class DocumentSimilarityRankerApproach extends AnnotatorApproach[DocumentSimilarityRankerModel] with HasEnableCachingProperties

Annotator that uses LSH techniques present in Spark ML lib to execute approximate nearest neighbors search on top of sentence embeddings.

It aims to capture the semantic meaning of a document in a dense, continuous vector space and return it to the ranker search.

For instantiated/pretrained models, see DocumentSimilarityRankerModel.

For extended examples of usage, see the jupyter notebook Document Similarity Ranker for Spark NLP.

Example

import com.johnsnowlabs.nlp.base._
import com.johnsnowlabs.nlp.annotator._
import com.johnsnowlabs.nlp.annotators.similarity.DocumentSimilarityRankerApproach
import com.johnsnowlabs.nlp.finisher.DocumentSimilarityRankerFinisher
import org.apache.spark.ml.Pipeline

import spark.implicits._

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

val sentenceEmbeddings = RoBertaSentenceEmbeddings
  .pretrained()
  .setInputCols("document")
  .setOutputCol("sentence_embeddings")

val documentSimilarityRanker = new DocumentSimilarityRankerApproach()
  .setInputCols("sentence_embeddings")
  .setOutputCol("doc_similarity_rankings")
  .setSimilarityMethod("brp")
  .setNumberOfNeighbours(1)
  .setBucketLength(2.0)
  .setNumHashTables(3)
  .setVisibleDistances(true)
  .setIdentityRanking(false)

val documentSimilarityRankerFinisher = new DocumentSimilarityRankerFinisher()
  .setInputCols("doc_similarity_rankings")
  .setOutputCols(
    "finished_doc_similarity_rankings_id",
    "finished_doc_similarity_rankings_neighbors")
  .setExtractNearestNeighbor(true)

// Let's use a dataset where we can visually control similarity
// Documents are coupled, as 1-2, 3-4, 5-6, 7-8 and they were create to be similar on purpose
val data = Seq(
  "First document, this is my first sentence. This is my second sentence.",
  "Second document, this is my second sentence. This is my second sentence.",
  "Third document, climate change is arguably one of the most pressing problems of our time.",
  "Fourth document, climate change is definitely one of the most pressing problems of our time.",
  "Fifth document, Florence in Italy, is among the most beautiful cities in Europe.",
  "Sixth document, Florence in Italy, is a very beautiful city in Europe like Lyon in France.",
  "Seventh document, the French Riviera is the Mediterranean coastline of the southeast corner of France.",
  "Eighth document, the warmest place in France is the French Riviera coast in Southern France.")
  .toDF("text")

val pipeline = new Pipeline().setStages(
  Array(
    documentAssembler,
    sentenceEmbeddings,
    documentSimilarityRanker,
    documentSimilarityRankerFinisher))

val result = pipeline.fit(data).transform(data)

result
  .select("finished_doc_similarity_rankings_id", "finished_doc_similarity_rankings_neighbors")
  .show(10, truncate = false)
+-----------------------------------+------------------------------------------+
|finished_doc_similarity_rankings_id|finished_doc_similarity_rankings_neighbors|
+-----------------------------------+------------------------------------------+
|1510101612                         |[(1634839239,0.12448559591306324)]        |
|1634839239                         |[(1510101612,0.12448559591306324)]        |
|-612640902                         |[(1274183715,0.1220122862046063)]         |
|1274183715                         |[(-612640902,0.1220122862046063)]         |
|-1320876223                        |[(1293373212,0.17848855164122393)]        |
|1293373212                         |[(-1320876223,0.17848855164122393)]       |
|-1548374770                        |[(-1719102856,0.23297156732534166)]       |
|-1719102856                        |[(-1548374770,0.23297156732534166)]       |
+-----------------------------------+------------------------------------------+
Linear Supertypes
HasEnableCachingProperties, ParamsAndFeaturesWritable, HasFeatures, AnnotatorApproach[DocumentSimilarityRankerModel], CanBeLazy, DefaultParamsWritable, MLWritable, HasOutputAnnotatorType, HasOutputAnnotationCol, HasInputAnnotationCols, Estimator[DocumentSimilarityRankerModel], PipelineStage, Logging, Params, Serializable, Serializable, Identifiable, AnyRef, Any
Ordering
  1. Grouped
  2. Alphabetic
  3. By Inheritance
Inherited
  1. DocumentSimilarityRankerApproach
  2. HasEnableCachingProperties
  3. ParamsAndFeaturesWritable
  4. HasFeatures
  5. AnnotatorApproach
  6. CanBeLazy
  7. DefaultParamsWritable
  8. MLWritable
  9. HasOutputAnnotatorType
  10. HasOutputAnnotationCol
  11. HasInputAnnotationCols
  12. Estimator
  13. PipelineStage
  14. Logging
  15. Params
  16. Serializable
  17. Serializable
  18. Identifiable
  19. AnyRef
  20. Any
  1. Hide All
  2. Show All
Visibility
  1. Public
  2. All

Instance Constructors

  1. new DocumentSimilarityRankerApproach()

    Annotator reference id.

