com.logicalclocks.hsfs

Class FeatureView

java.lang.Object

com.logicalclocks.hsfs.FeatureView

public class FeatureView
extends Object

Nested Class Summary

Nested Classes

Modifier and Type	Class and Description
static class	FeatureView.FeatureViewBuilder

Constructor Summary

Constructors

Constructor and Description
FeatureView()
FeatureView(@NonNull String name, Integer version, @NonNull Query query, String description, @NonNull FeatureStore featureStore, List<String> labels)

Method Summary

Modifier and Type	Method and Description
void	addTag(String name, Object value) Add name/value tag to the feature view.
void	addTrainingDatasetTag(Integer version, String name, Object value) Add name/value tag to the training dataset.
static void	clean(FeatureStore featureStore, String featureViewName, Integer featureViewVersion)
Integer	createTrainingData(String startTime, String endTime, String description, DataFormat dataFormat)
Integer	createTrainingData(String startTime, String endTime, String description, DataFormat dataFormat, Boolean coalesce, StorageConnector storageConnector, String location, Long seed, StatisticsConfig statisticsConfig, Map<String,String> writeOptions, FilterLogic extraFilterLogic, Filter extraFilter)
Integer	createTrainTestSplit(Float testSize, String trainStart, String trainEnd, String testStart, String testEnd, String description, DataFormat dataFormat)
Integer	createTrainTestSplit(Float testSize, String trainStart, String trainEnd, String testStart, String testEnd, String description, DataFormat dataFormat, Boolean coalesce, StorageConnector storageConnector, String location, Long seed, StatisticsConfig statisticsConfig, Map<String,String> writeOptions, FilterLogic extraFilterLogic, Filter extraFilter)
Integer	createTrainValidationTestSplit(Float validationSize, Float testSize, String trainStart, String trainEnd, String validationStart, String validationEnd, String testStart, String testEnd, String description, DataFormat dataFormat)
Integer	createTrainValidationTestSplit(Float validationSize, Float testSize, String trainStart, String trainEnd, String validationStart, String validationEnd, String testStart, String testEnd, String description, DataFormat dataFormat, Boolean coalesce, StorageConnector storageConnector, String location, Long seed, StatisticsConfig statisticsConfig, Map<String,String> writeOptions, FilterLogic extraFilterLogic, Filter extraFilter)
void	delete()
void	deleteAllTrainingDatasets()
void	deleteTag(String name) Delete a tag of the feature view.
void	deleteTrainingDataset(Integer version)
void	deleteTrainingDatasetTag(Integer version, String name) Delete a tag of the training dataset.
org.apache.spark.sql.Dataset<org.apache.spark.sql.Row>	getBatchData(String startTime, String endTime)
org.apache.spark.sql.Dataset<org.apache.spark.sql.Row>	getBatchData(String startTime, String endTime, Map<String,String> readOptions)
String	getBatchQuery()
String	getBatchQuery(String startTime, String endTime)
String	getDescription()
List<TrainingDatasetFeature>	getFeatures()
FeatureStore	getFeatureStore()
List<Object>	getFeatureVector(Map<String,Object> entry)
List<Object>	getFeatureVector(Map<String,Object> entry, boolean external)
List<List<Object>>	getFeatureVectors(Map<String,List<Object>> entry)
List<List<Object>>	getFeatureVectors(Map<String,List<Object>> entry, boolean external)
Integer	getId()
