PretrainedPipeline

Represents a fully constructed and trained Spark NLP pipeline, ready to be used. This way, a whole pipeline can be defined in 1 line. Additionally, the LightPipeline version of the model can be retrieved with member lightModel.

For more extended examples see the Pipelines page and our Github Model Repository for available pipeline models.

Example

import com.johnsnowlabs.nlp.pretrained.PretrainedPipeline
import com.johnsnowlabs.nlp.SparkNLP
val testData = spark.createDataFrame(Seq(
(1, "Google has announced the release of a beta version of the popular TensorFlow machine learning library"),
(2, "Donald John Trump (born June 14, 1946) is the 45th and current president of the United States")
)).toDF("id", "text")

val pipeline = PretrainedPipeline("explain_document_dl", lang="en")

val annotation = pipeline.transform(testData)

annotation.select("entities.result").show(false)

/*
+----------------------------------+
|result                            |
+----------------------------------+
|[Google, TensorFlow]              |
|[Donald John Trump, United States]|
+----------------------------------+
*/

downloadName: Name of the Pipeline Model
lang: Language of the defined pipeline (Default: "en")
source: Source where to get the Pipeline Model

Linear Supertypes

Serializable, Serializable, Product, Equals, AnyRef, Any

Instance Constructors

new PretrainedPipeline(downloadName: String, lang: String)
new PretrainedPipeline(downloadName: String)

Support for java default argument interoperability
new PretrainedPipeline(downloadName: String, lang: String = "en", source: String = ResourceDownloader.publicLoc, parseEmbeddingsVectors: Boolean = false, diskLocation: Option[String] = None)

downloadName
Name of the Pipeline Model
lang
Language of the defined pipeline (Default: "en")
source
Source where to get the Pipeline Model

Value Members

final def !=(arg0: Any): Boolean

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

Definition Classes
AnyRef → Any
final def ==(arg0: Any): Boolean

Definition Classes
AnyRef → Any
def annotate(target: Array[String]): Array[Map[String, Seq[String]]]
def annotate(target: String): Map[String, Seq[String]]
def annotate(dataset: DataFrame, inputColumn: String): DataFrame
final def asInstanceOf[T0]: T0

Definition Classes
Any
def clone(): AnyRef

Attributes
protected[java.lang]
Definition Classes
AnyRef
Annotations
@throws( ... )
val diskLocation: Option[String]
val downloadName: String

Name of the Pipeline Model
final def eq(arg0: AnyRef): Boolean

Definition Classes
AnyRef
def finalize(): Unit

Attributes
protected[java.lang]
Definition Classes
AnyRef
Annotations
@throws( classOf[java.lang.Throwable] )
final def getClass(): Class[_]

Definition Classes
AnyRef → Any
final def isInstanceOf[T0]: Boolean

Definition Classes
Any
val lang: String

Language of the defined pipeline (Default: "en")
lazy val lightModel: LightPipeline
val model: PipelineModel
final def ne(arg0: AnyRef): Boolean

Definition Classes
AnyRef
final def notify(): Unit

Definition Classes
AnyRef
final def notifyAll(): Unit

Definition Classes
AnyRef
val parseEmbeddingsVectors: Boolean
val source: String

Source where to get the Pipeline Model
final def synchronized[T0](arg0: ⇒ T0): T0

Definition Classes
AnyRef
def transform(dataFrame: DataFrame): DataFrame
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( ... )

Related Docs: object PretrainedPipeline | package pretrained

case class PretrainedPipeline(downloadName: String, lang: String = "en", source: String = ResourceDownloader.publicLoc, parseEmbeddingsVectors: Boolean = false, diskLocation: Option[String] = None) extends Product with Serializable

Example

Instance Constructors

new PretrainedPipeline(downloadName: String, lang: String)

new PretrainedPipeline(downloadName: String)

new PretrainedPipeline(downloadName: String, lang: String = "en", source: String = ResourceDownloader.publicLoc, parseEmbeddingsVectors: Boolean = false, diskLocation: Option[String] = None)

Value Members

final def !=(arg0: Any): Boolean

final def ##(): Int

final def ==(arg0: Any): Boolean

def annotate(target: Array[String]): Array[Map[String, Seq[String]]]

def annotate(target: String): Map[String, Seq[String]]

def annotate(dataset: DataFrame, inputColumn: String): DataFrame

final def asInstanceOf[T0]: T0

def clone(): AnyRef

val diskLocation: Option[String]

val downloadName: String

final def eq(arg0: AnyRef): Boolean

def finalize(): Unit

final def getClass(): Class[_]

final def isInstanceOf[T0]: Boolean

val lang: String

lazy val lightModel: LightPipeline

val model: PipelineModel

final def ne(arg0: AnyRef): Boolean

final def notify(): Unit

final def notifyAll(): Unit

val parseEmbeddingsVectors: Boolean

val source: String

final def synchronized[T0](arg0: ⇒ T0): T0

def transform(dataFrame: DataFrame): DataFrame

final def wait(): Unit

final def wait(arg0: Long, arg1: Int): Unit

final def wait(arg0: Long): Unit

Inherited from Serializable

Inherited from Serializable

Inherited from Product

Inherited from Equals

Inherited from AnyRef

Inherited from Any

Ungrouped