TextMatcher

Instance Constructors

new TextMatcher()
new TextMatcher(uid: String)

uid
internal uid required to generate writable annotators

Type Members

type AnnotatorType = String

Definition Classes
HasOutputAnnotatorType

Value Members

final def !=(arg0: Any): Boolean

Definition Classes
AnyRef → Any
final def ##(): Int

Definition Classes
AnyRef → Any
final def $[T](param: Param[T]): T

Attributes
protected
Definition Classes
Params
def $$[T](feature: StructFeature[T]): T

Attributes
protected
Definition Classes
HasFeatures
def $$[K, V](feature: MapFeature[K, V]): Map[K, V]

Attributes
protected
Definition Classes
HasFeatures
def $$[T](feature: SetFeature[T]): Set[T]

Attributes
protected
Definition Classes
HasFeatures
def $$[T](feature: ArrayFeature[T]): Array[T]

Attributes
protected
Definition Classes
HasFeatures
final def ==(arg0: Any): Boolean

Definition Classes
AnyRef → Any
def _fit(dataset: Dataset[_], recursiveStages: Option[PipelineModel]): TextMatcherModel

Attributes
protected
Definition Classes
AnnotatorApproach
final def asInstanceOf[T0]: T0

Definition Classes
Any
def beforeTraining(spark: SparkSession): Unit

Definition Classes
AnnotatorApproach
val buildFromTokens: BooleanParam

Whether the TextMatcher should take the CHUNK from TOKEN or not
val caseSensitive: BooleanParam

whether to match regardless of case.
whether to match regardless of case. Defaults true
final def checkSchema(schema: StructType, inputAnnotatorType: String): Boolean

Attributes
protected
Definition Classes
HasInputAnnotationCols
final def clear(param: Param[_]): TextMatcher.this.type

Definition Classes
Params
def clone(): AnyRef

Attributes
protected[java.lang]
Definition Classes
AnyRef
Annotations
@throws( ... )
final def copy(extra: ParamMap): Estimator[TextMatcherModel]

Definition Classes
AnnotatorApproach → Estimator → PipelineStage → Params
def copyValues[T <: Params](to: T, extra: ParamMap): T

Attributes
protected
Definition Classes
Params
final def defaultCopy[T <: Params](extra: ParamMap): T

Attributes
protected
Definition Classes
Params
val description: String

Extracts entities from target dataset given in a text file
Extracts entities from target dataset given in a text file

Definition Classes
TextMatcher → AnnotatorApproach
val entities: ExternalResourceParam

entities external resource.
val entityValue: Param[String]

Value for the entity metadata field
final def eq(arg0: AnyRef): Boolean

Definition Classes
AnyRef
def equals(arg0: Any): Boolean

Definition Classes
AnyRef → Any
def explainParam(param: Param[_]): String

Definition Classes
Params
def explainParams(): String

Definition Classes
Params
final def extractParamMap(): ParamMap

Definition Classes
Params
final def extractParamMap(extra: ParamMap): ParamMap

Definition Classes
Params
val features: ArrayBuffer[Feature[_, _, _]]

Definition Classes
HasFeatures
def finalize(): Unit

Attributes
protected[java.lang]
Definition Classes
AnyRef
Annotations
@throws( classOf[java.lang.Throwable] )
final def fit(dataset: Dataset[_]): TextMatcherModel

Definition Classes
AnnotatorApproach → Estimator
def fit(dataset: Dataset[_], paramMaps: Array[ParamMap]): Seq[TextMatcherModel]

Definition Classes
Estimator
Annotations
@Since( "2.0.0" )
def fit(dataset: Dataset[_], paramMap: ParamMap): TextMatcherModel

Definition Classes
Estimator
Annotations
@Since( "2.0.0" )
def fit(dataset: Dataset[_], firstParamPair: ParamPair[_], otherParamPairs: ParamPair[_]*): TextMatcherModel

Definition Classes
Estimator
Annotations
@Since( "2.0.0" ) @varargs()
def get[T](feature: StructFeature[T]): Option[T]

Attributes
protected
Definition Classes
HasFeatures
def get[K, V](feature: MapFeature[K, V]): Option[Map[K, V]]

Attributes
protected
Definition Classes
HasFeatures
def get[T](feature: SetFeature[T]): Option[Set[T]]

Attributes
protected
Definition Classes
HasFeatures
def get[T](feature: ArrayFeature[T]): Option[Array[T]]

Attributes
protected
Definition Classes
HasFeatures
final def get[T](param: Param[T]): Option[T]

