CatBoostClassifier.this.type

    Permalink
  202. final def setBaggingTemperature(value: Float): CatBoostClassifier.this.type

    Permalink
    Definition Classes
    TrainingParamsTrait
  203. final def setBestModelMinTrees(value: Int): CatBoostClassifier.this.type

    Permalink
    Definition Classes
    TrainingParamsTrait
  204. final def setBootstrapType(value: EBootstrapType): CatBoostClassifier.this.type

    Permalink
    Definition Classes
    TrainingParamsTrait
  205. final def setBorderCount(value: Int): CatBoostClassifier.this.type

    Permalink
    Definition Classes
    QuantizationParamsTrait
  206. final def setClassNames(value: Array[String]): CatBoostClassifier.this.type

    Permalink
  207. final def setClassWeightsList(value: Array[Double]): CatBoostClassifier.this.type

    Permalink
  208. final def setClassWeightsMap(value: LinkedHashMap[String, Double]): CatBoostClassifier.this.type

    Permalink
  209. final def setClassesCount(value: Int): CatBoostClassifier.this.type

    Permalink
  210. final def setCustomMetric(value: Array[String]): CatBoostClassifier.this.type

    Permalink
    Definition Classes
    TrainingParamsTrait
  211. final def setDefault(paramPairs: ParamPair[_]*): CatBoostClassifier.this.type

    Permalink
    Attributes
    protected
    Definition Classes
    Params
  212. final def setDefault[T](param: Param[T], value: T): CatBoostClassifier.this.type

    Permalink
    Attributes
    protected
    Definition Classes
    Params
  213. final def setDepth(value: Int): CatBoostClassifier.this.type

    Permalink
    Definition Classes
    TrainingParamsTrait
  214. final def setDiffusionTemperature(value: Float): CatBoostClassifier.this.type

    Permalink
    Definition Classes
    TrainingParamsTrait
  215. final def setEarlyStoppingRounds(value: Int): CatBoostClassifier.this.type

    Permalink
    Definition Classes
    TrainingParamsTrait
  216. final def setEvalMetric(value: String): CatBoostClassifier.this.type

    Permalink
    Definition Classes
    TrainingParamsTrait
  217. final def setFeatureBorderType(value: EBorderSelectionType): CatBoostClassifier.this.type

    Permalink
    Definition Classes
    QuantizationParamsTrait
  218. final def setFeatureWeightsList(value: Array[Double]): CatBoostClassifier.this.type

    Permalink
    Definition Classes
    TrainingParamsTrait
  219. final def setFeatureWeightsMap(value: LinkedHashMap[String, Double]): CatBoostClassifier.this.type

    Permalink
    Definition Classes
    TrainingParamsTrait
  220. def setFeaturesCol(value: String): CatBoostClassifier

    Permalink
    Definition Classes
    Predictor
  221. final def setFirstFeatureUsePenaltiesList(value: Array[Double]): CatBoostClassifier.this.type

    Permalink
    Definition Classes
    TrainingParamsTrait
  222. final def setFirstFeatureUsePenaltiesMap(value: LinkedHashMap[String, Double]): CatBoostClassifier.this.type

    Permalink
    Definition Classes
    TrainingParamsTrait
  223. final def setFoldLenMultiplier(value: Float): CatBoostClassifier.this.type

    Permalink
    Definition Classes
    TrainingParamsTrait
  224. final def setFoldPermutationBlock(value: Int): CatBoostClassifier.this.type

    Permalink
    Definition Classes
    TrainingParamsTrait
  225. final def setHasTime(value: Boolean): CatBoostClassifier.this.type

    Permalink
    Definition Classes
    TrainingParamsTrait
  226. final def setIgnoredFeaturesIndices(value: Array[Int]): CatBoostClassifier.this.type

    Permalink
    Definition Classes
    IgnoredFeaturesParams
  227. final def setIgnoredFeaturesNames(value: Array[String]): CatBoostClassifier.this.type

    Permalink
    Definition Classes
    IgnoredFeaturesParams
  228. final def setInputBorders(value: String): CatBoostClassifier.this.type

    Permalink
    Definition Classes
    QuantizationParamsTrait
  229. final def setIterations(value: Int): CatBoostClassifier.this.type

    Permalink
    Definition Classes
    TrainingParamsTrait
  230. final def setL2LeafReg(value: Float): CatBoostClassifier.this.type

    Permalink
    Definition Classes
    TrainingParamsTrait
  231. def setLabelCol(value: String): CatBoostClassifier

    Permalink
    Definition Classes
    Predictor
  232. final def setLeafEstimationBacktracking(value: ELeavesEstimationStepBacktracking): CatBoostClassifier.this.type

    Permalink
    Definition Classes
    TrainingParamsTrait
  233. final def setLeafEstimationIterations(value: Int): CatBoostClassifier.this.type

