spark-nlp 5.0.2__py2.py3-none-any.whl → 5.1.1__py2.py3-none-any.whl

sparknlp/annotator/classifier_dl/roberta_for_zero_shot_classification.py

@@ -0,0 +1,225 @@
+#  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 RoBertaForZeroShotClassification."""
+
+from sparknlp.common import *
+
+
+class RoBertaForZeroShotClassification(AnnotatorModel,
+                                       HasCaseSensitiveProperties,
+                                       HasBatchedAnnotate,
+                                       HasClassifierActivationProperties,
+                                       HasCandidateLabelsProperties,
+                                       HasEngine):
+    """RoBertaForZeroShotClassification using a `ModelForSequenceClassification` trained on NLI (natural language
+    inference) tasks. Equivalent of `RoBertaForSequenceClassification` 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.
+
+    Note that the model will loop through all provided labels. So the more labels you have, the
+    longer this process will take.
+
+    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 = RoBertaForZeroShotClassification.pretrained() \\
+    ...     .setInputCols(["token", "document"]) \\
+    ...     .setOutputCol("label")
+
+    The default model is ``"roberta_base_zero_shot_classifier_nli"``, 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 = RoBertaForZeroShotClassification.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 = "RoBertaForZeroShotClassification"
+
+    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 RoBerta
+        (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.RoBertaForZeroShotClassification",
+                 java_model=None):
+        super(RoBertaForZeroShotClassification, 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
+        -------
+        RoBertaForZeroShotClassification
+            The restored model
+        """
+        from sparknlp.internal import _RoBertaForZeroShotClassification
+        jModel = _RoBertaForZeroShotClassification(folder, spark_session._jsparkSession)._java_obj
+        return RoBertaForZeroShotClassification(java_model=jModel)
+
+    @staticmethod
+    def pretrained(name="roberta_base_zero_shot_classifier_nli", lang="en", remote_loc=None):
+        """Downloads and loads a pretrained model.
+
+        Parameters
+        ----------
+        name : str, optional
+            Name of the pretrained model, by default
+            "roberta_base_zero_shot_classifier_nli"
+            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
+        -------
+        RoBertaForZeroShotClassification
+            The restored model
+        """
+        from sparknlp.pretrained import ResourceDownloader
+        return ResourceDownloader.downloadModel(RoBertaForZeroShotClassification, name, lang, remote_loc)

sparknlp/annotator/embeddings/__init__.py

@@ -25,6 +25,7 @@ from sparknlp.annotator.embeddings.elmo_embeddings import *
 from sparknlp.annotator.embeddings.e5_embeddings import *
 from sparknlp.annotator.embeddings.instructor_embeddings import *
 from sparknlp.annotator.embeddings.longformer_embeddings import *
+from sparknlp.annotator.embeddings.mpnet_embeddings import *
 from sparknlp.annotator.embeddings.roberta_embeddings import *
 from sparknlp.annotator.embeddings.roberta_sentence_embeddings import *
 from sparknlp.annotator.embeddings.sentence_embeddings import *

sparknlp/annotator/embeddings/doc2vec.py

@@ -344,3 +344,9 @@ class Doc2VecModel(AnnotatorModel, HasStorageRef, HasEmbeddingsProperties):
         from sparknlp.pretrained import ResourceDownloader
         return ResourceDownloader.downloadModel(Doc2VecModel, name, lang, remote_loc)
 
+    def getVectors(self):
+        """
+        Returns the vector representation of the words as a dataframe
+        with two fields, word and vector.
+        """
+        return self._call_java("getVectors")

