Package com.macrofocus.molap.subset

Class SubsetDataFrame<Row,Column,Value>

java.lang.Object

com.macrofocus.molap.dataframe.AbstractDataFrame<R,C,V>

com.macrofocus.molap.dataframe.AbstractMutableDataFrame<R,C,V>

com.macrofocus.molap.dataframe.ReMappedDataFrame<Row,Column,Value>

com.macrofocus.molap.subset.SubsetDataFrame<Row,Column,Value>

Type Parameters:

Row -

Column -

Value -

All Implemented Interfaces:

DataFrame<Row,Column,Value>, MutableDataFrame<Row,Column,Value>

public class SubsetDataFrame<Row,Column,Value>
extends ReMappedDataFrame<Row,Column,Value>

ToDo: Could use less memory by compressing all the pointers (int array), especially since direct traversal is not needed and accessing the pointers is unfrequent. Could be stored in a Gzipped byte array or ByteBuffer, or using some of the compression techniques of https://github.com/lemire/JavaFastPFOR ToDo: Also possible would to obtain how many unique values exist in each column to select appropriate data structure, as well as knowing whether the values could be accessed with less memory consuming (byte, short) pointers.

Nested Class Summary

Nested classes/interfaces inherited from class com.macrofocus.molap.dataframe.ReMappedDataFrame

ReMappedDataFrame.ReMappedRecipe<R,C>

Nested classes/interfaces inherited from class com.macrofocus.molap.dataframe.AbstractDataFrame

AbstractDataFrame.ColumnSeries

Field Summary

Fields inherited from class com.macrofocus.molap.dataframe.ReMappedDataFrame

dataFrame

Constructor Summary

Constructors

Constructor	Description
SubsetDataFrame(DataFrame<Row,Column,Value> dataFrame)
SubsetDataFrame(DataFrame<Row,Column,Value> dataFrame, com.macrofocus.filter.MutableIndexFilter<Row> outputFilter)
SubsetDataFrame(DataFrame<Row,Column,Value> dataFrame, com.macrofocus.filter.MutableIndexFilter<Row> outputFilter, com.macrofocus.selection.MutableSelection<Row> selection)

Method Summary

Modifier and Type	Method	Description
void	addDimension(Dimension<Row> dimension)
int[]	computeFiltered(int[] oldIndices, int[] newIndices)
int[]	computeUnfiltered(int[] oldIndices, int[] newIndices)
DefaultTextDimension<Row,Column,Value>	createTextDimension(Column... columns)
void	defineIndex(Column... columns)
<Bin> SingleBinningDimension<Row,Bin>	getBinningDimension(Column column, SingleBinningDimension.SingleBinningStrategy<Row,Bin> binningStrategy)
CategoricalDimension<Row,Column,Value>	getCategoricalDimension(Column column)
<Bin> DistributionDimension<Row,Value,Bin>	getDistributionDimension(Column column, DistributionDimension.DistributionStrategy<Value,Bin> distributionStrategy)
ItemsDimension<Row,Column,Value>	getItemsDimension()
OrdinalDimension<Row,Column,Value>	getOrdinalDimension(Column column)
com.macrofocus.filter.Filter<Row>	getOutputFilter()
DataFrame<Row,Column,Value>	getUnfilteredDataFrame()
protected void	invalidateFilters()
void	materializeIndex(Column... columns)
protected void	originalDataFrameChanged()
void	reduceDimension(Dimension<Row> dimension)
void	removeDimension(Dimension<Row> dimension)
void	reset()
protected void	scheduleUpdateFilters()
void	setExecutor(com.macrofocus.timer.CPExecutor executor)
void	setTimer(com.macrofocus.timer.CPTimer timer)
int[]	updateActiveIndices()
void	updateFilters()	Filter using TIntList
void	updateFiltersUsingArrays()	Filter using raw arrays
void	updateFiltersUsingTHashSet()	Deprecated.

Methods inherited from class com.macrofocus.molap.dataframe.ReMappedDataFrame

getColumnClass, getColumnIndex, getOriginalDataFrame, getRow, getRowClass, getRowIndex, getValueAt, invalidate, join, scheduleUpdate, setDataFrame, setRecipe, setValueAt, updateImmediatelly