    Permalink
    Definition Classes
    TrainingParamsTrait
  234. final def setLeafEstimationMethod(value: ELeavesEstimation): CatBoostClassifier.this.type

    Permalink
    Definition Classes
    TrainingParamsTrait
  235. final def setLearningRate(value: Float): CatBoostClassifier.this.type

    Permalink
    Definition Classes
    TrainingParamsTrait
  236. final def setLoggingLevel(value: ELoggingLevel): CatBoostClassifier.this.type

    Permalink
    Definition Classes
    TrainingParamsTrait
  237. final def setLossFunction(value: String): CatBoostClassifier.this.type

    Permalink
    Definition Classes
    TrainingParamsTrait
  238. final def setMetricPeriod(value: Int): CatBoostClassifier.this.type

    Permalink
    Definition Classes
    TrainingParamsTrait
  239. final def setModelShrinkMode(value: EModelShrinkMode): CatBoostClassifier.this.type

    Permalink
    Definition Classes
    TrainingParamsTrait
  240. final def setModelShrinkRate(value: Float): CatBoostClassifier.this.type

    Permalink
    Definition Classes
    TrainingParamsTrait
  241. final def setMvsReg(value: Float): CatBoostClassifier.this.type

    Permalink
    Definition Classes
    TrainingParamsTrait
  242. final def setNanMode(value: ENanMode): CatBoostClassifier.this.type

    Permalink
    Definition Classes
    QuantizationParamsTrait
  243. final def setOdPval(value: Float): CatBoostClassifier.this.type

    Permalink
    Definition Classes
    TrainingParamsTrait
  244. final def setOdType(value: EOverfittingDetectorType): CatBoostClassifier.this.type

    Permalink
    Definition Classes
    TrainingParamsTrait
  245. final def setOdWait(value: Int): CatBoostClassifier.this.type

    Permalink
    Definition Classes
    TrainingParamsTrait
  246. final def setOneHotMaxSize(value: Int): CatBoostClassifier.this.type

    Permalink
    Definition Classes
    TrainingParamsTrait
  247. final def setPenaltiesCoefficient(value: Float): CatBoostClassifier.this.type

    Permalink
    Definition Classes
    TrainingParamsTrait
  248. final def setPerFloatFeatureQuantizaton(value: Array[String]): CatBoostClassifier.this.type

    Permalink
    Definition Classes
    QuantizationParamsTrait
  249. final def setPerObjectFeaturePenaltiesList(value: Array[Double]): CatBoostClassifier.this.type

    Permalink
    Definition Classes
    TrainingParamsTrait
  250. final def setPerObjectFeaturePenaltiesMap(value: LinkedHashMap[String, Double]): CatBoostClassifier.this.type

    Permalink
    Definition Classes
    TrainingParamsTrait
  251. def setPredictionCol(value: String): CatBoostClassifier

    Permalink
    Definition Classes
    Predictor
  252. def setProbabilityCol(value: String): CatBoostClassifier

    Permalink
    Definition Classes
    ProbabilisticClassifier
  253. final def setRandomSeed(value: Int): CatBoostClassifier.this.type

    Permalink
    Definition Classes
    TrainingParamsTrait
  254. final def setRandomStrength(value: Float): CatBoostClassifier.this.type

    Permalink
    Definition Classes
    TrainingParamsTrait
  255. def setRawPredictionCol(value: String): CatBoostClassifier

    Permalink
    Definition Classes
    Classifier
  256. final def setRsm(value: Float): CatBoostClassifier.this.type

    Permalink
    Definition Classes
    TrainingParamsTrait
  257. final def setSamplingFrequency(value: ESamplingFrequency): CatBoostClassifier.this.type

    Permalink
    Definition Classes
    TrainingParamsTrait
  258. final def setSamplingUnit(value: ESamplingUnit): CatBoostClassifier.this.type

    Permalink
    Definition Classes
    TrainingParamsTrait
  259. final def setSaveSnapshot(value: Boolean): CatBoostClassifier.this.type

    Permalink
    Definition Classes
    TrainingParamsTrait
  260. final def setScalePosWeight(value: Float): CatBoostClassifier.this.type

    Permalink
  261. final def setScoreFunction(value: EScoreFunction): CatBoostClassifier.this.type

    Permalink
    Definition Classes
    TrainingParamsTrait
  262. final def setSnapshotFile(value: String): CatBoostClassifier.this.type

    Permalink
    Definition Classes
    TrainingParamsTrait
  263. final def setSnapshotInterval(value: Duration): CatBoostClassifier.this.type

    Permalink
    Definition Classes
    TrainingParamsTrait
  264. final def setSparkPartitionCount(value: Int): CatBoostClassifier.this.type

    Permalink
    Definition Classes
    TrainingParamsTrait
  265. final def setSubsample(value: Float): CatBoostClassifier.this.type

