org.deeplearning4j.util

Class TimeSeriesUtils

java.lang.Object

org.deeplearning4j.util.TimeSeriesUtils

public class TimeSeriesUtils
extends Object

Basic time series utils

Author:

Adam Gibson

Method Summary

Modifier and Type	Method and Description
static org.nd4j.linalg.api.ndarray.INDArray	movingAverage(org.nd4j.linalg.api.ndarray.INDArray toAvg, int n) Calculate a moving average given the length
static org.nd4j.linalg.primitives.Pair<org.nd4j.linalg.api.ndarray.INDArray,int[]>	pullLastTimeSteps(org.nd4j.linalg.api.ndarray.INDArray pullFrom, org.nd4j.linalg.api.ndarray.INDArray mask) Extract out the last time steps (2d array from 3d array input) accounting for the mask layer, if present.
static org.nd4j.linalg.api.ndarray.INDArray	reshape2dTo3d(org.nd4j.linalg.api.ndarray.INDArray in, int miniBatchSize)
static org.nd4j.linalg.api.ndarray.INDArray	reshape3dTo2d(org.nd4j.linalg.api.ndarray.INDArray in)
static org.nd4j.linalg.api.ndarray.INDArray	reshapePerOutputTimeSeriesMaskTo2d(org.nd4j.linalg.api.ndarray.INDArray perOutputTimeSeriesMask)
static org.nd4j.linalg.api.ndarray.INDArray	reshapeTimeSeriesMaskToVector(org.nd4j.linalg.api.ndarray.INDArray timeSeriesMask) Reshape time series mask arrays.
static org.nd4j.linalg.api.ndarray.INDArray	reshapeVectorToTimeSeriesMask(org.nd4j.linalg.api.ndarray.INDArray timeSeriesMaskAsVector, int minibatchSize) Reshape time series mask arrays.
static org.nd4j.linalg.api.ndarray.INDArray	reverseTimeSeries(org.nd4j.linalg.api.ndarray.INDArray in) Reverse an input time series along the time dimension
static org.nd4j.linalg.api.ndarray.INDArray	reverseTimeSeriesMask(org.nd4j.linalg.api.ndarray.INDArray mask) Reverse a (per time step) time series mask, with shape [minibatch, timeSeriesLength]

Methods inherited from class java.lang.Object

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

Method Detail

movingAverage

public static org.nd4j.linalg.api.ndarray.INDArray movingAverage(org.nd4j.linalg.api.ndarray.INDArray toAvg,
                                                                 int n)

Calculate a moving average given the length

Parameters:

toAvg - the array to average

n - the length of the moving window

Returns:

the moving averages for each row

reshapeTimeSeriesMaskToVector

public static org.nd4j.linalg.api.ndarray.INDArray reshapeTimeSeriesMaskToVector(org.nd4j.linalg.api.ndarray.INDArray timeSeriesMask)

Reshape time series mask arrays. This should match the assumptions (f order, etc) in RnnOutputLayer

Parameters:

timeSeriesMask - Mask array to reshape to a column vector

Returns:

Mask array as a column vector

reshapeVectorToTimeSeriesMask

public static org.nd4j.linalg.api.ndarray.INDArray reshapeVectorToTimeSeriesMask(org.nd4j.linalg.api.ndarray.INDArray timeSeriesMaskAsVector,
                                                                                 int minibatchSize)

Reshape time series mask arrays. This should match the assumptions (f order, etc) in RnnOutputLayer

Parameters:

timeSeriesMaskAsVector - Mask array to reshape to a column vector

Returns:

Mask array as a column vector

reshapePerOutputTimeSeriesMaskTo2d

public static org.nd4j.linalg.api.ndarray.INDArray reshapePerOutputTimeSeriesMaskTo2d(org.nd4j.linalg.api.ndarray.INDArray perOutputTimeSeriesMask)

reshape3dTo2d

public static org.nd4j.linalg.api.ndarray.INDArray reshape3dTo2d(org.nd4j.linalg.api.ndarray.INDArray in)

reshape2dTo3d

public static org.nd4j.linalg.api.ndarray.INDArray reshape2dTo3d(org.nd4j.linalg.api.ndarray.INDArray in,
                                                                 int miniBatchSize)

reverseTimeSeries

public static org.nd4j.linalg.api.ndarray.INDArray reverseTimeSeries(org.nd4j.linalg.api.ndarray.INDArray in)

Reverse an input time series along the time dimension

Parameters:

in - Input activations to reverse, with shape [minibatch, size, timeSeriesLength]

Returns:

Reversed activations

reverseTimeSeriesMask

public static org.nd4j.linalg.api.ndarray.INDArray reverseTimeSeriesMask(org.nd4j.linalg.api.ndarray.INDArray mask)

Reverse a (per time step) time series mask, with shape [minibatch, timeSeriesLength]

Parameters:

mask - Mask to reverse along time dimension

Returns:

Mask after reversing

pullLastTimeSteps

public static org.nd4j.linalg.primitives.Pair<org.nd4j.linalg.api.ndarray.INDArray,int[]> pullLastTimeSteps(org.nd4j.linalg.api.ndarray.INDArray pullFrom,
                                                                                                            org.nd4j.linalg.api.ndarray.INDArray mask)

Extract out the last time steps (2d array from 3d array input) accounting for the mask layer, if present.

Parameters:

pullFrom - Input time series array (rank 3) to pull the last time steps from

mask - Mask array (rank 2). May be null

Returns:

2d array of the last time steps