Package ai.libs.jaicore.ml.core.dataset.serialization

Class ArffDatasetAdapter

java.lang.Object

ai.libs.jaicore.ml.core.dataset.serialization.ArffDatasetAdapter

All Implemented Interfaces:

org.api4.java.ai.ml.core.dataset.serialization.IDatasetDeserializer<org.api4.java.ai.ml.core.dataset.supervised.ILabeledDataset<org.api4.java.ai.ml.core.dataset.supervised.ILabeledInstance>>, org.api4.java.common.control.ILoggingCustomizable

public class ArffDatasetAdapter
extends java.lang.Object
implements org.api4.java.ai.ml.core.dataset.serialization.IDatasetDeserializer<org.api4.java.ai.ml.core.dataset.supervised.ILabeledDataset<org.api4.java.ai.ml.core.dataset.supervised.ILabeledInstance>>, org.api4.java.common.control.ILoggingCustomizable

Handles dataset files in the arff format {@link https://waikato.github.io/weka-wiki/formats_and_processing/arff/}

Field Summary

Fields

Modifier and Type	Field	Description
static java.lang.String	K_CLASS_INDEX
static java.lang.String	K_RELATION_NAME
static java.util.regex.Pattern	REG_EXP_DATA_LINE
static java.lang.String	V_MISSING_VALUE

Constructor Summary

Constructors

Constructor	Description
ArffDatasetAdapter()
ArffDatasetAdapter(boolean sparseMode)
ArffDatasetAdapter(boolean sparseMode, org.api4.java.ai.ml.core.dataset.descriptor.IDatasetDescriptor datasetDescriptor)

Method Summary

Modifier and Type	Method	Description
protected org.api4.java.ai.ml.core.dataset.supervised.ILabeledDataset<org.api4.java.ai.ml.core.dataset.supervised.ILabeledInstance>	createDataset(ai.libs.jaicore.basic.kvstore.KVStore relationMetaData, java.util.List<org.api4.java.ai.ml.core.dataset.schema.attribute.IAttribute> attributes)
org.api4.java.ai.ml.core.dataset.supervised.ILabeledDataset<org.api4.java.ai.ml.core.dataset.supervised.ILabeledInstance>	deserializeDataset()
org.api4.java.ai.ml.core.dataset.supervised.ILabeledDataset<org.api4.java.ai.ml.core.dataset.supervised.ILabeledInstance>	deserializeDataset(org.api4.java.ai.ml.core.dataset.descriptor.IDatasetDescriptor datasetDescriptor)
org.api4.java.ai.ml.core.dataset.supervised.ILabeledDataset<org.api4.java.ai.ml.core.dataset.supervised.ILabeledInstance>	deserializeDataset(org.api4.java.ai.ml.core.dataset.descriptor.IFileDatasetDescriptor datasetDescriptor, int columnWithClassIndex)
org.api4.java.ai.ml.core.dataset.supervised.ILabeledDataset<org.api4.java.ai.ml.core.dataset.supervised.ILabeledInstance>	deserializeDataset(org.api4.java.ai.ml.core.dataset.descriptor.IFileDatasetDescriptor datasetFile, java.lang.String nameOfClassAttribute)
org.api4.java.ai.ml.core.dataset.schema.attribute.IAttribute	getAttributeWithName(org.api4.java.ai.ml.core.dataset.descriptor.IFileDatasetDescriptor datasetFile, java.lang.String nameOfAttribute)
java.lang.String	getLoggerName()
protected org.api4.java.ai.ml.core.dataset.schema.attribute.IAttribute	parseAttribute(java.lang.String line)	parses an attribute definition of an ARff file.
protected java.util.List<java.lang.Object>	parseInstance(boolean sparseData, java.util.List<org.api4.java.ai.ml.core.dataset.schema.attribute.IAttribute> attributes, int targetIndex, java.lang.String line)	Parses a single instance of an ARff file containing values for each attribute given (attributes parameter).
protected ai.libs.jaicore.basic.kvstore.KVStore	parseRelation(java.lang.String line)	Extracts meta data about a relation from a string.
org.api4.java.ai.ml.core.dataset.supervised.ILabeledDataset<org.api4.java.ai.ml.core.dataset.supervised.ILabeledInstance>	readDataset(boolean sparseMode, java.io.File datasetFile)
org.api4.java.ai.ml.core.dataset.supervised.ILabeledDataset<org.api4.java.ai.ml.core.dataset.supervised.ILabeledInstance>	readDataset(boolean sparseMode, java.io.File datasetFile, int columnWithClassIndex)	Parses the ARff dataset from the given file into a ILabeledDataset
org.api4.java.ai.ml.core.dataset.supervised.ILabeledDataset<org.api4.java.ai.ml.core.dataset.supervised.ILabeledInstance>	readDataset(java.io.File datasetFile)
void	serializeDataset(java.io.File arffOutputFile, org.api4.java.ai.ml.core.dataset.supervised.ILabeledDataset<? extends org.api4.java.ai.ml.core.dataset.supervised.ILabeledInstance> data)
void	setLoggerName(java.lang.String name)
java.lang.String[]	splitDenseInstanceLine(java.lang.String line)

