spark-nlp 4.2.6__py2.py3-none-any.whl → 6.2.1__py2.py3-none-any.whl

sparknlp/annotator/seq2seq/t5_transformer.py

@@ -39,10 +39,10 @@ class T5Transformer(AnnotatorModel, HasBatchedAnnotate, HasEngine):
 
     The default model is ``"t5_small"``, if no name is provided. For available
     pretrained models please see the `Models Hub
-    <https://nlp.johnsnowlabs.com/models?q=t5>`__.
+    <https://sparknlp.org/models?q=t5>`__.
 
-    For extended examples of usage, see the `Spark NLP Workshop
-    <https://github.com/JohnSnowLabs/spark-nlp-workshop/blob/master/tutorials/Certification_Trainings/Public/10.Question_Answering_and_Summarization_with_T5.ipynb>`__.
+    For extended examples of usage, see the `Examples
+    <https://github.com/JohnSnowLabs/spark-nlp/blob/master/examples/python/annotation/text/english/question-answering/Question_Answering_and_Summarization_with_T5.ipynb>`__.
 
     ====================== ======================
     Input Annotation types Output Annotation type
@@ -191,6 +191,23 @@ class T5Transformer(AnnotatorModel, HasBatchedAnnotate, HasEngine):
                            "A list of token ids which are ignored in the decoder's output",
                            typeConverter=TypeConverters.toListInt)
 
+    useCache = Param(Params._dummy(), "useCache", "Cache internal state of the model to improve performance",
+                     typeConverter=TypeConverters.toBoolean)
+
+    stopAtEos = Param(
+        Params._dummy(),
+        "stopAtEos",
+        "Stop text generation when the end-of-sentence token is encountered.",
+        typeConverter=TypeConverters.toBoolean
+    )
+
+    maxNewTokens = Param(
+        Params._dummy(),
+        "maxNewTokens",
+        "Maximum number of new tokens to be generated",
+        typeConverter=TypeConverters.toInt
+    )
+
     def setIgnoreTokenIds(self, value):
         """A list of token ids which are ignored in the decoder's output.
 
@@ -241,6 +258,26 @@ class T5Transformer(AnnotatorModel, HasBatchedAnnotate, HasEngine):
         """
         return self._set(maxOutputLength=value)
 
+    def setStopAtEos(self, b):
+        """Stop text generation when the end-of-sentence token is encountered.
+
+        Parameters
+        ----------
+        b : bool
+            whether to stop at end-of-sentence token or not
+        """
+        return self._set(stopAtEos=b)
+
+    def setMaxNewTokens(self, value):
+        """Sets the maximum number of new tokens to be generated
+
+        Parameters
+        ----------
+        value : int
+            the maximum number of new tokens to be generated
+        """
+        return self._set(maxNewTokens=value)
+
     def setDoSample(self, value):
         """Sets whether or not to use sampling, use greedy decoding otherwise.
 
@@ -312,6 +349,16 @@ class T5Transformer(AnnotatorModel, HasBatchedAnnotate, HasEngine):
         """
         return self._set(noRepeatNgramSize=value)
 
+    def setUseCache(self, value):
+        """Cache internal state of the model to improve performance
+
+        Parameters
+        ----------
+        value : bool
+            Whether or not to use cache
+        """
+        return self._set(useCache=value)
+
     @keyword_only
     def __init__(self, classname="com.johnsnowlabs.nlp.annotators.seq2seq.T5Transformer", java_model=None):
         super(T5Transformer, self).__init__(
@@ -329,7 +376,10 @@ class T5Transformer(AnnotatorModel, HasBatchedAnnotate, HasEngine):
             repetitionPenalty=1.0,
             noRepeatNgramSize=0,
             ignoreTokenIds=[],
-            batchSize=1
+            batchSize=1,
+            stopAtEos=True,
+            maxNewTokens=512,
+            useCache=False
         )
 
