spark-nlp 6.1.2rc1__py2.py3-none-any.whl → 6.1.3rc1__py2.py3-none-any.whl

{spark_nlp-6.1.2rc1.dist-info → spark_nlp-6.1.3rc1.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: spark-nlp
-Version: 6.1.2rc1
+Version: 6.1.3rc1
 Summary: John Snow Labs Spark NLP is a natural language processing library built on top of Apache Spark ML. It provides simple, performant & accurate NLP annotations for machine learning pipelines, that scale easily in a distributed environment.
 Home-page: https://github.com/JohnSnowLabs/spark-nlp
 Author: John Snow Labs
@@ -102,7 +102,7 @@ $ java -version
 $ conda create -n sparknlp python=3.7 -y
 $ conda activate sparknlp
 # spark-nlp by default is based on pyspark 3.x
-$ pip install spark-nlp==6.1.1 pyspark==3.3.1
+$ pip install spark-nlp==6.1.3 pyspark==3.3.1
 ```
 
 In Python console or Jupyter `Python3` kernel:
@@ -168,7 +168,7 @@ For a quick example of using pipelines and models take a look at our official [d
 
 ### Apache Spark Support
 
-Spark NLP *6.1.1* has been built on top of Apache Spark 3.4 while fully supports Apache Spark 3.0.x, 3.1.x, 3.2.x, 3.3.x, 3.4.x, and 3.5.x
+Spark NLP *6.1.3* has been built on top of Apache Spark 3.4 while fully supports Apache Spark 3.0.x, 3.1.x, 3.2.x, 3.3.x, 3.4.x, and 3.5.x
 
 | Spark NLP | Apache Spark 3.5.x | Apache Spark 3.4.x | Apache Spark 3.3.x | Apache Spark 3.2.x | Apache Spark 3.1.x | Apache Spark 3.0.x | Apache Spark 2.4.x | Apache Spark 2.3.x |
 |-----------|--------------------|--------------------|--------------------|--------------------|--------------------|--------------------|--------------------|--------------------|
@@ -198,7 +198,7 @@ Find out more about 4.x `SparkNLP` versions in our official [documentation](http
 
 ### Databricks Support
 
-Spark NLP 6.1.1 has been tested and is compatible with the following runtimes:
+Spark NLP 6.1.3 has been tested and is compatible with the following runtimes:
 
 | **CPU**            | **GPU**            |
 |--------------------|--------------------|
@@ -216,7 +216,7 @@ We are compatible with older runtimes. For a full list check databricks support
 
 ### EMR Support
 
-Spark NLP 6.1.1 has been tested and is compatible with the following EMR releases:
+Spark NLP 6.1.3 has been tested and is compatible with the following EMR releases:
 
 | **EMR Release**    |
 |--------------------|

{spark_nlp-6.1.2rc1.dist-info → spark_nlp-6.1.3rc1.dist-info}/RECORD

@@ -3,7 +3,7 @@ com/johnsnowlabs/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,
 com/johnsnowlabs/ml/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 com/johnsnowlabs/ml/ai/__init__.py,sha256=YQiK2M7U4d8y5irPy_HB8ae0mSpqS9583MH44pnKJXc,295
