datafu.pig.stats
Class VAR

java.lang.Object
  org.apache.pig.EvalFunc<java.lang.Double>
      datafu.pig.stats.VAR

All Implemented Interfaces:

org.apache.pig.Accumulator<java.lang.Double>, org.apache.pig.Algebraic

public class VAR
extends org.apache.pig.EvalFunc<java.lang.Double>
implements org.apache.pig.Algebraic, org.apache.pig.Accumulator<java.lang.Double>

Generates the Variance of a set of Values. This UDF uses the fact that variance(x) = average(x^2) - average(x)^2 This class implements * Algebraic, so if possible the execution will performed in a distributed fashion. VAR implements the Accumulator interface as well. Input: Bag of int, long, double, float or bytearray Output: Double

Example:

 define VAR datafu.pig.stats.VAR();
 
 -- input: 1,2,3,4,10,5,6,7,8,9
 input = LOAD 'input' AS (val:int);
 grouped = GROUP input ALL;
 variance = FOREACH grouped GENERATE VAR(input.val) AS variance;
 

Nested Class Summary

static class	VAR.Final
static class	VAR.Initial
static class	VAR.Intermediate

Field Summary

Fields inherited from class org.apache.pig.EvalFunc

log, pigLogger, reporter, returnType

Constructor Summary

VAR()

Method Summary

void	accumulate(org.apache.pig.data.Tuple b)
void	cleanup()
protected static org.apache.pig.data.Tuple	combine(org.apache.pig.data.DataBag values)
protected static long	count(org.apache.pig.data.Tuple input)
java.lang.Double	exec(org.apache.pig.data.Tuple input)
java.util.List<org.apache.pig.FuncSpec>	getArgToFuncMapping()
java.lang.String	getFinal()
java.lang.String	getInitial()
java.lang.String	getIntermed()
java.lang.Double	getValue()
org.apache.pig.impl.logicalLayer.schema.Schema	outputSchema(org.apache.pig.impl.logicalLayer.schema.Schema input)
protected static java.lang.Double	sum(org.apache.pig.data.Tuple input)
protected static java.lang.Double	sumSquare(org.apache.pig.data.Tuple input)

Methods inherited from class org.apache.pig.EvalFunc

finish, getCacheFiles, getInputSchema, getLogger, getPigLogger, getReporter, getReturnType, getSchemaName, isAsynchronous, progress, setInputSchema, setPigLogger, setReporter, setUDFContextSignature, warn

Methods inherited from class java.lang.Object

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

Constructor Detail

VAR

public VAR()

Method Detail

exec

public java.lang.Double exec(org.apache.pig.data.Tuple input)
                      throws java.io.IOException

Specified by:

exec in class org.apache.pig.EvalFunc<java.lang.Double>

Throws:

java.io.IOException

getInitial

public java.lang.String getInitial()

Specified by:

getInitial in interface org.apache.pig.Algebraic

getIntermed

public java.lang.String getIntermed()

Specified by:

getIntermed in interface org.apache.pig.Algebraic

getFinal

public java.lang.String getFinal()

Specified by:

getFinal in interface org.apache.pig.Algebraic

combine

protected static org.apache.pig.data.Tuple combine(org.apache.pig.data.DataBag values)
                                            throws org.apache.pig.backend.executionengine.ExecException

Throws:

org.apache.pig.backend.executionengine.ExecException

count

protected static long count(org.apache.pig.data.Tuple input)
                     throws org.apache.pig.backend.executionengine.ExecException

Throws:

org.apache.pig.backend.executionengine.ExecException

sum

protected static java.lang.Double sum(org.apache.pig.data.Tuple input)
                               throws org.apache.pig.backend.executionengine.ExecException,
                                      java.io.IOException

Throws:

org.apache.pig.backend.executionengine.ExecException

java.io.IOException

sumSquare

protected static java.lang.Double sumSquare(org.apache.pig.data.Tuple input)
                                     throws org.apache.pig.backend.executionengine.ExecException,
                                            java.io.IOException

Throws:

org.apache.pig.backend.executionengine.ExecException

java.io.IOException

outputSchema

public org.apache.pig.impl.logicalLayer.schema.Schema outputSchema(org.apache.pig.impl.logicalLayer.schema.Schema input)

Overrides:

outputSchema in class org.apache.pig.EvalFunc<java.lang.Double>

getArgToFuncMapping

public java.util.List<org.apache.pig.FuncSpec> getArgToFuncMapping()
                                                            throws org.apache.pig.impl.logicalLayer.FrontendException

Overrides:

getArgToFuncMapping in class org.apache.pig.EvalFunc<java.lang.Double>

Throws:

org.apache.pig.impl.logicalLayer.FrontendException

accumulate

public void accumulate(org.apache.pig.data.Tuple b)
                throws java.io.IOException

Specified by:

accumulate in interface org.apache.pig.Accumulator<java.lang.Double>

Throws:

java.io.IOException

cleanup

public void cleanup()

Specified by:

cleanup in interface org.apache.pig.Accumulator<java.lang.Double>

getValue

public java.lang.Double getValue()

Specified by:

getValue in interface org.apache.pig.Accumulator<java.lang.Double>