jsat.regression

Class RegressionDataSet

java.lang.Object

jsat.DataSet<RegressionDataSet>

jsat.regression.RegressionDataSet

public class RegressionDataSet
extends DataSet<RegressionDataSet>

A RegressionDataSet is a data set specifically for the task of performing regression. Each data point is paired with s double value that indicates its true regression value. An example of a regression problem would be mapping the inputs of a function to its outputs, and attempting to learn the function from the samples.

Author:

Edward Raff

Field Summary

Fields

Modifier and Type	Field and Description
protected List<DataPointPair<Double>>	dataPoints The list of all data points, paired with their true regression output

Fields inherited from class jsat.DataSet

categories, columnVecCache, numericalVariableNames, numNumerVals

Constructor Summary

Constructors

Constructor and Description
RegressionDataSet(int numerical, CategoricalData[] categories) Creates a new empty data set for regression
RegressionDataSet(List<DataPoint> data, int predicting) Creates a new data set for the given list of data points.
RegressionDataSet(List<DataPointPair<Double>> list) Creates a new regression data set by copying all the data points in the given list.

Method Summary

Modifier and Type	Method and Description
void	addDataPoint(DataPoint dp, double val)
void	addDataPoint(Vec numerical, double val) Creates a new data point with no categorical variables to be added to the data set.
void	addDataPoint(Vec numerical, int[] categories, double val) Creates a new data point to be added to the data set.
void	addDataPointPair(DataPointPair<Double> pair)
static RegressionDataSet	comineAllBut(List<RegressionDataSet> list, int exception)
List<DataPointPair<Double>>	getAsDPPList() Returns a new list containing copies of the data points in this data set, paired with their regression target values.
DataPoint	getDataPoint(int i) Returns the i'th data point in this set.
DataPointPair<Double>	getDataPointPair(int i) Returns the i'th data point in the data set paired with its target regressor value.
List<DataPointPair<Double>>	getDPPList() Returns a new list containing the data points in this data set, paired with their regression target values.
int	getSampleSize() Returns the number of data points in this data set
protected RegressionDataSet	getSubset(List<Integer> indicies) Creates a new dataset that is a subset of this dataset.
double	getTargetValue(int i) Returns the target regression value for the i'th data point in the data set.
Vec	getTargetValues() Returns a vector containing the target regression values for each data point.
RegressionDataSet	getTwiceShallowClone() Returns a new version of this data set that is of the same type, and contains a different listing pointing to shallow data point copies.
void	setDataPoint(int i, DataPoint dp) Replaces an already existing data point with the one given.
void	setTargetValue(int i, double val) Sets the target regression value associated with a given data point
RegressionDataSet	shallowClone() Returns a new version of this data set that is of the same type, and contains a different list pointing to the same data points.
static RegressionDataSet	usingDPPList(List<DataPointPair<Double>> list) Creates a new data set that uses the given list as its backing list.

Methods inherited from class jsat.DataSet

applyTransform, applyTransform, applyTransform, applyTransform, countMissingValues, cvSet, cvSet, getCategories, getCategoryName, getColumnMeanVariance, getDataMatrix, getDataMatrixView, getDataPointIterator, getDataPoints, getDataVectors, getDataWeights, getMissingDropped, getNumCategoricalVars, getNumericColumn, getNumericColumns, getNumericColumns, getNumericName, getNumFeatures, getNumNumericalVars, getOnlineColumnStats, getOnlineDenseStats, getSparsityStats, randomSplit, randomSplit, replaceNumericFeatures, setNumericName

Methods inherited from class java.lang.Object

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

Field Detail

dataPoints

protected List<DataPointPair<Double>> dataPoints

The list of all data points, paired with their true regression output

Constructor Detail

RegressionDataSet

public RegressionDataSet(int numerical,
                         CategoricalData[] categories)

Creates a new empty data set for regression

Parameters:

numerical - the number of numerical attributes that will be used, excluding the regression value

categories - an array of length equal to the number of categorical attributes, each object describing the attribute in question

RegressionDataSet

public RegressionDataSet(List<DataPoint> data,
                         int predicting)

Creates a new data set for the given list of data points. The data points will be copied, changes in one will not effect the other.

Parameters:

data - the list of data point to create a data set from

predicting - which of the numerical attributes is the regression target. Categorical attributes are ignored in the count of attributes for this value.

RegressionDataSet

public RegressionDataSet(List<DataPointPair<Double>> list)

Creates a new regression data set by copying all the data points in the given list. Alterations to this list will not effect this DataSet.

Parameters:

list - source of data points to copy

Method Detail

comineAllBut

public static RegressionDataSet comineAllBut(List<RegressionDataSet> list,
                                             int exception)

addDataPoint

public void addDataPoint(Vec numerical,
                         double val)

Creates a new data point with no categorical variables to be added to the data set. The arguments will be used directly, modifying them after will effect the data set.