 com/johnsnowlabs/nlp/__init__.py,sha256=DPIVXtONO5xXyOk-HB0-sNiHAcco17NN13zPS_6Uw8c,294
-sparknlp/__init__.py,sha256=sEwJ50P2C-LGn-MZ8oI6jO6N0OutYSL3b6bCVkOo2wc,13814
+sparknlp/__init__.py,sha256=UR0dRykX67j-Ksuzk5Xe-Mod5qCK24iBjHHa0omOp2w,13814
 sparknlp/annotation.py,sha256=I5zOxG5vV2RfPZfqN9enT1i4mo6oBcn3Lrzs37QiOiA,5635
 sparknlp/annotation_audio.py,sha256=iRV_InSVhgvAwSRe9NTbUH9v6OGvTM-FPCpSAKVu0mE,1917
 sparknlp/annotation_image.py,sha256=xhCe8Ko-77XqWVuuYHFrjKqF6zPd8Z-RY_rmZXNwCXU,2547
@@ -19,10 +19,13 @@ sparknlp/annotator/document_character_text_splitter.py,sha256=oNrOKJAKO2h1wr0bEu
 sparknlp/annotator/document_normalizer.py,sha256=hU2fG6vaPfdngQapoeSu-_zS_LiBZNp2tcVBGl6eTpk,10973
 sparknlp/annotator/document_token_splitter.py,sha256=-9xbQ9pVAjcKHQQrSk6Cb7f8W1cblCLwWXTNR8kFptA,7499
 sparknlp/annotator/document_token_splitter_test.py,sha256=NWO9mwhAIUJFuxPofB3c39iUm_6vKp4pteDsBOTH8ng,2684
+sparknlp/annotator/extractor.py,sha256=GObGwyl602jrt6EbnhZO2-KptrzVRop_5uA8HewpWcc,5303
 sparknlp/annotator/graph_extraction.py,sha256=b4SB3B_hFgCJT4e5Jcscyxdzfbvw3ujKTa6UNgX5Lhc,14471
 sparknlp/annotator/lemmatizer.py,sha256=w1nNMln2HgM4O1DOaISo5AGyzzFHuaIDQqWFcr4JmcA,8970
 sparknlp/annotator/n_gram_generator.py,sha256=KRX5xfxmorOfYQkQHZWkkXjwjC13gDTAXnukwgz6hKU,5274
 sparknlp/annotator/normalizer.py,sha256=7AkAOB-e8b2uyUBwYoq9HvMPijOwV3wEoxcB3BVsr4w,8780
+sparknlp/annotator/openai_completion.py,sha256=kigEY5G2lZl2THezx-WDDByJKY1Wx99CPoZdkpik9x4,16899
+sparknlp/annotator/openai_embeddings.py,sha256=eVnLK9t1jDOS58K2YHOyHakILG_4rGtzTIWelqieY9g,109860
 sparknlp/annotator/stemmer.py,sha256=Tl48voyG9wqbT5MAA1hDKW90NorU8rIDhttJxOo1s3Q,2948
 sparknlp/annotator/stop_words_cleaner.py,sha256=Z9yI9AWDIAXbPM2X6n84voiW31Z20XofCL-tTQNo5ro,7015
 sparknlp/annotator/tf_ner_dl_graph_builder.py,sha256=ovsRBUfw9lJkuetmrcYRmW1Ll-33sdDPi4xJ0M_Fs7k,6379
@@ -64,6 +67,7 @@ sparknlp/annotator/classifier_dl/mpnet_for_question_answering.py,sha256=w9hHLrQb
 sparknlp/annotator/classifier_dl/mpnet_for_sequence_classification.py,sha256=M__giFElL6Q3I88QD6OoXDzdQDk_Zp5sS__Kh_XpLdo,7308
 sparknlp/annotator/classifier_dl/mpnet_for_token_classification.py,sha256=SgFAJcv7ZE3BmJOehK_CjAaueqaaK6PR33zA5aE9-Ww,6754
 sparknlp/annotator/classifier_dl/multi_classifier_dl.py,sha256=ylKQzS7ROyeKeiOF4BZiIkQV1sfrnfUUQ9LXFSFK_Vo,16045
+sparknlp/annotator/classifier_dl/roberta_bert_for_zero_shot_classification.py,sha256=nP0D_jg8xPFUMP9uGNvmACIqfwAneDddVXbioHLHFJ0,8818
 sparknlp/annotator/classifier_dl/roberta_for_multiple_choice.py,sha256=SlzkA_fKurWOQDhvWlEBiMUfLgIoaRRglIdENMv7u38,6008
