Class/Object

com.johnsnowlabs.nlp.annotators.classifier.dl

ClassifierDLApproach

Related Docs: object ClassifierDLApproach | package dl

Permalink

class ClassifierDLApproach extends AnnotatorApproach[ClassifierDLModel] with ParamsAndFeaturesWritable

Trains a ClassifierDL for generic Multi-class Text Classification.

ClassifierDL uses the state-of-the-art Universal Sentence Encoder as an input for text classifications. The ClassifierDL annotator uses a deep learning model (DNNs) we have built inside TensorFlow and supports up to 100 classes.

For instantiated/pretrained models, see ClassifierDLModel.

Notes:

For extended examples of usage, see the Spark NLP Workshop [1] [2] and the ClassifierDLTestSpec.

Example

In this example, the training data "sentiment.csv" has the form of

text,label
This movie is the best movie I have wached ever! In my opinion this movie can win an award.,0
This was a terrible movie! The acting was bad really bad!,1
...

Then traning can be done like so:

import com.johnsnowlabs.nlp.base.DocumentAssembler
import com.johnsnowlabs.nlp.embeddings.UniversalSentenceEncoder
import com.johnsnowlabs.nlp.annotators.classifier.dl.ClassifierDLApproach
import org.apache.spark.ml.Pipeline

val smallCorpus = spark.read.option("header","true").csv("src/test/resources/classifier/sentiment.csv")

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

val useEmbeddings = UniversalSentenceEncoder.pretrained()
  .setInputCols("document")
  .setOutputCol("sentence_embeddings")

val docClassifier = new ClassifierDLApproach()
  .setInputCols("sentence_embeddings")
  .setOutputCol("category")
  .setLabelColumn("label")
  .setBatchSize(64)
  .setMaxEpochs(20)
  .setLr(5e-3f)
  .setDropout(0.5f)

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

val pipelineModel = pipeline.fit(smallCorpus)
See also

SentimentDLApproach for sentiment analysis

MultiClassifierDLApproach for multi-class classification

Linear Supertypes
ParamsAndFeaturesWritable, HasFeatures, AnnotatorApproach[ClassifierDLModel], CanBeLazy, DefaultParamsWritable, MLWritable, HasOutputAnnotatorType, HasOutputAnnotationCol, HasInputAnnotationCols, Estimator[ClassifierDLModel], PipelineStage, Logging, Params, Serializable, Serializable, Identifiable, AnyRef, Any
Ordering
  1. Grouped
  2. Alphabetic
  3. By Inheritance
Inherited
  1. ClassifierDLApproach
  2. ParamsAndFeaturesWritable
  3. HasFeatures
  4. AnnotatorApproach
  5. CanBeLazy
  6. DefaultParamsWritable
  7. MLWritable
  8. HasOutputAnnotatorType
  9. HasOutputAnnotationCol
  10. HasInputAnnotationCols
  11. Estimator
  12. PipelineStage
  13. Logging
  14. Params
  15. Serializable
  16. Serializable
  17. Identifiable
  18. AnyRef
  19. Any
  1. Hide All
  2. Show All
Visibility
  1. Public
  2. All

Instance Constructors

  1. new ClassifierDLApproach()

    Permalink
  2. new ClassifierDLApproach(uid: String)

    Permalink

Type Members

  1. type AnnotatorType = String

    Permalink
    Definition Classes
    HasOutputAnnotatorType

Value Members

  1. final def !=(arg0: Any): Boolean

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

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

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

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

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

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

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

    Permalink
    Definition Classes
    AnyRef → Any
  9. def _fit(dataset: Dataset[_], recursiveStages: Option[PipelineModel]): ClassifierDLModel

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

    Permalink
    Definition Classes
    Any
  11. val batchSize: IntParam

    Permalink

    Batch size (Default: 64)

  12. def beforeTraining(spark: SparkSession): Unit

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

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

    Permalink
    Definition Classes
    Params
  15. def clone(): AnyRef

    Permalink
    Attributes
    protected[java.lang]
    Definition Classes
    AnyRef
    Annotations
    @throws( ... )
  16. val configProtoBytes: IntArrayParam

    Permalink

    ConfigProto from tensorflow, serialized into byte array.

    ConfigProto from tensorflow, serialized into byte array. Get with config_proto.SerializeToString()

  17. final def copy(extra: ParamMap): Estimator[ClassifierDLModel]

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

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

    Permalink
    Attributes
    protected
    Definition Classes
    Params
  20. val description: String

    Permalink

    Trains TensorFlow model for multi-class text classification

    Trains TensorFlow model for multi-class text classification

    Definition Classes
    ClassifierDLApproachAnnotatorApproach
  21. val dropout: FloatParam

    Permalink

    Dropout coefficient (Default: 0.5f)

  22. val enableOutputLogs: BooleanParam

    Permalink

    Whether to output to annotators log folder (Default: false)

