datafile = 'E:/Wendy/Desktop/TrainingSet/data/A04.mat'# 采樣率400
data = scio.loadmat(datafile)
#rint(data) # dict

sig = data['ecg']# (x,1)
#print(sig)
sig = np.reshape(sig,(-1)) # (x,)轉(zhuǎn)換為一維向量
print(sig)
sigPlot = sig[1:5*200]# # 獲取前1000個信號
fig = plt.figure(figsize=(20, 10),dpi=400)
plt.plot(sigPlot)
plt.show()

datafile = 'E:/Wendy/Desktop/TrainingSet/ref/R04.mat'# 采樣率400
data = scio.loadmat(datafile)
#print(data)
label = data['ref'][0][0]
S_ref = label[0];
S_ref = np.reshape(S_ref,(-1)) # 轉(zhuǎn)換為一維向量
V_ref = label[1];
V_ref = np.reshape(V_ref,(-1)) # 轉(zhuǎn)換為一維向量

a = len(sig)
Fs = 400 # 采樣率為400
segLen = 5*Fs # 2000
num = int(a/segLen)
print(num)

all_data=[]
all_label = [];
i=1
while i<num+1: 
    all_data.append(np.array(sig[(i-1)*segLen:i*segLen]))
    # 標簽
    if set(S_ref) & set(range((i-1)*segLen,i*segLen)):
        all_label.append(2)
    elif set(V_ref) & set(range((i-1)*segLen,i*segLen)):
        all_label.append(1)        
    else:
        all_label.append(0)    
    i=i+1
type(all_data)# list類型
type(all_label)# list類型
print((np.array(all_data)).shape) # 17650為數(shù)據(jù)長度,2000為數(shù)據(jù)個數(shù)
print((np.array(all_label)).shape)
#print(all_data)

import pickle
res = {'data':all_data, 'label':all_label} # 字典類型dict
with open('./cpsc2020.pkl', 'wb') as fout: # #將結(jié)果保存為cpsc2020.pkl
    pickle.dump(res, fout)

import numpy as np
import pandas as pd
import scipy.io
from matplotlib import pyplot as plt
import pickle
from sklearn.model_selection import train_test_split
from collections import Counter
from tqdm import tqdm

def read_data_physionet():
    """
    only N V, S
    """
    # read pkl
    with open('./cpsc2020.pkl', 'rb') as fin:
        res = pickle.load(fin) # 加載數(shù)據(jù)集
    ## 數(shù)據(jù)歸一化
    all_data = res['data']
    for i in range(len(all_data)):
        tmp_data = all_data[i]
        tmp_std = np.std(tmp_data) # 獲取數(shù)據(jù)標準差
        tmp_mean = np.mean(tmp_data) # 獲取數(shù)據(jù)均值
        if(tmp_std==0):   # i=1239-1271均為0
            tmp_std = 1 
        all_data[i] = (tmp_data - tmp_mean) / tmp_std  # 歸一化
    all_data = []
    ## 標簽編碼
    all_label = []
    for i in range(len(res['label'])):
        if res['label'][i] == 1:
            all_label.append(1)
            all_data.append(res['data'][i])
        elif res['label'][i] == 2:
            all_label.append(2)
            all_data.append(res['data'][i])
        else:
            all_label.append(0)
            all_data.append(res['data'][i])       
    all_label = np.array(all_label)
    all_data = np.array(all_data)

    # 劃分訓(xùn)練集和測試集,訓(xùn)練集90%，測試集10%
    X_train, X_test, Y_train, Y_test = train_test_split(all_data, all_label, test_size=0.1, random_state=15)
    
 
    print('訓(xùn)練集和測試集中 其他類別(0)；室早(1)；房早(2)的數(shù)量: ')
    print(Counter(Y_train), Counter(Y_test))
    
    # 打亂訓(xùn)練集
    shuffle_pid = np.random.permutation(Y_train.shape[0])
    X_train = X_train[shuffle_pid]
    Y_train = Y_train[shuffle_pid]

    # 擴展為二維(x,1)
    X_train = np.expand_dims(X_train, 1)
    X_test = np.expand_dims(X_test, 1)

    return X_train, X_test, Y_train, Y_test
X_train, X_test, Y_train, Y_test = read_data_physionet()

# 構(gòu)建數(shù)據(jù)結(jié)構(gòu) MyDataset
# 單條數(shù)據(jù)信號的形狀為：1*2000
import numpy as np
from collections import Counter
from tqdm import tqdm
from matplotlib import pyplot as plt
from sklearn.metrics import classification_report 

import torch
import torch.nn as nn
import torch.optim as optim
import torch.nn.functional as F
from torch.utils.data import Dataset, DataLoader

class MyDataset(Dataset):
    def __init__(self, data, label):
        self.data = data
        self.label = label
    #把numpy轉(zhuǎn)換為Tensor
    def __getitem__(self, index):
        return (torch.tensor(self.data[index], dtype=torch.float), torch.tensor(self.label[index], dtype=torch.long))

    def __len__(self):
        return len(self.data)

# 搭建神經(jīng)網(wǎng)絡(luò)
class CNN(nn.Module):
    def __init__(self):
        super(CNN, self).__init__()
        self.conv1 = nn.Sequential(         # input shape (1, 1, 2000)
            nn.Conv1d(
                in_channels=1,
                out_channels=16,
                kernel_size=5,
                stride=1, 
                padding=2,
            ),                              # output shape (16, 1, 2000)
            nn.Dropout(0.2),
            nn.ReLU(),
            nn.MaxPool1d(kernel_size=5),    # choose max value in 1x5 area, output shape (16, 1, 400)2000/5
        )
        self.conv2 = nn.Sequential(         # input shape (16, 1, 400)
            nn.Conv1d(16, 32, 5, 1, 2),     # output shape (32, 1, 400)
            nn.Dropout(0.2),
            nn.ReLU(),
            nn.MaxPool1d(kernel_size=5),    # output shape (32, 1, 400/5=80)
        )
        self.out = nn.Linear(32 *  80, 3)   # fully connected layer, output 3 classes

    def forward(self, x):
        x = self.conv1(x)
        x = self.conv2(x)
        x = x.view(x.size(0), -1)
        output = self.out(x)
        #output.Softmax()
        return output, x
cnn = CNN()
print(cnn)