public class StatisticsBuilder
extends java.lang.Object
Constructor and Description |
---|
StatisticsBuilder(DataHandleInternal handle)
Creates a new instance.
|
Modifier and Type | Method and Description |
---|---|
StatisticsClassification |
getClassificationPerformance(java.lang.String[] features,
java.lang.String clazz,
ARXClassificationConfiguration<?> config)
Creates a new set of statistics for the given classification task
|
StatisticsClassification |
getClassificationPerformance(java.lang.String[] features,
java.lang.String clazz,
ARXClassificationConfiguration<?> config,
ARXFeatureScaling scaling)
Creates a new set of statistics for the given classification task
|
StatisticsClassification |
getClassificationPerformance(java.lang.String clazz,
ARXClassificationConfiguration<?> config)
Creates a new set of statistics for the given classification task
|
StatisticsContingencyTable |
getContingencyTable(int column1,
boolean orderFromDefinition1,
int column2,
boolean orderFromDefinition2)
Returns a contingency table for the given columns.
|
StatisticsContingencyTable |
getContingencyTable(int column1,
int column2)
Returns a contingency table for the given columns.
|
StatisticsContingencyTable |
getContingencyTable(int column1,
int size1,
boolean orderFromDefinition1,
int column2,
int size2,
boolean orderFromDefinition2)
Returns a contingency table for the given columns.
|
StatisticsContingencyTable |
getContingencyTable(int column1,
int size1,
int column2,
int size2)
Returns a contingency table for the given columns.
|
StatisticsContingencyTable |
getContingencyTable(int column1,
int size1,
java.lang.String[][] hierarchy1,
int column2,
int size2,
java.lang.String[][] hierarchy2)
Returns a contingency table for the given columns.
|
StatisticsContingencyTable |
getContingencyTable(int column1,
java.lang.String[][] hierarchy1,
int column2,
java.lang.String[][] hierarchy2)
Returns a contingency table for the given columns.
|
java.lang.String[] |
getDistinctValues(int column)
Returns the distinct set of data items from the given column.
|
java.lang.String[] |
getDistinctValuesOrdered(int column)
Returns an ordered list of the distinct set of data items from the given column.
|
java.lang.String[] |
getDistinctValuesOrdered(int column,
boolean orderFromDefinition)
Returns an ordered list of the distinct set of data items from the given column.
|
java.lang.String[] |
getDistinctValuesOrdered(int column,
java.lang.String[][] hierarchy)
Returns an ordered list of the distinct set of data items from the given column.
|
StatisticsEquivalenceClasses |
getEquivalenceClassStatistics()
Returns statistics about the equivalence classes.
|
StatisticsFrequencyDistribution |
getFrequencyDistribution(int column)
Returns a frequency distribution for the values in the given column.
|
StatisticsFrequencyDistribution |
getFrequencyDistribution(int column,
boolean orderFromDefinition)
Returns a frequency distribution for the values in the given column.
|
StatisticsFrequencyDistribution |
getFrequencyDistribution(int column,
java.lang.String[][] hierarchy)
Returns a frequency distribution for the values in the given column.
|
StatisticsBuilderInterruptible |
getInterruptibleInstance()
Returns an interruptible instance of this object.
|
StatisticsQuality |
getQualityStatistics()
Returns data quality according to various models.
|
StatisticsQuality |
getQualityStatistics(DataHandle output)
Returns data quality according to various models.
|
StatisticsQuality |
getQualityStatistics(DataHandle output,
java.util.Set<java.lang.String> qis)
Returns data quality according to various models.
|
StatisticsQuality |
getQualityStatistics(java.util.Set<java.lang.String> qis)
Returns data quality according to various models.
|
<T> java.util.Map<java.lang.String,StatisticsSummary<?>> |
getSummaryStatistics(boolean listwiseDeletion)
Returns summary statistics for all attributes.
|
public StatisticsBuilder(DataHandleInternal handle)
handle
- public StatisticsClassification getClassificationPerformance(java.lang.String clazz, ARXClassificationConfiguration<?> config) throws java.text.ParseException
clazz
- - The class attributeconfig
- - The configurationjava.text.ParseException
public StatisticsClassification getClassificationPerformance(java.lang.String[] features, java.lang.String clazz, ARXClassificationConfiguration<?> config) throws java.text.ParseException
features
- - The feature attributesclazz
- - The class attributesconfig
- - The configurationjava.text.ParseException
public StatisticsClassification getClassificationPerformance(java.lang.String[] features, java.lang.String clazz, ARXClassificationConfiguration<?> config, ARXFeatureScaling scaling) throws java.text.ParseException
features
- - The feature attributesclazz
- - The class attributesconfig
- - The configurationscaling
- - Feature scalingjava.text.ParseException
public StatisticsContingencyTable getContingencyTable(int column1, boolean orderFromDefinition1, int column2, boolean orderFromDefinition2)
column1
- The first columnorderFromDefinition1
- Indicates whether the order that should be assumed for string data items
can (and should) be derived from the hierarchy provided in the data
definition (if any)column2
- The second columnorderFromDefinition2
- Indicates whether the order that should be assumed for string data items
can (and should) be derived from the hierarchy provided in the data
definition (if any)public StatisticsContingencyTable getContingencyTable(int column1, int column2)
column1
- The first columncolumn2
- The second columnpublic StatisticsContingencyTable getContingencyTable(int column1, int size1, boolean orderFromDefinition1, int column2, int size2, boolean orderFromDefinition2)
column1
- The first columnsize1
- The maximal size in this dimensionorderFromDefinition1
- Indicates whether the order that should be assumed for string data items
can (and should) be derived from the hierarchy provided in the data
definition (if any)column2
- The second columnsize2
- The maximal size in this dimensionorderFromDefinition2
- Indicates whether the order that should be assumed for string data items
can (and should) be derived from the hierarchy provided in the data
definition (if any)public StatisticsContingencyTable getContingencyTable(int column1, int size1, int column2, int size2)
column1
- The first columnsize1
- The maximal size in this dimensioncolumn2
- The second columnsize2
- The maximal size in this dimensionpublic StatisticsContingencyTable getContingencyTable(int column1, int size1, java.lang.String[][] hierarchy1, int column2, int size2, java.lang.String[][] hierarchy2)
column1
- The first columnsize1
- The maximal size in this dimensionhierarchy1
- The hierarchy for the first column, may be nullcolumn2
- The second columnsize2
- The maximal size in this dimensionhierarchy2
- The hierarchy for the second column, may be nullpublic StatisticsContingencyTable getContingencyTable(int column1, java.lang.String[][] hierarchy1, int column2, java.lang.String[][] hierarchy2)
column1
- The first columnhierarchy1
- The hierarchy for the first column, may be nullcolumn2
- The second columnhierarchy2
- The hierarchy for the second column, may be nullpublic java.lang.String[] getDistinctValues(int column)
column
- The columnpublic java.lang.String[] getDistinctValuesOrdered(int column)
column
- The columnpublic java.lang.String[] getDistinctValuesOrdered(int column, boolean orderFromDefinition)
column
- The columnorderFromDefinition
- Indicates whether the order that should be assumed for string data
items can (and should) be derived from the hierarchy provided in the
data definition (if any)public java.lang.String[] getDistinctValuesOrdered(int column, java.lang.String[][] hierarchy)
column
- The columnhierarchy
- The hierarchy, may be nullpublic StatisticsEquivalenceClasses getEquivalenceClassStatistics()
public StatisticsFrequencyDistribution getFrequencyDistribution(int column)
column
- The columnpublic StatisticsFrequencyDistribution getFrequencyDistribution(int column, boolean orderFromDefinition)
column
- The columnorderFromDefinition
- Indicates whether the order that should be assumed for string data items
should be derived from the hierarchy provided in the data definition (if any)public StatisticsFrequencyDistribution getFrequencyDistribution(int column, java.lang.String[][] hierarchy)
column
- The columnhierarchy
- The hierarchy, may be nullpublic StatisticsBuilderInterruptible getInterruptibleInstance()
public StatisticsQuality getQualityStatistics()
public StatisticsQuality getQualityStatistics(DataHandle output)
output
- public StatisticsQuality getQualityStatistics(DataHandle output, java.util.Set<java.lang.String> qis)
output
- qis
- public StatisticsQuality getQualityStatistics(java.util.Set<java.lang.String> qis)
qis
- public <T> java.util.Map<java.lang.String,StatisticsSummary<?>> getSummaryStatistics(boolean listwiseDeletion)
listwiseDeletion
- A flag enabling list-wise deletion