LightGBMClassifier

class LightGBMClassifier.LightGBMClassifier(baggingFraction=1.0, baggingFreq=0, baggingSeed=3, defaultListenPort=12400, featureFraction=1.0, featuresCol='features', labelCol='label', learningRate=0.1, maxBin=255, maxDepth=-1, minSumHessianInLeaf=0.001, numIterations=100, numLeaves=31, parallelism='data_parallel', predictionCol='prediction', probabilityCol='probability', rawPredictionCol='rawPrediction', thresholds=None)

Bases: mmlspark.Utils.ComplexParamsMixin, pyspark.ml.util.JavaMLReadable, pyspark.ml.util.JavaMLWritable, pyspark.ml.wrapper.JavaEstimator

Trains a LightGBM Binary Classification model, a fast, distributed, high performance gradient boosting framework based on decision tree algorithms. For more information please see here: https://github.com/Microsoft/LightGBM.

Parameters:

• baggingFraction (double) – Bagging fraction (default: 1.0)
• baggingFreq (int) – Bagging frequence (default: 0)
• baggingSeed (int) – Bagging seed (default: 3)
• defaultListenPort (int) – The default listen port on executors, used for testing (default: 12400)
• featureFraction (double) – Feature fraction (default: 1.0)
• featuresCol (str) – features column name (default: features)
• labelCol (str) – label column name (default: label)
• learningRate (double) – Learning rate or shrinkage rate (default: 0.1)
• maxBin (int) – Max bin (default: 255)
• maxDepth (int) – Max depth (default: -1)
• minSumHessianInLeaf (double) – minimal sum hessian in one leaf (default: 0.001)
• numIterations (int) – Number of iterations, LightGBM constructs num_class * num_iterations trees (default: 100)
• numLeaves (int) – Number of leaves (default: 31)
• parallelism (str) – Tree learner parallelism, can be set to data_parallel or voting_parallel (default: data_parallel)
• predictionCol (str) – prediction column name (default: prediction)
• probabilityCol (str) – Column name for predicted class conditional probabilities. Note: Not all models output well-calibrated probability estimates! These probabilities should be treated as confidences, not precise probabilities (default: probability)
• rawPredictionCol (str) – raw prediction (a.k.a. confidence) column name (default: rawPrediction)
• thresholds (object) – Thresholds in multi-class classification to adjust the probability of predicting each class. Array must have length equal to the number of classes, with values > 0 excepting that at most one value may be 0. The class with largest value p/t is predicted, where p is the original probability of that class and t is the class’s threshold

getBaggingFraction()

Returns:Bagging fraction (default: 1.0) Return type:double

getBaggingFreq()

Returns:Bagging frequence (default: 0) Return type:int

getBaggingSeed()

Returns:Bagging seed (default: 3) Return type:int

getDefaultListenPort()

Returns:The default listen port on executors, used for testing (default: 12400) Return type:int

getFeatureFraction()

Returns:Feature fraction (default: 1.0) Return type:double

getFeaturesCol()

Returns:features column name (default: features) Return type:str

static getJavaPackage()

Returns package name String.

getLabelCol()

Returns:label column name (default: label) Return type:str

getLearningRate()

Returns:Learning rate or shrinkage rate (default: 0.1) Return type:double

getMaxBin()

Returns:Max bin (default: 255) Return type:int

getMaxDepth()

Returns:Max depth (default: -1) Return type:int

getMinSumHessianInLeaf()

Returns:minimal sum hessian in one leaf (default: 0.001) Return type:double

getNumIterations()

Returns:Number of iterations, LightGBM constructs num_class * num_iterations trees (default: 100) Return type:int

getNumLeaves()

Returns:Number of leaves (default: 31) Return type:int

getParallelism()

Returns:Tree learner parallelism, can be set to data_parallel or voting_parallel (default: data_parallel) Return type:str

getPredictionCol()

Returns:prediction column name (default: prediction) Return type:str

getProbabilityCol()

Returns:Column name for predicted class conditional probabilities. Note: Not all models output well-calibrated probability estimates! These probabilities should be treated as confidences, not precise probabilities (default: probability) Return type:str

getRawPredictionCol()

Returns:raw prediction (a.k.a. confidence) column name (default: rawPrediction) Return type:str

getThresholds()

Returns:Thresholds in multi-class classification to adjust the probability of predicting each class. Array must have length equal to the number of classes, with values > 0 excepting that at most one value may be 0. The class with largest value p/t is predicted, where p is the original probability of that class and t is the class’s threshold Return type:object

classmethod read()

Returns an MLReader instance for this class.

setBaggingFraction(value)

Parameters:baggingFraction (double) – Bagging fraction (default: 1.0)

setBaggingFreq(value)

