PartitionTransformer

class PartitionTransformer extends AnnotatorModel[PartitionTransformer] with HasSimpleAnnotate[PartitionTransformer] with HasReaderProperties with HasEmailReaderProperties with HasExcelReaderProperties with HasHTMLReaderProperties with HasPowerPointProperties with HasTextReaderProperties with HasPdfToTextProperties with HasXmlReaderProperties with HasChunkerProperties

The PartitionTransformer annotator allows you to use the Partition feature more smoothly within existing Spark NLP workflows, enabling seamless reuse of your pipelines. PartitionTransformer can be used for extracting structured content from various document types using Spark NLP readers. It supports reading from files, URLs, in-memory strings, or byte arrays, and returns parsed output as a structured Spark DataFrame.

Supported formats include plain text, HTML, Word (.doc/.docx), Excel (.xls/.xlsx), PowerPoint (.ppt/.pptx), email files (.eml, .msg), and PDFs.

Example

import com.johnsnowlabs.partition.PartitionTransformer
import com. johnsnowlabs. nlp. base. DocumentAssembler
import org.apache.spark.ml.Pipeline
import spark.implicits._
val urls = Seq("https://www.blizzard.com", "https://www.google.com/").toDS.toDF("text")

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

val partition = new PartitionTransformer()
  .setInputCols("document")
  .setOutputCol("partition")
  .setContentType("url")
  .setHeaders(Map("Accept-Language" -> "es-ES"))

val pipeline = new Pipeline()
  .setStages(Array(documentAssembler, partition))

val pipelineModel = pipeline.fit(testDataSet)
val resultDf = pipelineModel.transform(testDataSet)

resultDf.show()
+--------------------+--------------------+--------------------+
|                text|            document|           partition|
+--------------------+--------------------+--------------------+
|https://www.blizz...|[{Title, Juegos d...|[{document, 0, 16...|
|https://www.googl...|[{Title, Gmail Im...|[{document, 0, 28...|
+--------------------+--------------------+--------------------+

Linear Supertypes

HasChunkerProperties, HasXmlReaderProperties, HasPdfToTextProperties, HasTextReaderProperties, HasPowerPointProperties, HasHTMLReaderProperties, HasExcelReaderProperties, HasEmailReaderProperties, HasReaderProperties, HasSimpleAnnotate[PartitionTransformer], AnnotatorModel[PartitionTransformer], CanBeLazy, RawAnnotator[PartitionTransformer], HasOutputAnnotationCol, HasInputAnnotationCols, HasOutputAnnotatorType, ParamsAndFeaturesWritable, HasFeatures, DefaultParamsWritable, MLWritable, Model[PartitionTransformer], Transformer, PipelineStage, Logging, Params, Serializable, Serializable, Identifiable, AnyRef, Any

Ordering

Grouped
Alphabetic
By Inheritance

Inherited

PartitionTransformer
HasChunkerProperties
HasXmlReaderProperties
HasPdfToTextProperties
HasTextReaderProperties
HasPowerPointProperties
HasHTMLReaderProperties
HasExcelReaderProperties
HasEmailReaderProperties
HasReaderProperties
HasSimpleAnnotate
AnnotatorModel
CanBeLazy
RawAnnotator
HasOutputAnnotationCol
HasInputAnnotationCols
HasOutputAnnotatorType
ParamsAndFeaturesWritable
HasFeatures
DefaultParamsWritable
MLWritable
Model
Transformer
PipelineStage
Logging
Params
Serializable
Serializable
Identifiable
AnyRef
Any

Hide All
Show All

Visibility

Public
All

Instance Constructors

new PartitionTransformer()
new PartitionTransformer(uid: String)

Type Members

type AnnotationContent = Seq[Row]
internal types to show Rows as a relevant StructType Should be deleted once Spark releases UserDefinedTypes to @developerAPI
internal types to show Rows as a relevant StructType Should be deleted once Spark releases UserDefinedTypes to @developerAPI

Attributes
protected
Definition Classes
AnnotatorModel
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 _transform(dataset: Dataset[_], recursivePipeline: Option[PipelineModel]): DataFrame

Definition Classes
PartitionTransformer → AnnotatorModel
val addAttachmentContent: Param[Boolean]

Definition Classes
HasEmailReaderProperties
def afterAnnotate(dataset: DataFrame): DataFrame

Attributes
protected
Definition Classes
AnnotatorModel
def annotate(annotations: Seq[Annotation]): Seq[Annotation]
takes a document and annotations and produces new annotations of this annotator's annotation type
takes a document and annotations and produces new annotations of this annotator's annotation type
annotations
Annotations that correspond to inputAnnotationCols generated by previous annotators if any
returns
any number of annotations processed for every input annotation. Not necessary one to one relationship

