spark-nlp 4.2.6__py2.py3-none-any.whl → 6.2.1__py2.py3-none-any.whl

sparknlp/annotator/cleaners/extractor.py

@@ -0,0 +1,191 @@
+#  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
+    )
+
+    index = Param(
+        Params._dummy(),
+        "index",
+        "Specifies the index of the pattern to extract in text after or before",
+        typeConverter=TypeConverters.toInt
+    )
+
+    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)
+
+    def setIndex(self, value):
+        """Sets the index of the pattern to extract in text after or before.
+
+        Parameters
+        ----------
+        value : int
+            Specifies the index of the pattern to extract in text after or before.
+        """
+        return self._set(index=value)
+
+    @keyword_only
+    def __init__(self, classname="com.johnsnowlabs.nlp.annotators.cleaners.Extractor", java_model=None):
+        super(Extractor, self).__init__(
+            classname=classname,
+            java_model=java_model
+        )

sparknlp/annotator/coref/spanbert_coref.py

@@ -20,7 +20,8 @@ class SpanBertCorefModel(AnnotatorModel,
                          HasEmbeddingsProperties,
                          HasCaseSensitiveProperties,
                          HasStorageRef,
-                         HasEngine):
+                         HasEngine,
+                         HasMaxSentenceLengthLimit):
     """
     A coreference resolution model based on SpanBert.
 
@@ -38,10 +39,10 @@ class SpanBertCorefModel(AnnotatorModel,
 
     The default model is ``"spanbert_base_coref"``, if no name is provided. For available
     pretrained models please see the `Models Hub
-    <https://nlp.johnsnowlabs.com/models?q=coref>`__.
+    <https://sparknlp.org/models?q=coref>`__.
 
     For extended examples of usage, see the
-    `Spark NLP Workshop <https://github.com/JohnSnowLabs/spark-nlp-workshop/blob/master/jupyter/annotation/english/coreference-resolution/Coreference_Resolution_SpanBertCorefModel.ipynb>`__.
+    `Examples <https://github.com/JohnSnowLabs/spark-nlp/blob/master/examples/python/annotation/text/english/coreference-resolution/Coreference_Resolution_SpanBertCorefModel.ipynb>`__.
 
     ====================== ======================
     Input Annotation types Output Annotation type
@@ -114,11 +115,6 @@ class SpanBertCorefModel(AnnotatorModel,
 
     outputAnnotatorType = AnnotatorType.DEPENDENCY
 
-    maxSentenceLength = Param(Params._dummy(),
-                              "maxSentenceLength",
-                              "Max sentence length to process",
-                              typeConverter=TypeConverters.toInt)
-
     maxSegmentLength = Param(Params._dummy(),
                              "maxSegmentLength",
                              "Max segment length",
@@ -144,16 +140,6 @@ class SpanBertCorefModel(AnnotatorModel,
         """
         return self._set(configProtoBytes=b)
 
-    def setMaxSentenceLength(self, value):
-        """Sets max sentence length to process.
-
-        Parameters
-        ----------
-        value : int
-            Max sentence length to process
-        """
-        return self._set(maxSentenceLength=value)
-
     def setMaxSegmentLength(self, value):
         """Sets max segment length
 

sparknlp/annotator/cv/__init__.py

@@ -12,3 +12,18 @@
 #  See the License for the specific language governing permissions and
 #  limitations under the License.
 from sparknlp.annotator.cv.vit_for_image_classification import *
+from sparknlp.annotator.cv.swin_for_image_classification import *
+from sparknlp.annotator.cv.convnext_for_image_classification import *
+from sparknlp.annotator.cv.vision_encoder_decoder_for_image_captioning import *
+from sparknlp.annotator.cv.clip_for_zero_shot_classification import *
+from sparknlp.annotator.cv.blip_for_question_answering import *
+from sparknlp.annotator.cv.janus_for_multimodal import *
+from sparknlp.annotator.cv.mllama_for_multimodal import *
+from sparknlp.annotator.cv.qwen2vl_transformer import *
+from sparknlp.annotator.cv.llava_for_multimodal import *
+from sparknlp.annotator.cv.phi3_vision_for_multimodal import *
+from sparknlp.annotator.cv.smolvlm_transformer import *
+from sparknlp.annotator.cv.paligemma_for_multimodal import *
+from sparknlp.annotator.cv.gemma3_for_multimodal import *
+from sparknlp.annotator.cv.internvl_for_multimodal import *
+from sparknlp.annotator.cv.florence2_transformer import *