Methods inherited from class java.lang.Object

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

Field Detail

V_MISSING_VALUE

public static final java.lang.String V_MISSING_VALUE

See Also:

Constant Field Values

K_RELATION_NAME

public static final java.lang.String K_RELATION_NAME

See Also:

Constant Field Values

K_CLASS_INDEX

public static final java.lang.String K_CLASS_INDEX

See Also:

Constant Field Values

REG_EXP_DATA_LINE

public static final java.util.regex.Pattern REG_EXP_DATA_LINE

Constructor Detail

ArffDatasetAdapter

public ArffDatasetAdapter(boolean sparseMode,
                          org.api4.java.ai.ml.core.dataset.descriptor.IDatasetDescriptor datasetDescriptor)

ArffDatasetAdapter

public ArffDatasetAdapter(boolean sparseMode)

ArffDatasetAdapter

public ArffDatasetAdapter()

Method Detail

getAttributeWithName

public org.api4.java.ai.ml.core.dataset.schema.attribute.IAttribute getAttributeWithName(org.api4.java.ai.ml.core.dataset.descriptor.IFileDatasetDescriptor datasetFile,
                                                                                         java.lang.String nameOfAttribute)
                                                                                  throws org.api4.java.ai.ml.core.dataset.serialization.DatasetDeserializationFailedException

Throws:

org.api4.java.ai.ml.core.dataset.serialization.DatasetDeserializationFailedException

deserializeDataset

public org.api4.java.ai.ml.core.dataset.supervised.ILabeledDataset<org.api4.java.ai.ml.core.dataset.supervised.ILabeledInstance> deserializeDataset(org.api4.java.ai.ml.core.dataset.descriptor.IFileDatasetDescriptor datasetFile,
                                                                                                                                                    java.lang.String nameOfClassAttribute)
                                                                                                                                             throws org.api4.java.ai.ml.core.dataset.serialization.DatasetDeserializationFailedException

Throws:

org.api4.java.ai.ml.core.dataset.serialization.DatasetDeserializationFailedException

deserializeDataset

public org.api4.java.ai.ml.core.dataset.supervised.ILabeledDataset<org.api4.java.ai.ml.core.dataset.supervised.ILabeledInstance> deserializeDataset(org.api4.java.ai.ml.core.dataset.descriptor.IFileDatasetDescriptor datasetDescriptor,
                                                                                                                                                    int columnWithClassIndex)
                                                                                                                                             throws org.api4.java.ai.ml.core.dataset.serialization.DatasetDeserializationFailedException

Throws:

org.api4.java.ai.ml.core.dataset.serialization.DatasetDeserializationFailedException

deserializeDataset

public org.api4.java.ai.ml.core.dataset.supervised.ILabeledDataset<org.api4.java.ai.ml.core.dataset.supervised.ILabeledInstance> deserializeDataset(org.api4.java.ai.ml.core.dataset.descriptor.IDatasetDescriptor datasetDescriptor)
                                                                                                                                             throws org.api4.java.ai.ml.core.dataset.serialization.DatasetDeserializationFailedException,
                                                                                                                                                    java.lang.InterruptedException

Specified by:

deserializeDataset in interface org.api4.java.ai.ml.core.dataset.serialization.IDatasetDeserializer<org.api4.java.ai.ml.core.dataset.supervised.ILabeledDataset<org.api4.java.ai.ml.core.dataset.supervised.ILabeledInstance>>

Throws:

org.api4.java.ai.ml.core.dataset.serialization.DatasetDeserializationFailedException

java.lang.InterruptedException

deserializeDataset

public org.api4.java.ai.ml.core.dataset.supervised.ILabeledDataset<org.api4.java.ai.ml.core.dataset.supervised.ILabeledInstance> deserializeDataset()
                                                                                                                                             throws java.lang.InterruptedException,
                                                                                                                                                    org.api4.java.ai.ml.core.dataset.serialization.DatasetDeserializationFailedException

Throws:

java.lang.InterruptedException

org.api4.java.ai.ml.core.dataset.serialization.DatasetDeserializationFailedException

parseRelation

protected ai.libs.jaicore.basic.kvstore.KVStore parseRelation(java.lang.String line)

Extracts meta data about a relation from a string.

