spark-nlp 2.6.3rc1__py2.py3-none-any.whl → 6.2.1__py2.py3-none-any.whl

sparknlp/annotator/classifier_dl/roberta_for_question_answering.py

@@ -0,0 +1,168 @@
+#  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 RoBertaForQuestionAnswering(AnnotatorModel,
+                                  HasCaseSensitiveProperties,
+                                  HasBatchedAnnotate,
+                                  HasEngine,
+                                  HasMaxSentenceLengthLimit):
+    """RoBertaForQuestionAnswering can load 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 = RoBertaForQuestionAnswering.pretrained() \\
+    ...     .setInputCols(["document_question", "document_context"]) \\
+    ...     .setOutputCol("answer")
+
+    The default model is ``"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 = RoBertaForQuestionAnswering.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 = "RoBertaForQuestionAnswering"
+
+    inputAnnotatorTypes = [AnnotatorType.DOCUMENT, AnnotatorType.DOCUMENT]
+
+    outputAnnotatorType = AnnotatorType.CHUNK
+
+    configProtoBytes = Param(Params._dummy(),
+                             "configProtoBytes",
+                             "ConfigProto from tensorflow, serialized into byte array. Get with config_proto.SerializeToString()",
+                             TypeConverters.toListInt)
+
+    coalesceSentences = Param(Params._dummy(), "coalesceSentences",
+                              "Instead of 1 class per sentence (if inputCols is '''sentence''') output 1 class per document by averaging probabilities in all sentences.",
+                              TypeConverters.toBoolean)
+
+    def setConfigProtoBytes(self, b):
+        """Sets configProto from tensorflow, serialized into byte array.
+
+        Parameters
+        ----------
+        b : List[int]
+            ConfigProto from tensorflow, serialized into byte array
+        """
+        return self._set(configProtoBytes=b)
+
+    @keyword_only
+    def __init__(self, classname="com.johnsnowlabs.nlp.annotators.classifier.dl.RoBertaForQuestionAnswering",
+                 java_model=None):
+        super(RoBertaForQuestionAnswering, 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
+        -------
+        RoBertaForQuestionAnswering
+            The restored model
+        """
+        from sparknlp.internal import _RoBertaQuestionAnsweringLoader
+        jModel = _RoBertaQuestionAnsweringLoader(folder, spark_session._jsparkSession)._java_obj
+        return RoBertaForQuestionAnswering(java_model=jModel)
+
+    @staticmethod
+    def pretrained(name="roberta_base_qa_squad2", lang="en", remote_loc=None):
+        """Downloads and loads a pretrained model.
+
+        Parameters
+        ----------
+        name : str, optional
+            Name of the pretrained model, by default
+            "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
+        -------
+        RoBertaForQuestionAnswering
+            The restored model
+        """
+        from sparknlp.pretrained import ResourceDownloader
+        return ResourceDownloader.downloadModel(RoBertaForQuestionAnswering, name, lang, remote_loc)

