LogisticRegressionSummary (Spark 4.1.0-preview3 JavaDoc)

All Superinterfaces:: ClassificationSummary, Serializable, Summary

All Known Subinterfaces:: BinaryLogisticRegressionSummary, BinaryLogisticRegressionTrainingSummary, LogisticRegressionTrainingSummary

All Known Implementing Classes:: BinaryLogisticRegressionSummaryImpl, BinaryLogisticRegressionTrainingSummaryImpl, LogisticRegressionSummaryImpl, LogisticRegressionTrainingSummaryImpl

public interface LogisticRegressionSummary extends ClassificationSummary

Abstraction for logistic regression results for a given model.

Method Summary

Modifier and Type

Method

Description

BinaryLogisticRegressionSummary

asBinary()

Convenient method for casting to binary logistic regression summary.

String

featuresCol()

Field in "predictions" which gives the features of each instance as a vector.

String

probabilityCol()

Field in "predictions" which gives the probability of each class as a vector.

Methods inherited from interface org.apache.spark.ml.classification.ClassificationSummary
accuracy, falsePositiveRateByLabel, fMeasureByLabel, fMeasureByLabel, labelCol, labels, precisionByLabel, predictionCol, predictions, recallByLabel, truePositiveRateByLabel, weightCol, weightedFalsePositiveRate, weightedFMeasure, weightedFMeasure, weightedPrecision, weightedRecall, weightedTruePositiveRate

Method Details
- asBinary
  
  BinaryLogisticRegressionSummary asBinary()
  
  Convenient method for casting to binary logistic regression summary. This method will throw an Exception if the summary is not a binary summary.
  
  Returns:
  
  (undocumented)
- featuresCol
  
  String featuresCol()
  
  Field in "predictions" which gives the features of each instance as a vector.
- probabilityCol
  
  String probabilityCol()
  
  Field in "predictions" which gives the probability of each class as a vector.