Package com.dataai.etl.spark.functions

Class BusinessFunctions

java.lang.Object

com.dataai.etl.spark.functions.BusinessFunctions

public final class BusinessFunctions
extends Object

Method Summary

Modifier and Type	Method	Description
static org.apache.spark.sql.Dataset<org.apache.spark.sql.Row>	anomalyScores(org.apache.spark.sql.Dataset<org.apache.spark.sql.Row> input, List<String> groupFields, String valueField, double minimumScore)
static org.apache.spark.sql.Dataset<org.apache.spark.sql.Row>	cohort(org.apache.spark.sql.Dataset<org.apache.spark.sql.Row> input, String entityField, String activityDateField, String valueField, TimePeriod period)
static org.apache.spark.sql.Dataset<org.apache.spark.sql.Row>	drift(org.apache.spark.sql.Dataset<org.apache.spark.sql.Row> input, String comparedField, String segmentField, String baseSegment, String comparisonSegment)
static org.apache.spark.sql.Dataset<org.apache.spark.sql.Row>	funnel(org.apache.spark.sql.Dataset<org.apache.spark.sql.Row> input, String stageField, String entityField, String valueField, List<String> orderedStages)
static org.apache.spark.sql.Dataset<org.apache.spark.sql.Row>	kpi(org.apache.spark.sql.Dataset<org.apache.spark.sql.Row> input, List<String> dimensionFields, String numeratorField, String denominatorField, KpiOperation operation)
static org.apache.spark.sql.Dataset<org.apache.spark.sql.Row>	outliers(org.apache.spark.sql.Dataset<org.apache.spark.sql.Row> input, List<String> groupFields, String valueField, OutlierMethod method, double threshold, Double businessMinimum, Double businessMaximum)
static org.apache.spark.sql.Dataset<org.apache.spark.sql.Row>	pareto(org.apache.spark.sql.Dataset<org.apache.spark.sql.Row> input, String dimensionField, String valueField, Aggregation aggregation)

Methods inherited from class java.lang.Object

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

Method Details

pareto

public static org.apache.spark.sql.Dataset<org.apache.spark.sql.Row> pareto(org.apache.spark.sql.Dataset<org.apache.spark.sql.Row> input,
 String dimensionField,
 String valueField,
 Aggregation aggregation)

drift

public static org.apache.spark.sql.Dataset<org.apache.spark.sql.Row> drift(org.apache.spark.sql.Dataset<org.apache.spark.sql.Row> input,
 String comparedField,
 String segmentField,
 String baseSegment,
 String comparisonSegment)

outliers

public static org.apache.spark.sql.Dataset<org.apache.spark.sql.Row> outliers(org.apache.spark.sql.Dataset<org.apache.spark.sql.Row> input,
 List<String> groupFields,
 String valueField,
 OutlierMethod method,
 double threshold,
 Double businessMinimum,
 Double businessMaximum)

anomalyScores

public static org.apache.spark.sql.Dataset<org.apache.spark.sql.Row> anomalyScores(org.apache.spark.sql.Dataset<org.apache.spark.sql.Row> input,
 List<String> groupFields,
 String valueField,
 double minimumScore)

kpi

public static org.apache.spark.sql.Dataset<org.apache.spark.sql.Row> kpi(org.apache.spark.sql.Dataset<org.apache.spark.sql.Row> input,
 List<String> dimensionFields,
 String numeratorField,
 String denominatorField,
 KpiOperation operation)

funnel

public static org.apache.spark.sql.Dataset<org.apache.spark.sql.Row> funnel(org.apache.spark.sql.Dataset<org.apache.spark.sql.Row> input,
 String stageField,
 String entityField,
 String valueField,
 List<String> orderedStages)

cohort

public static org.apache.spark.sql.Dataset<org.apache.spark.sql.Row> cohort(org.apache.spark.sql.Dataset<org.apache.spark.sql.Row> input,
 String entityField,
 String activityDateField,
 String valueField,
 TimePeriod period)