Document organization

Number-Of-CNN-Layers/_mian_tensorflow_oneLayerCNN.py

@@ -0,0 +1,112 @@
+import datetime
+import os
+
+import numpy as np
+import pywt
+import wfdb
+import tensorflow as tf
+from tensorflow import keras
+from utils_oneLayerCNN import loadData, plot_history_tf, plot_heat_map
+
+#from ECG_read_weiyuqing_without_wfdb import ECGDATAPATH
+#PATH of this test
+Project_PATH = "../Number-Of-CNN-Layers/One/"
+#PICTUREPATH= Project_PATH + "picture/"
+log_dir = Project_PATH + "logs/" + datetime.datetime.now().strftime("%Y%m%d-%H%M%S")
+model_Path_one = Project_PATH  + "model/ecg_model_one_layer.h5"
+#model_Path_one = Project_PATH + "ecg_model_one_layer.h5"
+
+RATIO = 0.3
+RANDOM_SEED = 42
+BATCH_SIZE = 128
+NUM_EPOCHS = 30
+
+
+def CNN_model_level_one():
+    leavlOneModel = tf.keras.models.Sequential([
+
+        # #four CNN layers test
+        # tf.keras.layers.InputLayer(input_shape=(300,)),
+        # # reshape the tensor with shape (batch_size, 300) to (batch_size, 300, 1)
+        # tf.keras.layers.Reshape(target_shape=(300, 1)),
+        # # the first convolution layer, 4 21x1 convolution kernels, output shape (batch_size, 300, 4)
+        # tf.keras.layers.Conv1D(filters=4, kernel_size=21, strides=1, padding='SAME', activation='relu'),
+        # # the first pooling layer, max pooling, pooling size=3 , stride=2, output shape (batch_size, 150, 4)
+        # tf.keras.layers.MaxPool1D(pool_size=3, strides=2, padding='SAME'),
+        # # the second convolution layer, 16 23x1 convolution kernels, output shape (batch_size, 150, 16)
+        # tf.keras.layers.Conv1D(filters=16, kernel_size=23, strides=1, padding='SAME', activation='relu'),
+        # # the second pooling layer, max pooling, pooling size=3, stride=2, output shape (batch_size, 75, 16)
+        # tf.keras.layers.MaxPool1D(pool_size=3, strides=2, padding='SAME'),
+        # # the third convolution layer, 32 25x1 convolution kernels, output shape (batch_size, 75, 32)
+        # tf.keras.layers.Conv1D(filters=32, kernel_size=25, strides=1, padding='SAME', activation='relu'),
+        # # the third pooling layer, average pooling, pooling size=3, stride=2, output shape (batch_size, 38, 32)
+        # tf.keras.layers.AvgPool1D(pool_size=3, strides=2, padding='SAME'),
+        # # the fourth convolution layer, 64 27x1 convolution kernels, output shape (batch_size, 38, 64)
+        # tf.keras.layers.Conv1D(filters=64, kernel_size=27, strides=1, padding='SAME', activation='relu'),
+        # # flatten layer, for the next fully connected layer, output shape (batch_size, 38*64)
+        # tf.keras.layers.Flatten(),
+        # # fully connected layer, 128 nodes, output shape (batch_size, 128)
+        # tf.keras.layers.Dense(128, activation='relu'),
+        # # Dropout layer, dropout rate = 0.2
+        # tf.keras.layers.Dropout(rate=0.2),
+        # # fully connected layer, 5 nodes (number of classes), output shape (batch_size, 5)
+        # tf.keras.layers.Dense(5, activation='softmax')
+
+        #take test for one CNN layers model
+
+        tf.keras.layers.InputLayer(input_shape=(300, 1)),
+
+        # ECG data cant add 0 in edge, will broken data ,take false answer. So we need padding same data in edge.
+
+        # take four 21*1 conv excitation function used RElu
+        tf.keras.layers.Conv1D(filters=4, kernel_size=21, strides=1, padding='same', activation='relu'),
+        # take four 3*1 pool,take strids 2.
