spark-nlp 5.5.3__py2.py3-none-any.whl → 6.0.1__py2.py3-none-any.whl

sparknlp/annotator/classifier_dl/roberta_for_multiple_choice.py

@@ -0,0 +1,161 @@
+#  Copyright 2017-2025 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.
+
+from sparknlp.common import *
+
+class RoBertaForMultipleChoice(AnnotatorModel,
+                               HasCaseSensitiveProperties,
+                               HasBatchedAnnotate,
+                               HasEngine,
+                               HasMaxSentenceLengthLimit):
+    """RoBertaForMultipleChoice can load RoBERTa Models with a multiple choice classification head on top
+    (a linear layer on top of the pooled output and a softmax) e.g. for RocStories/SWAG tasks.
+
+    Pretrained models can be loaded with :meth:`.pretrained` of the companion
+    object:
+
+    >>> spanClassifier = RoBertaForMultipleChoice.pretrained() \\
+    ...     .setInputCols(["document_question", "document_context"]) \\
+    ...     .setOutputCol("answer")
+
+    The default model is ``"roberta_base_uncased_multiple_choice"``, if no name is
+    provided.
+
+    For available pretrained models please see the `Models Hub
+    <https://sparknlp.org/models?task=Multiple+Choice>`__.
+
+    To see which models are compatible and how to import them see
+    `Import Transformers into Spark NLP 🚀
+    <https://github.com/JohnSnowLabs/spark-nlp/discussions/5669>`_.
+
+    ====================== ======================
+    Input Annotation types Output Annotation type
+    ====================== ======================
+    ``DOCUMENT, DOCUMENT``    ``CHUNK``
+    ====================== ======================
+
+    Parameters
+    ----------
+    batchSize
+        Batch size. Large values allows faster processing but requires more
+        memory, by default 8
+    caseSensitive
+        Whether to ignore case in tokens for embeddings matching, by default
+        False
+    maxSentenceLength
+        Max sentence length to process, by default 512
+
+    Examples
+    --------
+    >>> import sparknlp
+    >>> from sparknlp.base import *
+    >>> from sparknlp.annotator import *
+    >>> from pyspark.ml import Pipeline
+    >>> documentAssembler = MultiDocumentAssembler() \\
+    ...     .setInputCols(["question", "context"]) \\
+    ...     .setOutputCols(["document_question", "document_context"])
+    >>> questionAnswering = RoBertaForMultipleChoice.pretrained() \\
+    ...     .setInputCols(["document_question", "document_context"]) \\
+    ...     .setOutputCol("answer") \\
+    ...     .setCaseSensitive(False)
+    >>> pipeline = Pipeline().setStages([
+    ...     documentAssembler,
+    ...     questionAnswering
+    ... ])
+    >>> data = spark.createDataFrame([["The Eiffel Tower is located in which country??", "Germany, France, Italy"]]).toDF("question", "context")
+    >>> result = pipeline.fit(data).transform(data)
+    >>> result.select("answer.result").show(truncate=False)
+    +--------------------+
+    |result              |
+    +--------------------+
+    |[France]             |
+    +--------------------+
+    """
+    name = "RobertaForMultipleChoice"
+
+    inputAnnotatorTypes = [AnnotatorType.DOCUMENT, AnnotatorType.DOCUMENT]
+
+    outputAnnotatorType = AnnotatorType.CHUNK
+
+    choicesDelimiter = Param(Params._dummy(),
+                             "choicesDelimiter",
+                             "Delimiter character use to split the choices",
+                             TypeConverters.toString)
+
+    def setChoicesDelimiter(self, value):
+        """Sets delimiter character use to split the choices
+
+        Parameters
+        ----------
+        value : string
+            Delimiter character use to split the choices
+        """
+        return self._set(caseSensitive=value)
+
+    @keyword_only
+    def __init__(self, classname="com.johnsnowlabs.nlp.annotators.classifier.dl.RoBertaForMultipleChoice",
+                 java_model=None):
+        super(RoBertaForMultipleChoice, self).__init__(
+            classname=classname,
+            java_model=java_model
+        )
+        self._setDefault(
+            batchSize=4,
+            maxSentenceLength=512,
+            caseSensitive=False,
+            choicesDelimiter = ","
+        )
+
+    @staticmethod
+    def loadSavedModel(folder, spark_session):
+        """Loads a locally saved model.
+
+        Parameters
+        ----------
+        folder : str
+            Folder of the saved model
+        spark_session : pyspark.sql.SparkSession
+            The current SparkSession
+
+        Returns
+        -------
+        RobertaForQuestionAnswering
+            The restored model
+        """
+        from sparknlp.internal import _RoBertaMultipleChoiceLoader
+        jModel = _RoBertaMultipleChoiceLoader(folder, spark_session._jsparkSession)._java_obj
+        return RoBertaForMultipleChoice(java_model=jModel)
+
+    @staticmethod
+    def pretrained(name="Roberta_base_uncased_multiple_choice", lang="en", remote_loc=None):
+        """Downloads and loads a pretrained model.
+
+        Parameters
+        ----------
+        name : str, optional
+            Name of the pretrained model, by default
+            "Roberta_base_uncased_multiple_choice"
+        lang : str, optional
+            Language of the pretrained model, by default "en"
+        remote_loc : str, optional
+            Optional remote address of the resource, by default None. Will use
+            Spark NLPs repositories otherwise.
+
+        Returns
+        -------
+        RoBertaForMultipleChoice
+            The restored model
+        """
+        from sparknlp.pretrained import ResourceDownloader
+        return ResourceDownloader.downloadModel(RoBertaForMultipleChoice, name, lang, remote_loc)