Parameters:

numerical - the numerical values for the data point

Throws:

IllegalArgumentException - if the given values are inconsistent with the data this class stores.

addDataPoint

public void addDataPoint(Vec numerical,
                         int[] categories,
                         double val)

Creates a new data point to be added to the data set. The arguments will be used directly, modifying them after will effect the data set.

Parameters:

numerical - the numerical values for the data point

categories - the categorical values for the data point

val - the target value to predict

Throws:

IllegalArgumentException - if the given values are inconsistent with the data this class stores.

addDataPoint

public void addDataPoint(DataPoint dp,
                         double val)

addDataPointPair

public void addDataPointPair(DataPointPair<Double> pair)

getDataPoint

public DataPoint getDataPoint(int i)

Description copied from class: DataSet

Returns the i'th data point in this set. The order will never chance so long as no data points are added or removed from the set.

Specified by:

getDataPoint in class DataSet<RegressionDataSet>

Parameters:

i - the i'th data point in this set

Returns:

the i'th data point in this set

getDataPointPair

public DataPointPair<Double> getDataPointPair(int i)

Returns the i'th data point in the data set paired with its target regressor value. Modifying the DataPointPair will effect the data set.

Parameters:

i - the index of the data point to obtain

Returns:

the i'th DataPOintPair

getAsDPPList

public List<DataPointPair<Double>> getAsDPPList()

Returns a new list containing copies of the data points in this data set, paired with their regression target values. MModifications to the list or data points will not effect this data set

Returns:

a list of copies of the data points in this set

getDPPList

public List<DataPointPair<Double>> getDPPList()

Returns a new list containing the data points in this data set, paired with their regression target values. Modifications to the list will not effect the data set, but modifying the points will. For a copy of the points, use the getAsDPPList() method.

Returns:

a list of the data points in this set

setDataPoint

public void setDataPoint(int i,
                         DataPoint dp)

Description copied from class: DataSet

Replaces an already existing data point with the one given. Any values associated with the data point, but not apart of it, will remain intact.

Specified by:

setDataPoint in class DataSet<RegressionDataSet>

Parameters:

i - the i'th dataPoint to set.

dp - the data point to set at the specified index

setTargetValue

public void setTargetValue(int i,
                           double val)

Sets the target regression value associated with a given data point

Parameters:

i - the index in the data set

val - the new target value

Throws:

ArithmeticException - if val is infinite or NaN

getSubset

protected RegressionDataSet getSubset(List<Integer> indicies)

Description copied from class: DataSet

Creates a new dataset that is a subset of this dataset.

Specified by:

getSubset in class DataSet<RegressionDataSet>

Parameters:

indicies - the indices of data points to insert into the new dataset, and will be placed in the order listed.

Returns:

a new dataset that is a specified subset of this dataset, and backed by the same values

getSampleSize

public int getSampleSize()

Description copied from class: DataSet

Returns the number of data points in this data set

Specified by:

getSampleSize in class DataSet<RegressionDataSet>

Returns:

the number of data points in this data set

getTargetValues

public Vec getTargetValues()

Returns a vector containing the target regression values for each data point. The vector is a copy, and modifications to it will not effect the data set.

Returns:

a vector containing the target values for each data point

getTargetValue

public double getTargetValue(int i)

Returns the target regression value for the i'th data point in the data set.

Parameters:

i - the data point to get the regression value of

Returns:

the target regression value

usingDPPList

public static RegressionDataSet usingDPPList(List<DataPointPair<Double>> list)

Creates a new data set that uses the given list as its backing list. No copying is done, and changes to this list will be reflected in this data set, and the other way.

Parameters:

list - the list of datapoint to back a new data set with

Returns:

a new data set

shallowClone

public RegressionDataSet shallowClone()

Description copied from class: DataSet

Returns a new version of this data set that is of the same type, and contains a different list pointing to the same data points.

Specified by:

shallowClone in class DataSet<RegressionDataSet>

Returns:

a shallow copy of this data set

getTwiceShallowClone

public RegressionDataSet getTwiceShallowClone()

Description copied from class: DataSet

Returns a new version of this data set that is of the same type, and contains a different listing pointing to shallow data point copies. Because the data point object contains the weight itself, the weight is not shared - while the vector and array information is. This allows altering the weights of the data points while preserving the original weights.
Altering the list or weights of the returned data set will not be reflected in the original. Altering the feature values will.

Overrides:

getTwiceShallowClone in class DataSet<RegressionDataSet>

Returns:

a shallow copy of shallow data point copies for this data set.