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

sparknlp/annotator/sentiment/vivekn_sentiment.py

@@ -0,0 +1,242 @@
+#  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 ViveknSentiment."""
+
+
+from sparknlp.common import *
+from sparknlp.common.annotator_type import AnnotatorType
+
+
+class ViveknSentimentApproach(AnnotatorApproach):
+    """Trains a sentiment analyser inspired by the algorithm by Vivek Narayanan.
+
+    The analyzer requires sentence boundaries to give a score in context.
+    Tokenization is needed to make sure tokens are within bounds. Transitivity
+    requirements are also required.
+
+    The training data needs to consist of a column for normalized text and a
+    label column (either ``"positive"`` or ``"negative"``).
+
+    For extended examples of usage, see the `Examples
+    <https://github.com/JohnSnowLabs/spark-nlp/blob/master/examples/python/training/english/vivekn-sentiment/VivekNarayanSentimentApproach.ipynb>`__.
+
+    ====================== ======================
+    Input Annotation types Output Annotation type
+    ====================== ======================
+    ``TOKEN, DOCUMENT``    ``SENTIMENT``
+    ====================== ======================
+
+    Parameters
+    ----------
+    sentimentCol
+        column with the sentiment result of every row. Must be 'positive' or 'negative'
+    pruneCorpus
+        Removes unfrequent scenarios from scope. The higher the better performance. Defaults 1
+
+    References
+    ----------
+    The algorithm is based on the paper `"Fast and accurate sentiment
+    classification using an enhanced Naive Bayes model"
+    <https://arxiv.org/abs/1305.6143>`__.
+
+    https://github.com/vivekn/sentiment/
+
+    Examples
+    --------
+    >>> import sparknlp
+    >>> from sparknlp.base import *
+    >>> from sparknlp.annotator import *
+    >>> from pyspark.ml import Pipeline
+    >>> document = DocumentAssembler() \\
+    ...     .setInputCol("text") \\
+    ...     .setOutputCol("document")
+    >>> token = Tokenizer() \\
+    ...     .setInputCols(["document"]) \\
+    ...     .setOutputCol("token")
+    >>> normalizer = Normalizer() \\
+    ...     .setInputCols(["token"]) \\
+    ...     .setOutputCol("normal")
+    >>> vivekn = ViveknSentimentApproach() \\
+    ...     .setInputCols(["document", "normal"]) \\
+    ...     .setSentimentCol("train_sentiment") \\
+    ...     .setOutputCol("result_sentiment")
+    >>> finisher = Finisher() \\
+    ...     .setInputCols(["result_sentiment"]) \\
+    ...     .setOutputCols("final_sentiment")
+    >>> pipeline = Pipeline().setStages([document, token, normalizer, vivekn, finisher])
+    >>> training = spark.createDataFrame([
+    ...     ("I really liked this movie!", "positive"),
+    ...     ("The cast was horrible", "negative"),
+    ...     ("Never going to watch this again or recommend it to anyone", "negative"),
+    ...     ("It's a waste of time", "negative"),
+    ...     ("I loved the protagonist", "positive"),
+    ...     ("The music was really really good", "positive")
+    ... ]).toDF("text", "train_sentiment")
+    >>> pipelineModel = pipeline.fit(training)
+    >>> data = spark.createDataFrame([
+    ...     ["I recommend this movie"],
+    ...     ["Dont waste your time!!!"]
