ai.djl.basicdataset

Class AirfoilRandomAccess

java.lang.Object

ai.djl.training.dataset.RandomAccessDataset

ai.djl.basicdataset.AirfoilRandomAccess

All Implemented Interfaces:

ai.djl.training.dataset.Dataset

public final class AirfoilRandomAccess
extends ai.djl.training.dataset.RandomAccessDataset

Airfoil Self-Noise Data Set from https://archive.ics.uci.edu/ml/datasets/Airfoil+Self-Noise.

1503 instances 6 attributes

Nested Class Summary

Nested Classes

Modifier and Type	Class and Description
static class	AirfoilRandomAccess.Builder A builder to construct a AirfoilRandomAccess.

Nested classes/interfaces inherited from class ai.djl.training.dataset.RandomAccessDataset

ai.djl.training.dataset.RandomAccessDataset.BaseBuilder<T extends ai.djl.training.dataset.RandomAccessDataset.BaseBuilder>

Nested classes/interfaces inherited from interface ai.djl.training.dataset.Dataset

ai.djl.training.dataset.Dataset.Usage

Field Summary

Fields inherited from class ai.djl.training.dataset.RandomAccessDataset

dataBatchifier, device, executor, labelBatchifier, limit, pipeline, prefetchNumber, sampler, targetPipeline

Method Summary

Modifier and Type	Method and Description
void	addAllFeatures() Move all available features to set.
void	addFeature(java.lang.String feature) Adds a feature if it exists.
protected long	availableSize()
static AirfoilRandomAccess.Builder	builder() Creates a builder to build a AirfoilRandomAccess.
protected ai.djl.training.dataset.Record	get(ai.djl.ndarray.NDManager manager, long index)
org.apache.commons.csv.CSVRecord	getCSVRecord(int index) Returns the CSVRecord for a given index.
int	getFeatureArraySize() Returns the size of the feature array(column count).
ai.djl.ndarray.NDArray	getFeatureNDArray(ai.djl.ndarray.NDManager manager, int index) Return the NDArray at index 'index' with the set features.
java.util.List<java.lang.String>	getFeatureOrder() Gets the feature order of the columns.
float[]	getLabel(int index) Returns the label value for a given index.
float	getRecordFloat(org.apache.commons.csv.CSVRecord record, java.lang.String feature) Returns float for a given record and feature.
float[]	getValueFloat(org.apache.commons.csv.CSVRecord record, java.lang.String feature) Returns the float value of the record's feature in a float[].
void	prepare(ai.djl.util.Progress progress)
void	removeAllFeatures() Move all currently set features to available.
void	removeFeature(java.lang.String feature) Removes a feature from the active set if it exists.
void	selectFirstN(int n) Chooses the 1st N records to be used (not reversible).
void	whitenAll() Remove mean and rescale variance to 1 for all features.

Methods inherited from class ai.djl.training.dataset.RandomAccessDataset

getData, getData, randomSplit, size

Methods inherited from class java.lang.Object

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

Methods inherited from interface ai.djl.training.dataset.Dataset

prepare

Method Detail

whitenAll

public void whitenAll()
               throws java.io.IOException,
                      ai.djl.translate.TranslateException

Remove mean and rescale variance to 1 for all features.

Throws:

java.io.IOException - for various exceptions depending on the dataset

ai.djl.translate.TranslateException - if there is an error while processing input

getFeatureOrder

public java.util.List<java.lang.String> getFeatureOrder()

Gets the feature order of the columns.

Returns:

a list of the features in order shown in the FeatureNDArray

getRecordFloat

public float getRecordFloat(org.apache.commons.csv.CSVRecord record,
                            java.lang.String feature)

Returns float for a given record and feature.

Parameters:

record - record which holds the raw data

feature - feature to be selected

Returns:

float

selectFirstN

public void selectFirstN(int n)
                  throws java.io.IOException,
                         ai.djl.translate.TranslateException

Chooses the 1st N records to be used (not reversible).

TODO: make standalone without need for whiten() after to set data[] (speed penalty)

Parameters:

n - number of records to be used starting from the beginning

Throws:

java.io.IOException - for various exceptions depending on the dataset

ai.djl.translate.TranslateException - if there is an error while processing input

builder

public static AirfoilRandomAccess.Builder builder()

Creates a builder to build a AirfoilRandomAccess.

Returns:

a new builder

getLabel

public float[] getLabel(int index)

Returns the label value for a given index.

Parameters:

index - index of label

Returns:

float value wrapped in a float array

get

protected ai.djl.training.dataset.Record get(ai.djl.ndarray.NDManager manager,
                                             long index)

Specified by:

get in class ai.djl.training.dataset.RandomAccessDataset

getCSVRecord

public org.apache.commons.csv.CSVRecord getCSVRecord(int index)

Returns the CSVRecord for a given index.

Parameters:

index - index of desired record

Returns:

the requested CSVRecord

getValueFloat

public float[] getValueFloat(org.apache.commons.csv.CSVRecord record,
                             java.lang.String feature)

Returns the float value of the record's feature in a float[].

Parameters:

record - The CSVRecord to get the feature from

feature - The feature value to be acquired

Returns:

the float value of the feature wrapped in a float array

getFeatureArraySize

public int getFeatureArraySize()

Returns the size of the feature array(column count).

Returns:

size of enabled features

getFeatureNDArray

public ai.djl.ndarray.NDArray getFeatureNDArray(ai.djl.ndarray.NDManager manager,
                                                int index)

Return the NDArray at index 'index' with the set features.

Parameters:

manager - NDManager to maintain created NDArray

index - Index of wanted NDArray

Returns:

NDArray of features

removeAllFeatures

public void removeAllFeatures()

Move all currently set features to available.

addAllFeatures

public void addAllFeatures()

Move all available features to set.

addFeature

public void addFeature(java.lang.String feature)

Adds a feature if it exists.

Parameters:

feature - requested feature

removeFeature

public void removeFeature(java.lang.String feature)

Removes a feature from the active set if it exists.

Parameters:

feature - to be removed feature

prepare

public void prepare(ai.djl.util.Progress progress)
             throws java.io.IOException

Throws:

java.io.IOException

availableSize

protected long availableSize()

Specified by:

availableSize in class ai.djl.training.dataset.RandomAccessDataset