     @staticmethod

sparknlp/annotator/similarity/document_similarity_ranker.py

@@ -0,0 +1,379 @@
+#  Copyright 2017-2023 John Snow Labs
+#
+#  Licensed under the Apache License, Version 2.0 (the "License");
+#  you may not use this file except in compliance with the License.
+#  You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+#  Unless required by applicable law or agreed to in writing, software
+#  distributed under the License is distributed on an "AS IS" BASIS,
+#  WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+#  See the License for the specific language governing permissions and
+#  limitations under the License.
+"""Contains classes for DocumentSimilarityRanker."""
+
+from sparknlp.common import *
+from pyspark import keyword_only
+from pyspark.ml.param import TypeConverters, Params, Param
+from sparknlp.internal import AnnotatorTransformer
+
+
+class DocumentSimilarityRankerApproach(AnnotatorApproach, 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 <https://github.com/JohnSnowLabs/spark-nlp/blob/master/examples/python/annotation/text/english/text-similarity/doc-sim-ranker/test_doc_sim_ranker.ipynb>`__.
+
+    ======================= ===========================
+    Input Annotation types  Output Annotation type
+    ======================= ===========================
+    ``SENTENCE_EMBEDDINGS`` ``DOC_SIMILARITY_RANKINGS``
+    ======================= ===========================
+
+    Parameters
+    ----------
+    enableCaching
+        Whether to enable caching DataFrames or RDDs during the training
+    similarityMethod
+        The similarity method used to calculate the neighbours.
+        (Default: 'brp',Bucketed Random Projection for Euclidean Distance)
+    numberOfNeighbours
+        The number of neighbours the model will return (Default:`10`)
+    bucketLength
+        Controls the average size of hash buckets. A larger bucket
+        length (i.e., fewer buckets) increases the probability of features
+        being hashed to the same bucket (increasing the numbers of true and false positives)
+    numHashTables
+      Number of hash tables, where increasing number of hash tables lowers the
+      false negative rate, and decreasing it improves the running performance.
+    visibleDistances
+        "Whether to set visibleDistances in ranking output (Default: `false`).
+    identityRanking
+        Whether to include identity in ranking result set. Useful for debug. (Default: `false`).
+
+    Examples
+    --------
+    >>> import sparknlp
+    >>> from sparknlp.base import *
+    >>> from sparknlp.annotator import *
+    >>> from pyspark.ml import Pipeline
+    >>> from sparknlp.annotator.similarity.document_similarity_ranker import *
+    >>> document_assembler = DocumentAssembler() \
+    ...             .setInputCol("text") \
+    ...             .setOutputCol("document")
+    >>> sentence_embeddings = E5Embeddings.pretrained() \
+    ...             .setInputCols(["document"]) \
+    ...             .setOutputCol("sentence_embeddings")
+    >>> document_similarity_ranker = DocumentSimilarityRankerApproach() \
+    ...             .setInputCols("sentence_embeddings") \
+    ...             .setOutputCol("doc_similarity_rankings") \
+    ...             .setSimilarityMethod("brp") \
+    ...             .setNumberOfNeighbours(1) \
+    ...             .setBucketLength(2.0) \
+    ...             .setNumHashTables(3) \
+    ...             .setVisibleDistances(True) \
+    ...             .setIdentityRanking(False)
+    >>> document_similarity_ranker_finisher = DocumentSimilarityRankerFinisher() \
+    ...         .setInputCols("doc_similarity_rankings") \
+    ...         .setOutputCols(
+    ...             "finished_doc_similarity_rankings_id",
+    ...             "finished_doc_similarity_rankings_neighbors") \
+    ...         .setExtractNearestNeighbor(True)
+    >>> pipeline = Pipeline(stages=[
+    ...             document_assembler,
+    ...             sentence_embeddings,
+    ...             document_similarity_ranker,
+    ...             document_similarity_ranker_finisher
+    ...         ])
+    >>> docSimRankerPipeline = pipeline.fit(data).transform(data)
+    >>> (
+    ...     docSimRankerPipeline
+    ...         .select(
+    ...                "finished_doc_similarity_rankings_id",
+    ...                "finished_doc_similarity_rankings_neighbors"
+    ...         ).show(10, 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)]       |
+    +-----------------------------------+------------------------------------------+
+    """
+
+    inputAnnotatorTypes = [AnnotatorType.SENTENCE_EMBEDDINGS]
+
+    outputAnnotatorType = AnnotatorType.DOC_SIMILARITY_RANKINGS
+
+    similarityMethod = Param(Params._dummy(),
+                             "similarityMethod",
+                             "The similarity method used to calculate the neighbours. (Default: 'brp', "