 sparknlp/annotator/classifier_dl/roberta_for_question_answering.py,sha256=WRxu1uhXnY9C4UHdtJ8qiVGhPSX7sCdSaML0AWHOdJw,6471
 sparknlp/annotator/classifier_dl/roberta_for_sequence_classification.py,sha256=z97uH5WkG8kPX1Y9qtpLwD7egl0kzbVmxtq4xzZgNNI,7857
@@ -167,8 +171,9 @@ sparknlp/annotator/sentence/sentence_detector_dl.py,sha256=-Osj9Bm9KyZRTAWkOsK9c
 sparknlp/annotator/sentiment/__init__.py,sha256=Lq3vKaZS1YATLMg0VNXSVtkWL5q5G9taGBvdrvSwnfg,766
 sparknlp/annotator/sentiment/sentiment_detector.py,sha256=m545NGU0Xzg_PO6_qIfpli1uZj7JQcyFgqe9R6wAPFI,8154
 sparknlp/annotator/sentiment/vivekn_sentiment.py,sha256=4rpXWDgzU6ddnbrSCp9VdLb2epCc9oZ3c6XcqxEw8nk,9655
-sparknlp/annotator/seq2seq/__init__.py,sha256=Aj43G1MuQE0mW7LakCWPjiTkIGl7iHPAnKIwT_DfdIM,1781
+sparknlp/annotator/seq2seq/__init__.py,sha256=aDiph00Hyq7L8uDY0frtyuHtqFodBqTMbixx_nq4z1I,1841
 sparknlp/annotator/seq2seq/auto_gguf_model.py,sha256=yhZQHMHfp88rQvLHTWyS-8imZrwqp-8RQQwnw6PmHfc,11749
+sparknlp/annotator/seq2seq/auto_gguf_reranker.py,sha256=QpGpyO1_epWzMospTFrfVVLj2KZ_n3gbHN269vo9fbU,12667
 sparknlp/annotator/seq2seq/auto_gguf_vision_model.py,sha256=swBek2026dW6BOX5O9P8Uq41X2GC71VGW0ADFeUIvs0,15299
 sparknlp/annotator/seq2seq/bart_transformer.py,sha256=I1flM4yeCzEAKOdQllBC30XuedxVJ7ferkFhZ6gwEbE,18481
 sparknlp/annotator/seq2seq/cohere_transformer.py,sha256=43LZBVazZMgJRCsN7HaYjVYfJ5hRMV95QZyxMtXq-m4,13496
@@ -215,6 +220,7 @@ sparknlp/base/multi_document_assembler.py,sha256=4htET1fRAeOB6zhsNXsBq5rKZvn-LGD
 sparknlp/base/prompt_assembler.py,sha256=_C_9MdHqsxUjSOa3TqCV-6sSfSiRyhfHBQG5m7RlqxY,11578
 sparknlp/base/recursive_pipeline.py,sha256=V9rTnu8KMwgjoceykN9pF1mKGtOkkuiC_n9v8dE3LDk,4279
 sparknlp/base/table_assembler.py,sha256=Kxu3R2fY6JgCxEc07ibsMsjip6dgcPDHLiWAZ8gC_d8,5102
+sparknlp/base/token2_chunk.py,sha256=FtS2Doav9xL1IrC9ZUU4iXqyipp-iT3g68kZt-7YCcQ,2674
 sparknlp/base/token_assembler.py,sha256=qiHry07L7mVCqeHSH6hHxLygv1AsfZIE4jy1L75L3Do,5075
 sparknlp/common/__init__.py,sha256=MJuE__T1YS8f3As7X5sgzHibGjDeiFkQ5vc2bEEf0Ww,1148
 sparknlp/common/annotator_approach.py,sha256=CbkyaWl6rRX_VaXz2xJCjofijRGJGeJCsqQTDQgNTAw,1765
@@ -228,7 +234,7 @@ sparknlp/common/read_as.py,sha256=imxPGwV7jr4Li_acbo0OAHHRGCBbYv-akzEGaBWEfcY,12
 sparknlp/common/recursive_annotator_approach.py,sha256=vqugBw22cE3Ff7PIpRlnYFuOlchgL0nM26D8j-NdpqU,1449
 sparknlp/common/storage.py,sha256=D91H3p8EIjNspjqAYu6ephRpCUtdcAir4_PrAbkIQWE,4842
 sparknlp/common/utils.py,sha256=Yne6yYcwKxhOZC-U4qfYoDhWUP_6BIaAjI5X_P_df1E,1306
-sparknlp/internal/__init__.py,sha256=f5kxLz6bEX8FCMo6lek30MXbn_lDC-dBTI9s_fARblI,40748
