# Copyright Amazon.com, Inc. or its affiliates. All Rights Reserved.
#
# Licensed under the Apache License, Version 2.0 (the "License"). You
# may not use this file except in compliance with the License. A copy of
# the License is located at
#
#     http://aws.amazon.com/apache2.0/
#
# or in the "license" file accompanying this file. This file is
# distributed on an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF
# ANY KIND, either express or implied. See the License for the specific
# language governing permissions and limitations under the License.
from __future__ import absolute_import

import os

import pandas as pd

from sklearn.externals import joblib
from sklearn.linear_model import LogisticRegression


if __name__ == "__main__":
    training_data_directory = "/opt/ml/input/data/train"
    train_features_data = os.path.join(training_data_directory, "train_features.csv")
    train_labels_data = os.path.join(training_data_directory, "train_labels.csv")
    X_train = pd.read_csv(train_features_data, header=None)
    y_train = pd.read_csv(train_labels_data, header=None)

    model = LogisticRegression(class_weight="balanced", solver="lbfgs")
    model.fit(X_train, y_train)
    model_output_directory = os.path.join("/opt/ml/model", "model.joblib")
    joblib.dump(model, model_output_directory)