+                             "Bucketed Random Projection for Euclidean Distance)",
+                             typeConverter=TypeConverters.toString)
+
+    numberOfNeighbours = Param(Params._dummy(),
+                               "numberOfNeighbours",
+                               "The number of neighbours the model will return (Default:`10`)",
+                               typeConverter=TypeConverters.toInt)
+
+    bucketLength = Param(Params._dummy(),
+                         "bucketLength",
+                         "The bucket length that controls the average size of hash buckets. "
+                         "A larger bucket length (i.e., fewer buckets) increases the probability of features "
+                         "being hashed to the same bucket (increasing the numbers of true and false positives).",
+                         typeConverter=TypeConverters.toFloat)
+
+    numHashTables = Param(Params._dummy(),
+                          "numHashTables",
+                          "number of hash tables, where increasing number of hash tables lowers the "
+                          "false negative rate,and decreasing it improves the running performance.",
+                          typeConverter=TypeConverters.toInt)
+
+    visibleDistances = Param(Params._dummy(),
+                             "visibleDistances",
+                             "Whether to set visibleDistances in ranking output (Default: `false`).",
+                             typeConverter=TypeConverters.toBoolean)
+
+    identityRanking = Param(Params._dummy(),
+                            "identityRanking",
+                            "Whether to include identity in ranking result set. Useful for debug. (Default: `false`).",
+                            typeConverter=TypeConverters.toBoolean)
+
+    asRetrieverQuery = Param(Params._dummy(),
+                             "asRetrieverQuery",
+                             "Whether to set the model as retriever RAG with a specific query string."
+                             "(Default: `empty`)",
+                             typeConverter=TypeConverters.toString)
+
+    aggregationMethod = Param(Params._dummy(),
+                              "aggregationMethod",
+                              "Specifies the method used to aggregate multiple sentence embeddings into a single vector representation.",
+                              typeConverter=TypeConverters.toString)
+
+
+    def setSimilarityMethod(self, value):
+        """Sets the similarity method used to calculate the neighbours.
+            (Default: `"brp"`, Bucketed Random Projection for Euclidean Distance)
+
+        Parameters
+        ----------
+        value : str
+            the similarity method to calculate the neighbours.
+        """
+        return self._set(similarityMethod=value)
+
+    def setNumberOfNeighbours(self, value):
+        """Sets The number of neighbours the model will return for each document(Default:`"10"`).
+
+        Parameters
+        ----------
+        value : str
+            the number of neighbours the model will return for each document.
+        """
+        return self._set(numberOfNeighbours=value)
+
+    def setBucketLength(self, value):
+        """Sets the bucket length that controls the average size of hash buckets (Default:`"2.0"`).
+
+        Parameters
+        ----------
+        value : float
+            Sets the bucket length that controls the average size of hash buckets.
+        """
+        return self._set(bucketLength=value)
+
+    def setNumHashTables(self, value):
+        """Sets the number of hash tables.
+
+        Parameters
+        ----------
+        value : int
+            Sets the number of hash tables.
+        """
+        return self._set(numHashTables=value)
+
+    def setVisibleDistances(self, value):
+        """Sets the document distances visible in the result set.
+
+        Parameters
+        ----------
+        value : bool
+            Sets the document distances visible in the result set.
+            Default('False')
+        """
+        return self._set(visibleDistances=value)
+
+    def setIdentityRanking(self, value):
+        """Sets the document identity ranking inclusive in the result set.
+
+        Parameters
+        ----------
+        value : bool
+            Sets the document identity ranking inclusive in the result set.
+            Useful for debugging.
+            Default('False').
+        """
+        return self._set(identityRanking=value)
+
+    def asRetriever(self, value):
+        """Sets the query to use the document similarity ranker as a retriever in a RAG fashion.
+            (Default: `""`, empty if this annotator is not used as retriever)
+
+        Parameters
+        ----------
+        value : str
+             the query to use to select nearest neighbors in the retrieval process.
