oracle-ads 2.13.8__py3-none-any.whl → 2.13.9rc0__py3-none-any.whl

ads/templates/score_onnx_new.jinja2

@@ -1,473 +0,0 @@
-# score.py {{SCORE_VERSION}} generated by ADS {{ADS_VERSION}} on {{time_created}}
-import json
-import logging
-import os
-import sys
-from functools import lru_cache
-from io import StringIO
-from typing import Dict, Union
-
-import numpy as np
-import onnxruntime as rt
-import pandas as pd
-from io import BytesIO
-import base64
-
-
-model_name = '{{model_file_name}}'
-transformer_name = 'onnx_data_transformer.json'
-
-
-"""
-   Inference script. This script is used for prediction by scoring server when schema is known.
-"""
-
-
-@lru_cache(maxsize=10)
-def load_model(model_file_name=model_name):
-    """
-    Loads model from the serialized format
-
-    Returns
-    -------
-    model:  an onnxruntime session instance
-    """
-    model_dir = os.path.dirname(os.path.realpath(__file__))
-    if model_dir not in sys.path:
-        sys.path.insert(0, model_dir)
-    contents = os.listdir(model_dir)
-    if model_file_name in contents:
-        print(f'Start loading {model_file_name} from model directory {model_dir} ...')
-        loaded_model = rt.InferenceSession(os.path.join(model_dir, model_file_name))
-
-        print("Model is successfully loaded.")
-        return loaded_model
-    else:
-        raise Exception(f'{model_file_name} is not found in model directory {model_dir}')
-
-
-def deserialize(data):
-    """
-    Deserialize json-serialized data to data in original type when sent to
-    predict.
-
-    Parameters
-    ----------
-    data: serialized input data.
-
-    Returns
-    -------
-    data: deserialized input data.
-
-    """
-{% if data_deserializer == "json" %}
-    data_type = data.get('data_type', '') if isinstance(data, dict) else ''
-    json_data = data.get('data', data) if isinstance(data, dict) else data
-
-    if "numpy.ndarray" in data_type:
-        load_bytes = BytesIO(base64.b64decode(json_data.encode('utf-8')))
-        return np.load(load_bytes, allow_pickle=True)
-    if "pandas.core.series.Series" in data_type:
-        return pd.Series(json_data)
-    if "pandas.core.frame.DataFrame" in data_type:
-        return pd.read_json(json_data)
-    return json_data
-
-{% elif data_deserializer == "cloudpickle" %}
-    import cloudpickle
-    from pickle import UnpicklingError
-    deserialized_data = data
-    try:
-        deserialized_data = cloudpickle.loads(data)
-    except TypeError:
-        pass
-    except UnpicklingError:
-        logger.warning(
-            "bytes are passed directly to the model. If the model expects a specific data format, you need to write the conversion logic in `deserialize()` yourself."
-        )
-
-    return deserialized_data
-
-{% else %}
-    # Add further data deserialization if needed
-    return data
-{% endif %}
-
-def predict(data, model=load_model()):
-    """
-    Returns prediction given the model and data to predict
-
-    Parameters
-    ----------
-    model: Model session instance returned by load_model API
-    data: Data format as expected by the onnxruntime API
-
-    Returns
-    -------
-    predictions: Output from scoring server
-        Format: {'prediction':output from model.predict method}
-    """
-    data = deserialize(data)
-
-    if isinstance(data, str):
-        X = pd.read_json(StringIO(data))
-    elif isinstance(data, dict):
-        X = pd.DataFrame.from_dict(data)
-    else:
-        X = data
-
-    model_dir = os.path.dirname(os.path.realpath(__file__))
-    contents = os.listdir(model_dir)
-    # Note: User may need to edit this
-    if transformer_name in contents:
-        onnx_data_transformer = ONNXTransformer.load(os.path.join(model_dir, transformer_name))
-        X = onnx_data_transformer.transform(X)
-    else:
-        onnx_data_transformer = None
-
-    num_of_inputs = len(model.get_inputs())
-
-    if isinstance(X, list) or isinstance(X, np.ndarray):
-        if num_of_inputs == 1:
-            input_data = {model.get_inputs()[0].name: X}
-        else:
-            input_data = {}
-            for i in range(num_of_inputs):
-                input_data[model.get_inputs()[i].name] = X[i]
-        pred = model.run(None, input_data)
-
-        num_of_outputs = len(model.get_outputs())