    Annotator reference id. Used to identify elements in metadata or to refer to this annotator type

  2. new DocumentSimilarityRankerApproach(uid: String)

    uid

    required uid for storing annotator to disk

Type Members

  1. type AnnotatorType = String
    Definition Classes
    HasOutputAnnotatorType

Value Members

  1. final def !=(arg0: Any): Boolean
    Definition Classes
    AnyRef → Any
  2. final def ##(): Int
    Definition Classes
    AnyRef → Any
  3. final def $[T](param: Param[T]): T
    Attributes
    protected
    Definition Classes
    Params
  4. def $$[T](feature: StructFeature[T]): T
    Attributes
    protected
    Definition Classes
    HasFeatures
  5. def $$[K, V](feature: MapFeature[K, V]): Map[K, V]
    Attributes
    protected
    Definition Classes
    HasFeatures
  6. def $$[T](feature: SetFeature[T]): Set[T]
    Attributes
    protected
    Definition Classes
    HasFeatures
  7. def $$[T](feature: ArrayFeature[T]): Array[T]
    Attributes
    protected
    Definition Classes
    HasFeatures
  8. final def ==(arg0: Any): Boolean
    Definition Classes
    AnyRef → Any
  9. val DISTANCE: String
  10. val INDEX_COL_NAME: String
  11. val LSH_INPUT_COL_NAME: String
  12. val LSH_OUTPUT_COL_NAME: String
  13. val TEXT: String
  14. def _fit(dataset: Dataset[_], recursiveStages: Option[PipelineModel]): DocumentSimilarityRankerModel
    Attributes
    protected
    Definition Classes
    AnnotatorApproach
  15. val aggregationMethod: Param[String]

    Specifies the method used to aggregate multiple sentence embeddings into a single vector representation.

    Specifies the method used to aggregate multiple sentence embeddings into a single vector representation. Options include 'AVERAGE' (compute the mean of all embeddings), 'FIRST' (use the first embedding only), 'MAX' (compute the element-wise maximum across embeddings)

    Default AVERAGE

  16. final def asInstanceOf[T0]: T0
    Definition Classes
    Any
  17. def asRetriever(value: String): DocumentSimilarityRankerApproach.this.type
  18. val asRetrieverQuery: Param[String]
  19. def beforeTraining(spark: SparkSession): Unit
    Definition Classes
    AnnotatorApproach
  20. val bucketLength: Param[Double]
  21. final def checkSchema(schema: StructType, inputAnnotatorType: String): Boolean
    Attributes
    protected
    Definition Classes
    HasInputAnnotationCols
  22. final def clear(param: Param[_]): DocumentSimilarityRankerApproach.this.type
    Definition Classes
    Params
  23. def clone(): AnyRef
    Attributes
    protected[lang]
    Definition Classes
    AnyRef
    Annotations
    @throws( ... ) @native()
  24. final def copy(extra: ParamMap): Estimator[DocumentSimilarityRankerModel]
    Definition Classes
    AnnotatorApproach → Estimator → PipelineStage → Params
  25. def copyValues[T <: Params](to: T, extra: ParamMap): T
    Attributes
    protected
    Definition Classes
    Params
  26. final def defaultCopy[T <: Params](extra: ParamMap): T
    Attributes
    protected
    Definition Classes
    Params
  27. val description: AnnotatorType
    Definition Classes
    DocumentSimilarityRankerApproach → AnnotatorApproach
  28. val enableCaching: BooleanParam