Definition Classes
Params
def getBuildFromTokens: Boolean

Getter for buildFromTokens param
def getCaseSensitive: Boolean

whether to match regardless of case.
whether to match regardless of case. Defaults true
final def getClass(): Class[_]

Definition Classes
AnyRef → Any
final def getDefault[T](param: Param[T]): Option[T]

Definition Classes
Params
def getEntityValue: String

Getter for Value for the entity metadata field
def getInputCols: Array[String]

returns
input annotations columns currently used

Definition Classes
HasInputAnnotationCols
def getLazyAnnotator: Boolean

Definition Classes
CanBeLazy
def getMergeOverlapping: Boolean

whether to merge overlapping matched chunks.
whether to merge overlapping matched chunks. Defaults false
final def getOrDefault[T](param: Param[T]): T

Definition Classes
Params
final def getOutputCol: String

Gets annotation column name going to generate
Gets annotation column name going to generate

Definition Classes
HasOutputAnnotationCol
def getParam(paramName: String): Param[Any]

Definition Classes
Params
def getTokenizer: TokenizerModel
final def hasDefault[T](param: Param[T]): Boolean

Definition Classes
Params
def hasParam(paramName: String): Boolean

Definition Classes
Params
def hashCode(): Int

Definition Classes
AnyRef → Any
def initializeLogIfNecessary(isInterpreter: Boolean, silent: Boolean): Boolean

Attributes
protected
Definition Classes
Logging
def initializeLogIfNecessary(isInterpreter: Boolean): Unit

Attributes
protected
Definition Classes
Logging
val inputAnnotatorTypes: Array[String]

Output annotator type : DOCUMENT, TOKEN
Output annotator type : DOCUMENT, TOKEN

Definition Classes
TextMatcher → HasInputAnnotationCols
final val inputCols: StringArrayParam

columns that contain annotations necessary to run this annotator AnnotatorType is used both as input and output columns if not specified
columns that contain annotations necessary to run this annotator AnnotatorType is used both as input and output columns if not specified

Attributes
protected
Definition Classes
HasInputAnnotationCols
final def isDefined(param: Param[_]): Boolean

Definition Classes
Params
final def isInstanceOf[T0]: Boolean

Definition Classes
Any
final def isSet(param: Param[_]): Boolean

Definition Classes
Params
def isTraceEnabled(): Boolean

Attributes
protected
Definition Classes
Logging
val lazyAnnotator: BooleanParam

Definition Classes
CanBeLazy
def log: Logger

Attributes
protected
Definition Classes
Logging
def logDebug(msg: ⇒ String, throwable: Throwable): Unit

Attributes
protected
Definition Classes
Logging
def logDebug(msg: ⇒ String): Unit

Attributes
protected
Definition Classes
Logging
def logError(msg: ⇒ String, throwable: Throwable): Unit

Attributes
protected
Definition Classes
Logging
def logError(msg: ⇒ String): Unit

Attributes
protected
Definition Classes
Logging
def logInfo(msg: ⇒ String, throwable: Throwable): Unit

Attributes
protected
Definition Classes
Logging
def logInfo(msg: ⇒ String): Unit

Attributes
protected
Definition Classes
Logging
def logName: String

Attributes
protected
Definition Classes
Logging
def logTrace(msg: ⇒ String, throwable: Throwable): Unit

Attributes
protected
Definition Classes
Logging
def logTrace(msg: ⇒ String): Unit

Attributes
protected
Definition Classes
Logging
def logWarning(msg: ⇒ String, throwable: Throwable): Unit

Attributes
protected
Definition Classes
Logging
def logWarning(msg: ⇒ String): Unit

Attributes
protected
Definition Classes
Logging
val mergeOverlapping: BooleanParam

whether to merge overlapping matched chunks.
whether to merge overlapping matched chunks. Defaults false
def msgHelper(schema: StructType): String

Attributes
protected
Definition Classes
HasInputAnnotationCols
final def ne(arg0: AnyRef): Boolean

Definition Classes
AnyRef
final def notify(): Unit

Definition Classes
AnyRef
final def notifyAll(): Unit

Definition Classes
AnyRef
def onTrained(model: TextMatcherModel, spark: SparkSession): Unit

Definition Classes
AnnotatorApproach
def onWrite(path: String, spark: SparkSession): Unit

Attributes
protected
Definition Classes
ParamsAndFeaturesWritable
val outputAnnotatorType: AnnotatorType

Output annotator type : CHUNK
Output annotator type : CHUNK

Definition Classes
TextMatcher → HasOutputAnnotatorType
final val outputCol: Param[String]

Attributes
protected
Definition Classes
HasOutputAnnotationCol
lazy val params: Array[Param[_]]