sparknlp/annotator/classifier_dl/xlm_roberta_for_multiple_choice.py

@@ -0,0 +1,149 @@
+#  Copyright 2017-2022 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.
+
+from sparknlp.common import *
+
+
+class XlmRoBertaForMultipleChoice(AnnotatorModel,
+                                 HasCaseSensitiveProperties,
+                                 HasBatchedAnnotate,
+                                 HasEngine,
+                                 HasMaxSentenceLengthLimit):
+    """XlmRoBertaForMultipleChoice can load XLM-RoBERTa Models with a span classification head on top for extractive
+    question-answering tasks like SQuAD (a linear layer on top of the hidden-states output to compute span start
+    logits and span end logits).
+
+    Pretrained models can be loaded with :meth:`.pretrained` of the companion
+    object:
+
+    >>> spanClassifier = XlmRoBertaForMultipleChoice.pretrained() \\
+    ...     .setInputCols(["document_question", "document_context"]) \\
+    ...     .setOutputCol("answer")
+
+    The default model is ``"xlm_roberta_base_qa_squad2"``, if no name is
+    provided.
+
+    For available pretrained models please see the `Models Hub
+    <https://sparknlp.org/models?task=Question+Answering>`__.
+
+    To see which models are compatible and how to import them see
+    `Import Transformers into Spark NLP 🚀
+    <https://github.com/JohnSnowLabs/spark-nlp/discussions/5669>`_.
+
+    ====================== ======================
+    Input Annotation types Output Annotation type
+    ====================== ======================
+    ``DOCUMENT, DOCUMENT``    ``CHUNK``
+    ====================== ======================
+
+    Parameters
+    ----------
+    batchSize
+        Batch size. Large values allows faster processing but requires more
+        memory, by default 8
+    caseSensitive
+        Whether to ignore case in tokens for embeddings matching, by default
+        False
+    configProtoBytes
+        ConfigProto from tensorflow, serialized into byte array.
+    maxSentenceLength
+        Max sentence length to process, by default 128
+
+    Examples
+    --------
+    >>> import sparknlp
+    >>> from sparknlp.base import *
+    >>> from sparknlp.annotator import *
+    >>> from pyspark.ml import Pipeline
+    >>> documentAssembler = MultiDocumentAssembler() \\
+    ...     .setInputCols(["question", "context"]) \\
+    ...     .setOutputCol(["document_question", "document_context"])
+    >>> spanClassifier = XlmRoBertaForMultipleChoice.pretrained() \\
+    ...     .setInputCols(["document_question", "document_context"]) \\
+    ...     .setOutputCol("answer") \\
+    ...     .setCaseSensitive(False)
+    >>> pipeline = Pipeline().setStages([
+    ...     documentAssembler,
+    ...     spanClassifier
+    ... ])
+    >>> data = spark.createDataFrame([["What's my name?", "My name is Clara and I live in Berkeley."]]).toDF("question", "context")
+    >>> result = pipeline.fit(data).transform(data)
+    >>> result.select("answer.result").show(truncate=False)
+    +--------------------+
+    |result              |
+    +--------------------+
+    |[Clara]             |
+    +--------------------+
+    """
+    name = "XlmRoBertaForMultipleChoice"
+
+    inputAnnotatorTypes = [AnnotatorType.DOCUMENT, AnnotatorType.DOCUMENT]
+
+    outputAnnotatorType = AnnotatorType.CHUNK
+
+    @keyword_only
+    def __init__(self, classname="com.johnsnowlabs.nlp.annotators.classifier.dl.XlmRoBertaForMultipleChoice",
+                 java_model=None):
+        super(XlmRoBertaForMultipleChoice, self).__init__(
+            classname=classname,
+            java_model=java_model
+        )
+        self._setDefault(
+            batchSize=8,
+            maxSentenceLength=128,
+            caseSensitive=False
+        )
+
+    @staticmethod
+    def loadSavedModel(folder, spark_session):
+        """Loads a locally saved model.
+
+        Parameters
+        ----------
+        folder : str
+            Folder of the saved model
+        spark_session : pyspark.sql.SparkSession
+            The current SparkSession
+
+        Returns
+        -------
+        XlmRoBertaForMultipleChoice
+            The restored model
+        """
+        from sparknlp.internal import _XlmRoBertaMultipleChoiceLoader
+        jModel = _XlmRoBertaMultipleChoiceLoader(folder, spark_session._jsparkSession)._java_obj
+        return XlmRoBertaForMultipleChoice(java_model=jModel)
+
+    @staticmethod
+    def pretrained(name="xlm_roberta_base_mc", lang="en", remote_loc=None):
+        """Downloads and loads a pretrained model.
+
+        Parameters
+        ----------
+        name : str, optional
+            Name of the pretrained model, by default
+            "xlm_roberta_base_qa_squad2"
+        lang : str, optional
+            Language of the pretrained model, by default "en"
+        remote_loc : str, optional
+            Optional remote address of the resource, by default None. Will use
+            Spark NLPs repositories otherwise.
+
+        Returns
+        -------
+        XlmRoBertaForMultipleChoice
+            The restored model
+        """
+        from sparknlp.pretrained import ResourceDownloader
+        return ResourceDownloader.downloadModel(XlmRoBertaForMultipleChoice, name, lang, remote_loc)

