hex

Class DataInfo

java.lang.Object

water.Iced<T>

water.Keyed

hex.DataInfo

All Implemented Interfaces:

java.io.Externalizable, java.io.Serializable, java.lang.Cloneable, water.Freezable

public class DataInfo
extends water.Keyed

Created by tomasnykodym on 1/29/15.

See Also:

Serialized Form

Nested Class Summary

Nested Classes

Modifier and Type	Class and Description
class	DataInfo.Row
static class	DataInfo.TransformType

Field Summary

Fields

Modifier and Type	Field and Description
int[]	_activeCols
water.fvec.Frame	_adaptedFrame
int	_bins
int[]	_catMissing
int[]	_catOffsets
int	_cats
double	_etaOffset
int	_foldId
boolean	_intercept
int	_nfolds
double[]	_normMul
double[]	_normRespMul
double[]	_normRespSub
double[]	_normSub
int	_nums
boolean	_offset
DataInfo.TransformType	_predictor_transform
DataInfo.TransformType	_response_transform
int	_responses
boolean	_skipMissing
boolean	_useAllFactorLevels

Fields inherited from class water.Keyed

_key

Constructor Summary

Constructors

Constructor and Description
DataInfo(water.Key selfKey, water.fvec.Frame train, water.fvec.Frame valid, int nResponses, boolean useAllFactorLevels, DataInfo.TransformType predictor_transform, DataInfo.TransformType response_transform, boolean skipMissing, boolean missingBucket)
DataInfo(water.Key selfKey, water.fvec.Frame fr, int[][] catLevels, int responses, DataInfo.TransformType predictor_transform, DataInfo.TransformType response_transform, boolean skipMissing, int foldId, int nfolds)

Method Summary

Methods

Modifier and Type	Method and Description
protected long	checksum_impl()
java.lang.String[]	coefNames()
DataInfo	deep_clone()
DataInfo.Row	extractDenseRow(water.fvec.Chunk[] chunks, int rid, DataInfo.Row row)
DataInfo.Row[]	extractSparseRows(water.fvec.Chunk[] chunks, double[] beta) Extract (sparse) rows from given chunks.
DataInfo	filterExpandedColumns(int[] cols)
int	fullN()
int	getCategoricalId(int cid, int val)
DataInfo	getFold(int foldId, int nfolds)
int	largestCat()
DataInfo.Row	newDenseRow()
int	numStart()
DataInfo	setWeights(water.fvec.Vec v)
java.lang.String	toString()
void	unScaleNumericals(float[] in, float[] out) Undo the standardization/normalization of numerical columns
water.fvec.Vec	weightsVec()

Methods inherited from class water.Keyed

checksum, remove_impl, remove, remove, remove, remove

Methods inherited from class water.Iced

clone, frozenType, read_impl, read, readExternal, readJSON_impl, readJSON, toJsonString, write_impl, write, writeExternal, writeHTML_impl, writeHTML, writeJSON_impl, writeJSON

Methods inherited from class java.lang.Object

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

Field Detail

_activeCols

public int[] _activeCols

_adaptedFrame

public water.fvec.Frame _adaptedFrame

_responses

public int _responses

_predictor_transform

public DataInfo.TransformType _predictor_transform

_response_transform

public DataInfo.TransformType _response_transform

_useAllFactorLevels

public boolean _useAllFactorLevels

_nums

public int _nums

_bins

public int _bins

_cats

public int _cats

_catOffsets

public int[] _catOffsets

_catMissing

public int[] _catMissing

_normMul

public double[] _normMul

_normSub

public double[] _normSub

_normRespMul

public double[] _normRespMul

_normRespSub

public double[] _normRespSub

_foldId

public int _foldId

_nfolds

public int _nfolds

_intercept

public boolean _intercept

_offset

public boolean _offset

_skipMissing

public final boolean _skipMissing

_etaOffset

public double _etaOffset

Constructor Detail

DataInfo

public DataInfo(water.Key selfKey,
        water.fvec.Frame fr,
        int[][] catLevels,
        int responses,
        DataInfo.TransformType predictor_transform,
        DataInfo.TransformType response_transform,
        boolean skipMissing,
        int foldId,
        int nfolds)

DataInfo

public DataInfo(water.Key selfKey,
        water.fvec.Frame train,
        water.fvec.Frame valid,
        int nResponses,
        boolean useAllFactorLevels,
        DataInfo.TransformType predictor_transform,
        DataInfo.TransformType response_transform,
        boolean skipMissing,
        boolean missingBucket)

Method Detail

weightsVec

public water.fvec.Vec weightsVec()

setWeights

public DataInfo setWeights(water.fvec.Vec v)

checksum_impl

protected long checksum_impl()

Specified by:

checksum_impl in class water.Keyed

deep_clone

public DataInfo deep_clone()

filterExpandedColumns

public DataInfo filterExpandedColumns(int[] cols)

toString

public java.lang.String toString()

Overrides:

toString in class java.lang.Object

getFold

public DataInfo getFold(int foldId,
               int nfolds)

fullN

public final int fullN()

largestCat

public final int largestCat()

numStart

public final int numStart()

coefNames

public final java.lang.String[] coefNames()

unScaleNumericals

public final void unScaleNumericals(float[] in,
                     float[] out)

Undo the standardization/normalization of numerical columns

Parameters:

in - input values

out - output values (can be the same as input)

getCategoricalId

public final int getCategoricalId(int cid,
                   int val)

extractDenseRow

public final DataInfo.Row extractDenseRow(water.fvec.Chunk[] chunks,
                           int rid,
                           DataInfo.Row row)

newDenseRow

public DataInfo.Row newDenseRow()

extractSparseRows

public final DataInfo.Row[] extractSparseRows(water.fvec.Chunk[] chunks,
                               double[] beta)

Extract (sparse) rows from given chunks. Essentially turns the dataset 90 degrees.

Parameters:

chunks -

Returns: