oracle-ads 2.13.9rc0__py3-none-any.whl → 2.13.9rc1__py3-none-any.whl

ads/templates/score_generic.jinja2

@@ -0,0 +1,165 @@
+# 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

@@ -0,0 +1,217 @@
+# 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

@@ -0,0 +1,185 @@
+# 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))}