Package com.dataai.etl.spark.functions

Class AnalyticsFunctions

java.lang.Object

com.dataai.etl.spark.functions.AnalyticsFunctions

public final class AnalyticsFunctions
extends Object

Method Summary

Modifier and Type	Method	Description
static org.apache.spark.sql.Dataset<org.apache.spark.sql.Row>	correlations(org.apache.spark.sql.Dataset<org.apache.spark.sql.Row> input, List<String> numericFields)
static org.apache.spark.sql.Dataset<org.apache.spark.sql.Row>	correlationThreshold(org.apache.spark.sql.Dataset<org.apache.spark.sql.Row> input, List<String> numericFields, double minimumAbsoluteCorrelation, String direction)
static org.apache.spark.sql.Dataset<org.apache.spark.sql.Row>	groupedSummary(org.apache.spark.sql.Dataset<org.apache.spark.sql.Row> input, List<String> groupFields, String valueField, Aggregation aggregation)
static org.apache.spark.sql.Dataset<org.apache.spark.sql.Row>	linearRegression(org.apache.spark.sql.Dataset<org.apache.spark.sql.Row> input, String xField, String yField, String groupField, Double predictionX)
static org.apache.spark.sql.Dataset<org.apache.spark.sql.Row>	pivot(org.apache.spark.sql.Dataset<org.apache.spark.sql.Row> input, String rowField, String columnField, String valueField, Aggregation aggregation)
static org.apache.spark.sql.Dataset<org.apache.spark.sql.Row>	ranking(org.apache.spark.sql.Dataset<org.apache.spark.sql.Row> input, String rankField, List<String> withinGroupFields, String valueField, Aggregation aggregation, RankMode mode, int limitPerGroup)
static org.apache.spark.sql.Dataset<org.apache.spark.sql.Row>	variance(org.apache.spark.sql.Dataset<org.apache.spark.sql.Row> input, List<String> groupFields, String compareField, String baseValue, String comparisonValue, String valueField, Aggregation aggregation)

Methods inherited from class java.lang.Object

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

Method Details

groupedSummary

public static org.apache.spark.sql.Dataset<org.apache.spark.sql.Row> groupedSummary(org.apache.spark.sql.Dataset<org.apache.spark.sql.Row> input,
 List<String> groupFields,
 String valueField,
 Aggregation aggregation)

pivot

public static org.apache.spark.sql.Dataset<org.apache.spark.sql.Row> pivot(org.apache.spark.sql.Dataset<org.apache.spark.sql.Row> input,
 String rowField,
 String columnField,
 String valueField,
 Aggregation aggregation)

variance

public static org.apache.spark.sql.Dataset<org.apache.spark.sql.Row> variance(org.apache.spark.sql.Dataset<org.apache.spark.sql.Row> input,
 List<String> groupFields,
 String compareField,
 String baseValue,
 String comparisonValue,
 String valueField,
 Aggregation aggregation)

ranking

public static org.apache.spark.sql.Dataset<org.apache.spark.sql.Row> ranking(org.apache.spark.sql.Dataset<org.apache.spark.sql.Row> input,
 String rankField,
 List<String> withinGroupFields,
 String valueField,
 Aggregation aggregation,
 RankMode mode,
 int limitPerGroup)

correlations

public static org.apache.spark.sql.Dataset<org.apache.spark.sql.Row> correlations(org.apache.spark.sql.Dataset<org.apache.spark.sql.Row> input,
 List<String> numericFields)

correlationThreshold

public static org.apache.spark.sql.Dataset<org.apache.spark.sql.Row> correlationThreshold(org.apache.spark.sql.Dataset<org.apache.spark.sql.Row> input,
 List<String> numericFields,
 double minimumAbsoluteCorrelation,
 String direction)

linearRegression

public static org.apache.spark.sql.Dataset<org.apache.spark.sql.Row> linearRegression(org.apache.spark.sql.Dataset<org.apache.spark.sql.Row> input,
 String xField,
 String yField,
 String groupField,
 Double predictionX)