Parameters:

line - The line which is to be parsed to extract the necessary information from the relation name.

Returns:

A KVStore containing the parsed meta data.

parseAttribute

protected org.api4.java.ai.ml.core.dataset.schema.attribute.IAttribute parseAttribute(java.lang.String line)
                                                                               throws org.api4.java.ai.ml.core.dataset.serialization.UnsupportedAttributeTypeException

parses an attribute definition of an ARff file. General format: @Attribute <attribute_name > <attribute_type>

Parameters:

line - to be analyzed

Returns:

Object of class IAttribute

Throws:

org.api4.java.ai.ml.core.dataset.serialization.UnsupportedAttributeTypeException - when the parsed Attribute not implemented

splitDenseInstanceLine

public java.lang.String[] splitDenseInstanceLine(java.lang.String line)

parseInstance

protected java.util.List<java.lang.Object> parseInstance(boolean sparseData,
                                                         java.util.List<org.api4.java.ai.ml.core.dataset.schema.attribute.IAttribute> attributes,
                                                         int targetIndex,
                                                         java.lang.String line)

Parses a single instance of an ARff file containing values for each attribute given (attributes parameter). Syntax , , ...

Parameters:

sparseData - if true there are ? in the data - if it false there are not

attributes - List of given IAttribute Objects.

targetIndex -

line - line of data

Returns:

list of IAttribute values

createDataset

protected org.api4.java.ai.ml.core.dataset.supervised.ILabeledDataset<org.api4.java.ai.ml.core.dataset.supervised.ILabeledInstance> createDataset(ai.libs.jaicore.basic.kvstore.KVStore relationMetaData,
                                                                                                                                                  java.util.List<org.api4.java.ai.ml.core.dataset.schema.attribute.IAttribute> attributes)

readDataset

public org.api4.java.ai.ml.core.dataset.supervised.ILabeledDataset<org.api4.java.ai.ml.core.dataset.supervised.ILabeledInstance> readDataset(java.io.File datasetFile)
                                                                                                                                      throws org.api4.java.ai.ml.core.dataset.serialization.DatasetDeserializationFailedException

Throws:

org.api4.java.ai.ml.core.dataset.serialization.DatasetDeserializationFailedException

readDataset

public org.api4.java.ai.ml.core.dataset.supervised.ILabeledDataset<org.api4.java.ai.ml.core.dataset.supervised.ILabeledInstance> readDataset(boolean sparseMode,
                                                                                                                                             java.io.File datasetFile)
                                                                                                                                      throws org.api4.java.ai.ml.core.dataset.serialization.DatasetDeserializationFailedException

Throws:

org.api4.java.ai.ml.core.dataset.serialization.DatasetDeserializationFailedException

readDataset

public org.api4.java.ai.ml.core.dataset.supervised.ILabeledDataset<org.api4.java.ai.ml.core.dataset.supervised.ILabeledInstance> readDataset(boolean sparseMode,
                                                                                                                                             java.io.File datasetFile,
                                                                                                                                             int columnWithClassIndex)
                                                                                                                                      throws org.api4.java.ai.ml.core.dataset.serialization.DatasetDeserializationFailedException

Parses the ARff dataset from the given file into a ILabeledDataset

Parameters:

sparseMode -

datasetFile - file to be parsed

columnWithClassIndex -

Throws:

org.api4.java.ai.ml.core.dataset.serialization.DatasetDeserializationFailedException

serializeDataset

public void serializeDataset(java.io.File arffOutputFile,
                             org.api4.java.ai.ml.core.dataset.supervised.ILabeledDataset<? extends org.api4.java.ai.ml.core.dataset.supervised.ILabeledInstance> data)
                      throws java.io.IOException

Throws:

java.io.IOException

getLoggerName

public java.lang.String getLoggerName()

Specified by:

getLoggerName in interface org.api4.java.common.control.ILoggingCustomizable

setLoggerName

public void setLoggerName(java.lang.String name)

Specified by:

setLoggerName in interface org.api4.java.common.control.ILoggingCustomizable