Definition Classes
PartitionTransformer → HasSimpleAnnotate
val appendCells: Param[Boolean]

Definition Classes
HasExcelReaderProperties
final def asInstanceOf[T0]: T0

Definition Classes
Any
def beforeAnnotate(dataset: Dataset[_]): Dataset[_]

Attributes
protected
Definition Classes
AnnotatorModel
val cellSeparator: Param[String]

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

Attributes
protected
Definition Classes
HasInputAnnotationCols
val chunkingStrategy: Param[String]

Definition Classes
HasChunkerProperties
final def clear(param: Param[_]): PartitionTransformer.this.type

Definition Classes
Params
def clone(): AnyRef

Attributes
protected[lang]
Definition Classes
AnyRef
Annotations
@throws( ... ) @native()
val combineTextUnderNChars: Param[Int]

Definition Classes
HasChunkerProperties
val contentPath: Param[String]

Definition Classes
HasReaderProperties
val contentType: Param[String]

Definition Classes
HasReaderProperties
def copy(extra: ParamMap): PartitionTransformer
requirement for annotators copies
requirement for annotators copies

Definition Classes
RawAnnotator → Model → Transformer → 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
def dfAnnotate: UserDefinedFunction
Wraps annotate to happen inside SparkSQL user defined functions in order to act with org.apache.spark.sql.Column
Wraps annotate to happen inside SparkSQL user defined functions in order to act with org.apache.spark.sql.Column
returns
udf function to be applied to inputCols using this annotator's annotate function as part of ML transformation

Definition Classes
HasSimpleAnnotate
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
val explodeDocs: BooleanParam

Definition Classes
HasReaderProperties
def extraValidate(structType: StructType): Boolean

Attributes
protected
Definition Classes
RawAnnotator
def extraValidateMsg: String
Override for additional custom schema checks
Override for additional custom schema checks

Attributes
protected
Definition Classes
RawAnnotator
final val extractCoordinates: BooleanParam

Definition Classes
HasPdfToTextProperties
final def extractParamMap(): ParamMap

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

Definition Classes
Params
val extractTagAttributes: StringArrayParam

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

Definition Classes
HasFeatures
def finalize(): Unit

Attributes
protected[lang]
Definition Classes
AnyRef
Annotations
@throws( classOf[java.lang.Throwable] )
val flattenOutput: BooleanParam

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

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

Definition Classes
Params
final def getInputCol: String

Definition Classes
HasReaderProperties
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
val groupBrokenParagraphs: Param[Boolean]

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

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

Definition Classes
Params
def hasParent: Boolean

Definition Classes
Model
def hashCode(): Int

Definition Classes
AnyRef → Any
Annotations
@native()
val headers: Param[Map[String, String]]

Definition Classes
HasHTMLReaderProperties
val ignoreExceptions: BooleanParam

Definition Classes
HasReaderProperties
val includePageBreaks: Param[Boolean]

Definition Classes
HasReaderProperties
val includeSlideNotes: Param[Boolean]

Definition Classes
HasPowerPointProperties
val includeTitleTag: Param[Boolean]

Definition Classes
HasHTMLReaderProperties
val inferTableStructure: Param[Boolean]

Definition Classes
HasReaderProperties
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]
Annotator reference id.
Annotator reference id. Used to identify elements in metadata or to refer to this annotator type

Definition Classes
PartitionTransformer → HasInputAnnotationCols
final val inputCol: Param[String]

Attributes
protected
Definition Classes
HasReaderProperties
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 logger: Logger

Attributes
protected
val maxCharacters: Param[Int]

Definition Classes
HasChunkerProperties
val maxLineCount: Param[Int]

Definition Classes
HasTextReaderProperties
def msgHelper(schema: StructType): String

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

Definition Classes
AnyRef
val newAfterNChars: Param[Int]

Definition Classes
HasChunkerProperties
final val normalizeLigatures: BooleanParam

Definition Classes
HasPdfToTextProperties
final def notify(): Unit

Definition Classes
AnyRef
Annotations
@native()
final def notifyAll(): Unit

Definition Classes
AnyRef
Annotations
@native()
def onWrite(path: String, spark: SparkSession): Unit

Attributes
protected
Definition Classes
ParamsAndFeaturesWritable
val onlyLeafNodes: Param[Boolean]

Definition Classes
HasXmlReaderProperties
final val onlyPageNum: BooleanParam

Definition Classes
HasPdfToTextProperties
val optionalInputAnnotatorTypes: Array[String]