List<String>	getLabels()
String	getName()
HashSet<String>	getPrimaryKeys() Set of primary key names that is used as keys in input dict object for `get_serving_vector` method.
Query	getQuery()
Object	getTag(String name) Get a single tag value of the feature view.
Map<String,Object>	getTags() Get all tags of the feature view.
List<org.apache.spark.sql.Dataset<org.apache.spark.sql.Row>>	getTrainingData(Integer version)
List<org.apache.spark.sql.Dataset<org.apache.spark.sql.Row>>	getTrainingData(Integer version, Map<String,String> readOptions)
Object	getTrainingDatasetTag(Integer version, String name) Get a single tag value of the training dataset.
Map<String,Object>	getTrainingDatasetTags(Integer version) Get all tags of the training dataset.
List<org.apache.spark.sql.Dataset<org.apache.spark.sql.Row>>	getTrainTestSplit(Integer version)
List<org.apache.spark.sql.Dataset<org.apache.spark.sql.Row>>	getTrainTestSplit(Integer version, Map<String,String> readOptions)
List<org.apache.spark.sql.Dataset<org.apache.spark.sql.Row>>	getTrainValidationTestSplit(Integer version)
List<org.apache.spark.sql.Dataset<org.apache.spark.sql.Row>>	getTrainValidationTestSplit(Integer version, Map<String,String> readOptions)
String	getType()
Integer	getVersion()
void	initBatchScoring(Integer trainingDatasetVersion)
void	initServing()
void	initServing(Boolean batch, Boolean external)
void	purgeAllTrainingData()
void	purgeTrainingData(Integer version)
void	recreateTrainingDataset(Integer version, Map<String,String> writeOptions)
void	setDescription(String description)
void	setFeatures(List<TrainingDatasetFeature> features)
void	setFeatureStore(FeatureStore featureStore)
void	setId(Integer id)
void	setLabels(List<String> labels)
void	setName(String name)
void	setQuery(Query query)
void	setType(String type)
void	setVersion(Integer version)
List<org.apache.spark.sql.Dataset<org.apache.spark.sql.Row>>	trainingData(String startTime, String endTime, String description)
List<org.apache.spark.sql.Dataset<org.apache.spark.sql.Row>>	trainingData(String startTime, String endTime, String description, Long seed, StatisticsConfig statisticsConfig, Map<String,String> readOptions, FilterLogic extraFilterLogic, Filter extraFilter)
List<org.apache.spark.sql.Dataset<org.apache.spark.sql.Row>>	trainTestSplit(Float testSize, String trainStart, String trainEnd, String testStart, String testEnd, String description)
List<org.apache.spark.sql.Dataset<org.apache.spark.sql.Row>>	trainTestSplit(Float testSize, String trainStart, String trainEnd, String testStart, String testEnd, String description, Long seed, StatisticsConfig statisticsConfig, Map<String,String> readOptions, FilterLogic extraFilterLogic, Filter extraFilter)
List<org.apache.spark.sql.Dataset<org.apache.spark.sql.Row>>	trainValidationTestSplit(Float validationSize, Float testSize, String trainStart, String trainEnd, String validationStart, String validationEnd, String testStart, String testEnd, String description)
List<org.apache.spark.sql.Dataset<org.apache.spark.sql.Row>>	trainValidationTestSplit(Float validationSize, Float testSize, String trainStart, String trainEnd, String validationStart, String validationEnd, String testStart, String testEnd, String description, Long seed, StatisticsConfig statisticsConfig, Map<String,String> readOptions, FilterLogic extraFilterLogic, Filter extraFilter)
FeatureView	update(FeatureView other)

