Package org.apache.spark.ml.fpm

Class AssociationRules

Object

org.apache.spark.ml.fpm.AssociationRules

public class AssociationRules
extends Object

Constructor Summary

Constructors

Constructor	Description
AssociationRules()

Method Summary

Modifier and Type	Method	Description
static <T> Dataset<Row>	getAssociationRulesFromFP(Dataset<?> dataset, String itemsCol, String freqCol, double minConfidence, scala.collection.Map<T,Object> itemSupport, long numTrainingRecords, scala.reflect.ClassTag<T> evidence$2)	Computes the association rules with confidence above minConfidence.

Methods inherited from class java.lang.Object

equals, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

Constructor Details

AssociationRules

public AssociationRules()

Method Details

getAssociationRulesFromFP

public static <T> Dataset<Row> getAssociationRulesFromFP(Dataset<?> dataset,
 String itemsCol,
 String freqCol,
 double minConfidence,
 scala.collection.Map<T,Object> itemSupport,
 long numTrainingRecords,
 scala.reflect.ClassTag<T> evidence$2)

Computes the association rules with confidence above minConfidence.

Parameters:

dataset - DataFrame("items"[Array], "freq"[Long]) containing frequent itemsets obtained from algorithms like FPGrowth.

itemsCol - column name for frequent itemsets

freqCol - column name for appearance count of the frequent itemsets

minConfidence - minimum confidence for generating the association rules

itemSupport - map containing an item and its support

numTrainingRecords - count of training Dataset

evidence$2 - (undocumented)

Returns:

a DataFrame("antecedent"[Array], "consequent"[Array], "confidence"[Double], "lift" [Double]) containing the association rules.