    Whether to enable caching DataFrames or RDDs during the training

    Whether to enable caching DataFrames or RDDs during the training

    Definition Classes
    HasEnableCachingProperties
  29. final def eq(arg0: AnyRef): Boolean
    Definition Classes
    AnyRef
  30. def equals(arg0: Any): Boolean
    Definition Classes
    AnyRef → Any
  31. def explainParam(param: Param[_]): String
    Definition Classes
    Params
  32. def explainParams(): String
    Definition Classes
    Params
  33. final def extractParamMap(): ParamMap
    Definition Classes
    Params
  34. final def extractParamMap(extra: ParamMap): ParamMap
    Definition Classes
    Params
  35. val features: ArrayBuffer[Feature[_, _, _]]
    Definition Classes
    HasFeatures
  36. def finalize(): Unit
    Attributes
    protected[lang]
    Definition Classes
    AnyRef
    Annotations
    @throws( classOf[java.lang.Throwable] )
  37. final def fit(dataset: Dataset[_]): DocumentSimilarityRankerModel
    Definition Classes
    AnnotatorApproach → Estimator
  38. def fit(dataset: Dataset[_], paramMaps: Seq[ParamMap]): Seq[DocumentSimilarityRankerModel]
    Definition Classes
    Estimator
    Annotations
    @Since( "2.0.0" )
  39. def fit(dataset: Dataset[_], paramMap: ParamMap): DocumentSimilarityRankerModel
    Definition Classes
    Estimator
    Annotations
    @Since( "2.0.0" )
  40. def fit(dataset: Dataset[_], firstParamPair: ParamPair[_], otherParamPairs: ParamPair[_]*): DocumentSimilarityRankerModel
    Definition Classes
    Estimator
    Annotations
    @Since( "2.0.0" ) @varargs()
  41. def get[T](feature: StructFeature[T]): Option[T]
    Attributes
    protected
    Definition Classes
    HasFeatures
  42. def get[K, V](feature: MapFeature[K, V]): Option[Map[K, V]]
    Attributes
    protected
    Definition Classes
    HasFeatures
  43. def get[T](feature: SetFeature[T]): Option[Set[T]]
    Attributes
    protected
    Definition Classes
    HasFeatures
  44. def get[T](feature: ArrayFeature[T]): Option[Array[T]]
    Attributes
    protected
    Definition Classes
    HasFeatures
  45. final def get[T](param: Param[T]): Option[T]
    Definition Classes
    Params
  46. def getAggregationMethod: String
  47. def getAsRetrieverQuery: String
  48. def getBucketLength: Double
  49. final def getClass(): Class[_]
    Definition Classes
    AnyRef → Any
    Annotations
    @native()
  50. final def getDefault[T](param: Param[T]): Option[T]
    Definition Classes
    Params
  51. def getEnableCaching: Boolean

    Definition Classes
    HasEnableCachingProperties
  52. def getIdentityRanking: Boolean
  53. def getInputCols: Array[String]

    returns

    input annotations columns currently used

    Definition Classes
    HasInputAnnotationCols
  54. def getLazyAnnotator: Boolean
    Definition Classes
    CanBeLazy
  55. def getNeighborsResultSet(query: (Int, Vector), similarityDataset: DataFrame): NeighborsResultSet
  56. def getNumberOfNeighbours: Int
  57. final def getOrDefault[T](param: Param[T]): T
    Definition Classes
    Params
  58. final def getOutputCol: String