  23. final def eq(arg0: AnyRef): Boolean

    Permalink
    Definition Classes
    AnyRef
  24. def equals(arg0: Any): Boolean

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

    Permalink
    Definition Classes
    Params
  26. def explainParams(): String

    Permalink
    Definition Classes
    Params
  27. final def extractParamMap(): ParamMap

    Permalink
    Definition Classes
    Params
  28. final def extractParamMap(extra: ParamMap): ParamMap

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

    Permalink
    Definition Classes
    HasFeatures
  30. def finalize(): Unit

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

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

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

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

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

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

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

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

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

    Permalink
    Definition Classes
    Params
  40. def getBatchSize: Int

    Permalink

    Batch size (Default: 64)

  41. final def getClass(): Class[_]

    Permalink
    Definition Classes
    AnyRef → Any
  42. def getConfigProtoBytes: Option[Array[Byte]]

    Permalink

    Tensorflow config Protobytes passed to the TF session

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

    Permalink
    Definition Classes
    Params
  44. def getDropout: Float

    Permalink

    Dropout coefficient (Default: 0.5f)

  45. def getEnableOutputLogs: Boolean

    Permalink

    Whether to output to annotators log folder (Default: false)

  46. def getInputCols: Array[String]

    Permalink

    returns

    input annotations columns currently used

    Definition Classes
    HasInputAnnotationCols
  47. def getLabelColumn: String

    Permalink

    Column with label per each document

  48. def getLazyAnnotator: Boolean

    Permalink
    Definition Classes
    CanBeLazy
  49. def getLr: Float

    Permalink

    Learning Rate (Default: 5e-3f)

  50. def getMaxEpochs: Int

    Permalink

    Maximum number of epochs to train (Default: 10)

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

    Permalink
    Definition Classes
    Params
  52. final def getOutputCol: String

    Permalink

    Gets annotation column name going to generate

    Gets annotation column name going to generate

    Definition Classes
    HasOutputAnnotationCol
  53. def getOutputLogsPath: String

    Permalink

    Folder path to save training logs (Default: "")

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

    Permalink
    Definition Classes
    Params
  55. def getRandomSeed: Int

    Permalink

    Random seed

  56. def getValidationSplit: Float

    Permalink

    Choose the proportion of training dataset to be validated against the model on each Epoch (Default: 0.0f).

    Choose the proportion of training dataset to be validated against the model on each Epoch (Default: 0.0f). The value should be between 0.0 and 1.0 and by default it is 0.0 and off.

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

    Permalink
    Definition Classes
    Params
  58. def hasParam(paramName: String): Boolean

    Permalink
    Definition Classes
    Params
  59. def hashCode(): Int

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

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

    Permalink
    Attributes
    protected
    Definition Classes
    Logging
  62. val inputAnnotatorTypes: Array[AnnotatorType]

    Permalink

    Input annotator type : SENTENCE_EMBEDDINGS

    Input annotator type : SENTENCE_EMBEDDINGS

    Definition Classes
    ClassifierDLApproachHasInputAnnotationCols
  63. final val inputCols: StringArrayParam

    Permalink

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

    Permalink
    Definition Classes
    Params
  65. final def isInstanceOf[T0]: Boolean

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

    Permalink
    Definition Classes
    Params
  67. def isTraceEnabled(): Boolean

    Permalink
    Attributes
    protected
    Definition Classes
    Logging
  68. val labelColumn: Param[String]

    Permalink

    Column with label per each document

  69. val lazyAnnotator: BooleanParam

    Permalink
    Definition Classes
    CanBeLazy
  70. def loadSavedModel(): TensorflowWrapper

    Permalink
  71. def log: Logger

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

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

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

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

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

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

    Permalink
    Attributes
    protected
    Definition Classes
    Logging
  78. def logName: String

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

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

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

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

    Permalink
    Attributes
    protected
    Definition Classes
    Logging
  83. val lr: FloatParam

    Permalink

    Learning Rate (Default: 5e-3f)

  84. val maxEpochs: IntParam

    Permalink

    Maximum number of epochs to train (Default: 10)

  85. def msgHelper(schema: StructType): String

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

    Permalink
    Definition Classes
    AnyRef
  87. final def notify(): Unit

    Permalink
    Definition Classes
    AnyRef
  88. final def notifyAll(): Unit

    Permalink
    Definition Classes
    AnyRef
  89. def onTrained(model: ClassifierDLModel, spark: SparkSession): Unit

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

    Permalink
    Attributes
    protected
    Definition Classes
    ParamsAndFeaturesWritable
  91. val optionalInputAnnotatorTypes: Array[String]

    Permalink
    Definition Classes
    HasInputAnnotationCols
  92. val outputAnnotatorType: String

    Permalink

    Output annotator type : CATEGORY

    Output annotator type : CATEGORY

    Definition Classes
    ClassifierDLApproachHasOutputAnnotatorType
  93. final val outputCol: Param[String]

    Permalink
    Attributes
    protected
    Definition Classes
    HasOutputAnnotationCol
  94. val outputLogsPath: Param[String]