sparknlp/annotator/cleaners/__init__.py

@@ -0,0 +1,15 @@
+#  Copyright 2017-2025 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.
+from sparknlp.annotator.cleaners.extractor import *
+from sparknlp.annotator.cleaners.cleaner import *

sparknlp/annotator/cleaners/cleaner.py

@@ -0,0 +1,202 @@
+#  Copyright 2017-2025 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 Cleaner."""
+from sparknlp.annotator import MarianTransformer
+from sparknlp.common import *
+
+class Cleaner(MarianTransformer):
+    name = "Cleaner"
+
+    inputAnnotatorTypes = [AnnotatorType.TOKEN]
+
+    outputAnnotatorType = AnnotatorType.CHUNK
+
+    encoding = Param(Params._dummy(),
+                   "encoding",
+                   "The encoding to be used for decoding the byte string (default is utf-8)",
+                   typeConverter=TypeConverters.toString)
+
+    cleanPrefixPattern = Param(Params._dummy(),
+                     "cleanPrefixPattern",
+                     "The pattern for the prefix. Can be a simple string or a regex pattern.",
+                     typeConverter=TypeConverters.toString)
+
+    cleanPostfixPattern = Param(Params._dummy(),
+                               "cleanPostfixPattern",
+                               "The pattern for the postfix. Can be a simple string or a regex pattern.",
+                               typeConverter=TypeConverters.toString)
+
+    cleanerMode = Param(
+        Params._dummy(),
+        "cleanerMode",
+        "possible values: " +
+        "clean, bytes_string_to_string, clean_non_ascii_chars, clean_ordered_bullets, clean_postfix, clean_prefix, remove_punctuation, replace_unicode_quotes",
+        typeConverter=TypeConverters.toString
+    )
+
+    extraWhitespace = Param(Params._dummy(),
+                    "extraWhitespace",
+                    "Whether to remove extra whitespace.",
+                    typeConverter=TypeConverters.toBoolean)
+
+    dashes = Param(Params._dummy(),
+                "dashes",
+                "Whether to handle dashes in text.",
+                typeConverter=TypeConverters.toBoolean)
+
+    bullets = Param(Params._dummy(),
+                   "bullets",
+                   "Whether to handle bullets in text.",
+                   typeConverter=TypeConverters.toBoolean)
+
+    trailingPunctuation = Param(Params._dummy(),
+                    "trailingPunctuation",
+                    "Whether to remove trailing punctuation from text.",
+                    typeConverter=TypeConverters.toBoolean)
+
+    lowercase = Param(Params._dummy(),
+                "lowercase",
+                "Whether to convert text to lowercase.",
+                typeConverter=TypeConverters.toBoolean)
+
+    ignoreCase = Param(Params._dummy(),
+                      "ignoreCase",
+                      "If true, ignores case in the pattern.",
+                      typeConverter=TypeConverters.toBoolean)
+
+    strip = Param(Params._dummy(),
+               "strip",
+               "If true, removes leading or trailing whitespace from the cleaned string.",
+               typeConverter=TypeConverters.toBoolean)
+
+    def setEncoding(self, value):
+        """Sets the encoding to be used for decoding the byte string (default is utf-8).
+
+        Parameters
+        ----------
+        value : str
+            The encoding to be used for decoding the byte string (default is utf-8)