Methods inherited from class java.lang.Object

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

Constructor Detail

FeatureView

public FeatureView(@NonNull
                   @NonNull String name,
                   Integer version,
                   @NonNull
                   @NonNull Query query,
                   String description,
                   @NonNull
                   @NonNull FeatureStore featureStore,
                   List<String> labels)

FeatureView

public FeatureView()

Method Detail

delete

public void delete()
            throws FeatureStoreException,
                   IOException

Throws:

FeatureStoreException

IOException

clean

public static void clean(FeatureStore featureStore,
                         String featureViewName,
                         Integer featureViewVersion)
                  throws FeatureStoreException,
                         IOException

Throws:

FeatureStoreException

IOException

update

public FeatureView update(FeatureView other)
                   throws FeatureStoreException,
                          IOException

Throws:

FeatureStoreException

IOException

initServing

public void initServing()
                 throws FeatureStoreException,
                        IOException,
                        SQLException,
                        ClassNotFoundException

Throws:

FeatureStoreException

IOException

SQLException

ClassNotFoundException

initServing

public void initServing(Boolean batch,
                        Boolean external)
                 throws FeatureStoreException,
                        IOException,
                        SQLException,
                        ClassNotFoundException

Throws:

FeatureStoreException

IOException

SQLException

ClassNotFoundException

initBatchScoring

public void initBatchScoring(Integer trainingDatasetVersion)

getFeatureVector

public List<Object> getFeatureVector(Map<String,Object> entry)
                              throws SQLException,
                                     FeatureStoreException,
                                     IOException,
                                     ClassNotFoundException

Throws:

SQLException

FeatureStoreException

IOException

ClassNotFoundException

getFeatureVector

public List<Object> getFeatureVector(Map<String,Object> entry,
                                     boolean external)
                              throws SQLException,
                                     FeatureStoreException,
                                     IOException,
                                     ClassNotFoundException

Throws:

SQLException

FeatureStoreException

IOException

ClassNotFoundException

getFeatureVectors

public List<List<Object>> getFeatureVectors(Map<String,List<Object>> entry)
                                     throws SQLException,
                                            FeatureStoreException,
                                            IOException,
                                            ClassNotFoundException

Throws:

SQLException

FeatureStoreException

IOException

ClassNotFoundException

getFeatureVectors

public List<List<Object>> getFeatureVectors(Map<String,List<Object>> entry,
                                            boolean external)
                                     throws SQLException,
                                            FeatureStoreException,
                                            IOException,
                                            ClassNotFoundException

Throws:

SQLException

FeatureStoreException

IOException

ClassNotFoundException

getBatchQuery

public String getBatchQuery()
                     throws FeatureStoreException,
                            IOException,
                            ParseException

Throws:

FeatureStoreException

IOException

ParseException

getBatchQuery

public String getBatchQuery(String startTime,
                            String endTime)
                     throws FeatureStoreException,
                            IOException,
                            ParseException

Throws:

FeatureStoreException

IOException

ParseException

getBatchData

public org.apache.spark.sql.Dataset<org.apache.spark.sql.Row> getBatchData(String startTime,
                                                                           String endTime)
                                                                    throws FeatureStoreException,
                                                                           IOException,
                                                                           ParseException

Throws:

FeatureStoreException

IOException

ParseException

getBatchData

public org.apache.spark.sql.Dataset<org.apache.spark.sql.Row> getBatchData(String startTime,
                                                                           String endTime,
                                                                           Map<String,String> readOptions)
                                                                    throws FeatureStoreException,
                                                                           IOException,
                                                                           ParseException

Throws:

FeatureStoreException

IOException

ParseException

addTag

public void addTag(String name,
                   Object value)
            throws FeatureStoreException,
                   IOException

Add name/value tag to the feature view.

Parameters:

name - name of the tag

value - value of the tag. The value of a tag can be any valid json - primitives, arrays or json objects

Throws:

FeatureStoreException - FeatureStoreException

IOException - IOException

getTags

public Map<String,Object> getTags()
                           throws FeatureStoreException,
                                  IOException

Get all tags of the feature view.

Returns:

a map of tag name and values. The value of a tag can be any valid json - primitives, arrays or json objects

Throws:

FeatureStoreException - FeatureStoreException

IOException - IOException

getTag

public Object getTag(String name)
              throws FeatureStoreException,
                     IOException

Get a single tag value of the feature view.

Parameters:

name - name of the tag

Returns:

The value of a tag can be any valid json - primitives, arrays or json objects

Throws:

FeatureStoreException - FeatureStoreException

IOException - IOException

deleteTag

public void deleteTag(String name)
               throws FeatureStoreException,
                      IOException

Delete a tag of the feature view.