+    ... ]).toDF("text")
+    >>> result = pipelineModel.transform(data)
+    >>> result.select("final_sentiment").show(truncate=False)
+    +---------------+
+    |final_sentiment|
+    +---------------+
+    |[positive]     |
+    |[negative]     |
+    +---------------+
+    """
+
+    inputAnnotatorTypes = [AnnotatorType.TOKEN, AnnotatorType.DOCUMENT]
+
+    outputAnnotatorType = AnnotatorType.SENTIMENT
+
+    sentimentCol = Param(Params._dummy(),
+                         "sentimentCol",
+                         "column with the sentiment result of every row. Must be 'positive' or 'negative'",
+                         typeConverter=TypeConverters.toString)
+
+    pruneCorpus = Param(Params._dummy(),
+                        "pruneCorpus",
+                        "Removes unfrequent scenarios from scope. The higher the better performance. Defaults 1",
+                        typeConverter=TypeConverters.toInt)
+
+    importantFeatureRatio = Param(Params._dummy(),
+                                  "importantFeatureRatio",
+                                  "proportion of feature content to be considered relevant. Defaults to 0.5",
+                                  typeConverter=TypeConverters.toFloat)
+
+    unimportantFeatureStep = Param(Params._dummy(),
+                                   "unimportantFeatureStep",
+                                   "proportion to lookahead in unimportant features. Defaults to 0.025",
+                                   typeConverter=TypeConverters.toFloat)
+
+    featureLimit = Param(Params._dummy(),
+                         "featureLimit",
+                         "content feature limit, to boost performance in very dirt text. Default disabled with -1",
+                         typeConverter=TypeConverters.toInt)
+
+    @keyword_only
+    def __init__(self):
+        super(ViveknSentimentApproach, self).__init__(
+            classname="com.johnsnowlabs.nlp.annotators.sda.vivekn.ViveknSentimentApproach")
+        self._setDefault(pruneCorpus=1, importantFeatureRatio=0.5, unimportantFeatureStep=0.025, featureLimit=-1)
+
+    def setSentimentCol(self, value):
+        """Sets column with the sentiment result of every row.
+
+        Must be either 'positive' or 'negative'.
+
+        Parameters
+        ----------
+        value : str
+            Name of the column
+        """
+        return self._set(sentimentCol=value)
+
+    def setPruneCorpus(self, value):
+        """Sets the removal of unfrequent scenarios from scope, by default 1.
+
+        The higher the better performance.
+
+        Parameters
+        ----------
+        value : int
+            The frequency
+        """
+        return self._set(pruneCorpus=value)
+
+    def _create_model(self, java_model):
+        return ViveknSentimentModel(java_model=java_model)
+
+
+class ViveknSentimentModel(AnnotatorModel):
+    """Sentiment analyser inspired by the algorithm by Vivek Narayanan.
+
+    This is the instantiated model of the :class:`.ViveknSentimentApproach`. For
+    training your own model, please see the documentation of that class.
+
+    The analyzer requires sentence boundaries to give a score in context.
+    Tokenization is needed to make sure tokens are within bounds. Transitivity
+    requirements are also required.
+
+    For extended examples of usage, see the `Examples
+    <https://github.com/JohnSnowLabs/spark-nlp/blob/master/examples/python/training/english/vivekn-sentiment/VivekNarayanSentimentApproach.ipynb>`__.
+
+    ====================== ======================
+    Input Annotation types Output Annotation type
+    ====================== ======================
+    ``TOKEN, DOCUMENT``    ``SENTIMENT``
+    ====================== ======================
+
+    Parameters
+    ----------
+    None
+
+    References
+    ----------
+    The algorithm is based on the paper `"Fast and accurate sentiment
+    classification using an enhanced Naive Bayes model"
+    <https://arxiv.org/abs/1305.6143>`__.
+
+    https://github.com/vivekn/sentiment/
+    """
+    name = "ViveknSentimentModel"
+
+    inputAnnotatorTypes = [AnnotatorType.TOKEN, AnnotatorType.DOCUMENT]
+
+    outputAnnotatorType = AnnotatorType.SENTIMENT
+
+    importantFeatureRatio = Param(Params._dummy(),
+                                  "importantFeatureRatio",
+                                  "proportion of feature content to be considered relevant. Defaults to 0.5",
+                                  typeConverter=TypeConverters.toFloat)
+
+    unimportantFeatureStep = Param(Params._dummy(),
+                                   "unimportantFeatureStep",
+                                   "proportion to lookahead in unimportant features. Defaults to 0.025",
+                                   typeConverter=TypeConverters.toFloat)
+
+    featureLimit = Param(Params._dummy(),
+                         "featureLimit",
+                         "content feature limit, to boost performance in very dirt text. Default disabled with -1",
+                         typeConverter=TypeConverters.toInt)
+
+    def __init__(self, classname="com.johnsnowlabs.nlp.annotators.sda.vivekn.ViveknSentimentModel", java_model=None):
+        super(ViveknSentimentModel, self).__init__(
+            classname=classname,
+            java_model=java_model
+        )
+
+    @staticmethod
+    def pretrained(name="sentiment_vivekn", lang="en", remote_loc=None):
+        """Downloads and loads a pretrained model.