+
+        tf.keras.layers.MaxPool1D(pool_size=3, strides=2, padding='same'),
+
+        # tf.keras.layers.Conv1D(filters=4, kernel_size=21, strides=1, padding='same', activation='relu'),
+        # tf.keras.layers.MaxPool1D(pool_size=3, strides=2, padding='same'),
+
+        tf.keras.layers.Flatten(),
+        tf.keras.layers.Dense(128, activation='relu'),
+        tf.keras.layers.Dropout(rate=0.2),
+        tf.keras.layers.Dense(5, activation='softmax')
+    ])
+    return leavlOneModel
+
+
+def main():
+    # get traxin test
+    X_train, X_test, y_train, y_test = loadData(RATIO, RANDOM_SEED)
+
+    # get model or create model
+    if os.path.exists(model_Path_one):
+        print(' get model in h5 file')
+        model = tf.keras.models.load_model(filepath=model_Path_one)
+    else:
+        # create new model(if model unexists)
+        model = CNN_model_level_one()
+        model.compile(optimizer='adam',
+                      loss='sparse_categorical_crossentropy',
+                      metrics=['accuracy'])
+        model.summary()
+        # TB make
+        tensorboard_callback = tf.keras.callbacks.TensorBoard(log_dir=log_dir,
+                                                              histogram_freq=1,
+                                                              )
+        # Training and validation
+        history = model.fit(X_train, y_train, epochs=NUM_EPOCHS,
+                            batch_size=BATCH_SIZE,
+                            validation_data=(X_test, y_test),
+                            callbacks=[tensorboard_callback])
+        # validation_split=RATIO,
+        model.save(filepath=model_Path_one)
+        plot_history_tf(history)
+
+    y_pred = np.argmax(model.predict(X_test), axis=-1)
+    plot_heat_map(y_test, y_pred)
+
+
+if __name__ == '__main__':
+    os.environ["CUDA_VISIBLE_DEVICES"] = "-1"
+    main()

Number-Of-CNN-Layers/utils_oneLayerCNN.py

@@ -0,0 +1,172 @@
+# this file give
+import os
+
+import wfdb
+import pywt
+import seaborn
+import numpy as np
+import matplotlib.pyplot as plt
+from sklearn.metrics import confusion_matrix
+from sklearn.model_selection import train_test_split
+
+# from _mian_tensorflow import Project_PATH
+Project_PATH = '../Number-Of-CNN-Layers/One/'
+
+PICTUREPATH = Project_PATH + 'picture/'
+
+# from ECG_read_weiyuqing_without_wfdb import ECGDATAPATH
+MITBITECGDATAPATH = '../MIT-BIT/'
+
+
+# wavelet denoise preprocess using mallat algorithm
+
+def denoise(date):
+    # Wavelet db5 level9
+    coeffs = pywt.wavedec(data=date, wavelet='db5', level=9)
+    cA9, cD9, cD8, cD7, cD6, cD5, cD4, cD3, cD2, cD1 = coeffs
+    # noice del
+    threshold = (np.median(np.abs(cD1)) / 0.6745) * (np.sqrt(2 * np.log(len(cD1))))
+    # take cD 1,2 turn 0 to denoise
+    cD1.fill(0)
+    cD2.fill(0)
+    for i in range(1, len(coeffs) - 2):
+        coeffs[i] = pywt.threshold(coeffs[i], threshold)
+    # get signal that before wavelet
+    rdata = pywt.waverec(coeffs=coeffs, wavelet='db5')
+    return rdata
+
+
+# get ECG data,date type and denoise
+# this function without return
+# use append take return data to pass data
+def getDataSet(number, X_data, Y_data):
+    ecgClassSet = ['N', 'A', 'V', 'L', 'R']
+    print('get' + number + ' ECG data')
+    record = wfdb.rdrecord(MITBITECGDATAPATH + number, channel_names=['MLII'])
+    data = record.p_signal.flatten()
+    # use def denoise
+    rdata = denoise(date=data)
+
+    # get type of ECG data
+    annotation = wfdb.rdann(MITBITECGDATAPATH + number, 'atr')
+    Rlocation = annotation.sample  # annotation.sample:get R
+    Rclass = annotation.symbol
+
+    # delete stable date near R
+    start = 10
+    end = 5
+    i = start
+    j = len(annotation.symbol) - end
+
+    # get NAVLR type data
+    while i < j:
+        try:
+            lable = ecgClassSet.index(Rclass[i])