Parameters:

name - name of the tag to be deleted

Throws:

FeatureStoreException - FeatureStoreException

IOException - IOException

createTrainingData

public Integer createTrainingData(String startTime,
                                  String endTime,
                                  String description,
                                  DataFormat dataFormat)
                           throws IOException,
                                  FeatureStoreException,
                                  ParseException

Throws:

IOException

FeatureStoreException

ParseException

createTrainingData

public Integer createTrainingData(String startTime,
                                  String endTime,
                                  String description,
                                  DataFormat dataFormat,
                                  Boolean coalesce,
                                  StorageConnector storageConnector,
                                  String location,
                                  Long seed,
                                  StatisticsConfig statisticsConfig,
                                  Map<String,String> writeOptions,
                                  FilterLogic extraFilterLogic,
                                  Filter extraFilter)
                           throws IOException,
                                  FeatureStoreException,
                                  ParseException

Throws:

IOException

FeatureStoreException

ParseException

createTrainTestSplit

public Integer createTrainTestSplit(Float testSize,
                                    String trainStart,
                                    String trainEnd,
                                    String testStart,
                                    String testEnd,
                                    String description,
                                    DataFormat dataFormat)
                             throws IOException,
                                    FeatureStoreException,
                                    ParseException

Throws:

IOException

FeatureStoreException

ParseException

createTrainTestSplit

public Integer createTrainTestSplit(Float testSize,
                                    String trainStart,
                                    String trainEnd,
                                    String testStart,
                                    String testEnd,
                                    String description,
                                    DataFormat dataFormat,
                                    Boolean coalesce,
                                    StorageConnector storageConnector,
                                    String location,
                                    Long seed,
                                    StatisticsConfig statisticsConfig,
                                    Map<String,String> writeOptions,
                                    FilterLogic extraFilterLogic,
                                    Filter extraFilter)
                             throws IOException,
                                    FeatureStoreException,
                                    ParseException

Throws:

IOException

FeatureStoreException

ParseException

createTrainValidationTestSplit

public Integer createTrainValidationTestSplit(Float validationSize,
                                              Float testSize,
                                              String trainStart,
                                              String trainEnd,
                                              String validationStart,
                                              String validationEnd,
                                              String testStart,
                                              String testEnd,
                                              String description,
                                              DataFormat dataFormat)
                                       throws IOException,
                                              FeatureStoreException,
                                              ParseException

Throws:

IOException

FeatureStoreException

ParseException

createTrainValidationTestSplit

public Integer createTrainValidationTestSplit(Float validationSize,
                                              Float testSize,
                                              String trainStart,
                                              String trainEnd,
                                              String validationStart,
                                              String validationEnd,
                                              String testStart,
                                              String testEnd,
                                              String description,
                                              DataFormat dataFormat,
                                              Boolean coalesce,
                                              StorageConnector storageConnector,
                                              String location,
                                              Long seed,
                                              StatisticsConfig statisticsConfig,
                                              Map<String,String> writeOptions,
                                              FilterLogic extraFilterLogic,
                                              Filter extraFilter)
                                       throws IOException,
                                              FeatureStoreException,
                                              ParseException

Throws:

IOException

FeatureStoreException

ParseException

recreateTrainingDataset

public void recreateTrainingDataset(Integer version,
                                    Map<String,String> writeOptions)
                             throws FeatureStoreException,
                                    IOException

Throws:

FeatureStoreException

IOException

getTrainingData

public List<org.apache.spark.sql.Dataset<org.apache.spark.sql.Row>> getTrainingData(Integer version)
                                                                             throws IOException,
                                                                                    FeatureStoreException,
                                                                                    ParseException

Throws:

IOException

FeatureStoreException

ParseException

getTrainingData

public List<org.apache.spark.sql.Dataset<org.apache.spark.sql.Row>> getTrainingData(Integer version,
                                                                                    Map<String,String> readOptions)
                                                                             throws IOException,
                                                                                    FeatureStoreException,
                                                                                    ParseException

Throws:

IOException

FeatureStoreException

ParseException

getTrainTestSplit

public List<org.apache.spark.sql.Dataset<org.apache.spark.sql.Row>> getTrainTestSplit(Integer version)
                                                                               throws IOException,
                                                                                      FeatureStoreException,
                                                                                      ParseException