+        """
+        return self._set(asRetrieverQuery=value)
+
+    def setAggregationMethod(self, value):
+        """Set the method used to aggregate multiple sentence embeddings into a single vector
+           representation.
+
+        Parameters
+        ----------
+        value : str
+           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')
+        """
+        return self._set(aggregationMethod=value)
+
+    @keyword_only
+    def __init__(self):
+        super(DocumentSimilarityRankerApproach, self)\
+            .__init__(classname="com.johnsnowlabs.nlp.annotators.similarity.DocumentSimilarityRankerApproach")
+        self._setDefault(
+            similarityMethod="brp",
+            numberOfNeighbours=10,
+            bucketLength=2.0,
+            numHashTables=3,
+            visibleDistances=False,
+            identityRanking=False,
+            asRetrieverQuery=""
+        )
+
+    def _create_model(self, java_model):
+        return DocumentSimilarityRankerModel(java_model=java_model)
+
+
+class DocumentSimilarityRankerModel(AnnotatorModel, HasEmbeddingsProperties):
+
+    name = "DocumentSimilarityRankerModel"
+    inputAnnotatorTypes = [AnnotatorType.SENTENCE_EMBEDDINGS]
+    outputAnnotatorType = AnnotatorType.DOC_SIMILARITY_RANKINGS
+
+    def __init__(self, classname="com.johnsnowlabs.nlp.annotators.similarity.DocumentSimilarityRankerModel",
+                 java_model=None):
+        super(DocumentSimilarityRankerModel, self).__init__(
+            classname=classname,
+            java_model=java_model
+        )
+
+
+class DocumentSimilarityRankerFinisher(AnnotatorTransformer):
+    """Instantiated model of the DocumentSimilarityRankerApproach. For usage and examples see the
+    documentation of the main class.
+
+    ======================= ===========================
+    Input Annotation types  Output Annotation type
+    ======================= ===========================
+    ``SENTENCE_EMBEDDINGS`` ``DOC_SIMILARITY_RANKINGS``
+    ======================= ===========================
+
+    Parameters
+    ----------
+    extractNearestNeighbor
+        Whether to extract the nearest neighbor document
+    """
+    inputCols = Param(Params._dummy(),
+                      "inputCols",
+                      "name of input annotation cols containing document similarity ranker results",
+                      typeConverter=TypeConverters.toListString)
+    outputCols = Param(Params._dummy(),
+                       "outputCols",
+                       "output DocumentSimilarityRankerFinisher output cols",
+                       typeConverter=TypeConverters.toListString)
+    extractNearestNeighbor = Param(Params._dummy(), "extractNearestNeighbor",
+                             "whether to extract the nearest neighbor document",
+                             typeConverter=TypeConverters.toBoolean)
+
+    name = "DocumentSimilarityRankerFinisher"
+
+    @keyword_only
+    def __init__(self):
+        super(DocumentSimilarityRankerFinisher, self).__init__(classname="com.johnsnowlabs.nlp.finisher.DocumentSimilarityRankerFinisher")
+        self._setDefault(
+            extractNearestNeighbor=False
+        )
+
+    @keyword_only
+    def setParams(self):
+        kwargs = self._input_kwargs
+        return self._set(**kwargs)
+
+    def setInputCols(self, *value):
+        """Sets name of input annotation columns containing embeddings.
+
+        Parameters
+        ----------
+        *value : str
+            Input columns for the annotator
+        """
+
+        if len(value) == 1 and type(value[0]) == list:
+            return self._set(inputCols=value[0])
+        else:
+            return self._set(inputCols=list(value))
+
+    def setOutputCols(self, *value):
+        """Sets names of finished output columns.
+
+        Parameters
+        ----------
+        *value : List[str]
+            Input columns for the annotator
+        """
+
+        if len(value) == 1 and type(value[0]) == list:
+            return self._set(outputCols=value[0])
+        else:
+            return self._set(outputCols=list(value))
+
+    def setExtractNearestNeighbor(self, value):
+        """Sets whether to extract the nearest neighbor document, by default False.
+
+        Parameters
+        ----------
+        value : bool
+            Whether to extract the nearest neighbor document
+        """
+
+        return self._set(extractNearestNeighbor=value)
+
+    def getInputCols(self):
+        """Gets input columns name of annotations."""
+        return self.getOrDefault(self.inputCols)
+
+    def getOutputCols(self):
+        """Gets output columns name of annotations."""
+        if len(self.getOrDefault(self.outputCols)) == 0:
+            return ["finished_" + input_col for input_col in self.getInputCols()]
+        else:
+            return self.getOrDefault(self.outputCols)