+sparknlp/internal/__init__.py,sha256=m7Y7y-IPkB6aJuGUCM54eOueGOEt65C3ujAzN16hegQ,40995
 sparknlp/internal/annotator_java_ml.py,sha256=UGPoThG0rGXUOXGSQnDzEDW81Mu1s5RPF29v7DFyE3c,1187
 sparknlp/internal/annotator_transformer.py,sha256=fXmc2IWXGybqZpbEU9obmbdBYPc798y42zvSB4tqV9U,1448
 sparknlp/internal/extended_java_wrapper.py,sha256=hwP0133-hDiDf5sBF-P3MtUsuuDj1PpQbtGZQIRwzfk,2240
@@ -248,6 +254,7 @@ sparknlp/reader/__init__.py,sha256=-Toj3AIBki-zXPpV8ezFTI2LX1yP_rK2bhpoa8nBkTw,6
 sparknlp/reader/enums.py,sha256=MNGug9oJ1BBLM1Pbske13kAabalDzHa2kucF5xzFpHs,770
 sparknlp/reader/pdf_to_text.py,sha256=eWw-cwjosmcSZ9eHso0F5QQoeGBBnwsOhzhCXXvMjZA,7169
 sparknlp/reader/reader2doc.py,sha256=LRqfaL9nidhlPkJIwTJo7SnGYmNNfOqwEdrsWYGEdnI,7146
+sparknlp/reader/reader2image.py,sha256=JIwgVtznBpSExLl3JX7QY3BT4CUmZf1JWbsSwKLV1aY,3099
 sparknlp/reader/reader2table.py,sha256=GC6Yz0gQ83S6XKOi329TUNQuAvLrBxysqDkDRZPvcYA,4759
 sparknlp/reader/sparknlp_reader.py,sha256=MJs8v_ECYaV1SOabI1L_2MkVYEDVImtwgbYypO7DJSY,20623
 sparknlp/training/__init__.py,sha256=qREi9u-5Vc2VjpL6-XZsyvu5jSEIdIhowW7_kKaqMqo,852
@@ -280,7 +287,7 @@ sparknlp/training/_tf_graph_builders_1x/ner_dl/dataset_encoder.py,sha256=R4yHFN3
 sparknlp/training/_tf_graph_builders_1x/ner_dl/ner_model.py,sha256=EoCSdcIjqQ3wv13MAuuWrKV8wyVBP0SbOEW41omHlR0,23189
 sparknlp/training/_tf_graph_builders_1x/ner_dl/ner_model_saver.py,sha256=k5CQ7gKV6HZbZMB8cKLUJuZxoZWlP_DFWdZ--aIDwsc,2356
 sparknlp/training/_tf_graph_builders_1x/ner_dl/sentence_grouper.py,sha256=pAxjWhjazSX8Vg0MFqJiuRVw1IbnQNSs-8Xp26L4nko,870
-spark_nlp-6.1.2rc1.dist-info/METADATA,sha256=4qK5_LPihfkDmSrLBQgH38R_VE5lzDnsygPpOccUTdc,19777
-spark_nlp-6.1.2rc1.dist-info/WHEEL,sha256=JNWh1Fm1UdwIQV075glCn4MVuCRs0sotJIq-J6rbxCU,109
-spark_nlp-6.1.2rc1.dist-info/top_level.txt,sha256=uuytur4pyMRw2H_txNY2ZkaucZHUs22QF8-R03ch_-E,13
-spark_nlp-6.1.2rc1.dist-info/RECORD,,
+spark_nlp-6.1.3rc1.dist-info/METADATA,sha256=q-hbjHon_67zz6Zp0s7KhdoSSIQw0z9l-tzYPDs6pfU,19777
+spark_nlp-6.1.3rc1.dist-info/WHEEL,sha256=JNWh1Fm1UdwIQV075glCn4MVuCRs0sotJIq-J6rbxCU,109
+spark_nlp-6.1.3rc1.dist-info/top_level.txt,sha256=uuytur4pyMRw2H_txNY2ZkaucZHUs22QF8-R03ch_-E,13
+spark_nlp-6.1.3rc1.dist-info/RECORD,,

sparknlp/__init__.py

@@ -66,7 +66,7 @@ sys.modules['com.johnsnowlabs.ml.ai'] = annotator
 annotators = annotator
 embeddings = annotator
 
-__version__ = "6.1.1"
+__version__ = "6.1.3"
 
 
 def start(gpu=False,

sparknlp/annotator/classifier_dl/roberta_bert_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/extractor.py

@@ -0,0 +1,174 @@
+#  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 Extractor."""