Definition Classes
Params
def save(path: String): Unit

Definition Classes
MLWritable
Annotations
@Since( "1.6.0" ) @throws( ... )
def set[T](feature: StructFeature[T], value: T): TextMatcher.this.type

Attributes
protected
Definition Classes
HasFeatures
def set[K, V](feature: MapFeature[K, V], value: Map[K, V]): TextMatcher.this.type

Attributes
protected
Definition Classes
HasFeatures
def set[T](feature: SetFeature[T], value: Set[T]): TextMatcher.this.type

Attributes
protected
Definition Classes
HasFeatures
def set[T](feature: ArrayFeature[T], value: Array[T]): TextMatcher.this.type

Attributes
protected
Definition Classes
HasFeatures
final def set(paramPair: ParamPair[_]): TextMatcher.this.type

Attributes
protected
Definition Classes
Params
final def set(param: String, value: Any): TextMatcher.this.type

Attributes
protected
Definition Classes
Params
final def set[T](param: Param[T], value: T): TextMatcher.this.type

Definition Classes
Params
def setBuildFromTokens(v: Boolean): TextMatcher.this.type

Setter for buildFromTokens param
def setCaseSensitive(v: Boolean): TextMatcher.this.type

whether to match regardless of case.
whether to match regardless of case. Defaults true
def setDefault[T](feature: StructFeature[T], value: () ⇒ T): TextMatcher.this.type

Attributes
protected
Definition Classes
HasFeatures
def setDefault[K, V](feature: MapFeature[K, V], value: () ⇒ Map[K, V]): TextMatcher.this.type

Attributes
protected
Definition Classes
HasFeatures
def setDefault[T](feature: SetFeature[T], value: () ⇒ Set[T]): TextMatcher.this.type

Attributes
protected
Definition Classes
HasFeatures
def setDefault[T](feature: ArrayFeature[T], value: () ⇒ Array[T]): TextMatcher.this.type

Attributes
protected
Definition Classes
HasFeatures
final def setDefault(paramPairs: ParamPair[_]*): TextMatcher.this.type

Attributes
protected
Definition Classes
Params
final def setDefault[T](param: Param[T], value: T): TextMatcher.this.type

Attributes
protected
Definition Classes
Params
def setEntities(path: String, readAs: Format, options: Map[String, String] = Map("format" -> "text")): TextMatcher.this.type

path
a path to a file that contains the entities in the specified format.
readAs
the format of the file, can be one of {ReadAs.LINE_BY_LINE, ReadAs.SPARK_DATASET}. Defaults to LINE_BY_LINE.
options
a map of additional parameters. Defaults to {“format”: “text”}.
returns
this
def setEntities(value: ExternalResource): TextMatcher.this.type

Provides a file with phrases to match.
Provides a file with phrases to match. Default: Looks up path in configuration.
def setEntityValue(v: String): TextMatcher.this.type

Setter for Value for the entity metadata field
final def setInputCols(value: String*): TextMatcher.this.type

Definition Classes
HasInputAnnotationCols
final def setInputCols(value: Array[String]): TextMatcher.this.type

Overrides required annotators column if different than default
Overrides required annotators column if different than default

Definition Classes
HasInputAnnotationCols
def setLazyAnnotator(value: Boolean): TextMatcher.this.type

Definition Classes
CanBeLazy
def setMergeOverlapping(v: Boolean): TextMatcher.this.type

whether to merge overlapping matched chunks.
whether to merge overlapping matched chunks. Defaults false
final def setOutputCol(value: String): TextMatcher.this.type

Overrides annotation column name when transforming
Overrides annotation column name when transforming

Definition Classes
HasOutputAnnotationCol
def setTokenizer(tokenizer: TokenizerModel): TextMatcher.this.type
final def synchronized[T0](arg0: ⇒ T0): T0

Definition Classes
AnyRef
def toString(): String

Definition Classes
Identifiable → AnyRef → Any
val tokenizer: StructFeature[TokenizerModel]

Tokenizer
def train(dataset: Dataset[_], recursivePipeline: Option[PipelineModel]): TextMatcherModel

Definition Classes
TextMatcher → AnnotatorApproach
final def transformSchema(schema: StructType): StructType

requirement for pipeline transformation validation.
requirement for pipeline transformation validation. It is called on fit()

Definition Classes
AnnotatorApproach → PipelineStage
def transformSchema(schema: StructType, logging: Boolean): StructType

Attributes
protected
Definition Classes
PipelineStage
Annotations
@DeveloperApi()
val uid: String

internal uid required to generate writable annotators
internal uid required to generate writable annotators