+            x_train = rdata[Rlocation[i] - 99:Rlocation[i] + 201]
+            X_data.append(x_train)
+            Y_data.append(lable)
+            i += 1
+        except ValueError:
+            i += 1
+    return
+
+
+# RATIO=The ratio of the training set to the test set，usually is 0.3
+def loadData(ratio, random_seed):
+    numberSet = ['100', '101', '103', '105', '106', '107', '108', '109', '111', '112', '113', '114', '115',
+                 '116', '117', '119', '121', '122', '123', '124', '200', '201', '202', '203', '205', '208',
+                 '210', '212', '213', '214', '215', '217', '219', '220', '221', '222', '223', '228', '230',
+                 '231', '232', '233', '234']
+    dataSet = []
+    labelSet = []
+    for n in numberSet:
+        getDataSet(n, dataSet, labelSet)
+
+    # dataSet = np.array(dataSet).reshape(-1, 300)
+    # labelSet = np.array(labelSet).reshape(-1, 1)
+
+    # reshape the data and split the dataset
+    dataSet = np.array(dataSet).reshape(-1, 300)
+    lableSet = np.array(labelSet).reshape(-1)
+    X_train, X_test, y_train, y_test = train_test_split(dataSet, lableSet, test_size=ratio, random_state=random_seed)
+    # print(X_train, X_test, y_train, y_test)
+    return X_train, X_test, y_train, y_test
+
+    # train_ds = np.hstack((dataSet, labelSet))
+    # np.random.shuffle(train_ds)
+    #
+    # X = train_ds[:, :300].reshape(-1, 300, 1)
+    # Y = train_ds[:, 300]
+    # # cut test and train data from ECG data
+    # shuffle_index = np.random.permutation(len(X))
+    # test_length = int(RATIO * len(shuffle_index))
+    # test_index = shuffle_index[:test_length]
+    # train_index = shuffle_index[test_index:]
+    # X_test, Y_test = X[test_index:], Y[test_index]
+    # X_train, Y_train = X[train_index], Y[train_index]
+    # return X_train, Y_test, X_test, Y_train
+
+
+# confusion matrix
+def plot_heat_map(y_test, y_pred):
+    con_mat = confusion_matrix(y_test, y_pred)
+    # normalize
+    # con_mat_norm = con_mat.astype('float') / con_mat.sum(axis=1)[:, np.newaxis]
+    # con_mat_norm = np.around(con_mat_norm, decimals=2)
+    # os.remove(PICTUREPATH+'confusion_matrix.png')
+    # plot
+    plt.figure(figsize=(8, 8))
+    seaborn.heatmap(con_mat, annot=True, fmt='.20g', cmap='Blues')
+    plt.ylim(0, 5)
+    plt.xlabel('Predicted labels')
+    plt.ylabel('True labels')
+    plt.title('Confusion Matrix')
+    plt.savefig(PICTUREPATH + 'confusion_matrix.png')
+    plt.show()
+
+
+def plot_history_tf(history):
+    # os.remove(PICTUREPATH+'accuracy.png')
+    # os.remove(PICTUREPATH+'loss.png')
+
+    plt.figure(figsize=(8, 8))
+    plt.plot(history.history['accuracy'])
+    plt.plot(history.history['val_accuracy'])
+    plt.title('Model Accuracy')
+    plt.ylabel('Accuracy')
+    plt.xlabel('Epoch')
+    plt.legend(['Train', 'Test'], loc='upper left')
+    plt.savefig(PICTUREPATH + 'accuracy.png')
+    plt.show()
+
+    plt.figure(figsize=(8, 8))
+    plt.plot(history.history['loss'])
+    plt.plot(history.history['val_loss'])
+    plt.title('Model Loss')
+    plt.ylabel('Loss')
+    plt.xlabel('Epoch')
+    plt.legend(['Train', 'Test'], loc='upper left')
+    plt.savefig(PICTUREPATH + 'loss.png')
+    plt.show()
+
+
+def plot_history_torch(history):
+    plt.figure(figsize=(8, 8))
+    plt.plot(history['train_acc'])
+    plt.plot(history['test_acc'])
+    plt.title('Model Accuracy')
+    plt.ylabel('Accuracy')
+    plt.xlabel('Epoch')
+    plt.legend(['Train', 'Test'], loc='upper left')
+    plt.savefig(PICTUREPATH + 'accuracy.png')
+    plt.show()
+
+    plt.figure(figsize=(8, 8))
+    plt.plot(history['train_loss'])
+    plt.plot(history['test_loss'])
+    plt.title('Model Loss')
+    plt.ylabel('Loss')
+    plt.xlabel('Epoch')
+    plt.legend(['Train', 'Test'], loc='upper left')
+    plt.savefig(PICTUREPATH + 'loss.png')
+    plt.show()