&`i%UddlZddlmZmZmZmZmZddlZddl Z ddl m Z ddl mZmZmZddlmZddlmZddlmZmZ ddlZejZn #e$rdZYnwxYwejejeeje jej iZ!eee efe"d<ed Gd d e#Z$ed Gd dej%Z&dS)N)CallableDictOptionalTypeUnion) DataBatchType) BatchFormat_convert_batch_type_to_numpy_convert_batch_type_to_pandas) Preprocessor) Checkpoint) DeveloperAPI PublicAPI TYPE_TO_ENUMbeta) stabilityceZdZdZdS)!PredictorNotSerializableExceptionz;Error raised when trying to serialize a Predictor instance.N)__name__ __module__ __qualname____doc__g/home/jaya/work/projects/VOICE-AGENT/VIET/agent-env/lib/python3.11/site-packages/ray/train/predictor.pyrr sEEDrrc eZdZdZddeefdZeej de ddfdZ ede e jge jfddfd Zdeefd Zdeeddfd Zeedefd Zedefd ZdZdedefdZeddZedeejeeejffdeejeeejfffdZdZ dS) PredictoraVPredictors load models from checkpoints to perform inference. .. note:: The base ``Predictor`` class cannot be instantiated directly. Only one of its subclasses can be used. **How does a Predictor work?** Predictors expose a ``predict`` method that accepts an input batch of type ``DataBatchType`` and outputs predictions of the same type as the input batch. When the ``predict`` method is called the following occurs: - The input batch is converted into a pandas DataFrame. Tensor input (like a ``np.ndarray``) will be converted into a single column Pandas Dataframe. - If there is a :ref:`Preprocessor ` saved in the provided :class:`Checkpoint `, the preprocessor will be used to transform the DataFrame. - The transformed DataFrame will be passed to the model for inference (via the ``predictor._predict_pandas`` method). - The predictions will be outputted by ``predict`` in the same type as the original input. **How do I create a new Predictor?** To implement a new Predictor for your particular framework, you should subclass the base ``Predictor`` and implement the following two methods: 1. ``_predict_pandas``: Given a pandas.DataFrame input, return a pandas.DataFrame containing predictions. 2. ``from_checkpoint``: Logic for creating a Predictor from a :class:`Checkpoint `. 3. Optionally ``_predict_numpy`` for better performance when working with tensor data to avoid extra copies from Pandas conversions. N preprocessorc"||_d|_dS)zBSubclasseses must call Predictor.__init__() to set a preprocessor.FN) _preprocessor_cast_tensor_columnsselfrs r__init__zPredictor.__init__Ms5A%*!!!r checkpointreturnc t)aCreate a specific predictor from a checkpoint. Args: checkpoint: Checkpoint to load predictor data from. kwargs: Arguments specific to predictor implementations. Returns: Predictor: Predictor object. NotImplementedError)clsr%kwargss rfrom_checkpointzPredictor.from_checkpointT "!r pandas_udfcFGfddtS)zCreate a Predictor from a Pandas UDF. Args: pandas_udf: A function that takes a pandas.DataFrame and other optional kwargs and returns a pandas.DataFrame. c@eZdZededdffd Zdfd ZdS) 5Predictor.from_pandas_udf..PandasUDFPredictorr%r&rcSNr)r*r%r+PandasUDFPredictors rr,zEPredictor.from_pandas_udf..PandasUDFPredictor.from_checkpointns))+++r pd.DataFramec|fi|Sr3r)r#dfr+r.s r_predict_pandaszEPredictor.from_pandas_udf..PandasUDFPredictor._predict_pandasrs!z"/////rN)r&r5)rrr classmethodr r,r8)r4r.srr4r1msi  , ,+ , , , , ,[ , 0 0 0 0 0 0 0 0rr4)r)r*r.r4s `@rfrom_pandas_udfzPredictor.from_pandas_udfbsN 0 0 0 0 0 0 0 0 0 0 0"!