+
+        Parameters
+        ----------
+        name : str, optional
+            Name of the pretrained model, by default "sentiment_vivekn"
+        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
+        -------
+        ViveknSentimentModel
+            The restored model
+        """
+        from sparknlp.pretrained import ResourceDownloader
+        return ResourceDownloader.downloadModel(ViveknSentimentModel, name, lang, remote_loc)

sparknlp/annotator/seq2seq/__init__.py

@@ -0,0 +1,35 @@
+#  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.
+
+"""Module of annotators for sequence-to-sequence transformers."""
+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 *
+from sparknlp.annotator.seq2seq.phi2_transformer import *
+from sparknlp.annotator.seq2seq.mistral_transformer import *
+from sparknlp.annotator.seq2seq.auto_gguf_model import *
+from sparknlp.annotator.seq2seq.auto_gguf_vision_model import *
+from sparknlp.annotator.seq2seq.phi3_transformer import *
+from sparknlp.annotator.seq2seq.nllb_transformer import *
+from sparknlp.annotator.seq2seq.cpm_transformer import *
+from sparknlp.annotator.seq2seq.qwen_transformer import *
+from sparknlp.annotator.seq2seq.starcoder_transformer import *
+from sparknlp.annotator.seq2seq.llama3_transformer import *
+from sparknlp.annotator.seq2seq.cohere_transformer import *
+from sparknlp.annotator.seq2seq.olmo_transformer import *
+from sparknlp.annotator.seq2seq.phi4_transformer import *
+from sparknlp.annotator.seq2seq.auto_gguf_reranker import *

sparknlp/annotator/seq2seq/auto_gguf_model.py

@@ -0,0 +1,304 @@
+#  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 the AutoGGUFModel."""
+from sparknlp.common import *
+
+
+class AutoGGUFModel(AnnotatorModel, HasBatchedAnnotate, HasLlamaCppProperties, CompletionPostProcessing):
+    """
+    Annotator that uses the llama.cpp library to generate text completions with large language
+    models.
+
+    For settable parameters, and their explanations, see the parameters of this class and refer to
+    the llama.cpp documentation of
+    `server.cpp <https://github.com/ggerganov/llama.cpp/tree/7d5e8777ae1d21af99d4f95be10db4870720da91/examples/server>`__
+    for more information.
+
+    If the parameters are not set, the annotator will default to use the parameters provided by
+    the model.
+
+    Pretrained models can be loaded with :meth:`.pretrained` of the companion
+    object:
+
+    >>> auto_gguf_model = AutoGGUFModel.pretrained() \\
+    ...     .setInputCols(["document"]) \\
+    ...     .setOutputCol("completions")
+
+    The default model is ``"Phi_4_mini_instruct_Q4_K_M_gguf"``, if no name is provided.
+
+    AutoGGUFModel is also able to load pretrained models from AutoGGUFVisionModel. Just
+    specify the same name for the pretrained method, and it will load the text-part of the
+    multimodal model automatically.
+
+    For extended examples of usage, see the
+    `AutoGGUFModelTest <https://github.com/JohnSnowLabs/spark-nlp/tree/master/src/test/scala/com/johnsnowlabs/nlp/annotators/seq2seq/AutoGGUFModelTest.scala>`__
+    and the
+    `example notebook <https://github.com/JohnSnowLabs/spark-nlp/tree/master/examples/python/llama.cpp/llama.cpp_in_Spark_NLP_AutoGGUFModel.ipynb>`__.
+
+    For available pretrained models please see the `Models Hub <https://sparknlp.org/models>`__.