Methods inherited from class com.macrofocus.molap.dataframe.AbstractMutableDataFrame

reindexRows, reindexRows

Methods inherited from class com.macrofocus.molap.dataframe.AbstractDataFrame

addDataFrameListener, addWeakDataFrameListener, aggregate, aggregate, append, appendAndReindex, benchmark, columns, filter, getCentroid, getColumn, getColumnAddress, getColumnCount, getColumnKey, getColumnName, getConstant, getCount, getCountDistinct, getCountDistinctWithNull, getCube, getDataFrameAggregation, getDistributiveStatistics, getFirst, getFirstQuartile, getMax, getMean, getMedian, getMin, getRandom, getRowAddress, getRowCount, getRowKey, getStatistics, getStdDev, getSum, getThirdQuartile, getUnivariateStatistics, getVariance, getVarianceByPopulation, getWeightedMean, getWeightedSum, notifyDataFrameChanged, orderRows, print, print, printSchema, reindexColumns, reindexRows, reindexRows, reindexRows, remapColumns, removeColumns, removeDataFrameListener, removeDataFrameListeners, removeDuplicates, rows

Methods inherited from class java.lang.Object

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

Methods inherited from interface com.macrofocus.molap.dataframe.DataFrame

addDataFrameListener, addWeakDataFrameListener, aggregate, aggregate, append, appendAndReindex, benchmark, columns, filter, getCentroid, getColumn, getColumnAddress, getColumnCount, getColumnKey, getColumnName, getConstant, getCount, getCountDistinct, getCountDistinctWithNull, getDataFrameAggregation, getDistributiveStatistics, getFirst, getFirstQuartile, getMax, getMean, getMedian, getMin, getRandom, getRowAddress, getRowCount, getRowKey, getStatistics, getStdDev, getSum, getThirdQuartile, getUnivariateStatistics, getVariance, getVarianceByPopulation, getWeightedMean, getWeightedSum, orderRows, print, print, printSchema, reindexColumns, reindexRows, reindexRows, reindexRows, remapColumns, removeColumns, removeDataFrameListener, removeDataFrameListeners, removeDuplicates, rows

Methods inherited from interface com.macrofocus.molap.dataframe.MutableDataFrame

reindexRows, reindexRows

Constructor Detail

SubsetDataFrame

public SubsetDataFrame(DataFrame<Row,Column,Value> dataFrame,
                       com.macrofocus.filter.MutableIndexFilter<Row> outputFilter)

SubsetDataFrame

public SubsetDataFrame(DataFrame<Row,Column,Value> dataFrame,
                       com.macrofocus.filter.MutableIndexFilter<Row> outputFilter,
                       com.macrofocus.selection.MutableSelection<Row> selection)

SubsetDataFrame

public SubsetDataFrame(DataFrame<Row,Column,Value> dataFrame)

Method Detail

getUnfilteredDataFrame

public DataFrame<Row,Column,Value> getUnfilteredDataFrame()

getOutputFilter

public com.macrofocus.filter.Filter<Row> getOutputFilter()

getBinningDimension

public <Bin> SingleBinningDimension<Row,Bin> getBinningDimension(Column column,
                                                                       SingleBinningDimension.SingleBinningStrategy<Row,Bin> binningStrategy)

getCategoricalDimension

public CategoricalDimension<Row,Column,Value> getCategoricalDimension(Column column)

getDistributionDimension

public <Bin> DistributionDimension<Row,Value,Bin> getDistributionDimension(Column column,
                                                                                       DistributionDimension.DistributionStrategy<Value,Bin> distributionStrategy)

getOrdinalDimension

public OrdinalDimension<Row,Column,Value> getOrdinalDimension(Column column)

getItemsDimension

public ItemsDimension<Row,Column,Value> getItemsDimension()

createTextDimension

public DefaultTextDimension<Row,Column,Value> createTextDimension(Column... columns)

addDimension

public void addDimension(Dimension<Row> dimension)

removeDimension

public void removeDimension(Dimension<Row> dimension)

updateFilters

public void updateFilters()

Filter using TIntList

updateFiltersUsingArrays

public void updateFiltersUsingArrays()

Filter using raw arrays

updateActiveIndices

public int[] updateActiveIndices()

updateFiltersUsingTHashSet

@Deprecated
public void updateFiltersUsingTHashSet()

Deprecated.

defineIndex

public void defineIndex(Column... columns)

materializeIndex

public void materializeIndex(Column... columns)

originalDataFrameChanged

protected void originalDataFrameChanged()

Overrides:

originalDataFrameChanged in class ReMappedDataFrame<Row,Column,Value>

setTimer

public void setTimer(com.macrofocus.timer.CPTimer timer)

invalidateFilters

protected void invalidateFilters()

scheduleUpdateFilters

protected void scheduleUpdateFilters()

computeFiltered

public int[] computeFiltered(int[] oldIndices,
                             int[] newIndices)

computeUnfiltered

public int[] computeUnfiltered(int[] oldIndices,
                               int[] newIndices)

reset

public void reset()

setExecutor

public void setExecutor(com.macrofocus.timer.CPExecutor executor)

reduceDimension

public void reduceDimension(Dimension<Row> dimension)