Definition Classes
HasInputAnnotationCols
final val originCol: Param[String]

Definition Classes
HasPdfToTextProperties
val outputAnnotatorType: AnnotatorType

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

Attributes
protected
Definition Classes
HasOutputAnnotationCol
val outputFormat: Param[String]

Definition Classes
HasHTMLReaderProperties
val overlap: Param[Int]

Definition Classes
HasChunkerProperties
val overlapAll: Param[Boolean]

Definition Classes
HasChunkerProperties
final val pageNumCol: Param[String]

Definition Classes
HasPdfToTextProperties
val paragraphSplit: Param[String]

Definition Classes
HasTextReaderProperties
lazy val params: Array[Param[_]]

Definition Classes
Params
var parent: Estimator[PartitionTransformer]

Definition Classes
Model
final val partitionNum: IntParam

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

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

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

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

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

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

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

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

Definition Classes
Params
def setAddAttachmentContent(value: Boolean): PartitionTransformer.this.type

Definition Classes
HasEmailReaderProperties
def setAppendCells(value: Boolean): PartitionTransformer.this.type

Definition Classes
HasExcelReaderProperties
def setCellSeparator(value: String): PartitionTransformer.this.type

Definition Classes
HasExcelReaderProperties
def setChunkingStrategy(value: String): PartitionTransformer.this.type

Definition Classes
HasChunkerProperties
def setComBineTextUnderNChars(value: Int): PartitionTransformer.this.type

Definition Classes
HasChunkerProperties
def setContentPath(value: String): PartitionTransformer.this.type

Definition Classes
HasReaderProperties
def setContentType(value: String): PartitionTransformer.this.type

Definition Classes
HasReaderProperties
def setDefault[T](feature: StructFeature[T], value: () ⇒ T): PartitionTransformer.this.type

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

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

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

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

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

Attributes
protected[org.apache.spark.ml]
Definition Classes
Params
def setExplodeDocs(value: Boolean): PartitionTransformer.this.type

Definition Classes
HasReaderProperties
def setExtractCoordinates(value: Boolean): PartitionTransformer.this.type

Definition Classes
HasPdfToTextProperties
def setExtractTagAttributes(attributes: Array[String]): PartitionTransformer.this.type
Specify which tag attributes should have their values extracted as text when parsing tag-based formats (e.g., HTML or XML).
Specify which tag attributes should have their values extracted as text when parsing tag-based formats (e.g., HTML or XML).
attributes
array of attribute names to extract
returns
this instance with the updated extractTagAttributes parameter

Definition Classes
HasTextReaderProperties
def setFlattenOutput(value: Boolean): PartitionTransformer.this.type

Definition Classes
HasReaderProperties
def setGroupBrokenParagraphs(value: Boolean): PartitionTransformer.this.type
Enable or disable merging of fragmented lines into coherent paragraphs when parsing text.
Enable or disable merging of fragmented lines into coherent paragraphs when parsing text. When enabled, heuristics based on line length and structure are used to group lines.
value
true to group broken paragraphs, false to preserve original line breaks
returns
this instance with the updated groupBrokenParagraphs parameter

Definition Classes
HasTextReaderProperties
def setHeaders(value: Map[String, String]): PartitionTransformer.this.type

Definition Classes
HasHTMLReaderProperties
def setHeadersPython(headers: Map[String, String]): PartitionTransformer.this.type

Definition Classes
HasHTMLReaderProperties
def setIgnoreExceptions(value: Boolean): PartitionTransformer.this.type

Definition Classes
HasReaderProperties
def setIncludePageBreaks(value: Boolean): PartitionTransformer.this.type

Definition Classes
HasReaderProperties
def setIncludeSlideNotes(value: Boolean): PartitionTransformer.this.type

Definition Classes
HasPowerPointProperties
def setIncludeTitleTag(value: Boolean): PartitionTransformer.this.type

Definition Classes
HasHTMLReaderProperties
def setInferTableStructure(value: Boolean): PartitionTransformer.this.type

Definition Classes
HasReaderProperties
final def setInputCol(value: String): PartitionTransformer.this.type

Definition Classes
HasReaderProperties
def setInputCols(value: Array[String]): PartitionTransformer.this.type
Overrides required annotators column if different than default
Overrides required annotators column if different than default

Definition Classes
PartitionTransformer → HasInputAnnotationCols
final def setInputCols(value: String*): PartitionTransformer.this.type

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

Definition Classes
CanBeLazy
def setMaxCharacters(value: Int): PartitionTransformer.this.type