    Permalink

    Folder path to save training logs (Default: "")

  95. lazy val params: Array[Param[_]]

    Permalink
    Definition Classes
    Params
  96. val randomSeed: IntParam

    Permalink

    Random seed for shuffling the dataset

  97. def save(path: String): Unit

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

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

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

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

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

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

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

    Permalink
    Definition Classes
    Params
  105. def setBatchSize(batch: Int): ClassifierDLApproach.this.type

    Permalink

    Batch size (Default: 64)

  106. def setConfigProtoBytes(bytes: Array[Int]): ClassifierDLApproach.this.type

    Permalink

    Tensorflow config Protobytes passed to the TF session

  107. def setDefault[T](feature: StructFeature[T], value: () ⇒ T): ClassifierDLApproach.this.type

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

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

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

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

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

    Permalink
    Attributes
    protected
    Definition Classes
    Params
  113. def setDropout(dropout: Float): ClassifierDLApproach.this.type

    Permalink

    Dropout coefficient (Default: 0.5f)

  114. def setEnableOutputLogs(enableOutputLogs: Boolean): ClassifierDLApproach.this.type

    Permalink

    Whether to output to annotators log folder (Default: false)

  115. final def setInputCols(value: String*): ClassifierDLApproach.this.type

    Permalink
    Definition Classes
    HasInputAnnotationCols
  116. def setInputCols(value: Array[String]): ClassifierDLApproach.this.type

    Permalink

    Overrides required annotators column if different than default

    Overrides required annotators column if different than default

    Definition Classes
    HasInputAnnotationCols
  117. def setLabelColumn(column: String): ClassifierDLApproach.this.type

    Permalink

    Column with label per each document

  118. def setLazyAnnotator(value: Boolean): ClassifierDLApproach.this.type

    Permalink
    Definition Classes
    CanBeLazy
  119. def setLr(lr: Float): ClassifierDLApproach.this.type

    Permalink

    Learning Rate (Default: 5e-3f)

  120. def setMaxEpochs(epochs: Int): ClassifierDLApproach.this.type

    Permalink

    Maximum number of epochs to train (Default: 10)

  121. final def setOutputCol(value: String): ClassifierDLApproach.this.type

    Permalink

    Overrides annotation column name when transforming

    Overrides annotation column name when transforming

    Definition Classes
    HasOutputAnnotationCol
  122. def setOutputLogsPath(path: String): ClassifierDLApproach.this.type

    Permalink

    Folder path to save training logs (Default: "")

  123. def setRandomSeed(seed: Int): ClassifierDLApproach.this.type

    Permalink

    Random seed

  124. def setValidationSplit(validationSplit: Float): ClassifierDLApproach.this.type

    Permalink

    Choose the proportion of training dataset to be validated against the model on each Epoch (Default: 0.0f).

    Choose the proportion of training dataset to be validated against the model on each Epoch (Default: 0.0f). The value should be between 0.0 and 1.0 and by default it is 0.0 and off.

  125. def setVerbose(verbose: Level): ClassifierDLApproach.this.type

    Permalink

    Level of verbosity during training (Default: Verbose.Silent.id)

  126. def setVerbose(verbose: Int): ClassifierDLApproach.this.type

    Permalink

    Level of verbosity during training (Default: Verbose.Silent.id)

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

    Permalink
    Definition Classes
    AnyRef
  128. def toString(): String

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

    Permalink
  130. final def transformSchema(schema: StructType): StructType

    Permalink

    requirement for pipeline transformation validation.

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

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

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

    Permalink
    Definition Classes
    ClassifierDLApproach → Identifiable
  133. def validate(schema: StructType): Boolean

    Permalink

    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
  134. val validationSplit: FloatParam

    Permalink

    Choose the proportion of training dataset to be validated against the model on each Epoch (Default: 0.0f).

    Choose the proportion of training dataset to be validated against the model on each Epoch (Default: 0.0f). The value should be between 0.0 and 1.0 and by default it is 0.0 and off.

  135. val verbose: IntParam

    Permalink

    Level of verbosity during training (Default: Verbose.Silent.id)

  136. final def wait(): Unit

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

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

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

    Permalink
    Definition Classes
    ParamsAndFeaturesWritable → DefaultParamsWritable → MLWritable

Inherited from ParamsAndFeaturesWritable

Inherited from HasFeatures

Inherited from CanBeLazy

Inherited from DefaultParamsWritable

Inherited from MLWritable

Inherited from HasOutputAnnotatorType

Inherited from HasOutputAnnotationCol

Inherited from HasInputAnnotationCols

Inherited from Estimator[ClassifierDLModel]

Inherited from PipelineStage

Inherited from Logging

Inherited from Params

Inherited from Serializable

Inherited from Serializable

Inherited from Identifiable

Inherited from AnyRef

Inherited from Any

Parameters

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

Annotator types

Required input and expected output annotator types

Members

Parameter setters

Parameter getters