-        if num_of_outputs == 1:
-            return {'prediction': pred[0].tolist() if isinstance(pred[0], np.ndarray) else pred[0]}
-        else:
-            return {'prediction': [x.tolist() if isinstance(x, np.ndarray) else x for x in pred]}
-
-    onnx_transformed_rows = []
-
-    if num_of_inputs == 1:
-        for name, row in X.iterrows():
-            onnx_transformed_rows.append(list(row))
-        input_data = {model.get_inputs()[0].name: onnx_transformed_rows}
-    else:
-        input_data = {}
-        model_inputs = model.get_inputs()
-        i = 0
-        for _, col in X.items():
-            if isinstance(col, pd.Series):
-                col_val = [[item] for item in col.values.tolist()]
-            elif isinstance(col, np.array):
-                col_val = [[item] for item in col.tolist()]
-            elif isinstance(col, list):
-                col_val = [[item] for item in col]
-            input_data[model_inputs[i].name] = col_val
-            i += 1
-    pred = model.run(None, input_data)
-    return {'prediction':pred[0].tolist() if isinstance(pred[0], np.ndarray) else pred[0]}
-
-
-class ONNXTransformer(object):
-    """
-    This is a transformer to convert X [pandas.Dataframe, pd.Series] data into Onnx
-    readable dtypes and formats. It is Serializable, so it can be reloaded at another time.
-
-
-    Examples
-    --------
-    >>> from ads.model.transformer.onnx_transformer import ONNXTransformer
-    >>> onnx_data_transformer = ONNXTransformer()
-    >>> train_transformed = onnx_data_transformer.fit_transform(train.X, {"column_name1": "impute_value1", "column_name2": "impute_value2"}})
-    >>> test_transformed = onnx_data_transformer.transform(test.X)
-    """
-
-    def __init__(self):
-        self.impute_values = {}
-        self.dtypes = None
-        self._fitted = False
-
-    @staticmethod
-    def _handle_dtypes(X: Union[pd.DataFrame, pd.Series, np.ndarray, list]):
-        """Handles the dtypes for pandas dataframe and pandas Series.
-
-        Parameters
-        ----------
-        X : Union[pd.DataFrame, pd.Series, np.ndarray, list]
-            The Dataframe for the training data
-
-        Returns
-        -------
-        Union[pd.DataFrame, pd.Series, np.ndarray, list]
-            The transformed(numerical values are cast to float32) X data
-        """
-        # Data type cast could be expensive doing it in a for loop
-        # Especially with wide datasets
-        # So cast the numerical columns first, without loop
-        # Then impute missing values
-        if isinstance(X, pd.Series):
-            series_name = X.name if X.name else 0
-            _X = X.to_frame()
-            _X = ONNXTransformer._handle_dtypes_dataframe(_X)[series_name]
-        elif isinstance(X, pd.DataFrame):
-            _X = ONNXTransformer._handle_dtypes_dataframe(X)
-        elif isinstance(X, np.ndarray):
-            _X = ONNXTransformer._handle_dtypes_np_array(X)
-        else:
-            # if users convert pandas dataframe with mixed types to numpy array directly
-            # it will turn the whole numpy array into object even though some columns are
-            # numerical and some are not. In that case, we need to do extra work to identify
-            # which columns are really numerical which for now, we only convert to float32
-            # if numpy array is all numerical. else, nothing will be done.
-            _X = X
-        return _X
-
-    @staticmethod
-    def _handle_dtypes_dataframe(X: pd.DataFrame):
-        """handle the dtypes for pandas dataframe.
-
-        Parameters
-        ----------
-        X : pandas.DataFrame
-            The Dataframe for the training data
-
-        Returns
-        -------
-        pandas.DataFrame
-            The transformed X data
-        """
-        dict_astype = {}
-        for k, v in zip(X.columns, X.dtypes):
-            if "int" in str(v) or "float" in str(v) or "bool" in str(v):
-                dict_astype[k] = "float32"
-        _X = X.astype(dict_astype)
-        if len(dict_astype) > 0:
-            logging.warning("Numerical values in `X` are cast to float32.")
-        return _X
-
-    @staticmethod
-    def _handle_dtypes_np_array(X: np.ndarray):
-        """handle the dtypes for pandas dataframe.