Definition Classes
HasChunkerProperties
def setMaxLineCount(value: Int): PartitionTransformer.this.type
Set the maximum number of lines to evaluate when estimating paragraph layout characteristics.
Set the maximum number of lines to evaluate when estimating paragraph layout characteristics. This limits the amount of text inspected for layout heuristics.
value
maximum number of lines to inspect
returns
this instance with the updated maxLineCount parameter

Definition Classes
HasTextReaderProperties
def setNewAfterNChars(value: Int): PartitionTransformer.this.type

Definition Classes
HasChunkerProperties
def setNormalizeLigatures(value: Boolean): PartitionTransformer.this.type

Definition Classes
HasPdfToTextProperties
def setOnlyLeafNodes(value: Boolean): PartitionTransformer.this.type

Definition Classes
HasXmlReaderProperties
def setOnlyPageNum(value: Boolean): PartitionTransformer.this.type

Definition Classes
HasPdfToTextProperties
def setOriginCol(value: String): PartitionTransformer.this.type

Definition Classes
HasPdfToTextProperties
final def setOutputCol(value: String): PartitionTransformer.this.type
Overrides annotation column name when transforming
Overrides annotation column name when transforming

Definition Classes
HasOutputAnnotationCol
def setOutputFormat(value: String): PartitionTransformer.this.type

Definition Classes
HasHTMLReaderProperties
def setOverlap(value: Int): PartitionTransformer.this.type

Definition Classes
HasChunkerProperties
def setOverlapAll(value: Boolean): PartitionTransformer.this.type

Definition Classes
HasChunkerProperties
def setPageNumCol(value: String): PartitionTransformer.this.type

Definition Classes
HasPdfToTextProperties
def setParagraphSplit(value: String): PartitionTransformer.this.type
Set the regular expression used to detect paragraph boundaries when grouping broken paragraphs.
Set the regular expression used to detect paragraph boundaries when grouping broken paragraphs.
value
regex pattern string to detect paragraph boundaries
returns
this instance with the updated paragraphSplit parameter

Definition Classes
HasTextReaderProperties
def setParent(parent: Estimator[PartitionTransformer]): PartitionTransformer

Definition Classes
Model
def setPartitionNum(value: Int): PartitionTransformer.this.type

Definition Classes
HasPdfToTextProperties
def setShortLineWordThreshold(value: Int): PartitionTransformer.this.type
Set the maximum number of words for a line to be considered "short" when grouping broken paragraphs.
Set the maximum number of words for a line to be considered "short" when grouping broken paragraphs. Short lines often indicate line-wrapping within a paragraph rather than a real paragraph break.
value
maximum word count for a line to be considered short
returns
this instance with the updated shortLineWordThreshold parameter

Definition Classes
HasTextReaderProperties
def setSort(value: Boolean): PartitionTransformer.this.type

Definition Classes
HasPdfToTextProperties
def setSplitPage(value: Boolean): PartitionTransformer.this.type

Definition Classes
HasPdfToTextProperties
def setStoreContent(value: Boolean): PartitionTransformer.this.type

Definition Classes
HasReaderProperties
def setStoreSplittedPdf(value: Boolean): PartitionTransformer.this.type

Definition Classes
HasPdfToTextProperties
def setTextStripper(value: String): PartitionTransformer.this.type

Definition Classes
HasPdfToTextProperties
def setThreshold(value: Double): PartitionTransformer.this.type
Set the threshold ratio of empty lines used to decide between new line-based or broken-paragraph grouping.
Set the threshold ratio of empty lines used to decide between new line-based or broken-paragraph grouping. Lower values make it easier to choose broken-paragraph grouping.
value
ratio between 0.0 and 1.0 representing the empty-line threshold
returns
this instance with the updated threshold parameter

Definition Classes
HasTextReaderProperties
def setTimeout(value: Int): PartitionTransformer.this.type

Definition Classes
HasHTMLReaderProperties
def setTitleFontSize(value: Int): PartitionTransformer.this.type

Definition Classes
HasReaderProperties
def setTitleLengthSize(value: Int): PartitionTransformer.this.type
Set the maximum character length used to determine if a text block qualifies as a title during parsing.
Set the maximum character length used to determine if a text block qualifies as a title during parsing.
value
maximum number of characters to treat a block as a title
returns
this instance with the updated titleLengthSize parameter

Definition Classes
HasTextReaderProperties
def setXmlKeepTags(value: Boolean): PartitionTransformer.this.type

Definition Classes
HasXmlReaderProperties
val shortLineWordThreshold: Param[Int]

Definition Classes
HasTextReaderProperties
final val sort: BooleanParam

Definition Classes
HasPdfToTextProperties
final val splitPage: BooleanParam

Definition Classes
HasPdfToTextProperties
val storeContent: Param[Boolean]