    Gets annotation column name going to generate

    Gets annotation column name going to generate

    Definition Classes
    HasOutputAnnotationCol
  59. def getParam(paramName: String): Param[Any]
    Definition Classes
    Params
  60. def getSimilarityMethod: String
  61. def getVisibleDistances: Boolean
  62. final def hasDefault[T](param: Param[T]): Boolean
    Definition Classes
    Params
  63. def hasParam(paramName: String): Boolean
    Definition Classes
    Params
  64. def hashCode(): Int
    Definition Classes
    AnyRef → Any
    Annotations
    @native()
  65. val identityRanking: BooleanParam
  66. def initializeLogIfNecessary(isInterpreter: Boolean, silent: Boolean): Boolean
    Attributes
    protected
    Definition Classes
    Logging
  67. def initializeLogIfNecessary(isInterpreter: Boolean): Unit
    Attributes
    protected
    Definition Classes
    Logging
  68. 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
    DocumentSimilarityRankerApproach → HasInputAnnotationCols
  69. 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
  70. final def isDefined(param: Param[_]): Boolean
    Definition Classes
    Params
  71. final def isInstanceOf[T0]: Boolean
    Definition Classes
    Any
  72. final def isSet(param: Param[_]): Boolean
    Definition Classes
    Params
  73. def isTraceEnabled(): Boolean
    Attributes
    protected
    Definition Classes
    Logging
  74. val lazyAnnotator: BooleanParam
    Definition Classes
    CanBeLazy
  75. def log: Logger
    Attributes
    protected
    Definition Classes
    Logging
  76. def logDebug(msg: ⇒ String, throwable: Throwable): Unit
    Attributes
    protected
    Definition Classes
    Logging
  77. def logDebug(msg: ⇒ String): Unit
    Attributes
    protected
    Definition Classes
    Logging
  78. def logError(msg: ⇒ String, throwable: Throwable): Unit
    Attributes
    protected
    Definition Classes
    Logging
  79. def logError(msg: ⇒ String): Unit
    Attributes
    protected
    Definition Classes
    Logging
  80. def logInfo(msg: ⇒ String, throwable: Throwable): Unit
    Attributes
    protected
    Definition Classes
    Logging
  81. def logInfo(msg: ⇒ String): Unit
    Attributes
    protected
    Definition Classes
    Logging
  82. def logName: String
    Attributes
    protected
    Definition Classes
    Logging
  83. def logTrace(msg: ⇒ String, throwable: Throwable): Unit
    Attributes
    protected
    Definition Classes
    Logging
  84. def logTrace(msg: ⇒ String): Unit
    Attributes
    protected
    Definition Classes
    Logging
  85. def logWarning(msg: ⇒ String, throwable: Throwable): Unit
    Attributes
    protected
    Definition Classes
    Logging
  86. def logWarning(msg: ⇒ String): Unit
    Attributes
    protected
    Definition Classes
    Logging
  87. def msgHelper(schema: StructType): String
    Attributes
    protected
    Definition Classes
    HasInputAnnotationCols
  88. final def ne(arg0: AnyRef): Boolean
    Definition Classes
    AnyRef
  89. final def notify(): Unit
    Definition Classes
    AnyRef
    Annotations
    @native()
  90. final def notifyAll(): Unit
    Definition Classes
    AnyRef
    Annotations
    @native()
  91. val numHashTables: Param[Int]
  92. val numberOfNeighbours: Param[Int]

    The number of neighbours the model will return (Default:"10").

  93. def onTrained(model: DocumentSimilarityRankerModel, spark: SparkSession): Unit
    Definition Classes
    AnnotatorApproach
  94. def onWrite(path: String, spark: SparkSession): Unit
    Attributes
    protected
    Definition Classes
    ParamsAndFeaturesWritable
  95. val optionalInputAnnotatorTypes: Array[String]
    Definition Classes
    HasInputAnnotationCols
  96. val outputAnnotatorType: AnnotatorType
    Definition Classes
    DocumentSimilarityRankerApproach → HasOutputAnnotatorType
  97. final val outputCol: Param[String]
    Attributes
    protected
    Definition Classes
    HasOutputAnnotationCol
  98. lazy val params: Array[Param[_]]
    Definition Classes
    Params
  99. def save(path: String): Unit
    Definition Classes
    MLWritable
    Annotations
    @Since( "1.6.0" ) @throws( ... )
  100. def set[T](feature: StructFeature[T], value: T): DocumentSimilarityRankerApproach.this.type
    Attributes
    protected
    Definition Classes
    HasFeatures
  101. def set[K, V](feature: MapFeature[K, V], value: Map[K, V]): DocumentSimilarityRankerApproach.this.type
    Attributes
    protected
    Definition Classes
    HasFeatures
  102. def set[T](feature: SetFeature[T], value: Set[T]): DocumentSimilarityRankerApproach.this.type
    Attributes
    protected
    Definition Classes
    HasFeatures
  103. def set[T](feature: ArrayFeature[T], value: Array[T]): DocumentSimilarityRankerApproach.this.type
    Attributes
    protected
    Definition Classes
    HasFeatures
  104. final def set(paramPair: ParamPair[_]): DocumentSimilarityRankerApproach.this.type
    Attributes
    protected
    Definition Classes
    Params
  105. final def set(param: String, value: Any): DocumentSimilarityRankerApproach.this.type
    Attributes
    protected
    Definition Classes
    Params
  106. final def set[T](param: Param[T], value: T): DocumentSimilarityRankerApproach.this.type
    Definition Classes
    Params
  107. def setAggregationMethod(strategy: String): DocumentSimilarityRankerApproach.this.type

    Set the method used to aggregate multiple sentence embeddings into a single vector representation.