+from sparknlp.common import *
+
+class Extractor(AnnotatorModel):
+    name = "Extractor"
+
+    inputAnnotatorTypes = [AnnotatorType.DOCUMENT]
+
+    outputAnnotatorType = AnnotatorType.CHUNK
+
+    emailDateTimeTzPattern = Param(Params._dummy(),
+                                   "emailDateTimeTzPattern",
+                                   "Specifies the date-time pattern for email timestamps, including time zone formatting.",
+                                   typeConverter=TypeConverters.toString)
+
+    emailAddress = Param(
+        Params._dummy(),
+        "emailAddress",
+        "Specifies the pattern for email addresses.",
+        typeConverter=TypeConverters.toString
+    )
+
+    ipAddressPattern = Param(
+        Params._dummy(),
+        "ipAddressPattern",
+        "Specifies the pattern for IP addresses.",
+        typeConverter=TypeConverters.toString
+    )
+
+    ipAddressNamePattern = Param(
+        Params._dummy(),
+        "ipAddressNamePattern",
+        "Specifies the pattern for IP addresses with names.",
+        typeConverter=TypeConverters.toString
+    )
+
+    mapiIdPattern = Param(
+        Params._dummy(),
+        "mapiIdPattern",
+        "Specifies the pattern for MAPI IDs.",
+        typeConverter=TypeConverters.toString
+    )
+
+    usPhoneNumbersPattern = Param(
+        Params._dummy(),
+        "usPhoneNumbersPattern",
+        "Specifies the pattern for US phone numbers.",
+        typeConverter=TypeConverters.toString
+    )
+
+    imageUrlPattern = Param(
+        Params._dummy(),
+        "imageUrlPattern",
+        "Specifies the pattern for image URLs.",
+        typeConverter=TypeConverters.toString
+    )
+
+    textPattern = Param(
+        Params._dummy(),
+        "textPattern",
+        "Specifies the pattern for text after and before.",
+        typeConverter=TypeConverters.toString
+    )
+
+    extractorMode = Param(
+        Params._dummy(),
+        "extractorMode",
+        "possible values: " +
+        "email_date, email_address, ip_address, ip_address_name, mapi_id, us_phone_numbers, image_urls, bullets, text_after, text_before",
+        typeConverter=TypeConverters.toString
+    )
+
+    def setEmailDateTimeTzPattern(self, value):
+        """Sets specifies the date-time pattern for email timestamps, including time zone formatting.
+
+        Parameters
+        ----------
+        value : str
+            Specifies the date-time pattern for email timestamps, including time zone formatting.
+        """
+        return self._set(emailDateTimeTzPattern=value)
+
+    def setEmailAddress(self, value):
+        """Sets the pattern for email addresses.
+
+        Parameters
+        ----------
+        value : str
+            Specifies the pattern for email addresses.
+        """
+        return self._set(emailAddress=value)
+
+    def setIpAddressPattern(self, value):
+        """Sets the pattern for IP addresses.
+
+        Parameters
+        ----------
+        value : str
+            Specifies the pattern for IP addresses.
+        """
+        return self._set(ipAddressPattern=value)
+
+    def setIpAddressNamePattern(self, value):
+        """Sets the pattern for IP addresses with names.
+
+        Parameters
+        ----------
+        value : str
+            Specifies the pattern for IP addresses with names.
+        """
+        return self._set(ipAddressNamePattern=value)
+
+    def setMapiIdPattern(self, value):
+        """Sets the pattern for MAPI IDs.
+
+        Parameters
+        ----------
+        value : str
+            Specifies the pattern for MAPI IDs.
+        """
+        return self._set(mapiIdPattern=value)
+
+    def setUsPhoneNumbersPattern(self, value):
+        """Sets the pattern for US phone numbers.
+
+        Parameters
+        ----------
+        value : str
+            Specifies the pattern for US phone numbers.
+        """
+        return self._set(usPhoneNumbersPattern=value)
+
+    def setImageUrlPattern(self, value):
+        """Sets the pattern for image URLs.
+
+        Parameters
+        ----------
+        value : str
+            Specifies the pattern for image URLs.
+        """
+        return self._set(imageUrlPattern=value)
+
+    def setTextPattern(self, value):
+        """Sets the pattern for text after and before.
+
+        Parameters
+        ----------
+        value : str
+            Specifies the pattern for text after and before.
+        """
+        return self._set(textPattern=value)
+
+    def setExtractorMode(self, value):
+        return self._set(extractorMode=value)
+
+    @keyword_only
+    def __init__(self, classname="com.johnsnowlabs.nlp.annotators.Extractor", java_model=None):
+        super(Extractor, self).__init__(
+            classname=classname,
+            java_model=java_model
+        )