"""
@File  : data_loader.py
@Author: tao.jing
@Date  : 2022/5/18
@Desc  :
"""
import os
import numpy as np
import h5py

from config import _C

# from pyts.approximation import PiecewiseAggregateApproximation
# from pyts.preprocessing import MinMaxScaler


'''def data_to_h5(data_array_2D,data_num):
    gram_num = []
    for data_number in range(data_num):
        gram_channel = []
        for channel in range(16):
            channel_pop = 0
            if channel == 12:
                channel_pop = 1
            if channel_pop == 0:
                Y_smooth1 = data_array_2D[data_number, 0:250, channel]
                Y_smooth2 = data_array_2D[data_number, 250:1250, channel]
                Y_smooth3 = data_array_2D[data_number, 1250:1500, channel]
                # print(Y_smooth1.shape, Y_smooth1.size)

                X_smooth1 = range(250)
                X_smooth2 = range(1000)
                X_smooth3 = range(250)

                smooth1 = [X_smooth1, Y_smooth1]
                smooth2 = [X_smooth2, Y_smooth2]
                smooth3 = [X_smooth3, Y_smooth3]
                # PAA
                transformer_smooth1 = PiecewiseAggregateApproximation(window_size=50)
                result1 = transformer_smooth1.transform(smooth1)

                transformer_smooth2 = PiecewiseAggregateApproximation(window_size=20)
                result2 = transformer_smooth2.transform(smooth2)

                transformer_smooth3 = PiecewiseAggregateApproximation(window_size=50)
                result3 = transformer_smooth3.transform(smooth3)

                result = np.concatenate((result1, result2, result3), axis=1)

                # Scaling in interval [0,1]
                scaler = MinMaxScaler()
                scaled_X = scaler.transform(result)

                scaled_X1 = []
                for data in scaled_X[1, :]:
                    if data >= 1:
                        scaled_X1.append(0.99999)
                    else:
                        scaled_X1.append(data)

                arccos_X = np.arccos(scaled_X1)

                field = [a + b for a in arccos_X for b in arccos_X]
                gram = np.cos(field)
                gram = gram.reshape(-1, 60)
                gram_channel.append(gram)
                # print(np.array(gram_channel).shape)
        gram_num.append(gram_channel)
    return np.array(gram_num)


def convert_data_to_h5():
    train_data_name_path = _C.path.train_data_name_path
    test_data_name_path = _C.path.test_data_name_path

    train_data_files = list()
    test_data_files = list()
    with open(train_data_name_path, 'r') as f:
        lines = f.readlines()
        for line in lines:
            name = line.rstrip()
            data_file_path =\
                np.loadtxt(os.path.join(_C.path.enose_train_data_dir, name))
            train_data_files.append(data_file_path)
    print(len(train_data_files))

    with open(test_data_name_path, 'r') as f:
        lines = f.readlines()
        for line in lines:
            name = line.rstrip()
            data_file_path =\
                np.loadtxt(os.path.join(_C.path.enose_test_data_dir, name))
            test_data_files.append(data_file_path)
    print(len(test_data_files))

    train_label_array = np.loadtxt(os.path.join(_C.path.train_label_name_path))
    test_label_array = np.loadtxt(os.path.join(_C.path.test_label_name_path))

    train_data_files = [x[:1500] for x in train_data_files]
    train_data_array = np.asarray(train_data_files)
    train_data_array_2D = data_to_h5(train_data_array,_C.data.train_num)
    # print(train_data_array_2D.shape)

    test_data_files = [x[:1500] for x in test_data_files]
    test_data_array = np.asarray(test_data_files)
    test_data_array_2D = data_to_h5(test_data_array,_C.data.test_num)
    # print(test_data_array_2D.shape)

    train_data_array_1D = train_data_array[:, :, [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 13, 14, 15]]
    test_data_array_1D = test_data_array[:, :, [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 13, 14, 15]]



    with h5py.File('enose_fire.h5', 'w') as hf:
        hf['enose_train_data_2D'] = train_data_array_2D
        hf['enose_train_data_1D'] = train_data_array_1D
        hf['enose_train_label'] = train_label_array
        hf['enose_test_data_2D'] = test_data_array_2D
        hf['enose_test_data_1D'] = test_data_array_1D
        hf['enose_test_label'] = test_label_array'''



def load_enose_data():
    enose_train_data = None
    enose_train_label = None
    enose_test_data = None
    enose_test_label = None

    with h5py.File(_C.path.enose_data_h5_path, 'r') as hf:
        enose_train_data_2D = hf['enose_train_data_2D'][:]
        enose_train_data_1D = hf['enose_train_data_1D'][:]
        enose_train_label = hf['enose_train_label'][:]
        enose_test_data_2D = hf['enose_test_data_2D'][:]
        enose_test_data_1D = hf['enose_test_data_1D'][:]
        enose_test_label = hf['enose_test_label'][:]

    #print(enose_data.shape)
    #print(enose_label.shape)

    return enose_train_data_2D,enose_train_data_1D, enose_train_label,enose_test_data_2D,enose_test_data_1D,enose_test_label


def load_split_data(valid_ratio=0.2, shuffle=True):
    enose_train_data = None
    enose_train_label = None
    enose_test_data = None
    enose_test_label = None

    with h5py.File(_C.path.enose_data_h5_path, 'r') as hf:
        enose_train_data_2D = hf['enose_train_data_2D'][:]
        enose_train_data_1D = hf['enose_train_data_1D'][:]
        enose_train_label = hf['enose_train_label'][:]
        enose_test_data_2D = hf['enose_test_data_2D'][:]
        enose_test_data_1D = hf['enose_test_data_1D'][:]
        enose_test_label = hf['enose_test_label'][:]

    return (enose_train_data_2D,enose_train_data_1D, enose_train_label), (enose_test_data_2D,enose_test_data_1D, enose_test_label)


if __name__ == '__main__':
    # convert_data_to_h5()
    load_enose_data()