    Permalink
    Definition Classes
    TrainingParamsTrait
  266. final def setTargetBorder(value: Float): CatBoostClassifier.this.type

    Permalink
  267. final def setThreadCount(value: Int): CatBoostClassifier.this.type

    Permalink
    Definition Classes
    ThreadCountParams
  268. def setThresholds(value: Array[Double]): CatBoostClassifier

    Permalink
    Definition Classes
    ProbabilisticClassifier
  269. final def setTrainDir(value: String): CatBoostClassifier.this.type

    Permalink
    Definition Classes
    TrainingParamsTrait
  270. final def setUseBestModel(value: Boolean): CatBoostClassifier.this.type

    Permalink
    Definition Classes
    TrainingParamsTrait
  271. final def setWorkerInitializationTimeout(value: Duration): CatBoostClassifier.this.type

    Permalink
    Definition Classes
    TrainingParamsTrait
  272. final val snapshotFile: Param[String]

    Permalink
    Definition Classes
    TrainingParamsTrait
  273. final val snapshotInterval: DurationParam

    Permalink
    Definition Classes
    TrainingParamsTrait
  274. final val sparkPartitionCount: IntParam

    Permalink
    Definition Classes
    TrainingParamsTrait
  275. final val subsample: FloatParam

    Permalink
    Definition Classes
    TrainingParamsTrait
  276. final def synchronized[T0](arg0: ⇒ T0): T0

    Permalink
    Definition Classes
    AnyRef
  277. final val targetBorder: FloatParam

    Permalink
  278. final val threadCount: IntParam

    Permalink
    Definition Classes
    ThreadCountParams
  279. final val thresholds: DoubleArrayParam

    Permalink
    Definition Classes
    HasThresholds
  280. def toString(): String

    Permalink
    Definition Classes
    Identifiable → AnyRef → Any
  281. def train(dataset: Dataset[_]): CatBoostClassificationModel

    Permalink
    Attributes
    protected
    Definition Classes
    CatBoostPredictorTrait → Predictor
  282. final val trainDir: Param[String]

    Permalink
    Definition Classes
    TrainingParamsTrait
  283. def transformSchema(schema: StructType): StructType

    Permalink
    Definition Classes
    Predictor → PipelineStage
  284. def transformSchema(schema: StructType, logging: Boolean): StructType

    Permalink
    Attributes
    protected
    Definition Classes
    PipelineStage
    Annotations
    @DeveloperApi()
  285. val uid: String

    Permalink
    Definition Classes
    CatBoostClassifier → Identifiable
  286. final val useBestModel: BooleanParam

    Permalink
    Definition Classes
    TrainingParamsTrait
  287. def validateAndTransformSchema(schema: StructType, fitting: Boolean, featuresDataType: DataType): StructType

    Permalink
    Attributes
    protected
    Definition Classes
    ProbabilisticClassifierParams → ClassifierParams → PredictorParams
  288. final def wait(): Unit

    Permalink
    Definition Classes
    AnyRef
    Annotations
    @throws( ... )
  289. final def wait(arg0: Long, arg1: Int): Unit

    Permalink
    Definition Classes
    AnyRef
    Annotations
    @throws( ... )
  290. final def wait(arg0: Long): Unit

    Permalink
    Definition Classes
    AnyRef
    Annotations
    @throws( ... )
  291. final val weightCol: Param[String]

    Permalink
    Definition Classes
    HasWeightCol
  292. final val workerInitializationTimeout: DurationParam

    Permalink
    Definition Classes
    TrainingParamsTrait
  293. def write: MLWriter

    Permalink
    Definition Classes
    DefaultParamsWritable → MLWritable

Inherited from TrainingParamsTrait

Inherited from QuantizationParamsTrait

Inherited from ThreadCountParams

Inherited from IgnoredFeaturesParams

Inherited from DefaultParamsWritable

Inherited from MLWritable

Inherited from DatasetParamsTrait

Inherited from HasWeightCol

Inherited from ProbabilisticClassifier[Vector, CatBoostClassifier, CatBoostClassificationModel]

Inherited from ProbabilisticClassifierParams

Inherited from HasThresholds

Inherited from HasProbabilityCol

Inherited from Classifier[Vector, CatBoostClassifier, CatBoostClassificationModel]

Inherited from ClassifierParams

Inherited from HasRawPredictionCol

Inherited from Predictor[Vector, CatBoostClassifier, CatBoostClassificationModel]

Inherited from PredictorParams

Inherited from HasPredictionCol

Inherited from HasFeaturesCol

Inherited from HasLabelCol

Inherited from Estimator[CatBoostClassificationModel]

Inherited from PipelineStage

Inherited from Logging

Inherited from Params

Inherited from Serializable

Inherited from Serializable

Inherited from Identifiable

Inherited from AnyRef

Inherited from Any

Ungrouped