sparknlp/annotator/cv/blip_for_question_answering.py

@@ -0,0 +1,172 @@
+#  Copyright 2017-2024 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 BLIPForQuestionAnswering(AnnotatorModel,
+                               HasBatchedAnnotateImage,
+                               HasImageFeatureProperties,
+                               HasEngine,
+                               HasCandidateLabelsProperties,
+                               HasRescaleFactor):
+    """BLIPForQuestionAnswering can load BLIP models  for visual question answering.
+    The model consists of a vision encoder, a text encoder as well as a text decoder.
+    The vision encoder will encode the input image, the text encoder will encode the input question together
+    with the encoding of the image, and the text decoder will output the answer to the question.
+
+    Pretrained models can be loaded with :meth:`.pretrained` of the companion
+    object:
+
+    >>> visualQAClassifier = BLIPForQuestionAnswering.pretrained() \\
+    ...     .setInputCols(["image_assembler"]) \\
+    ...     .setOutputCol("answer")
+
+    The default model is ``"blip_vqa_base"``, 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
+    ====================== ======================
+    ``IMAGE``              ``DOCUMENT``
+    ====================== ======================
+
+    Parameters
+    ----------
+    batchSize
+        Batch size. Large values allows faster processing but requires more
+        memory, by default 2
+    configProtoBytes
+        ConfigProto from tensorflow, serialized into byte array.
+    maxSentenceLength
+        Max sentence length to process, by default 50
+
+    Examples
+    --------
+    >>> import sparknlp
+    >>> from sparknlp.base import *
+    >>> from sparknlp.annotator import *
+    >>> from pyspark.ml import Pipeline
+    >>> image_df = SparkSessionForTest.spark.read.format("image").load(path=images_path)
+    >>> test_df = image_df.withColumn("text", lit("What's this picture about?"))
+    >>> imageAssembler = ImageAssembler() \\
+    ...     .setInputCol("image") \\
+    ...     .setOutputCol("image_assembler")
+    >>> visualQAClassifier = BLIPForQuestionAnswering.pretrained() \\
+    ...     .setInputCols("image_assembler") \\
+    ...     .setOutputCol("answer") \\
+    ...     .setSize(384)
+    >>> pipeline = Pipeline().setStages([
+    ...     imageAssembler,
+    ...     visualQAClassifier
+    ... ])
+    >>> result = pipeline.fit(test_df).transform(test_df)
+    >>> result.select("image_assembler.origin", "answer.result").show(false)
+    +--------------------------------------+------+
+    |origin                                |result|
+    +--------------------------------------+------+
+    |[file:///content/images/cat_image.jpg]|[cats]|
+    +--------------------------------------+------+
+    """
+
+    name = "BLIPForQuestionAnswering"
+
+    inputAnnotatorTypes = [AnnotatorType.IMAGE]
+
+    outputAnnotatorType = AnnotatorType.DOCUMENT
+
+    configProtoBytes = Param(Params._dummy(),
+                             "configProtoBytes",
+                             "ConfigProto from tensorflow, serialized into byte array. Get with "
+                             "config_proto.SerializeToString()",
+                             TypeConverters.toListInt)
+
+    maxSentenceLength = Param(Params._dummy(),
+                            "maxSentenceLength",
+                            "Maximum sentence length that the annotator will process. Above this, the sentence is skipped",
+                            typeConverter=TypeConverters.toInt)
+
+    def setMaxSentenceSize(self, value):
+        """Sets Maximum sentence length that the annotator will process, by
+        default 50.
+
+        Parameters
+        ----------
+        value : int
+            Maximum sentence length that the annotator will process
+        """
+        return self._set(maxSentenceLength=value)
+
+
+    @keyword_only
+    def __init__(self, classname="com.johnsnowlabs.nlp.annotators.cv.BLIPForQuestionAnswering",
+                 java_model=None):
+        super(BLIPForQuestionAnswering, self).__init__(
+            classname=classname,
+            java_model=java_model
+        )
+        self._setDefault(
+            batchSize=2,
+            size=384,
+            maxSentenceLength=50
+        )
+
+    @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
+        -------
+        CLIPForZeroShotClassification
+            The restored model
+        """
+        from sparknlp.internal import _BLIPForQuestionAnswering
+        jModel = _BLIPForQuestionAnswering(folder, spark_session._jsparkSession)._java_obj
+        return BLIPForQuestionAnswering(java_model=jModel)
+
+    @staticmethod
+    def pretrained(name="blip_vqa_base", lang="en", remote_loc=None):
+        """Downloads and loads a pretrained model.
+
+        Parameters
+        ----------
+        name : str, optional
+            Name of the pretrained model, by default
+            "blip_vqa_tf"
+        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
+        -------
+        CLIPForZeroShotClassification
+            The restored model
+        """
+        from sparknlp.pretrained import ResourceDownloader
+        return ResourceDownloader.downloadModel(BLIPForQuestionAnswering, name, lang, remote_loc)