sparknlp/annotator/spell_check/context_spell_checker.py

@@ -37,7 +37,7 @@ class ContextSpellCheckerApproach(AnnotatorApproach):
 
     For extended examples of usage, see the article
     `Training a Contextual Spell Checker for Italian Language <https://towardsdatascience.com/training-a-contextual-spell-checker-for-italian-language-66dda528e4bf>`__,
-    the `Spark NLP Workshop <https://github.com/JohnSnowLabs/spark-nlp-workshop/blob/master/tutorials/blogposts/5.TrainingContextSpellChecker.ipynb>`__.
+    the `Examples <https://github.com/JohnSnowLabs/spark-nlp/blob/master/examples/python/training/italian/Training_Context_Spell_Checker_Italian.ipynb>`__.
 
     ====================== ======================
     Input Annotation types Output Annotation type
@@ -92,6 +92,10 @@ class ContextSpellCheckerApproach(AnnotatorApproach):
         correction.
     configProtoBytes
         ConfigProto from tensorflow, serialized into byte array.
+    maxSentLen
+        Maximum length for a sentence - internal use during training.
+    graphFolder
+        Folder path that contain external graph files.
 
     References
     ----------
@@ -226,6 +230,16 @@ class ContextSpellCheckerApproach(AnnotatorApproach):
                              "ConfigProto from tensorflow, serialized into byte array. Get with config_proto.SerializeToString()",
                              TypeConverters.toListInt)
 
+    maxSentLen = Param(Params._dummy(),
+                       "maxSentLen",
+                       "Maximum length of a sentence to be considered for training.",
+                       typeConverter=TypeConverters.toInt)
+
+    graphFolder = Param(Params._dummy(),
+                        "graphFolder",
+                        "Folder path that contain external graph files.",
+                        typeConverter=TypeConverters.toString)
+
     def setLanguageModelClasses(self, count):
         """Sets number of classes to use during factorization of the softmax
         output in the Language Model.
@@ -393,18 +407,6 @@ class ContextSpellCheckerApproach(AnnotatorApproach):
         """
         return self._set(weightedDistPath=path)
 
-    def setWeightedDistPath(self, path):
-        """Sets the path to the file containing the weights for the levenshtein
-        distance.
-
-        Parameters
-        ----------
-        path : str
-            Path to the file containing the weights for the levenshtein
-            distance.
-        """
-        return self._set(weightedDistPath=path)
-
     def setMaxWindowLen(self, length):
         """Sets the maximum size for the window used to remember history prior
         to every correction.
@@ -427,6 +429,26 @@ class ContextSpellCheckerApproach(AnnotatorApproach):
         """
         return self._set(configProtoBytes=b)
 
+    def setGraphFolder(self, path):
+        """Sets folder path that contain external graph files.
+
+        Parameters
+        ----------
+        path : str
+            Folder path that contain external graph files.
+        """
+        return self._set(graphFolder=path)
+
+    def setMaxSentLen(self, sentlen):
+        """Sets the maximum length of a sentence.
+
+        Parameters
+        ----------
+        sentlen : int
+            Maximum length of a sentence
+        """
+        return self._set(maxSentLen=sentlen)
+
     def addVocabClass(self, label, vocab, userdist=3):
         """Adds a new class of words to correct, based on a vocabulary.
 
@@ -494,9 +516,9 @@ class ContextSpellCheckerModel(AnnotatorModel, HasEngine):
 
 
     The default model is ``"spellcheck_dl"``, if no name is provided.
-    For available pretrained models please see the `Models Hub <https://nlp.johnsnowlabs.com/models?task=Spell+Check>`__.
+    For available pretrained models please see the `Models Hub <https://sparknlp.org/models?task=Spell+Check>`__.
 