sparknlp/annotator/classifier_dl/roberta_for_sequence_classification.py

@@ -0,0 +1,201 @@
+#  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.
+"""Contains classes for RoBertaForSequenceClassification."""
+
+from sparknlp.common import *
+
+
+class RoBertaForSequenceClassification(AnnotatorModel,
+                                       HasCaseSensitiveProperties,
+                                       HasBatchedAnnotate,
+                                       HasClassifierActivationProperties,
+                                       HasEngine,
+                                       HasMaxSentenceLengthLimit):
+    """RoBertaForSequenceClassification can load RoBERTa Models with sequence classification/regression head on
+    top (a linear layer on top of the pooled output) e.g. for multi-class document classification tasks.
+
+    Pretrained models can be loaded with :meth:`.pretrained` of the companion
+    object:
+
+    >>> sequenceClassifier = RoBertaForSequenceClassification.pretrained() \\
+    ...     .setInputCols(["token", "document"]) \\
+    ...     .setOutputCol("label")
+
+    The default model is ``"roberta_base_sequence_classifier_imdb"``, if no name is
+    provided.
+
+    For available pretrained models please see the `Models Hub
+    <https://sparknlp.org/models?task=Text+Classification>`__.
+
+    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, TOKEN``    ``CATEGORY``
+    ====================== ======================
+
+    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
+        True
+    configProtoBytes
+        ConfigProto from tensorflow, serialized into byte array.
+    maxSentenceLength
+        Max sentence length to process, by default 128
+    coalesceSentences
+        Instead of 1 class per sentence (if inputCols is `sentence`) output
+        1 class per document by averaging probabilities in all sentences, by
+        default False.
+    activation
+        Whether to calculate logits via Softmax or Sigmoid, by default
+        `"softmax"`.
+
+    Examples
+    --------
+    >>> import sparknlp
+    >>> from sparknlp.base import *
+    >>> from sparknlp.annotator import *
+    >>> from pyspark.ml import Pipeline
+    >>> documentAssembler = DocumentAssembler() \\
+    ...     .setInputCol("text") \\
+    ...     .setOutputCol("document")
+    >>> tokenizer = Tokenizer() \\
+    ...     .setInputCols(["document"]) \\
+    ...     .setOutputCol("token")
+    >>> sequenceClassifier = RoBertaForSequenceClassification.pretrained() \\
+    ...     .setInputCols(["token", "document"]) \\
+    ...     .setOutputCol("label") \\
+    ...     .setCaseSensitive(True)
+    >>> pipeline = Pipeline().setStages([
+    ...     documentAssembler,
+    ...     tokenizer,
+    ...     sequenceClassifier
+    ... ])
+    >>> data = spark.createDataFrame([["I loved this movie when I was a child.", "It was pretty boring."]]).toDF("text")
+    >>> result = pipeline.fit(data).transform(data)
+    >>> result.select("label.result").show(truncate=False)
+    +------+
+    |result|
+    +------+
+    |[pos] |
+    |[neg] |
+    +------+
+    """
+    name = "RoBertaForSequenceClassification"
+
+    inputAnnotatorTypes = [AnnotatorType.DOCUMENT, AnnotatorType.TOKEN]
+
+    outputAnnotatorType = AnnotatorType.CATEGORY
+
+    configProtoBytes = Param(Params._dummy(),
+                             "configProtoBytes",
+                             "ConfigProto from tensorflow, serialized into byte array. Get with config_proto.SerializeToString()",
+                             TypeConverters.toListInt)
+
+    coalesceSentences = Param(Params._dummy(), "coalesceSentences",
+                              "Instead of 1 class per sentence (if inputCols is '''sentence''') output 1 class per document by averaging probabilities in all sentences.",
+                              TypeConverters.toBoolean)
+
+    def getClasses(self):
+        """
+        Returns labels used to train this model
+        """
+        return self._call_java("getClasses")
+
+    def setConfigProtoBytes(self, b):
+        """Sets configProto from tensorflow, serialized into byte array.
+
+        Parameters
+        ----------
+        b : List[int]
+            ConfigProto from tensorflow, serialized into byte array
+        """
+        return self._set(configProtoBytes=b)
+
+    def setCoalesceSentences(self, value):
+        """Instead of 1 class per sentence (if inputCols is '''sentence''') output 1 class per document by averaging probabilities in all sentences.
+        Due to max sequence length limit in almost all transformer models such as BERT (512 tokens), this parameter helps feeding all the sentences
+        into the model and averaging all the probabilities for the entire document instead of probabilities per sentence. (Default: true)
+
+        Parameters
+        ----------
+        value : bool
+            If the output of all sentences will be averaged to one output
+        """
+        return self._set(coalesceSentences=value)
+
+    @keyword_only
+    def __init__(self, classname="com.johnsnowlabs.nlp.annotators.classifier.dl.RoBertaForSequenceClassification",
+                 java_model=None):
+        super(RoBertaForSequenceClassification, self).__init__(
+            classname=classname,
+            java_model=java_model
+        )
+        self._setDefault(
+            batchSize=8,
+            maxSentenceLength=128,
+            caseSensitive=True,
+            coalesceSentences=False,
+            activation="softmax"
+        )
+
+    @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
+        -------
+        RoBertaForSequenceClassification
+            The restored model
+        """
+        from sparknlp.internal import _RoBertaSequenceClassifierLoader
+        jModel = _RoBertaSequenceClassifierLoader(folder, spark_session._jsparkSession)._java_obj
+        return RoBertaForSequenceClassification(java_model=jModel)
+
+    @staticmethod
+    def pretrained(name="roberta_base_sequence_classifier_imdb", lang="en", remote_loc=None):
+        """Downloads and loads a pretrained model.
+
+        Parameters
+        ----------
+        name : str, optional
+            Name of the pretrained model, by default
+            "roberta_base_sequence_classifier_imdb"
+        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
+        -------
+        RoBertaForSequenceClassification
+            The restored model
+        """
+        from sparknlp.pretrained import ResourceDownloader
+        return ResourceDownloader.downloadModel(RoBertaForSequenceClassification, name, lang, remote_loc)