sparknlp/annotator/cv/clip_for_zero_shot_classification.py

@@ -0,0 +1,193 @@
+#  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 concerning CLIPForZeroShotClassification."""
+
+from sparknlp.common import *
+
+
+class CLIPForZeroShotClassification(AnnotatorModel,
+                                    HasBatchedAnnotateImage,
+                                    HasImageFeatureProperties,
+                                    HasEngine,
+                                    HasCandidateLabelsProperties,
+                                    HasRescaleFactor):
+    """Zero Shot Image Classifier based on CLIP.
+
+    CLIP (Contrastive Language-Image Pre-Training) is a neural network that was trained on image
+    and text pairs. It has the ability to predict images without training on any hard-coded
+    labels. This makes it very flexible, as labels can be provided during inference. This is
+    similar to the zero-shot capabilities of the GPT-2 and 3 models.
+
+    Pretrained models can be loaded with ``pretrained`` of the companion object:
+
+
+    .. code-block:: python
+
+        imageClassifier = CLIPForZeroShotClassification.pretrained() \\
+            .setInputCols(["image_assembler"]) \\
+            .setOutputCol("label")
+
+
+    The default model is ``"zero_shot_classifier_clip_vit_base_patch32"``, if no name is provided.
+
+    For available pretrained models please see the
+    `Models Hub <https://sparknlp.org/models?task=Zero-Shot+Classification>`__.
+
+    Models from the HuggingFace 🤗 Transformers library are also compatible with Spark NLP 🚀. To
+    see which models are compatible and how to import them see
+    https://github.com/JohnSnowLabs/spark-nlp/discussions/5669 and to see more extended
+    examples, see
+    `CLIPForZeroShotClassificationTestSpec <https://github.com/JohnSnowLabs/spark-nlp/blob/master/src/test/scala/com/johnsnowlabs/nlp/annotators/cv/CLIPForZeroShotClassificationTestSpec.scala>`__.
+
+    ====================== ======================
+    Input Annotation types Output Annotation type
+    ====================== ======================
+    ``IMAGE``              ``CATEGORY``
+    ====================== ======================
+
+    Parameters
+    ----------
+    batchSize
+        Batch size, by default `2`.
+    candidateLabels
+        Array of labels for classification
+
+    Examples
+    --------
+    >>> import sparknlp
+    >>> from sparknlp.base import *
+    >>> from sparknlp.annotator import *
+    >>> from pyspark.ml import Pipeline
+    >>> imageDF = spark.read \\
+    ...     .format("image") \\
+    ...     .option("dropInvalid", value = True) \\
+    ...     .load("src/test/resources/image/")
+    >>> imageAssembler = ImageAssembler() \\
+    ...     .setInputCol("image") \\
+    ...     .setOutputCol("image_assembler")
+    >>> candidateLabels = [
+    ...     "a photo of a bird",
+    ...     "a photo of a cat",
+    ...     "a photo of a dog",
+    ...     "a photo of a hen",
+    ...     "a photo of a hippo",
+    ...     "a photo of a room",
+    ...     "a photo of a tractor",
+    ...     "a photo of an ostrich",
+    ...     "a photo of an ox"]
+    >>> imageClassifier = CLIPForZeroShotClassification \\
+    ...     .pretrained() \\
+    ...     .setInputCols(["image_assembler"]) \\
+    ...     .setOutputCol("label") \\
+    ...     .setCandidateLabels(candidateLabels)