+        """
+        return self._set(encoding=value)
+
+    def setCleanPrefixPattern(self, value):
+        """Sets the pattern for the prefix. Can be a simple string or a regex pattern.
+
+        Parameters
+        ----------
+        value : str
+            The pattern for the prefix. Can be a simple string or a regex pattern.
+        """
+        return self._set(cleanPrefixPattern=value)
+
+    def setCleanPostfixPattern(self, value):
+        """Sets the pattern for the postfix. Can be a simple string or a regex pattern.
+
+        Parameters
+        ----------
+        value : str
+            The pattern for the postfix. Can be a simple string or a regex pattern.
+        """
+        return self._set(cleanPostfixPattern=value)
+
+    def setCleanerMode(self, value):
+        """Sets the cleaner mode.
+
+        Possible values:
+            clean, bytes_string_to_string, clean_non_ascii_chars, clean_ordered_bullets,
+            clean_postfix, clean_prefix, remove_punctuation, replace_unicode_quotes
+
+        Parameters
+        ----------
+        value : str
+            The mode for cleaning operations.
+        """
+        return self._set(cleanerMode=value)
+
+    def setExtraWhitespace(self, value):
+        """Sets whether to remove extra whitespace.
+
+        Parameters
+        ----------
+        value : bool
+            Whether to remove extra whitespace.
+        """
+        return self._set(extraWhitespace=value)
+
+    def setDashes(self, value):
+        """Sets whether to handle dashes in text.
+
+        Parameters
+        ----------
+        value : bool
+            Whether to handle dashes in text.
+        """
+        return self._set(dashes=value)
+
+    def setBullets(self, value):
+        """Sets whether to handle bullets in text.
+
+        Parameters
+        ----------
+        value : bool
+            Whether to handle bullets in text.
+        """
+        return self._set(bullets=value)
+
+    def setTrailingPunctuation(self, value):
+        """Sets whether to remove trailing punctuation from text.
+
+        Parameters
+        ----------
+        value : bool
+            Whether to remove trailing punctuation from text.
+        """
+        return self._set(trailingPunctuation=value)
+
+    def setLowercase(self, value):
+        """Sets whether to convert text to lowercase.
+
+        Parameters
+        ----------
+        value : bool
+            Whether to convert text to lowercase.
+        """
+        return self._set(lowercase=value)
+
+    def setIgnoreCase(self, value):
+        """Sets whether to ignore case in the pattern.
+
+        Parameters
+        ----------
+        value : bool
+            If true, ignores case in the pattern.
+        """
+        return self._set(ignoreCase=value)
+
+    def setStrip(self, value):
+        """Sets whether to remove leading or trailing whitespace from the cleaned string.
+
+        Parameters
+        ----------
+        value : bool
+            If true, removes leading or trailing whitespace from the cleaned string.
+        """
+        return self._set(strip=value)
+
+    @keyword_only
+    def __init__(self, classname="com.johnsnowlabs.nlp.annotators.cleaners.Cleaner", java_model=None):
+        super(Cleaner, self).__init__(
+            classname=classname,
+            java_model=java_model
+        )