    Set the method used to aggregate multiple sentence embeddings into a single vector representation. Options include 'AVERAGE' (compute the mean of all embeddings), 'FIRST' (use the first embedding only), 'MAX' (compute the element-wise maximum across embeddings)

    Default AVERAGE

  108. def setBucketLength(value: Double): DocumentSimilarityRankerApproach.this.type
  109. def setDefault[T](feature: StructFeature[T], value: () ⇒ T): DocumentSimilarityRankerApproach.this.type
    Attributes
    protected
    Definition Classes
    HasFeatures
  110. def setDefault[K, V](feature: MapFeature[K, V], value: () ⇒ Map[K, V]): DocumentSimilarityRankerApproach.this.type
    Attributes
    protected
    Definition Classes
    HasFeatures
  111. def setDefault[T](feature: SetFeature[T], value: () ⇒ Set[T]): DocumentSimilarityRankerApproach.this.type
    Attributes
    protected
    Definition Classes
    HasFeatures
  112. def setDefault[T](feature: ArrayFeature[T], value: () ⇒ Array[T]): DocumentSimilarityRankerApproach.this.type
    Attributes
    protected
    Definition Classes
    HasFeatures
  113. final def setDefault(paramPairs: ParamPair[_]*): DocumentSimilarityRankerApproach.this.type
    Attributes
    protected
    Definition Classes
    Params
  114. final def setDefault[T](param: Param[T], value: T): DocumentSimilarityRankerApproach.this.type
    Attributes
    protected[org.apache.spark.ml]
    Definition Classes
    Params
  115. def setEnableCaching(value: Boolean): DocumentSimilarityRankerApproach.this.type

    Definition Classes
    HasEnableCachingProperties
  116. def setIdentityRanking(value: Boolean): DocumentSimilarityRankerApproach.this.type
  117. final def setInputCols(value: String*): DocumentSimilarityRankerApproach.this.type
    Definition Classes
    HasInputAnnotationCols
  118. def setInputCols(value: Array[String]): DocumentSimilarityRankerApproach.this.type

    Overrides required annotators column if different than default

    Overrides required annotators column if different than default

    Definition Classes
    HasInputAnnotationCols
  119. def setLazyAnnotator(value: Boolean): DocumentSimilarityRankerApproach.this.type
    Definition Classes
    CanBeLazy
  120. def setNumHashTables(value: Int): DocumentSimilarityRankerApproach.this.type
  121. def setNumberOfNeighbours(value: Int): DocumentSimilarityRankerApproach.this.type
  122. final def setOutputCol(value: String): DocumentSimilarityRankerApproach.this.type

    Overrides annotation column name when transforming

    Overrides annotation column name when transforming

    Definition Classes
    HasOutputAnnotationCol
  123. def setSimilarityMethod(value: String): DocumentSimilarityRankerApproach.this.type
  124. def setVisibleDistances(value: Boolean): DocumentSimilarityRankerApproach.this.type
  125. val similarityMethod: Param[String]

    The similarity method used to calculate the neighbours.

    The similarity method used to calculate the neighbours. (Default: "brp", Bucketed Random Projection for Euclidean Distance)

  126. final def synchronized[T0](arg0: ⇒ T0): T0
    Definition Classes
    AnyRef
  127. def toString(): String
    Definition Classes
    Identifiable → AnyRef → Any
  128. def train(embeddingsDataset: Dataset[_], recursivePipeline: Option[PipelineModel]): DocumentSimilarityRankerModel
    Definition Classes
    DocumentSimilarityRankerApproach → AnnotatorApproach
  129. 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
  130. def transformSchema(schema: StructType, logging: Boolean): StructType
    Attributes
    protected
    Definition Classes
    PipelineStage
    Annotations
    @DeveloperApi()
  131. val uid: String
    Definition Classes
    DocumentSimilarityRankerApproach → Identifiable
  132. 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
  133. val visibleDistances: BooleanParam
  134. final def wait(): Unit
    Definition Classes
    AnyRef
    Annotations
    @throws( ... )
  135. final def wait(arg0: Long, arg1: Int): Unit
    Definition Classes
    AnyRef
    Annotations
    @throws( ... )
  136. final def wait(arg0: Long): Unit
    Definition Classes
    AnyRef
    Annotations
    @throws( ... ) @native()
  137. def write: MLWriter
    Definition Classes
    ParamsAndFeaturesWritable → DefaultParamsWritable → MLWritable

Inherited from HasEnableCachingProperties

Inherited from ParamsAndFeaturesWritable

Inherited from HasFeatures

Inherited from AnnotatorApproach[DocumentSimilarityRankerModel]

Inherited from CanBeLazy

Inherited from DefaultParamsWritable

Inherited from MLWritable

Inherited from HasOutputAnnotatorType

Inherited from HasOutputAnnotationCol

Inherited from HasInputAnnotationCols

Inherited from Estimator[DocumentSimilarityRankerModel]

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.

Members

Parameter setters

Parameter getters