oracle-ads 2.13.7__py3-none-any.whl → 2.13.9rc0__py3-none-any.whl

ads/templates/score_generic.jinja2

@@ -1,165 +0,0 @@
-# score.py {{SCORE_VERSION}} generated by ADS {{ADS_VERSION}} on {{time_created}}
-import os
-import sys
-import json
-from functools import lru_cache
-
-model_name = '{{model_file_name}}'
-
-
-"""
-   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:  a model instance on which predict API can be invoked
-    """
-    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:
-        raise NotImplementedError("You need to implement the `load_model` function")
-    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.sklearn_model.SklearnModel.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" %}
-    import pandas as pd
-    import numpy as np
-    import base64
-    from io import BytesIO
-    if isinstance(data, bytes):
-        return data
-
-    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 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.
-
-    """
-    return deserialize(data, input_schema_path)
-
-
-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
-
-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}

ads/templates/score_huggingface_pipeline.jinja2

@@ -1,217 +0,0 @@
-# score.py {{SCORE_VERSION}} generated by ADS {{ADS_VERSION}}
-import os
-import sys
-from functools import lru_cache
-from transformers import pipeline
-import json
-from typing import Dict, List
-import numpy as np
-from io import BytesIO
-import base64
-import logging
-import torch
-
-
-task = '{{task}}'
-
-"""
-   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=""):
-    """
-    Loads model from the serialized format
-
-    Returns
-    -------
-    model:  a model instance on which predict API can be invoked.
-
-    """
-    model_dir = os.path.dirname(os.path.realpath(__file__))
-    if model_dir not in sys.path:
-        sys.path.insert(0, model_dir)
-
-    try:
-
-        model = pipeline(task, model = model_dir)
-        print("Model is successfully loaded.")
-    except Exception as e:
-        raise Exception(f'Failed to load the model. ' + str(e))
-
-    return model
-
-
-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" %}
-    if isinstance(data, bytes):
-        logging.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 data
-
-    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 "torch.Tensor" in data_type:
-        load_bytes = BytesIO(base64.b64decode(json_data.encode('utf-8')))
-        return torch.load(load_bytes)
-    if isinstance(json_data, bytes):
-        import cloudpickle
-        return cloudpickle.loads(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):
-    """
-    Preprocess json-serialized data to feed into predict function.
-
-    Parameters
-    ----------
-    data: Data format as expected by the predict API of the core estimator.
-
-    Returns
-    -------
-    data: Data format after any processing.
-
-    """
-    data = deserialize(data)
-
-    # Add further data preprocessing if needed
-    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.
-
-    """
-    if isinstance(yhat, dict):
-        return serialize_prediction(yhat)
-    elif isinstance(yhat, list):
-        serialized_yhat = []
-        for yhat_i in yhat:
-            serialized_yhat.append(serialize_prediction(yhat_i))
-        return serialized_yhat
-    elif isinstance(yhat, torch.Tensor):
-        return yhat.tolist()
-
-    if task == "conversational":
-        raise NotImplementedError("The model output of task `conversational` is not json serializable. Add code here to populate json serializable output.")
-
-    # Add further data postprocessing if needed
-    return yhat
-
-
-def serialize_prediction(yhat):
-    """
-    Serialize the values in the prediction.
-
-    Parameters
-    ----------
-    yhat: model prediction.
-
-    Returns
-    -------
-    yhat: Serialized model prediction.
-
-    """
-    if isinstance(yhat, dict):
-        for key, value in yhat.items():
-            if isinstance(value, torch.Tensor):
-                yhat[key] = value.tolist()
-            elif str(type(value)).startswith("<class 'PIL."):
-                import PIL
-                yhat[key] = np.asarray(value).tolist() if isinstance(value, PIL.Image.Image) else value
-    return yhat
-
-
-def validated_model_outputs(yhat):
-    """
-    Validates if the prediction is json serializable.
-
-    Parameters
-    ----------
-    yhat: Prediction.
-
-    Returns
-    -------
-    None
-
-    Raises
-    ------
-    TypeError
-        Type is not json serializable.
-
-    """
-    try:
-        json.dumps(yhat)
-    except:
-        raise TypeError("The output is not json serializable.")
-
-
-def predict(data, model=load_model()):
-    """
-    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
-
-    Returns
-    -------
-    predictions: Output from scoring server
-        Format: {'prediction': output from model.predict method}
-
-    """
-    inputs = pre_inference(data)
-
-    yhat = post_inference(
-    model(**inputs) if isinstance(inputs, dict) else model(inputs)
-    )
-    validated_model_outputs(yhat)
-    return {'prediction': yhat}

ads/templates/score_lightgbm.jinja2

@@ -1,185 +0,0 @@
-# score.py {{SCORE_VERSION}} generated by ADS {{ADS_VERSION}} on {{time_created}}
-import json
-import os
-import sys
-import lightgbm as lgb
-from functools import lru_cache
-import pandas as pd
-import numpy as np
-from io import BytesIO
-import base64
-import logging
-
-
-model_name = '{{model_file_name}}'
-
-
-"""
-   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:  a model instance on which predict API can be invoked
-    """
-    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 not in contents:
-        raise Exception(f'{model_file_name} is not found in model directory {model_dir}')
-
-{% if model_serializer == "joblib" %}
-    print(f'Start loading {model_file_name} from model directory {model_dir} ...')
-    import joblib
-    with open(os.path.join(os.path.dirname(os.path.realpath(__file__)), model_file_name), "rb") as file:
-        loaded_model = joblib.load(file)
-
-{% elif model_serializer == "lightgbm" %}
-    loaded_model = lgb.Booster(model_file=os.path.join(os.path.dirname(os.path.realpath(__file__)), model_file_name))
-
-{% else %}
-    raise NotImplementedError("`load_model()` needs to be implemented.")
-
-{% endif %}
-    print("Model is successfully loaded.")
-    return loaded_model
-
-@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.lightgbm_model.LightGBMModel.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):
-        logging.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 data
-
-    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 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}
-
-    """
-    inputs = pre_inference(data, input_schema_path)
-    return {'prediction': post_inference(model.predict(inputs))}