-    For extended examples of usage, see the `Spark NLP Workshop <https://github.com/JohnSnowLabs/spark-nlp-workshop/blob/master/tutorials/streamlit_notebooks/SPELL_CHECKER_EN.ipynb>`__.
+    For extended examples of usage, see the `Examples <https://github.com/JohnSnowLabs/spark-nlp/blob/master/examples/python/training/italian/Training_Context_Spell_Checker_Italian.ipynb>`__.
 
     ====================== ======================
     Input Annotation types Output Annotation type
@@ -525,13 +547,25 @@ class ContextSpellCheckerModel(AnnotatorModel, HasEngine):
     correctSymbols
         Whether to correct special symbols or skip spell checking for them
     compareLowcase
-        If true will compare tokens in low case with vocabulary
+        If true will compare tokens in low case with vocabulary.
     configProtoBytes
         ConfigProto from tensorflow, serialized into byte array.
+    vocabFreq
+        Frequency words from the vocabulary.
+    idsVocab
+        Mapping of ids to vocabulary.
+    vocabIds
+        Mapping of vocabulary to ids.
+    classes
+        Classes the spell checker recognizes.
+    weights
+        Levenshtein weights.
+    useNewLines
+        When set to true new lines will be treated as any other character. When set to false correction is applied on paragraphs as defined by newline characters.
 
 
     References
-    -------------
+    ----------
     For an in-depth explanation of the module see the article `Applying Context
     Aware Spell Checking in Spark NLP
     <https://medium.com/spark-nlp/applying-context-aware-spell-checking-in-spark-nlp-3c29c46963bc>`__.
@@ -624,6 +658,31 @@ class ContextSpellCheckerModel(AnnotatorModel, HasEngine):
                              "ConfigProto from tensorflow, serialized into byte array. Get with config_proto.SerializeToString()",
                              TypeConverters.toListInt)
 
+    vocabFreq = Param(
+        Params._dummy(),
+        "vocabFreq",
+        "Frequency words from the vocabulary.",
+        TypeConverters.identity,
+    )
+    idsVocab = Param(
+        Params._dummy(),
+        "idsVocab",
+        "Mapping of ids to vocabulary.",
+        TypeConverters.identity,
+    )
+    vocabIds = Param(
+        Params._dummy(),
+        "vocabIds",
+        "Mapping of vocabulary to ids.",
+        TypeConverters.identity,
+    )
+    classes = Param(
+        Params._dummy(),
+        "classes",
+        "Classes the spell checker recognizes.",
+        TypeConverters.identity,
+    )
+
     def setWordMaxDistance(self, dist):
         """Sets maximum distance for the generated candidates for every word.
 
@@ -718,6 +777,46 @@ class ContextSpellCheckerModel(AnnotatorModel, HasEngine):
         """
         return self._set(configProtoBytes=b)
 
+    def setVocabFreq(self, value: dict):
+        """Sets frequency words from the vocabulary.
+
+        Parameters
+        ----------
+        value : dict
+            Frequency words from the vocabulary.
+        """
+        return self._set(vocabFreq=value)
+
+    def setIdsVocab(self, idsVocab: dict):
+        """Sets mapping of ids to vocabulary.
+
+        Parameters
+        ----------
+        idsVocab : dict
+            Mapping of ids to vocabulary.
+        """
+        return self._set(idsVocab=idsVocab)
+
+    def setVocabIds(self, vocabIds: dict):
+        """Sets mapping of vocabulary to ids.
+
+        Parameters
+        ----------
+        vocabIds : dict
+            Mapping of vocabulary to ids.
+        """
+        return self._set(vocabIds=vocabIds)
+
+    def setClasses(self, value):
+        """Sets classes the spell checker recognizes.
+
+        Parameters
+        ----------
+        value : list
+            Classes the spell checker recognizes.
+        """
+        return self._set(classes=value)
+
     def getWordClasses(self):
         """Gets the classes of words to be corrected.