-
-        Parameters
-        ----------
-        X : np.ndarray
-            The ndarray for the training data
-
-        Returns
-        -------
-        np.ndarray
-            The transformed X data
-        """
-        if "int" in str(X.dtype) or "float" in str(X.dtype) or "bool" in str(X.dtype):
-            _X = X.astype("float32")
-            logging.warning("Numerical values in `X` are cast to float32.")
-        else:
-            _X = X
-        return _X
-
-    def fit(
-        self,
-        X: Union[pd.DataFrame, pd.Series, np.ndarray, list],
-        impute_values: Dict = None,
-    ):
-        """
-        Fits the OnnxTransformer on the dataset
-        Parameters
-        ----------
-        X : Union[pandas.DataFrame, pandas.Series, np.ndarray, list]
-            The Dataframe for the training data
-
-        Returns
-        -------
-        Self: ads.Model
-            The fitted estimator
-        """
-        _X = ONNXTransformer._handle_dtypes(X)
-        if isinstance(_X, pd.DataFrame):
-            self.dtypes = _X.dtypes
-        elif isinstance(_X, np.ndarray):
-            self.dtypes = _X.dtype
-        self.impute_values = impute_values if impute_values else {}
-        self._fitted = True
-        return self
-
-    def transform(self, X: Union[pd.DataFrame, pd.Series, np.ndarray, list]):
-        """
-        Transforms the data for the OnnxTransformer.
-
-        Parameters
-        ----------
-        X: Union[pandas.DataFrame, pandas.Series, np.ndarray, list]
-            The Dataframe for the training data
-
-        Returns
-        -------
-        Union[pandas.DataFrame, pandas.Series, np.ndarray, list]
-            The transformed X data
-        """
-        assert self._fitted, "Call fit_transform first!"
-        if self.dtypes is not None and len(self.dtypes) > 0:
-            if isinstance(X, list):
-                _X = np.array(X).astype(self.dtypes).tolist()
-            else:
-                _X = X.astype(self.dtypes)
-        else:
-            _X = X
-        _X = ONNXTransformer._handle_missing_value(_X, impute_values=self.impute_values)
-        return _X
-
-    @staticmethod
-    def _handle_missing_value(
-        X: Union[pd.DataFrame, pd.Series, np.ndarray, list], impute_values: Dict
-    ):
-        """Impute missing values in X according to impute_values.
-
-        Parameters
-        ----------
-        X: Union[pandas.DataFrame, pandas.Series, np.ndarray, list]
-            The Dataframe for the training data
-
-        Raises
-        ------
-        Exception if X has only one dim, but imputed_values has multiple values.
-        NotImplemented if X has the data type that is not supported.
-
-        Returns
-        -------
-        Union[pandas.DataFrame, pd.Series, np.ndarray, list]
-            The transformed X data
-        """
-        if isinstance(X, np.ndarray):
-            X = ONNXTransformer._handle_missing_value_dataframe(
-                pd.DataFrame(X), impute_values=impute_values
-            ).values
-        elif isinstance(X, list):
-            X = ONNXTransformer._handle_missing_value_dataframe(
-                pd.DataFrame(X), impute_values=impute_values
-            ).values.tolist()
-        elif isinstance(X, pd.DataFrame):
-            X = ONNXTransformer._handle_missing_value_dataframe(
-                X, impute_values=impute_values
-            )
-        elif isinstance(X, pd.Series):
-            X = X.replace(r"^\s*$", np.NaN, regex=True)
-            if len(impute_values.keys()) == 1:
-                for key, val in impute_values.items():
-                    X = X.fillna(val)
-            else:
-                raise Exception(
-                    "Multiple imputed values are provided, but `X` has only one dim."
-                )
-        else:
-            raise NotImplemented(
-                f"{type(X)} is not supported. Convert `X` to pandas dataframe or numpy array."
