# Copyright Amazon.com, Inc. or its affiliates. All Rights Reserved.
#
# SPDX-License-Identifier: MIT-0
#
# Permission is hereby granted, free of charge, to any person obtaining a copy of this
# software and associated documentation files (the "Software"), to deal in the Software
# without restriction, including without limitation the rights to use, copy, modify,
# merge, publish, distribute, sublicense, and/or sell copies of the Software, and to
# permit persons to whom the Software is furnished to do so.
#
# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR IMPLIED,
# INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, FITNESS FOR A
# PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT
# HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION
# OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE
# SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.

"""Evaluation script for measuring mean squared error."""
import json
import logging
import pathlib
import pickle
import tarfile

import numpy as np
import pandas as pd
import xgboost

from sklearn.metrics import mean_squared_error

logger = logging.getLogger()
logger.setLevel(logging.INFO)
logger.addHandler(logging.StreamHandler())


if __name__ == "__main__":
    logger.debug("Starting evaluation.")
    model_path = "/opt/ml/processing/model/model.tar.gz"
    with tarfile.open(model_path) as tar:
        tar.extractall(path=".")

    logger.debug("Loading xgboost model.")
    model = pickle.load(open("xgboost-model", "rb"))

    logger.debug("Reading test data.")
    test_path = "/opt/ml/processing/test/test.csv"
    df = pd.read_csv(test_path, header=None)

    logger.debug("Reading test data.")
    y_test = df.iloc[:, 0].to_numpy()
    df.drop(df.columns[0], axis=1, inplace=True)
    X_test = xgboost.DMatrix(df.values)

    logger.info("Performing predictions against test data.")
    predictions = model.predict(X_test)

    logger.debug("Calculating mean squared error.")
    mse = mean_squared_error(y_test, predictions)
    std = np.std(y_test - predictions)
    report_dict = {
        "regression_metrics": {
            "mse": {"value": mse, "standard_deviation": std},
        },
    }

    output_dir = "/opt/ml/processing/evaluation"
    pathlib.Path(output_dir).mkdir(parents=True, exist_ok=True)

    logger.info("Writing out evaluation report with mse: %f", mse)
    evaluation_path = f"{output_dir}/evaluation.json"
    with open(evaluation_path, "w") as f:
        f.write(json.dumps(report_dict))