Lemmatizer

Class to find lemmas out of words with the objective of returning a base dictionary word. Retrieves the significant part of a word. A dictionary of predefined lemmas must be provided with setDictionary. The dictionary can be set in either in the form of a delimited text file or directly as an ExternalResource. Pretrained models can be loaded with LemmatizerModel.pretrained.

For available pretrained models please see the Models Hub. For extended examples of usage, see the Spark NLP Workshop and the LemmatizerTestSpec.

Example

In this example, the lemma dictionary lemmas_small.txt has the form of

...
pick	->	pick	picks	picking	picked
peck	->	peck	pecking	pecked	pecks
pickle	->	pickle	pickles	pickled	pickling
pepper	->	pepper	peppers	peppered	peppering
...

where each key is delimited by -> and values are delimited by \t

import spark.implicits._
import com.johnsnowlabs.nlp.DocumentAssembler
import com.johnsnowlabs.nlp.annotator.Tokenizer
import com.johnsnowlabs.nlp.annotator.SentenceDetector
import com.johnsnowlabs.nlp.annotators.Lemmatizer
import org.apache.spark.ml.Pipeline

val documentAssembler = new DocumentAssembler()
  .setInputCol("text")
  .setOutputCol("document")

val sentenceDetector = new SentenceDetector()
  .setInputCols(Array("document"))
  .setOutputCol("sentence")

val tokenizer = new Tokenizer()
  .setInputCols(Array("sentence"))
  .setOutputCol("token")

val lemmatizer = new Lemmatizer()
  .setInputCols(Array("token"))
  .setOutputCol("lemma")
  .setDictionary("src/test/resources/lemma-corpus-small/lemmas_small.txt", "->", "\t")

val pipeline = new Pipeline()
  .setStages(Array(
    documentAssembler,
    sentenceDetector,
    tokenizer,
    lemmatizer
  ))

val data = Seq("Peter Pipers employees are picking pecks of pickled peppers.")
  .toDF("text")

val result = pipeline.fit(data).transform(data)
result.selectExpr("lemma.result").show(false)
+------------------------------------------------------------------+
|result                                                            |
+------------------------------------------------------------------+
|[Peter, Pipers, employees, are, pick, peck, of, pickle, pepper, .]|
+------------------------------------------------------------------+

See also: LemmatizerModel for the instantiated model and pretrained models.

Linear Supertypes

AnnotatorApproach[LemmatizerModel], CanBeLazy, DefaultParamsWritable, MLWritable, HasOutputAnnotatorType, HasOutputAnnotationCol, HasInputAnnotationCols, Estimator[LemmatizerModel], PipelineStage, Logging, Params, Serializable, Serializable, Identifiable, AnyRef, Any

Instance Constructors

new Lemmatizer()
new Lemmatizer(uid: String)

uid
required internal uid provided by constructor

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
final def ==(arg0: Any): Boolean

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

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

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

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

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

Definition Classes
Params
def clone(): AnyRef

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

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

Retrieves the significant part of a word
Retrieves the significant part of a word

Definition Classes
Lemmatizer → AnnotatorApproach
val dictionary: ExternalResourceParam

External dictionary to be used by the lemmatizer, which needs 'keyDelimiter' and 'valueDelimiter' for parsing the resource
External dictionary to be used by the lemmatizer, which needs 'keyDelimiter' and 'valueDelimiter' for parsing the resource
Example
```
...
pick	->	pick	picks	picking	picked
peck	->	peck	pecking	pecked	pecks
pickle	->	pickle	pickles	pickled	pickling
pepper	->	pepper	peppers	peppered	peppering
...
```
where each key is delimited by -> and values are delimited by \t
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
def finalize(): Unit

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

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

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

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

Definition Classes
Estimator
Annotations
@Since( "2.0.0" ) @varargs()
final def get[T](param: Param[T]): Option[T]

Definition Classes
Params
final def getClass(): Class[_]

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

Definition Classes
Params
def getDictionary: ExternalResource

External dictionary to be used by the lemmatizer
def getInputCols: Array[String]

returns
input annotations columns currently used

Definition Classes
HasInputAnnotationCols
def getLazyAnnotator: Boolean

Definition Classes
CanBeLazy
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
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[AnnotatorType]

Input annotator type : TOKEN
Input annotator type : TOKEN

Definition Classes
Lemmatizer → 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
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: LemmatizerModel, spark: SparkSession): Unit