+
+    ====================== ======================
+    Input Annotation types Output Annotation type
+    ====================== ======================
+    ``DOCUMENT``           ``DOCUMENT``
+    ====================== ======================
+
+    Parameters
+    ----------
+    nThreads
+        Set the number of threads to use during generation
+    nThreadsDraft
+        Set the number of threads to use during draft generation
+    nThreadsBatch
+        Set the number of threads to use during batch and prompt processing
+    nThreadsBatchDraft
+        Set the number of threads to use during batch and prompt processing
+    nCtx
+        Set the size of the prompt context
+    nBatch
+        Set the logical batch size for prompt processing (must be >=32 to use BLAS)
+    nUbatch
+        Set the physical batch size for prompt processing (must be >=32 to use BLAS)
+    nDraft
+        Set the number of tokens to draft for speculative decoding
+    nChunks
+        Set the maximal number of chunks to process
+    nSequences
+        Set the number of sequences to decode
+    pSplit
+        Set the speculative decoding split probability
+    nGpuLayers
+        Set the number of layers to store in VRAM (-1 - use default)
+    nGpuLayersDraft
+        Set the number of layers to store in VRAM for the draft model (-1 - use default)
+    gpuSplitMode
+        Set how to split the model across GPUs
+    mainGpu
+        Set the main GPU that is used for scratch and small tensors.
+    tensorSplit
+        Set how split tensors should be distributed across GPUs
+    grpAttnN
+        Set the group-attention factor
+    grpAttnW
+        Set the group-attention width
+    ropeFreqBase
+        Set the RoPE base frequency, used by NTK-aware scaling
+    ropeFreqScale
+        Set the RoPE frequency scaling factor, expands context by a factor of 1/N
+    yarnExtFactor
+        Set the YaRN extrapolation mix factor
+    yarnAttnFactor
+        Set the YaRN scale sqrt(t) or attention magnitude
+    yarnBetaFast
+        Set the YaRN low correction dim or beta
+    yarnBetaSlow
+        Set the YaRN high correction dim or alpha
+    yarnOrigCtx
+        Set the YaRN original context size of model
+    defragmentationThreshold
+        Set the KV cache defragmentation threshold
+    numaStrategy
+        Set optimization strategies that help on some NUMA systems (if available)
+    ropeScalingType
+        Set the RoPE frequency scaling method, defaults to linear unless specified by the model
+    poolingType
+        Set the pooling type for embeddings, use model default if unspecified
+    modelDraft
+        Set the draft model for speculative decoding
+    modelAlias
+        Set a model alias
+    lookupCacheStaticFilePath
+        Set path to static lookup cache to use for lookup decoding (not updated by generation)
+    lookupCacheDynamicFilePath
+        Set path to dynamic lookup cache to use for lookup decoding (updated by generation)
+    flashAttention
+        Whether to enable Flash Attention
+    inputPrefixBos
+        Whether to add prefix BOS to user inputs, preceding the `--in-prefix` string
+    useMmap
+        Whether to use memory-map model (faster load but may increase pageouts if not using mlock)
+    useMlock
+        Whether to force the system to keep model in RAM rather than swapping or compressing
+    noKvOffload
+        Whether to disable KV offload
+    systemPrompt
+        Set a system prompt to use
+    chatTemplate
+        The chat template to use
+    inputPrefix
+        Set the prompt to start generation with
+    inputSuffix
+        Set a suffix for infilling
+    cachePrompt
+        Whether to remember the prompt to avoid reprocessing it
+    nPredict
+        Set the number of tokens to predict
+    topK
+        Set top-k sampling
+    topP
+        Set top-p sampling
+    minP
+        Set min-p sampling
+    tfsZ
+        Set tail free sampling, parameter z
+    typicalP
+        Set locally typical sampling, parameter p
+    temperature
+        Set the temperature
+    dynatempRange
+        Set the dynamic temperature range
+    dynatempExponent
+        Set the dynamic temperature exponent
+    repeatLastN
+        Set the last n tokens to consider for penalties
+    repeatPenalty
+        Set the penalty of repeated sequences of tokens
+    frequencyPenalty
+        Set the repetition alpha frequency penalty
+    presencePenalty
+        Set the repetition alpha presence penalty
+    miroStat
+        Set MiroStat sampling strategies.
+    mirostatTau
+        Set the MiroStat target entropy, parameter tau
+    mirostatEta
+        Set the MiroStat learning rate, parameter eta
+    penalizeNl
+        Whether to penalize newline tokens
+    nKeep
+        Set the number of tokens to keep from the initial prompt
+    seed
+        Set the RNG seed
+    nProbs
+        Set the amount top tokens probabilities to output if greater than 0.
+    minKeep
+        Set the amount of tokens the samplers should return at least (0 = disabled)
+    grammar
+        Set BNF-like grammar to constrain generations
+    penaltyPrompt
+        Override which part of the prompt is penalized for repetition.