###rc|jS)z;Get the preprocessor to use prior to executing predictions.r r#s rget_preprocessorzPredictor.get_preprocessorws !!rc||_dS)z;Set the preprocessor to use prior to executing predictions.Nr<r"s rset_preprocessorzPredictor.set_preprocessor{s)rctjS)aBatch format hint for upstream producers to try yielding best block format. The preferred batch format to use if both `_predict_pandas` and `_predict_numpy` are implemented. Defaults to Pandas. Can be overriden by predictor classes depending on the framework type, e.g. TorchPredictor prefers Numpy and XGBoostPredictor prefers Pandas as native batch format. )r PANDAS)r*s rpreferred_batch_formatz Predictor.preferred_batch_formats !!rc|jtjk}|jtjk}|r|r|S|r tjS|r tjStd|jd)z4Determine the batch format to use for the predictor.z Predictor zG must implement at least one of `_predict_pandas` and `_predict_numpy`.) r8r_predict_numpyrCr rBNUMPYr)r)r*has_pandas_implementedhas_numpy_implementeds r_batch_format_to_usezPredictor._batch_format_to_uses"%!4 8Q!Q # 2i6N N ! &; --// / # % % " $ $%:S\::: rcd|_dS)aEnable automatic tensor column casting. If this is called on a predictor, the predictor will cast tensor columns to NumPy ndarrays in the input to the preprocessors and cast tensor columns back to the tensor extension type in the prediction outputs. TN)r!r=s r_set_cast_tensor_columnsz"Predictor._set_cast_tensor_columnss%)!!!rdatac bt|dstd tt|}nT#t$rGt dt|dt twxYw|jr|j |}| }|tj kre|tj kr|j t|fi|S|tjkr(t|jt#|fi|SdS|tjkrc|tj kr(t#|j t|fi|S|tjkr|jt#|fi|SdSdS)aPerform inference on a batch of data. Args: data: A batch of input data of type ``DataBatchType``. kwargs: Arguments specific to predictor implementations. These are passed directly to ``_predict_numpy`` or ``_predict_pandas``. Returns: DataBatchType: Prediction result. The return type will be the same as the input type. r zCSubclasses of Predictor must call Predictor.__init__(preprocessor).zInvalid input data type of z, supported types: N)hasattrr)rtypeKeyError RuntimeErrorlistkeysr transform_batchrIr rBr8r rFrEr )r#rLr+ batch_formatbatch_format_to_uses rpredictzPredictor.predicts t_-- %U  'T 3LL   6d4jj66|00223366     <%55d;;D"7799 ;- - -"k&888+t+1$77;A% (9994'D'(DT(J(JUUfUU:9[. . ."k&8883(D()Ft)L)LWWPVWW% (999*t*+G+M+MXXQWXXX / . :9s <AB r5c t)aPerform inference on a Pandas DataFrame. Args: data: A pandas DataFrame to perform predictions on. kwargs: Arguments specific to the predictor implementation. Returns: A pandas DataFrame containing the prediction result. r(r#rLr+s rr8zPredictor._predict_pandasr-rc t)aPerform inference on a Numpy data. All Predictors working with tensor data (like deep learning predictors) should implement this method. Args: data: A Numpy ndarray or dictionary of ndarrays to perform predictions on. kwargs: Arguments specific to the predictor implementation. Returns: A Numpy ndarray or dictionary of ndarray containing the prediction result. r(rYs rrEzPredictor._predict_numpys ""!rc td)NzPredictor instances are not serializable. Instead, you may want to serialize a checkpoint and initialize the Predictor with Predictor.from_checkpoint.)rr=s r __reduce__zPredictor.__reduce__s/ )   rr3)rLr5r&r5)!rrrrrr r$r9abcabstractmethodr r,rpd DataFramer:r>r@rr rCrIrKrrWr8rnpndarrayrstrrEr\rrrrr's$""H**Xl%;**** " "+ " " "[ "$!2<.",">?$ $$$[$("(<"8""""*Xl-C***** "{ " " "\[ "[[ ))).YM.Y .Y.Y.Y.Y` " " "\ """*d3 ?&;;<" rz4RZ00 1"""\"$     rr)'r]typingrrrrrnumpyrapandasr_ray.air.data_batch_typer"ray.air.util.data_batch_conversionr r r ray.datar ray.trainr ray.util.annotationsrrpyarrowTablepa_table ImportErrorrbrFdictr`rBr__annotations__rQrABCrrrrrss 88888888888888111111 "!!!!! 88888888NNN}HHHHH J !+ L+$8 d4 & 34 V         VV V V V V V V V V V s A AA