spark-nlp 5.2.2__py2.py3-none-any.whl → 5.3.0__py2.py3-none-any.whl

sparknlp/annotator/classifier_dl/bert_for_zero_shot_classification.py

@@ -41,7 +41,7 @@ class BertForZeroShotClassification(AnnotatorModel,
     ...     .setInputCols(["token", "document"]) \\
     ...     .setOutputCol("label")
 
-    The default model is ``"bert_base_cased_zero_shot_classifier_xnli"``, if no name is
+    The default model is ``"bert_zero_shot_classifier_mnli"``, if no name is
     provided.
 
     For available pretrained models please see the `Models Hub
@@ -189,14 +189,14 @@ class BertForZeroShotClassification(AnnotatorModel,
         return BertForZeroShotClassification(java_model=jModel)
 
     @staticmethod
-    def pretrained(name="bert_base_cased_zero_shot_classifier_xnli", lang="en", remote_loc=None):
+    def pretrained(name="bert_zero_shot_classifier_mnli", lang="xx", remote_loc=None):
         """Downloads and loads a pretrained model.
 
         Parameters
         ----------
         name : str, optional
             Name of the pretrained model, by default
-            "bert_base_cased_zero_shot_classifier_xnli"
+            "bert_zero_shot_classifier_mnli"
         lang : str, optional
             Language of the pretrained model, by default "en"
         remote_loc : str, optional

sparknlp/annotator/classifier_dl/deberta_for_zero_shot_classification.py

@@ -0,0 +1,206 @@
+#  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 DeBertaForZeroShotClassification."""
+
+from sparknlp.common import *
+
+
+class DeBertaForZeroShotClassification(AnnotatorModel,
+                                          HasCaseSensitiveProperties,
+                                          HasBatchedAnnotate,
+                                          HasClassifierActivationProperties,
+                                          HasCandidateLabelsProperties,
+                                          HasEngine):
+    """DeBertaForZeroShotClassification using a `ModelForSequenceClassification` trained on NLI (natural language
+    inference) tasks. Equivalent of `DeBertaForSequenceClassification` models, but these models don't require a hardcoded
+    number of potential classes, they can be chosen at runtime. It usually means it's slower but it is much more
+    flexible.
+    Any combination of sequences and labels can be passed and each combination will be posed as a premise/hypothesis
+    pair and passed to the pretrained model.
+    Pretrained models can be loaded with :meth:`.pretrained` of the companion
+    object:
+    >>> sequenceClassifier = DeBertaForZeroShotClassification.pretrained() \\
+    ...     .setInputCols(["token", "document"]) \\
+    ...     .setOutputCol("label")
+    The default model is ``"deberta_base_zero_shot_classifier_mnli_anli_v3"``, if no name is
+    provided.
+    For available pretrained models please see the `Models Hub
+    <https://sparknlp.orgtask=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 = DeBertaForZeroShotClassification.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 = "DeBertaForZeroShotClassification"
+
+    inputAnnotatorTypes = [AnnotatorType.DOCUMENT, AnnotatorType.TOKEN]
+
+    outputAnnotatorType = AnnotatorType.CATEGORY
+
+    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)
+
+    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 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)
+
+    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 DeBerta
+        (512 tokens), this parameter helps to feed 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.DeBertaForZeroShotClassification",
+                 java_model=None):
+        super(DeBertaForZeroShotClassification, 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
+        -------
+        DeBertaForZeroShotClassification
+            The restored model
+        """
+        from sparknlp.internal import _DeBertaForZeroShotClassification
+        jModel = _DeBertaForZeroShotClassification(folder, spark_session._jsparkSession)._java_obj
+        return DeBertaForZeroShotClassification(java_model=jModel)
+
+    @staticmethod
+    def pretrained(name="deberta_base_zero_shot_classifier_mnli_anli_v3", lang="en", remote_loc=None):
+        """Downloads and loads a pretrained model.
+        Parameters
+        ----------
+        name : str, optional
+            Name of the pretrained model, by default
+            "deberta_base_zero_shot_classifier_mnli_anli_v3"
+            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
+        -------
+        DeBertaForZeroShotClassification
+            The restored model
+        """
+        from sparknlp.pretrained import ResourceDownloader
+        return ResourceDownloader.downloadModel(DeBertaForZeroShotClassification, name, lang, remote_loc)