+    ignoreEos
+        Set whether to ignore end of stream token and continue generating (implies --logit-bias 2-inf)
+    disableTokenIds
+        Set the token ids to disable in the completion
+    stopStrings
+        Set strings upon seeing which token generation is stopped
+    samplers
+        Set which samplers to use for token generation in the given order
+    useChatTemplate
+        Set whether or not generate should apply a chat template
+
+    Notes
+    -----
+    To use GPU inference with this annotator, make sure to use the Spark NLP GPU package and set
+    the number of GPU layers with the `setNGpuLayers` method.
+
+    When using larger models, we recommend adjusting GPU usage with `setNCtx` and `setNGpuLayers`
+    according to your hardware to avoid out-of-memory errors.
+
+    Examples
+    --------
+    >>> import sparknlp
+    >>> from sparknlp.base import *
+    >>> from sparknlp.annotator import *
+    >>> from pyspark.ml import Pipeline
+    >>> document = DocumentAssembler() \\
+    ...     .setInputCol("text") \\
+    ...     .setOutputCol("document")
+    >>> autoGGUFModel = AutoGGUFModel.pretrained() \\
+    ...     .setInputCols(["document"]) \\
+    ...     .setOutputCol("completions") \\
+    ...     .setBatchSize(4) \\
+    ...     .setNPredict(20) \\
+    ...     .setNGpuLayers(99) \\
+    ...     .setTemperature(0.4) \\
+    ...     .setTopK(40) \\
+    ...     .setTopP(0.9) \\
+    ...     .setPenalizeNl(True)
+    >>> pipeline = Pipeline().setStages([document, autoGGUFModel])
+    >>> data = spark.createDataFrame([["Hello, I am a"]]).toDF("text")
+    >>> result = pipeline.fit(data).transform(data)
+    >>> result.select("completions").show(truncate = False)
+    +-----------------------------------------------------------------------------------------------------------------------------------+
+    |completions                                                                                                                        |
+    +-----------------------------------------------------------------------------------------------------------------------------------+
+    |[{document, 0, 78,  new user.  I am currently working on a project and I need to create a list of , {prompt -> Hello, I am a}, []}]|
+    +-----------------------------------------------------------------------------------------------------------------------------------+
+    """
+
+    name = "AutoGGUFModel"
+    inputAnnotatorTypes = [AnnotatorType.DOCUMENT]
+    outputAnnotatorType = AnnotatorType.DOCUMENT
+
+    @keyword_only
+    def __init__(self, classname="com.johnsnowlabs.nlp.annotators.seq2seq.AutoGGUFModel", java_model=None):
+        super(AutoGGUFModel, self).__init__(
+            classname=classname,
+            java_model=java_model
+        )
+        self._setDefault(
+            useChatTemplate=True,
+            nCtx=4096,
+            nBatch=512,
+            nPredict=100,
+            nGpuLayers=99,
+            systemPrompt="You are a helpful assistant."
+        )
+
+    @staticmethod
+    def loadSavedModel(path, spark_session):
+        """Loads a locally saved model.
+
+        Parameters
+        ----------
+        path : str
+            Path to the gguf model
+        spark_session : pyspark.sql.SparkSession
+            The current SparkSession
+
+        Returns
+        -------
+        AutoGGUFModel
+            The restored model
+        """
+        from sparknlp.internal import _AutoGGUFLoader
+        jModel = _AutoGGUFLoader(path, spark_session._jsparkSession)._java_obj
+        return AutoGGUFModel(java_model=jModel)
+
+    @staticmethod
+    def pretrained(name="Phi_4_mini_instruct_Q4_K_M_gguf", lang="en", remote_loc=None):
+        """Downloads and loads a pretrained model.
+
+        Parameters
+        ----------
+        name : str, optional
+            Name of the pretrained model, by default "Phi_4_mini_instruct_Q4_K_M_gguf"
+        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
+        -------
+        AutoGGUFModel
+            The restored model
+        """
+        from sparknlp.pretrained import ResourceDownloader
+        return ResourceDownloader.downloadModel(AutoGGUFModel, name, lang, remote_loc)
+
+    def close(self):
+        """Closes the llama.cpp model backend freeing resources. The model is reloaded when used again.
+        """
+        self._java_obj.close()