Parameters:baggingFreq (int) – Bagging frequence (default: 0)

setBaggingSeed(value)

Parameters:baggingSeed (int) – Bagging seed (default: 3)

setDefaultListenPort(value)

Parameters:defaultListenPort (int) – The default listen port on executors, used for testing (default: 12400)

setFeatureFraction(value)

Parameters:featureFraction (double) – Feature fraction (default: 1.0)

setFeaturesCol(value)

Parameters:featuresCol (str) – features column name (default: features)

setLabelCol(value)

Parameters:labelCol (str) – label column name (default: label)

setLearningRate(value)

Parameters:learningRate (double) – Learning rate or shrinkage rate (default: 0.1)

setMaxBin(value)

Parameters:maxBin (int) – Max bin (default: 255)

setMaxDepth(value)

Parameters:maxDepth (int) – Max depth (default: -1)

setMinSumHessianInLeaf(value)

Parameters:minSumHessianInLeaf (double) – minimal sum hessian in one leaf (default: 0.001)

setNumIterations(value)

Parameters:numIterations (int) – Number of iterations, LightGBM constructs num_class * num_iterations trees (default: 100)

setNumLeaves(value)

Parameters:numLeaves (int) – Number of leaves (default: 31)

setParallelism(value)

Parameters:parallelism (str) – Tree learner parallelism, can be set to data_parallel or voting_parallel (default: data_parallel)

setParams(baggingFraction=1.0, baggingFreq=0, baggingSeed=3, defaultListenPort=12400, featureFraction=1.0, featuresCol='features', labelCol='label', learningRate=0.1, maxBin=255, maxDepth=-1, minSumHessianInLeaf=0.001, numIterations=100, numLeaves=31, parallelism='data_parallel', predictionCol='prediction', probabilityCol='probability', rawPredictionCol='rawPrediction', thresholds=None)

Set the (keyword only) parameters

Parameters:

• baggingFraction (double) – Bagging fraction (default: 1.0)
• baggingFreq (int) – Bagging frequence (default: 0)
• baggingSeed (int) – Bagging seed (default: 3)
• defaultListenPort (int) – The default listen port on executors, used for testing (default: 12400)
• featureFraction (double) – Feature fraction (default: 1.0)
• featuresCol (str) – features column name (default: features)
• labelCol (str) – label column name (default: label)
• learningRate (double) – Learning rate or shrinkage rate (default: 0.1)
• maxBin (int) – Max bin (default: 255)
• maxDepth (int) – Max depth (default: -1)
• minSumHessianInLeaf (double) – minimal sum hessian in one leaf (default: 0.001)
• numIterations (int) – Number of iterations, LightGBM constructs num_class * num_iterations trees (default: 100)
• numLeaves (int) – Number of leaves (default: 31)
• parallelism (str) – Tree learner parallelism, can be set to data_parallel or voting_parallel (default: data_parallel)
• predictionCol (str) – prediction column name (default: prediction)
• probabilityCol (str) – Column name for predicted class conditional probabilities. Note: Not all models output well-calibrated probability estimates! These probabilities should be treated as confidences, not precise probabilities (default: probability)
• rawPredictionCol (str) – raw prediction (a.k.a. confidence) column name (default: rawPrediction)
• thresholds (object) – Thresholds in multi-class classification to adjust the probability of predicting each class. Array must have length equal to the number of classes, with values > 0 excepting that at most one value may be 0. The class with largest value p/t is predicted, where p is the original probability of that class and t is the class’s threshold

setPredictionCol(value)

Parameters:predictionCol (str) – prediction column name (default: prediction)

setProbabilityCol(value)

Parameters:probabilityCol (str) – Column name for predicted class conditional probabilities. Note: Not all models output well-calibrated probability estimates! These probabilities should be treated as confidences, not precise probabilities (default: probability)

setRawPredictionCol(value)

Parameters:rawPredictionCol (str) – raw prediction (a.k.a. confidence) column name (default: rawPrediction)

setThresholds(value)

Parameters:thresholds (object) – Thresholds in multi-class classification to adjust the probability of predicting each class. Array must have length equal to the number of classes, with values > 0 excepting that at most one value may be 0. The class with largest value p/t is predicted, where p is the original probability of that class and t is the class’s threshold

class LightGBMClassifier.M(java_model=None)

Bases: mmlspark.Utils.ComplexParamsMixin, pyspark.ml.wrapper.JavaModel, pyspark.ml.util.JavaMLWritable, pyspark.ml.util.JavaMLReadable

Model fitted by LightGBMClassifier.

This class is left empty on purpose. All necessary methods are exposed through inheritance.

static getJavaPackage()

Returns package name String.

classmethod read()

Returns an MLReader instance for this class.