sparknlp/annotator/classifier_dl/mpnet_for_question_answering.py

@@ -0,0 +1,148 @@
+#  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 MPNetForQuestionAnswering(AnnotatorModel,
+                                HasCaseSensitiveProperties,
+                                HasBatchedAnnotate,
+                                HasEngine,
+                                HasMaxSentenceLengthLimit):
+    """MPNetForQuestionAnswering can load MPNet 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 = MPNetForQuestionAnswering.pretrained() \\
+    ...     .setInputCols(["document_question", "document_context"]) \\
+    ...     .setOutputCol("answer")
+
+    The default model is ``"mpnet_base_question_answering_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
+    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 = MPNetForQuestionAnswering.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 = "MPNetForQuestionAnswering"
+
+    inputAnnotatorTypes = [AnnotatorType.DOCUMENT, AnnotatorType.DOCUMENT]
+
+    outputAnnotatorType = AnnotatorType.CHUNK
+
+
+    @keyword_only
+    def __init__(self, classname="com.johnsnowlabs.nlp.annotators.classifier.dl.MPNetForQuestionAnswering",
+                 java_model=None):
+        super(MPNetForQuestionAnswering, self).__init__(
+            classname=classname,
+            java_model=java_model
+        )
+        self._setDefault(
+            batchSize=8,
+            maxSentenceLength=384,
+            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
+        -------
+        MPNetForQuestionAnswering
+            The restored model
+        """
+        from sparknlp.internal import _MPNetForQuestionAnsweringLoader
+        jModel = _MPNetForQuestionAnsweringLoader(folder, spark_session._jsparkSession)._java_obj
+        return MPNetForQuestionAnswering(java_model=jModel)
+
+    @staticmethod
+    def pretrained(name="mpnet_base_question_answering_squad2", lang="en", remote_loc=None):
+        """Downloads and loads a pretrained model.
+
+        Parameters
+        ----------
+        name : str, optional
+            Name of the pretrained model, by default
+            "mpnet_base_question_answering_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
+        -------
+        MPNetForQuestionAnswering
+            The restored model
+        """
+        from sparknlp.pretrained import ResourceDownloader
+        return ResourceDownloader.downloadModel(MPNetForQuestionAnswering, name, lang, remote_loc)

sparknlp/annotator/classifier_dl/mpnet_for_sequence_classification.py

@@ -0,0 +1,188 @@
+#  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 MPNetForSequenceClassification."""
+
+from sparknlp.common import *
+
+
+class MPNetForSequenceClassification(AnnotatorModel,
+                                     HasCaseSensitiveProperties,
+                                     HasBatchedAnnotate,
+                                     HasClassifierActivationProperties,
+                                     HasEngine,
+                                     HasMaxSentenceLengthLimit):
+    """MPNetForSequenceClassification can load MPNet 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 = MPNetForSequenceClassification.pretrained() \\
+    ...     .setInputCols(["token", "document"]) \\
+    ...     .setOutputCol("label")
+
+    The default model is ``"mpnet_sequence_classifier_ukr_message"``, 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
+    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
+    >>> document = DocumentAssembler() \\
+    ...     .setInputCol("text") \\
+    ...     .setOutputCol("document")
+    >>> tokenizer = Tokenizer() \\
+    ...     .setInputCols(["document"]) \\
+    ...     .setOutputCol("token")
+    >>> sequenceClassifier = MPNetForSequenceClassification \\
+    ...     .pretrained() \\
+    ...     .setInputCols(["document", "token"]) \\
+    ...     .setOutputCol("label")
+    >>> data = spark.createDataFrame([
+    ...     ["I love driving my car."],
+    ...     ["The next bus will arrive in 20 minutes."],
+    ...     ["pineapple on pizza is the worst 🤮"],
+    ... ]).toDF("text")
+    >>> pipeline = Pipeline().setStages([document, tokenizer, sequenceClassifier])
+    >>> pipelineModel = pipeline.fit(data)
+    >>> results = pipelineModel.transform(data)
+    >>> results.select("label.result").show()
+    +--------------------+
+    |              result|
+    +--------------------+
+    |     [TRANSPORT/CAR]|
+    |[TRANSPORT/MOVEMENT]|
+    |              [FOOD]|
+    +--------------------+
+    """
+    name = "MPNetForSequenceClassification"
+
+    inputAnnotatorTypes = [AnnotatorType.DOCUMENT, AnnotatorType.TOKEN]
+
+    outputAnnotatorType = AnnotatorType.CATEGORY
+
+
+    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 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.MPNetForSequenceClassification",
+                 java_model=None):
+        super(MPNetForSequenceClassification, 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
+        -------
+        MPNetForSequenceClassification
+            The restored model
+        """
+        from sparknlp.internal import _MPNetForSequenceClassificationLoader
+        jModel = _MPNetForSequenceClassificationLoader(folder, spark_session._jsparkSession)._java_obj
+        return MPNetForSequenceClassification(java_model=jModel)
+
+    @staticmethod
+    def pretrained(name="mpnet_sequence_classifier_ukr_message", lang="en", remote_loc=None):
+        """Downloads and loads a pretrained model.
+
+        Parameters
+        ----------
+        name : str, optional
+            Name of the pretrained model, by default
+            "MPNet_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
+        -------
+        MPNetForSequenceClassification
+            The restored model
+        """
+        from sparknlp.pretrained import ResourceDownloader
+        return ResourceDownloader.downloadModel(MPNetForSequenceClassification, name, lang, remote_loc)

sparknlp/annotator/er/entity_ruler.py

@@ -228,5 +228,5 @@ class EntityRulerModel(AnnotatorModel, HasStorageModel):
 
     @staticmethod
     def loadStorage(path, spark, storage_ref):
-        HasStorageModel.loadStorages(path, spark, storage_ref, EntityRulerModel.databases)
+        HasStorageModel.loadStorages(path, spark, storage_ref, EntityRulerModel.database)
 

sparknlp/annotator/seq2seq/__init__.py

@@ -17,3 +17,5 @@ from sparknlp.annotator.seq2seq.gpt2_transformer import *
 from sparknlp.annotator.seq2seq.marian_transformer import *
 from sparknlp.annotator.seq2seq.t5_transformer import *
 from sparknlp.annotator.seq2seq.bart_transformer import *
+from sparknlp.annotator.seq2seq.llama2_transformer import *
+from sparknlp.annotator.seq2seq.m2m100_transformer import *