oracle-ads 2.13.9rc0__py3-none-any.whl → 2.13.10rc0__py3-none-any.whl

ads/templates/score_pyspark.jinja2

@@ -0,0 +1,154 @@
+# score.py {{SCORE_VERSION}} generated by ADS {{ADS_VERSION}} on {{time_created}}
+import os
+import sys
+import json
+from functools import lru_cache
+from collections.abc import Iterable
+
+# Importing pyspark libraries
+from pyspark.ml.pipeline import PipelineModel
+from pyspark.sql import SparkSession
+from pyspark.sql.types import StructType
+
+"""
+   Inference script. This script is used for prediction by scoring server when schema is known.
+"""
+
+model_name = '{{model_file_name}}'
+spark_input_schema = model_name + "_input_data_schema.json"
+
+spark = SparkSession \
+    .builder \
+    .appName('Spark Model Inference') \
+    .getOrCreate()
+
+
+@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.environ.get("OCI_DEPLOYMENT_PATH", os.path.dirname(os.path.realpath(__file__)))
+    if model_dir not in sys.path:
+        sys.path.insert(0, model_dir)
+    try:
+        print(f'Start loading {model_file_name} from model directory {model_dir} ...')
+        loaded_model = PipelineModel.load(os.path.join(model_dir, model_file_name))
+        print("Model is successfully loaded.")
+        return loaded_model
+    except Exception as e:
+        error_msg = f"Failed to load the model and gave the exception: {e}."
+        raise Exception(error_msg)
+
+@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.spark_model.SparkPipelineModel.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.
+
+    """
+    data_type = data.get('data_type', '') if isinstance(data, dict) else ''
+    json_data = data.get('data', data) if isinstance(data, dict) else data
+
+    spark_schema_path = os.path.join(os.path.dirname(os.path.realpath(__file__)), spark_input_schema)
+    with open(spark_schema_path) as f:
+        spark_schema = StructType.fromJson(json.loads(f.read()))
+
+    if isinstance(json_data, str) or not isinstance(json_data, Iterable):
+        json_data = [json_data]
+
+    try:
+        rdd_data = spark.sparkContext.parallelize(json_data)
+        return spark.read.json(rdd_data, schema=spark_schema)
+    except:
+        raise TypeError(f"Unsupported data_type: {data_type} or failed to load data with provided spark schema: {spark_schema}. Only supported data types are: pyspark.sql.dataframe.DataFrame, pyspark.pandas.dataframe.DataFrame, pandas.DataFrame, json")
+
+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, input_cols):
+    """
+    Post-process the model results
+
+    Parameters
+    ----------
+    yhat: Data format after calling model.predict.
+
+    Returns
+    -------
+    yhat: Data format after any processing.
+
+    """
+    return yhat.toPandas()['prediction'].to_list()
+
+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}
+
+    """
+
+    input = pre_inference(data, input_schema_path)
+    input_cols = input.columns
+    print("Dataset Count: " + str(input.count()))
+
+    yhat = post_inference(model.transform(input), input_cols)
+    return {'prediction': yhat}

ads/templates/score_pytorch.jinja2

@@ -0,0 +1,219 @@
+# score.py {{SCORE_VERSION}} generated by ADS {{ADS_VERSION}} on {{time_created}}
+import os
+import sys
+from functools import lru_cache
+import torch
+import json
+from typing import Dict, List
+import numpy as np
+import pandas as pd
+from io import BytesIO
+import base64
+import logging
+from random import randint
+
+
+def get_torch_device():
+    num_devices = torch.cuda.device_count()
+    if num_devices == 0:
+        return "cpu"
+    if num_devices == 1:
+        return "cuda:0"
+    else:
+        return f"cuda:{randint(0, num_devices-1)}"
+
+
+model_name = '{{model_file_name}}'
+device = torch.device(get_torch_device())
+
+"""
+   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 == "torchscript" %}
+    print(f'Start loading {model_file_name} from model directory {model_dir} ...')
+    the_model = torch.jit.load(os.path.join(model_dir, model_file_name))
+    print(f"loading {model_file_name} is complete.")
+
+{% elif model_serializer == "torch" %}
+    print(f'Start loading {model_file_name} from model directory {model_dir} ...')
+    model_state_dict = torch.load(os.path.join(model_dir, model_file_name))
+    print(f"loading {model_file_name} is complete.")
+
+    # User would need to provide reference to the TheModelClass and
+    # construct the the_model instance first before loading the parameters.
+    # the_model = TheModelClass(*args, **kwargs)
+    try:
+        the_model.load_state_dict(model_state_dict)
+    except NameError as e:
+        raise NotImplementedError("TheModelClass instance must be constructed before loading the parameters. Please modify the load_model() function in score.py." )
+    except Exception as e:
+        raise e
+
+    the_model.eval()
+{% else %}
+    raise NotImplementedError("`load_model()` needs to be implemented.")
+
+{% endif %}
+    print("Model is successfully loaded.")
+    the_model = the_model.to(device)
+    return the_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.pytorch_model.PyTorchModel.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-serialized 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 "torch.Tensor" in data_type:
+        load_bytes = BytesIO(base64.b64decode(json_data.encode('utf-8')))
+        return torch.load(load_bytes)
+    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))
+
+    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 json-serialized data to feed into predict function.
+
+    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)
+
+    # Add further data preprocessing if needed
+    data = data.to(device)
+    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, torch.Tensor):
+        return yhat.tolist()
+
+    # Add further data postprocessing if needed
+    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
+    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)
+
+    with torch.no_grad():
+        yhat = post_inference(
+        model(inputs).to("cpu")
+    )
+    return {'prediction': yhat}

ads/templates/score_scikit-learn.jinja2

@@ -0,0 +1,184 @@
+# score.py {{SCORE_VERSION}} generated by ADS {{ADS_VERSION}} on {{time_created}}
+import os
+import sys
+import json
+import pandas as pd
+import numpy as np
+from functools import lru_cache
+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} ...')
+    from joblib import load
+    with open(os.path.join(os.path.dirname(os.path.realpath(__file__)), model_file_name), "rb") as file:
+        loaded_model = load(file)
+
+{% elif model_serializer == "cloudpickle" %}
+    import cloudpickle
+    with open(os.path.join(os.path.dirname(os.path.realpath(__file__)), model_file_name), "rb") as file:
+        loaded_model = cloudpickle.load(file)
+
+{% 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.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" %}
+    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}
+
+    """
+    input = pre_inference(data, input_schema_path)
+    yhat = post_inference(model.predict(input))
+    return {'prediction': yhat}