-            )
-        return X
-
-    @staticmethod
-    def _handle_missing_value_dataframe(X: pd.DataFrame, impute_values: Dict):
-        for idx, val in impute_values.items():
-            if isinstance(idx, int):
-                X.iloc[:, idx] = (
-                    X.iloc[:, idx].replace(r"^\s*$", np.NaN, regex=True).fillna(val)
-                )
-            else:
-                X.loc[:, idx] = (
-                    X.loc[:, idx].replace(r"^\s*$", np.NaN, regex=True).fillna(val)
-                )
-        return X
-
-    def fit_transform(
-        self, X: Union[pd.DataFrame, pd.Series], impute_values: Dict = None
-    ):
-        """
-        Fits, then transforms the data
-        Parameters
-        ----------
-        X: Union[pandas.DataFrame, pandas.Series]
-            The Dataframe for the training data
-
-        Returns
-        -------
-        Union[pandas.DataFrame, pandas.Series]
-            The transformed X data
-        """
-        return self.fit(X, impute_values).transform(X)
-
-    def save(self, filename, **kwargs):
-        """
-        Saves the Onnx model to disk
-        Parameters
-        ----------
-        filename: Str
-            The filename location for where the model should be saved
-
-        Returns
-        -------
-        filename: Str
-            The filename where the model was saved
-        """
-        export_dict = {
-            "impute_values": {
-                "value": self.impute_values,
-                "dtype": str(type(self.impute_values)),
-            },
-            "dtypes": {}
-            if self.dtypes is None
-            else {
-                "value": {
-                    "index": list(self.dtypes.index),
-                    "values": [str(val) for val in self.dtypes.values],
-                }
-                if isinstance(self.dtypes, pd.Series)
-                else str(self.dtypes),
-                "dtype": str(type(self.dtypes)),
-            },
-            "_fitted": {"value": self._fitted, "dtype": str(type(self._fitted))},
-        }
-
-        with open(filename, "w") as f:
-            json.dump(export_dict, f, sort_keys=True, indent=4, separators=(",", ": "))
-        return filename
-
-    @staticmethod
-    def load(filename, **kwargs):
-        """
-        Loads the Onnx model to disk
-        Parameters
-        ----------
-        filename: Str
-            The filename location for where the model should be loaded
-
-        Returns
-        -------
-        onnx_transformer: ONNXTransformer
-            The loaded model
-        """
-        # Make sure you have  pandas, numpy, and sklearn imported
-        with open(filename, "r") as f:
-            export_dict = json.load(f)
-
-        onnx_transformer = ONNXTransformer()
-        for key in export_dict.keys():
-            if key not in ["impute_values", "dtypes"]:
-                try:
-                    setattr(onnx_transformer, key, export_dict[key]["value"])
-                except Exception as e:
-                    print(
-                        f"Warning: Failed to reload {key} from {filename} to OnnxTransformer."
-                    )
-                    raise e
-        if "value" in export_dict["dtypes"]:
-            if "index" in export_dict["dtypes"]["value"]:
-                onnx_transformer.dtypes = pd.Series(
-                    data=[
-                        np.dtype(val)
-                        for val in export_dict["dtypes"]["value"]["values"]
-                    ],
-                    index=export_dict["dtypes"]["value"]["index"],
-                )
-            else:
-                onnx_transformer.dtypes = export_dict["dtypes"]["value"]
-        else:
-            onnx_transformer.dtypes = {}
-        onnx_transformer.impute_values = export_dict["impute_values"]["value"]
-        return onnx_transformer

ads/templates/score_oracle_automl.jinja2

@@ -1,185 +0,0 @@
-# score.py {{SCORE_VERSION}} generated by ADS {{ADS_VERSION}} on {{time_created}}
-import json
-import os
-import sys
-from cloudpickle import cloudpickle
-from functools import lru_cache
-from io import StringIO
-import logging
-import sys
-import automl
-import pandas as pd
-import numpy as np
-{% for import in misc_imports %}
-import {{import}}
-{% endfor %}
-
-model_name = '{{model_file_name}}'
-
-"""
-   Inference script. This script is used for prediction by scoring server when schema is known.
-"""
-
-def init_automl_logger():
-    logger = logging.getLogger("automl")
-    handler = logging.StreamHandler(sys.stdout)
-    handler.setLevel(logging.ERROR)
-    formatter = logging.Formatter(
-        "%(asctime)s - %(name)s - %(levelname)s - %(message)s"
-    )
-    handler.setFormatter(formatter)
-    logger.addHandler(handler)
-    automl.init(engine="local", engine_opts={"n_jobs": 1}, logger=logger)
-
-
-@lru_cache(maxsize=10)
-def load_model(model_file_name=model_name):
-    """
-    Loads model from the serialized format
-
-    Returns
-    -------
-    model:  a model instance on which predict API can be invoked
-    """
-    init_automl_logger()
-    model_dir = os.path.dirname(os.path.realpath(__file__))
-    if model_dir not in sys.path:
-        sys.path.insert(0, model_dir)
-    contents = os.listdir(model_dir)
-    if model_file_name in contents:
-        print(f'Start loading {model_file_name} from model directory {model_dir} ...')