Definition Classes
HasReaderProperties
final val storeSplittedPdf: BooleanParam

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

Definition Classes
AnyRef
final val textStripper: Param[String]

Definition Classes
HasPdfToTextProperties
val threshold: Param[Double]

Definition Classes
HasTextReaderProperties
val timeout: Param[Int]

Definition Classes
HasHTMLReaderProperties
val titleFontSize: Param[Int]

Definition Classes
HasReaderProperties
val titleLengthSize: Param[Int]

Definition Classes
HasTextReaderProperties
def toString(): String

Definition Classes
Identifiable → AnyRef → Any
final def transform(dataset: Dataset[_]): DataFrame
Given requirements are met, this applies ML transformation within a Pipeline or stand-alone Output annotation will be generated as a new column, previous annotations are still available separately metadata is built at schema level to record annotations structural information outside its content
Given requirements are met, this applies ML transformation within a Pipeline or stand-alone Output annotation will be generated as a new column, previous annotations are still available separately metadata is built at schema level to record annotations structural information outside its content
dataset
Dataset[Row]

Definition Classes
AnnotatorModel → Transformer
def transform(dataset: Dataset[_], paramMap: ParamMap): DataFrame

Definition Classes
Transformer
Annotations
@Since( "2.0.0" )
def transform(dataset: Dataset[_], firstParamPair: ParamPair[_], otherParamPairs: ParamPair[_]*): DataFrame

Definition Classes
Transformer
Annotations
@Since( "2.0.0" ) @varargs()
final def transformSchema(schema: StructType): StructType
requirement for pipeline transformation validation.
requirement for pipeline transformation validation. It is called on fit()

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

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

Definition Classes
PartitionTransformer → 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
RawAnnotator
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( ... ) @native()
def wrapColumnMetadata(col: Column): Column

Attributes
protected
Definition Classes
RawAnnotator
def write: MLWriter

Definition Classes
ParamsAndFeaturesWritable → DefaultParamsWritable → MLWritable
val xmlKeepTags: Param[Boolean]

Definition Classes
HasXmlReaderProperties

Packages

PartitionTransformer

Example

Instance Constructors

Type Members

Value Members

Inherited from HasChunkerProperties

Inherited from HasXmlReaderProperties

Inherited from HasPdfToTextProperties

Inherited from HasTextReaderProperties

Inherited from HasPowerPointProperties

Inherited from HasHTMLReaderProperties

Inherited from HasExcelReaderProperties

Inherited from HasEmailReaderProperties

Inherited from HasReaderProperties

Inherited from HasSimpleAnnotate[PartitionTransformer]

Inherited from AnnotatorModel[PartitionTransformer]

Inherited from CanBeLazy

Inherited from RawAnnotator[PartitionTransformer]

Inherited from HasOutputAnnotationCol

Inherited from HasInputAnnotationCols

Inherited from HasOutputAnnotatorType

Inherited from ParamsAndFeaturesWritable

Inherited from HasFeatures

Inherited from DefaultParamsWritable

Inherited from MLWritable

Inherited from Model[PartitionTransformer]

Inherited from Transformer

Inherited from PipelineStage

Inherited from Logging

Inherited from Params

Inherited from Serializable

Inherited from Serializable

Inherited from Identifiable

Inherited from AnyRef

Inherited from Any

getParam

setParam

Ungrouped

Packages

PartitionTransformer 

Example

Instance Constructors

Type Members

Value Members

Inherited from HasChunkerProperties

Inherited from HasXmlReaderProperties

Inherited from HasPdfToTextProperties

Inherited from HasTextReaderProperties

Inherited from HasPowerPointProperties

Inherited from HasHTMLReaderProperties

Inherited from HasExcelReaderProperties

Inherited from HasEmailReaderProperties

Inherited from HasReaderProperties

Inherited from HasSimpleAnnotate[PartitionTransformer]

Inherited from AnnotatorModel[PartitionTransformer]

Inherited from CanBeLazy

Inherited from RawAnnotator[PartitionTransformer]

Inherited from HasOutputAnnotationCol

Inherited from HasInputAnnotationCols

Inherited from HasOutputAnnotatorType

Inherited from ParamsAndFeaturesWritable

Inherited from HasFeatures

Inherited from DefaultParamsWritable

Inherited from MLWritable

Inherited from Model[PartitionTransformer]

Inherited from Transformer

Inherited from PipelineStage

Inherited from Logging

Inherited from Params

Inherited from Serializable

Inherited from Serializable

Inherited from Identifiable

Inherited from AnyRef

Inherited from Any

getParam

setParam

Ungrouped

PartitionTransformer