+    >>> pipeline = Pipeline().setStages([imageAssembler, imageClassifier])
+    >>> pipelineDF = pipeline.fit(imageDF).transform(imageDF)
+    >>> pipelineDF \\
+    ...   .selectExpr("reverse(split(image.origin, '/'))[0] as image_name", "label.result") \\
+    ...   .show(truncate=False)
+    +-----------------+-----------------------+
+    |image_name       |result                 |
+    +-----------------+-----------------------+
+    |palace.JPEG      |[a photo of a room]    |
+    |egyptian_cat.jpeg|[a photo of a cat]     |
+    |hippopotamus.JPEG|[a photo of a hippo]   |
+    |hen.JPEG         |[a photo of a hen]     |
+    |ostrich.JPEG     |[a photo of an ostrich]|
+    |junco.JPEG       |[a photo of a bird]    |
+    |bluetick.jpg     |[a photo of a dog]     |
+    |chihuahua.jpg    |[a photo of a dog]     |
+    |tractor.JPEG     |[a photo of a tractor] |
+    |ox.JPEG          |[a photo of an ox]     |
+    +-----------------+-----------------------+
+    """
+    name = "CLIPForZeroShotClassification"
+
+    inputAnnotatorTypes = [AnnotatorType.IMAGE]
+
+    outputAnnotatorType = AnnotatorType.CATEGORY
+
+    configProtoBytes = Param(Params._dummy(),
+                             "configProtoBytes",
+                             "ConfigProto from tensorflow, serialized into byte array. Get with "
+                             "config_proto.SerializeToString()",
+                             TypeConverters.toListInt)
+
+    def getCandidateLabels(self):
+        """
+        Returns labels used to train this model
+        """
+        return self._call_java("getCandidateLabels")
+
+    @keyword_only
+    def __init__(self, classname="com.johnsnowlabs.nlp.annotators.cv.CLIPForZeroShotClassification",
+                 java_model=None):
+        super(CLIPForZeroShotClassification, self).__init__(
+            classname=classname,
+            java_model=java_model
+        )
+        self._setDefault(
+            batchSize=2,
+            doNormalize=True,
+            doRescale=True,
+            doResize=True,
+            imageMean=[0.48145466, 0.4578275, 0.40821073],
+            imageStd=[0.26862954, 0.26130258, 0.27577711],
+            resample=2,
+            rescaleFactor=1 / 255.0,
+            size=224
+        )
+
+    @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
+        -------
+        CLIPForZeroShotClassification
+            The restored model
+        """
+        from sparknlp.internal import _CLIPForZeroShotClassification
+        jModel = _CLIPForZeroShotClassification(folder, spark_session._jsparkSession)._java_obj
+        return CLIPForZeroShotClassification(java_model=jModel)
+
+    @staticmethod
+    def pretrained(name="zero_shot_classifier_clip_vit_base_patch32", lang="en", remote_loc=None):
+        """Downloads and loads a pretrained model.
+
+        Parameters
+        ----------
+        name : str, optional
+            Name of the pretrained model, by default
+            "image_classifier_vit_base_patch16_224"
+        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
+        -------
+        CLIPForZeroShotClassification
+            The restored model
+        """
+        from sparknlp.pretrained import ResourceDownloader
+        return ResourceDownloader.downloadModel(CLIPForZeroShotClassification, name, lang, remote_loc)