-        with open(os.path.join(os.path.dirname(os.path.realpath(__file__)), model_file_name), "rb") as file:
-            loaded_model = cloudpickle.load(file)
-
-        print("Model is successfully loaded.")
-        return loaded_model
-    else:
-        raise Exception(f'{model_file_name} is not found in model directory {model_dir}')
-
-@lru_cache(maxsize=1)
-def fetch_data_type_from_schema(input_schema_path=os.path.join(os.path.dirname(os.path.realpath(__file__)), "input_schema.json")):
-    """
-    Returns data type information fetch from input_schema.json.
-
-    Parameters
-    ----------
-    input_schema_path: path of input schema.
-
-    Returns
-    -------
-    data_type: data type fetch from input_schema.json.
-
-    """
-    data_type = {}
-    if os.path.exists(input_schema_path):
-        schema = json.load(open(input_schema_path))
-        for col in schema['schema']:
-            data_type[col['name']] = col['dtype']
-    else:
-        print("input_schema has to be passed in in order to recover the same data type. pass `X_sample` in `ads.model.framework.automl_model.AutoMLModel.prepare` function to generate the input_schema. Otherwise, the data type might be changed after serialization/deserialization.")
-    return data_type
-
-def deserialize(data, input_schema_path):
-    """
-    Deserialize json serialization data to data in original type when sent to predict.
-
-    Parameters
-    ----------
-    data: serialized input data.
-    input_schema_path: path of input schema.
-
-    Returns
-    -------
-    data: deserialized input data.
-
-    """
-{% if data_deserializer == "json" %}
-    if isinstance(data, bytes):
-        return pd.read_json(StringIO(data.decode("utf-8")))
-
-    data_type = data.get('data_type', '') if isinstance(data, dict) else ''
-    json_data = data.get('data', data) if isinstance(data, dict) else data
-
-    if "pandas.core.series.Series" in data_type:
-        return pd.Series(json_data)
-    if "pandas.core.frame.DataFrame" in data_type or isinstance(json_data, str):
-        return pd.read_json(json_data, dtype=fetch_data_type_from_schema(input_schema_path))
-    if isinstance(json_data, dict):
-        return pd.DataFrame.from_dict(json_data)
-
-    return json_data
-
-{% elif data_deserializer == "cloudpickle" %}
-    import cloudpickle
-    from pickle import UnpicklingError
-    deserialized_data = data
-    try:
-        deserialized_data = cloudpickle.loads(data)
-    except TypeError:
-        pass
-    except UnpicklingError:
-        logger.warning(
-            "bytes are passed directly to the model. If the model expects a specific data format, you need to write the conversion logic in `deserialize()` yourself."
-        )
-
-    return deserialized_data
-
-{% else %}
-    # Add further data deserialization if needed
-    return data
-{% endif %}
-
-def pre_inference(data, input_schema_path):
-    """
-    Preprocess data
-
-    Parameters
-    ----------
-    data: Data format as expected by the predict API of the core estimator.
-    input_schema_path: path of input schema.
-
-    Returns
-    -------
-    data: Data format after any processing.
-
-    """
-    data = deserialize(data, input_schema_path)
-    return data
-
-def post_inference(yhat):
-    """
-    Post-process the model results
-
-    Parameters
-    ----------
-    yhat: Data format after calling model.predict.
-
-    Returns
-    -------
-    yhat: Data format after any processing.
-
-    """
-    return yhat.tolist()
-
-
-def predict(data, model=load_model(), input_schema_path=os.path.join(os.path.dirname(os.path.realpath(__file__)), "input_schema.json")):
-    """
-    Returns prediction given the model and data to predict
-
-    Parameters
-    ----------
-    model: Model instance returned by load_model API
-    data: Data format as expected by the predict API of the core estimator. For eg. in case of sckit models it could be numpy array/List of list/Pandas DataFrame
-    input_schema_path: path of input schema.
-
-    Returns
-    -------
-    predictions: Output from scoring server
-        Format: {'prediction': output from model.predict method}
-
-    """
-    features = pre_inference(data, input_schema_path)
-    yhat = post_inference(
-        model.predict(features)
-    )
-    return {'prediction': yhat}