Throws:

IOException

FeatureStoreException

ParseException

getTrainTestSplit

public List<org.apache.spark.sql.Dataset<org.apache.spark.sql.Row>> getTrainTestSplit(Integer version,
                                                                                      Map<String,String> readOptions)
                                                                               throws IOException,
                                                                                      FeatureStoreException,
                                                                                      ParseException

Throws:

IOException

FeatureStoreException

ParseException

getTrainValidationTestSplit

public List<org.apache.spark.sql.Dataset<org.apache.spark.sql.Row>> getTrainValidationTestSplit(Integer version)
                                                                                         throws IOException,
                                                                                                FeatureStoreException,
                                                                                                ParseException

Throws:

IOException

FeatureStoreException

ParseException

getTrainValidationTestSplit

public List<org.apache.spark.sql.Dataset<org.apache.spark.sql.Row>> getTrainValidationTestSplit(Integer version,
                                                                                                Map<String,String> readOptions)
                                                                                         throws IOException,
                                                                                                FeatureStoreException,
                                                                                                ParseException

Throws:

IOException

FeatureStoreException

ParseException

trainingData

public List<org.apache.spark.sql.Dataset<org.apache.spark.sql.Row>> trainingData(String startTime,
                                                                                 String endTime,
                                                                                 String description)
                                                                          throws IOException,
                                                                                 FeatureStoreException,
                                                                                 ParseException

Throws:

IOException

FeatureStoreException

ParseException

trainingData

public List<org.apache.spark.sql.Dataset<org.apache.spark.sql.Row>> trainingData(String startTime,
                                                                                 String endTime,
                                                                                 String description,
                                                                                 Long seed,
                                                                                 StatisticsConfig statisticsConfig,
                                                                                 Map<String,String> readOptions,
                                                                                 FilterLogic extraFilterLogic,
                                                                                 Filter extraFilter)
                                                                          throws IOException,
                                                                                 FeatureStoreException,
                                                                                 ParseException

Throws:

IOException

FeatureStoreException

ParseException

trainTestSplit

public List<org.apache.spark.sql.Dataset<org.apache.spark.sql.Row>> trainTestSplit(Float testSize,
                                                                                   String trainStart,
                                                                                   String trainEnd,
                                                                                   String testStart,
                                                                                   String testEnd,
                                                                                   String description)
                                                                            throws IOException,
                                                                                   FeatureStoreException,
                                                                                   ParseException

Throws:

IOException

FeatureStoreException

ParseException

trainTestSplit

public List<org.apache.spark.sql.Dataset<org.apache.spark.sql.Row>> trainTestSplit(Float testSize,
                                                                                   String trainStart,
                                                                                   String trainEnd,
                                                                                   String testStart,
                                                                                   String testEnd,
                                                                                   String description,
                                                                                   Long seed,
                                                                                   StatisticsConfig statisticsConfig,
                                                                                   Map<String,String> readOptions,
                                                                                   FilterLogic extraFilterLogic,
                                                                                   Filter extraFilter)
                                                                            throws IOException,
                                                                                   FeatureStoreException,
                                                                                   ParseException

Throws:

IOException

FeatureStoreException

ParseException

trainValidationTestSplit

public List<org.apache.spark.sql.Dataset<org.apache.spark.sql.Row>> trainValidationTestSplit(Float validationSize,
                                                                                             Float testSize,
                                                                                             String trainStart,
                                                                                             String trainEnd,
                                                                                             String validationStart,
                                                                                             String validationEnd,
                                                                                             String testStart,
                                                                                             String testEnd,
                                                                                             String description)
                                                                                      throws IOException,
                                                                                             FeatureStoreException,
                                                                                             ParseException

Throws:

IOException

FeatureStoreException

ParseException

trainValidationTestSplit

public List<org.apache.spark.sql.Dataset<org.apache.spark.sql.Row>> trainValidationTestSplit(Float validationSize,
                                                                                             Float testSize,
                                                                                             String trainStart,
                                                                                             String trainEnd,
                                                                                             String validationStart,
                                                                                             String validationEnd,
                                                                                             String testStart,
                                                                                             String testEnd,
                                                                                             String description,
                                                                                             Long seed,
                                                                                             StatisticsConfig statisticsConfig,
                                                                                             Map<String,String> readOptions,
                                                                                             FilterLogic extraFilterLogic,
                                                                                             Filter extraFilter)
                                                                                      throws IOException,
                                                                                             FeatureStoreException,
                                                                                             ParseException

Throws:

IOException

FeatureStoreException

ParseException

purgeTrainingData

public void purgeTrainingData(Integer version)
                       throws FeatureStoreException,
                              IOException

Throws:

FeatureStoreException

IOException

purgeAllTrainingData

public void purgeAllTrainingData()
                          throws FeatureStoreException,
                                 IOException

Throws:

FeatureStoreException

IOException

deleteTrainingDataset

public void deleteTrainingDataset(Integer version)
                           throws FeatureStoreException,
                                  IOException

Throws:

FeatureStoreException

IOException

deleteAllTrainingDatasets

public void deleteAllTrainingDatasets()
                               throws FeatureStoreException,
                                      IOException

Throws:

FeatureStoreException

IOException

addTrainingDatasetTag

public void addTrainingDatasetTag(Integer version,
                                  String name,
                                  Object value)
                           throws FeatureStoreException,
                                  IOException

Add name/value tag to the training dataset.

Parameters:

version - tag version

name - name of the tag

value - value of the tag. The value of a tag can be any valid json - primitives, arrays or json objects

Throws:

FeatureStoreException - FeatureStoreException

IOException - IOException

getTrainingDatasetTags

public Map<String,Object> getTrainingDatasetTags(Integer version)
                                          throws FeatureStoreException,
                                                 IOException

Get all tags of the training dataset.

Parameters:

version - tag version

Returns:

a map of tag name and values. The value of a tag can be any valid json - primitives, arrays or json objects

Throws:

FeatureStoreException - FeatureStoreException

IOException - IOException

getTrainingDatasetTag

public Object getTrainingDatasetTag(Integer version,
                                    String name)
                             throws FeatureStoreException,
                                    IOException

Get a single tag value of the training dataset.

Parameters:

version - tag version

name - name of the tag

Returns:

The value of a tag can be any valid json - primitives, arrays or json objects

Throws:

FeatureStoreException - FeatureStoreException

IOException - IOException

deleteTrainingDatasetTag

public void deleteTrainingDatasetTag(Integer version,
                                     String name)
                              throws FeatureStoreException,
                                     IOException

Delete a tag of the training dataset.

Parameters:

version - tag version

name - name of the tag to be deleted

Throws:

FeatureStoreException - FeatureStoreException

IOException - IOException

getPrimaryKeys

public HashSet<String> getPrimaryKeys()
                               throws SQLException,
                                      IOException,
                                      FeatureStoreException,
                                      ClassNotFoundException

Set of primary key names that is used as keys in input dict object for `get_serving_vector` method.

Returns:

Set of serving keys

Throws:

SQLException - SQLException

IOException - IOException

FeatureStoreException - FeatureStoreException

ClassNotFoundException - ClassNotFoundException

getId

public Integer getId()

setId

public void setId(Integer id)

getName

public String getName()

setName

public void setName(String name)

getVersion

public Integer getVersion()

setVersion

public void setVersion(Integer version)

getDescription

public String getDescription()

setDescription

public void setDescription(String description)

getFeatures

public List<TrainingDatasetFeature> getFeatures()

setFeatures

public void setFeatures(List<TrainingDatasetFeature> features)

getFeatureStore

public FeatureStore getFeatureStore()

setFeatureStore

public void setFeatureStore(FeatureStore featureStore)

getQuery

public Query getQuery()

setQuery

public void setQuery(Query query)

getLabels

public List<String> getLabels()

setLabels

public void setLabels(List<String> labels)

getType

public String getType()

setType

public void setType(String type)