sparknlp/annotator/classifier_dl/roberta_for_token_classification.py

@@ -0,0 +1,189 @@
+#  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.
+"""Contains classes for RoBertaForTokenClassification."""
+
+from sparknlp.common import *
+
+
+class RoBertaForTokenClassification(AnnotatorModel,
+                                    HasCaseSensitiveProperties,
+                                    HasBatchedAnnotate,
+                                    HasEngine):
+    """RoBertaForTokenClassification can load RoBerta Models with a token
+    classification head on top (a linear layer on top of the hidden-states
+    output) e.g. for Named-Entity-Recognition (NER) tasks.
+
+    Pretrained models can be loaded with :meth:`.pretrained` of the companion
+    object:
+
+    >>> token_classifier = RoBertaForTokenClassification.pretrained() \\
+    ...     .setInputCols(["token", "document"]) \\
+    ...     .setOutputCol("label")
+
+    The default model is ``"roberta_base_token_classifier_conll03"``, if no name
+    is provided.
+
+    For available pretrained models please see the `Models Hub
+    <https://sparknlp.org/models?task=Named+Entity+Recognition>`__.
+
+    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, TOKEN``    ``NAMED_ENTITY``
+    ====================== ======================
+
+    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
+        True
+    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 = DocumentAssembler() \\
+    ...     .setInputCol("text") \\
+    ...     .setOutputCol("document")
+    >>> tokenizer = Tokenizer() \\
+    ...     .setInputCols(["document"]) \\
+    ...     .setOutputCol("token")
+    >>> tokenClassifier = RoBertaForTokenClassification.pretrained() \\
+    ...     .setInputCols(["token", "document"]) \\
+    ...     .setOutputCol("label") \\
+    ...     .setCaseSensitive(True)
+    >>> pipeline = Pipeline().setStages([
+    ...     documentAssembler,
+    ...     tokenizer,
+    ...     tokenClassifier
+    ... ])
+    >>> data = spark.createDataFrame([["John Lenon was born in London and lived in Paris. My name is Sarah and I live in London"]]).toDF("text")
+    >>> result = pipeline.fit(data).transform(data)
+    >>> result.select("label.result").show(truncate=False)
+    +------------------------------------------------------------------------------------+
+    |result                                                                              |
+    +------------------------------------------------------------------------------------+
+    |[B-PER, I-PER, O, O, O, B-LOC, O, O, O, B-LOC, O, O, O, O, B-PER, O, O, O, O, B-LOC]|
+    +------------------------------------------------------------------------------------+
+    """
+    name = "RoBertaForTokenClassification"
+
+    inputAnnotatorTypes = [AnnotatorType.DOCUMENT, AnnotatorType.TOKEN]
+
+    outputAnnotatorType = AnnotatorType.NAMED_ENTITY
+
+    maxSentenceLength = Param(Params._dummy(),
+                              "maxSentenceLength",
+                              "Max sentence length to process",
+                              typeConverter=TypeConverters.toInt)
+
+    configProtoBytes = Param(Params._dummy(),
+                             "configProtoBytes",
+                             "ConfigProto from tensorflow, serialized into byte array. Get with config_proto.SerializeToString()",
+                             TypeConverters.toListInt)
+
+    def getClasses(self):
+        """
+        Returns labels used to train this model
+        """
+        return self._call_java("getClasses")
+
+    def setConfigProtoBytes(self, b):
+        """Sets configProto from tensorflow, serialized into byte array.
+
+        Parameters
+        ----------
+        b : List[int]
+            ConfigProto from tensorflow, serialized into byte array
+        """
+        return self._set(configProtoBytes=b)
+
+    def setMaxSentenceLength(self, value):
+        """Sets max sentence length to process, by default 128.
+
+        Parameters
+        ----------
+        value : int
+            Max sentence length to process
+        """
+        return self._set(maxSentenceLength=value)
+
+    @keyword_only
+    def __init__(self, classname="com.johnsnowlabs.nlp.annotators.classifier.dl.RoBertaForTokenClassification",
+                 java_model=None):
+        super(RoBertaForTokenClassification, self).__init__(
+            classname=classname,
+            java_model=java_model
+        )
+        self._setDefault(
+            batchSize=8,
+            maxSentenceLength=128,
+            caseSensitive=True
+        )
+
+    @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
+        -------
+        RoBertaForTokenClassification
+            The restored model
+        """
+        from sparknlp.internal import _RoBertaTokenClassifierLoader
+        jModel = _RoBertaTokenClassifierLoader(folder, spark_session._jsparkSession)._java_obj
+        return RoBertaForTokenClassification(java_model=jModel)
+
+    @staticmethod
+    def pretrained(name="roberta_base_token_classifier_conll03", lang="en", remote_loc=None):
+        """Downloads and loads a pretrained model.
+
+        Parameters
+        ----------
+        name : str, optional
+            Name of the pretrained model, by default
+            "roberta_base_token_classifier_conll03"
+        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
+        -------
+        RoBertaForTokenClassification
+            The restored model
+        """
+        from sparknlp.pretrained import ResourceDownloader
+        return ResourceDownloader.downloadModel(RoBertaForTokenClassification, name, lang, remote_loc)