sparknlp/annotator/embeddings/mpnet_embeddings.py

@@ -0,0 +1,190 @@
+#  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 E5Embeddings."""
+
+from sparknlp.common import *
+
+
+class MPNetEmbeddings(AnnotatorModel,
+                           HasEmbeddingsProperties,
+                           HasCaseSensitiveProperties,
+                           HasStorageRef,
+                           HasBatchedAnnotate,
+                           HasMaxSentenceLengthLimit):
+    """Sentence embeddings using MPNet.
+
+    MPNet adopts a novel pre-training method, named masked and permuted language modeling,
+    to inherit the advantages of masked language modeling and permuted language modeling for
+    natural language understanding.
+
+    Pretrained models can be loaded with :meth:`.pretrained` of the companion
+    object:
+
+    >>> embeddings = MPNetEmbeddings.pretrained() \\
+    ...     .setInputCols(["document"]) \\
+    ...     .setOutputCol("mpnet_embeddings")
+
+
+    The default model is ``"all_mpnet_base_v2"``, if no name is provided.
+
+    For available pretrained models please see the
+    `Models Hub <https://sparknlp.org/models?q=MPNet>`__.
+
+
+    ====================== ======================
+    Input Annotation types Output Annotation type
+    ====================== ======================
+    ``DOCUMENT``            ``SENTENCE_EMBEDDINGS``
+    ====================== ======================
+
+    Parameters
+    ----------
+    batchSize
+        Size of every batch , by default 8
+    dimension
+        Number of embedding dimensions, by default 768
+    caseSensitive
+        Whether to ignore case in tokens for embeddings matching, by default False
+    maxSentenceLength
+        Max sentence length to process, by default 512
+    configProtoBytes
+        ConfigProto from tensorflow, serialized into byte array.
+
+    References
+    ----------
+    `MPNet: Masked and Permuted Pre-training for Language Understanding <https://arxiv.org/pdf/2004.09297>`__
+
+    https://github.com/microsoft/MPNet
+
+    **Paper abstract**
+
+    *BERT adopts masked language modeling (MLM) for pre-training and is one of the most successful pre-training models.
+     Since BERT neglects dependency among predicted tokens, XLNet introduces permuted language modeling (PLM) for
+     pre-training to address this problem. However, XLNet does not leverage the full position information of a sentence
+     and thus suffers from position discrepancy between pre-training and fine-tuning. In this paper, we propose MPNet,
+     a novel pre-training method that inherits the advantages of BERT and XLNet and avoids their limitations. MPNet
+     leverages the dependency among predicted tokens through permuted language modeling (vs. MLM in BERT), and takes
+     auxiliary position information as input to make the model see a full sentence and thus reducing the position
+     discrepancy (vs. PLM in XLNet). We pre-train MPNet on a large-scale dataset (over 160GB text corpora) and fine-tune
+     on a variety of down-streaming tasks (GLUE, SQuAD, etc). Experimental results show that MPNet outperforms MLM and
+     PLM by a large margin, and achieves better results on these tasks compared with previous state-of-the-art
+     pre-trained methods (e.g., BERT, XLNet, RoBERTa) under the same model setting.*
+
+    Examples
+    --------
+    >>> import sparknlp
+    >>> from sparknlp.base import *
+    >>> from sparknlp.annotator import *
+    >>> from pyspark.ml import Pipeline
+    >>> documentAssembler = DocumentAssembler() \\
+    ...     .setInputCol("text") \\
+    ...     .setOutputCol("document")
+    >>> embeddings = MPNetEmbeddings.pretrained() \\
+    ...     .setInputCols(["document"]) \\
+    ...     .setOutputCol("mpnet_embeddings")
+    >>> embeddingsFinisher = EmbeddingsFinisher() \\
+    ...     .setInputCols(["mpnet_embeddings"]) \\
+    ...     .setOutputCols("finished_embeddings") \\
+    ...     .setOutputAsVector(True)
+    >>> pipeline = Pipeline().setStages([
+    ...     documentAssembler,
+    ...     embeddings,
+    ...     embeddingsFinisher
+    ... ])
+    >>> data = spark.createDataFrame([["This is an example sentence", "Each sentence is converted"]]).toDF("text")
+    >>> result = pipeline.fit(data).transform(data)
+    >>> result.selectExpr("explode(finished_embeddings) as result").show(5, 80)
+    +--------------------------------------------------------------------------------+
+    |                                                                          result|
+    +--------------------------------------------------------------------------------+
+    |[[0.022502584, -0.078291744, -0.023030775, -0.0051000593, -0.080340415, 0.039...|
+    |[[0.041702367, 0.0010974605, -0.015534201, 0.07092203, -0.0017729357, 0.04661...|
+    +--------------------------------------------------------------------------------+
+    """
+
+    name = "MPNetEmbeddings"
+
+    inputAnnotatorTypes = [AnnotatorType.DOCUMENT]
+
+    outputAnnotatorType = AnnotatorType.SENTENCE_EMBEDDINGS
+    configProtoBytes = Param(Params._dummy(),
+                             "configProtoBytes",
+                             "ConfigProto from tensorflow, serialized into byte array. Get with config_proto.SerializeToString()",
+                             TypeConverters.toListInt)
+
+
+    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.embeddings.MPNetEmbeddings", java_model=None):
+        super(MPNetEmbeddings, self).__init__(
+            classname=classname,
+            java_model=java_model
+        )
+        self._setDefault(
+            dimension=768,
+            batchSize=8,
+            maxSentenceLength=512,
+            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
+        -------
+        MPNetEmbeddings
+            The restored model
+        """
+        from sparknlp.internal import _MPNetLoader
+        jModel = _MPNetLoader(folder, spark_session._jsparkSession)._java_obj
+        return MPNetEmbeddings(java_model=jModel)
+
+    @staticmethod
+    def pretrained(name="all_mpnet_base_v2", lang="en", remote_loc=None):
+        """Downloads and loads a pretrained model.
+
+        Parameters
+        ----------
+        name : str, optional
+            Name of the pretrained model, by default "all_mpnet_base_v2"
+        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
+        -------
+        MPNetEmbeddings
+            The restored model
+        """
+        from sparknlp.pretrained import ResourceDownloader
+        return ResourceDownloader.downloadModel(MPNetEmbeddings, name, lang, remote_loc)

sparknlp/annotator/embeddings/word2vec.py

@@ -345,3 +345,9 @@ class Word2VecModel(AnnotatorModel, HasStorageRef, HasEmbeddingsProperties):
         from sparknlp.pretrained import ResourceDownloader
         return ResourceDownloader.downloadModel(Word2VecModel, name, lang, remote_loc)
 
+    def getVectors(self):
+        """
+        Returns the vector representation of the words as a dataframe
+        with two fields, word and vector.
+        """
+        return self._call_java("getVectors")

sparknlp/annotator/openai/__init__.py

@@ -0,0 +1,16 @@
+#  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.
+"""Module of annotators for openai integration."""
+from sparknlp.annotator.openai.openai_completion import *
+from sparknlp.annotator.openai.openai_embeddings import *