Definition Classes
AnnotatorApproach
val optionalInputAnnotatorTypes: Array[String]

Definition Classes
HasInputAnnotationCols
val outputAnnotatorType: AnnotatorType

Output annotator type : TOKEN
Output annotator type : TOKEN

Definition Classes
Lemmatizer → 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( ... )
final def set(paramPair: ParamPair[_]): Lemmatizer.this.type

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

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

Definition Classes
Params
final def setDefault(paramPairs: ParamPair[_]*): Lemmatizer.this.type

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

Attributes
protected
Definition Classes
Params
def setDictionary(path: String, keyDelimiter: String, valueDelimiter: String, readAs: Format = ReadAs.TEXT, options: Map[String, String] = Map("format" -> "text")): Lemmatizer.this.type

External dictionary to be used by the lemmatizer, which needs keyDelimiter and valueDelimiter for parsing the resource
def setDictionary(value: ExternalResource): Lemmatizer.this.type

External dictionary already in the form of ExternalResource, for which the Map member options has entries defined for "keyDelimiter" and "valueDelimiter".
External dictionary already in the form of ExternalResource, for which the Map member options has entries defined for "keyDelimiter" and "valueDelimiter".
Example
```
val resource = ExternalResource(
  "src/test/resources/regex-matcher/rules.txt",
  ReadAs.TEXT,
  Map("keyDelimiter" -> "->", "valueDelimiter" -> "\t")
)
val lemmatizer = new Lemmatizer()
  .setInputCols(Array("token"))
  .setOutputCol("lemma")
  .setDictionary(resource)
```
final def setInputCols(value: String*): Lemmatizer.this.type

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

Definition Classes
CanBeLazy
final def setOutputCol(value: String): Lemmatizer.this.type

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

Definition Classes
HasOutputAnnotationCol
final def synchronized[T0](arg0: ⇒ T0): T0

Definition Classes
AnyRef
def toString(): String

Definition Classes
Identifiable → AnyRef → Any
def train(dataset: Dataset[_], recursivePipeline: Option[PipelineModel]): LemmatizerModel

Definition Classes
Lemmatizer → 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

required internal uid provided by constructor
required internal uid provided by constructor

Definition Classes
Lemmatizer → 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
DefaultParamsWritable → MLWritable

Inherited from AnnotatorApproach[LemmatizerModel]

Inherited from CanBeLazy

Inherited from DefaultParamsWritable

Inherited from MLWritable

Inherited from HasOutputAnnotatorType

Inherited from HasOutputAnnotationCol

Inherited from HasInputAnnotationCols

Inherited from Estimator[LemmatizerModel]

Inherited from PipelineStage

Inherited from Logging

Inherited from Params

Inherited from Serializable

Inherited from Identifiable

Inherited from AnyRef

Inherited from Any

Annotator types

Required input and expected output annotator types

Parameters

A list of (hyper-)parameter keys this annotator can take. Users can set and get the parameter values through setters and getters, respectively.

Related Docs: object Lemmatizer | package annotators

class Lemmatizer extends AnnotatorApproach[LemmatizerModel]

Example

Instance Constructors

new Lemmatizer()

new Lemmatizer(uid: String)

Type Members

type AnnotatorType = String

Value Members

final def !=(arg0: Any): Boolean

final def ##(): Int

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

final def ==(arg0: Any): Boolean

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

def arraysZip: UserDefinedFunction

final def asInstanceOf[T0]: T0

def beforeTraining(spark: SparkSession): Unit

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

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

def clone(): AnyRef

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

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

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

val description: String

val dictionary: ExternalResourceParam

Example

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

def finalize(): Unit

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

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

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

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

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

final def getClass(): Class[_]

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

def getDictionary: ExternalResource

def getInputCols: Array[String]

def getLazyAnnotator: Boolean

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

final def getOutputCol: String

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

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[AnnotatorType]

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

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

def logTrace(msg: ⇒ String): Unit

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

def logWarning(msg: ⇒ String): Unit

def msgHelper(schema: StructType): String

final def ne(arg0: AnyRef): Boolean

final def notify(): Unit

final def notifyAll(): Unit

def onTrained(model: LemmatizerModel, spark: SparkSession): Unit

val optionalInputAnnotatorTypes: Array[String]

val outputAnnotatorType: AnnotatorType

final val outputCol: Param[String]

lazy val params: Array[Param[_]]