Definition Classes
TextMatcher → Identifiable
def validate(schema: StructType): Boolean

takes a Dataset and checks to see if all the required annotation types are present.
takes a Dataset and checks to see if all the required annotation types are present.
schema
to be validated
returns
True if all the required types are present, else false

Attributes
protected
Definition Classes
AnnotatorApproach
final def wait(): Unit

Definition Classes
AnyRef
Annotations
@throws( ... )
final def wait(arg0: Long, arg1: Int): Unit

Definition Classes
AnyRef
Annotations
@throws( ... )
final def wait(arg0: Long): Unit

Definition Classes
AnyRef
Annotations
@throws( ... )
def write: MLWriter

Definition Classes
ParamsAndFeaturesWritable → DefaultParamsWritable → MLWritable

Related Docs: object TextMatcher | package annotators

class TextMatcher extends AnnotatorApproach[TextMatcherModel] with ParamsAndFeaturesWritable

Instance Constructors

new TextMatcher()

new TextMatcher(uid: String)

Type Members

type AnnotatorType = String

Value Members

final def !=(arg0: Any): Boolean

final def ##(): Int

final def $[T](param: Param[T]): T

def $$[T](feature: StructFeature[T]): T

def $$[K, V](feature: MapFeature[K, V]): Map[K, V]

def $$[T](feature: SetFeature[T]): Set[T]

def $$[T](feature: ArrayFeature[T]): Array[T]

final def ==(arg0: Any): Boolean

def _fit(dataset: Dataset[_], recursiveStages: Option[PipelineModel]): TextMatcherModel

final def asInstanceOf[T0]: T0

def beforeTraining(spark: SparkSession): Unit

val buildFromTokens: BooleanParam

val caseSensitive: BooleanParam

final def checkSchema(schema: StructType, inputAnnotatorType: String): Boolean

final def clear(param: Param[_]): TextMatcher.this.type

def clone(): AnyRef

final def copy(extra: ParamMap): Estimator[TextMatcherModel]

def copyValues[T <: Params](to: T, extra: ParamMap): T

final def defaultCopy[T <: Params](extra: ParamMap): T

val description: String

val entities: ExternalResourceParam

val entityValue: Param[String]

final def eq(arg0: AnyRef): Boolean

def equals(arg0: Any): Boolean

def explainParam(param: Param[_]): String

def explainParams(): String

final def extractParamMap(): ParamMap

final def extractParamMap(extra: ParamMap): ParamMap

val features: ArrayBuffer[Feature[_, _, _]]

def finalize(): Unit

final def fit(dataset: Dataset[_]): TextMatcherModel

def fit(dataset: Dataset[_], paramMaps: Array[ParamMap]): Seq[TextMatcherModel]

def fit(dataset: Dataset[_], paramMap: ParamMap): TextMatcherModel

def fit(dataset: Dataset[_], firstParamPair: ParamPair[_], otherParamPairs: ParamPair[_]*): TextMatcherModel

def get[T](feature: StructFeature[T]): Option[T]

def get[K, V](feature: MapFeature[K, V]): Option[Map[K, V]]

def get[T](feature: SetFeature[T]): Option[Set[T]]

def get[T](feature: ArrayFeature[T]): Option[Array[T]]

final def get[T](param: Param[T]): Option[T]

def getBuildFromTokens: Boolean

def getCaseSensitive: Boolean

final def getClass(): Class[_]

final def getDefault[T](param: Param[T]): Option[T]

def getEntityValue: String

def getInputCols: Array[String]

def getLazyAnnotator: Boolean

def getMergeOverlapping: Boolean

final def getOrDefault[T](param: Param[T]): T

final def getOutputCol: String

def getParam(paramName: String): Param[Any]

def getTokenizer: TokenizerModel

final def hasDefault[T](param: Param[T]): Boolean

def hasParam(paramName: String): Boolean

def hashCode(): Int

def initializeLogIfNecessary(isInterpreter: Boolean, silent: Boolean): Boolean

def initializeLogIfNecessary(isInterpreter: Boolean): Unit

val inputAnnotatorTypes: Array[String]

final val inputCols: StringArrayParam

final def isDefined(param: Param[_]): Boolean

final def isInstanceOf[T0]: Boolean

final def isSet(param: Param[_]): Boolean

def isTraceEnabled(): Boolean

val lazyAnnotator: BooleanParam

def log: Logger

def logDebug(msg: ⇒ String, throwable: Throwable): Unit

def logDebug(msg: ⇒ String): Unit

def logError(msg: ⇒ String, throwable: Throwable): Unit

def logError(msg: ⇒ String): Unit

def logInfo(msg: ⇒ String, throwable: Throwable): Unit

def logInfo(msg: ⇒ String): Unit

def logName: String