from data_load import data_format
import tensorflow as tf
import numpy as np
from keras.layers import Dropout
from keras import regularizers
from keras.callbacks import TensorBoard, LearningRateScheduler
import keras


def model_train(X_train, X_test, Y_train, Y_test):
    """_summary_
    Args:
        X_train (np.array): _description_
        X_test (np.array): _description_
        Y_train (np.array): _description_
        Y_test (np.array): _description_

    """
    # 数据随机化
    np.random.seed(7)
    np.random.shuffle(X_train)
    np.random.seed(7)
    np.random.shuffle(Y_train)
    tf.random.set_seed(7)

    # 构建模型
    model = tf.keras.models.Sequential([
        tf.keras.layers.Dense(10000, activation='relu'),  # 第一层
        Dropout(0.2),
        tf.keras.layers.Dense(800, activation='relu'),  # 第一层
        Dropout(0.2),
        tf.keras.layers.Dense(
            (len(np.unique(Y_train)) + 1), activation='relu', kernel_regularizer=regularizers.l2(0.01))
    ])

    # 损失函数
    loss_fn = tf.keras.losses.SparseCategoricalCrossentropy(from_logits=True)

    # 编译模型
    model.compile(
        optimizer='SGD',
        loss=loss_fn,
        metrics=['accuracy'])

    # 定义学习率指数递减的函数
    def lr_schedule(epoch):
        initial_learning_rate = 0.01
        decay_rate = 0.1
        decay_steps = 1500
        new_learning_rate = initial_learning_rate * \
            decay_rate ** (epoch / decay_steps)
        return new_learning_rate

    # 定义学习率调度器
    lr_scheduler = LearningRateScheduler(lr_schedule)

    # TensorBoard 回调
    log_dir = "logs/fit"
    tensorboard_callback = TensorBoard(log_dir=log_dir, histogram_freq=1)

    # 训练模型，添加 TensorBoard 回调
    model.fit(X_train, Y_train, epochs=1000,
              callbacks=[tensorboard_callback, lr_scheduler], batch_size=256)

    loss, accuracy = model.evaluate(X_test, Y_test)
    print("Test accuracy:", accuracy)

    # 保存模型
    keras.models.save_model(model, 'model')


if __name__ == "__main__":
    X_train, X_test, Y_train, Y_test = data_format(
        'data/archive/PowerQualityDistributionDataset1.csv')
    model_train(X_train, X_test, Y_train, Y_test)