利用深度学习(Keras)进行癫痫分类-Python案例

#导入工具库
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt

from keras.models import Sequential 
from keras import layers 
from keras import regularizers
from sklearn.model_selection import train_test_split 
from sklearn.metrics import roc_curve, auc


# 加载数据集
data = "data.csv"
df = pd.read_csv(data, header=0, index_col=0)
"""
查看数据集的head和信息
"""
print(df.head())
print(df.info())

"""
设置标签：
将目标变量转换为癫痫(y列编码为1)与非癫痫(2-5)

即将癫痫的目标变量设置为1，其他设置为标签0
"""
df["seizure"] = 0 
for i in range(11500): 
    if df["y"][i] == 1: 
        df["seizure"][i] = 1 
    else:
        df["seizure"][i] = 0

# 绘制并观察脑电波
plt.plot(range(178), df.iloc[11496,0:178]) 
plt.show()

"""
将把数据准备成神经网络可以接受的形式。
首先解析数据，
然后标准化值，
最后创建目标数组
"""
# 创建df1来保存波形数据点(waveform data points) 
df1 = df.drop(["seizure", "y"], axis=1)
# 1. 构建11500 x 178的二维数组
wave = np.zeros((11500, 178))

z=0
for index, row in df1.iterrows():

    wave[z,:] = row
    z +=1

# 打印数组形状
print(wave.shape) 
# 2. 标准化数据
"""
标准化数据，使其平均值为0，标准差为1
"""
mean = wave.mean(axis=0) 
wave -= mean 
std = wave.std(axis=0) 
wave /= std 
# 3. 创建目标数组
target = df["seizure"].values

"""
创建模型
"""
model = Sequential() 
model.add(layers.Dense(64, activation="relu", kernel_regularizer=regularizers.l1(0.001), input_shape = (178,))) 
model.add(layers.Dropout(0.5))
model.add(layers.Dense(64, activation="relu", kernel_regularizer=regularizers.l1(0.001))) 
model.add(layers.Dropout(0.5)) 
model.add(layers.Dense(1, activation="sigmoid")) 
model.summary()


"""
利用sklearn的train_test_split函数将所有的数据的20%作为测试集，其他的作为训练集
"""
x_train, x_test, y_train, y_test = train_test_split(wave, target, test_size=0.2, random_state=42)

#编译机器学习模型
model.compile(optimizer="rmsprop", loss="binary_crossentropy", metrics=["acc"])


"""
训练模型
epoch为100，
batch_size为128，
设置20%的数据集作为验证集
"""
history = model.fit(x_train, y_train, epochs=100, batch_size=128, validation_split=0.2, verbose=2)


# 测试数据(预测数据)
y_pred = model.predict(x_test).ravel()
# 计算ROC
fpr_keras, tpr_keras, thresholds_keras = roc_curve(y_test, y_pred) 
# 计算 AUC
AUC = auc(fpr_keras, tpr_keras)
# 绘制 ROC曲线
plt.plot(fpr_keras, tpr_keras, label='Keras Model(area = {:.3f})'.format(AUC)) 
plt.xlabel('False positive Rate') 
plt.ylabel('True positive Rate') 
plt.title('ROC curve') 
plt.legend(loc='best') 
plt.show()

Model: "sequential_1"
_________________________________________________________________
Layer (type)                 Output Shape              Param #
=================================================================
dense_1 (Dense)              (None, 64)                11456
_________________________________________________________________
dropout_1 (Dropout)          (None, 64)                0
_________________________________________________________________
dense_2 (Dense)              (None, 64)                4160
_________________________________________________________________
dropout_2 (Dropout)          (None, 64)                0
_________________________________________________________________
dense_3 (Dense)              (None, 1)                 65
=================================================================
Total params: 15,681
Trainable params: 15,681
Non-trainable params: 0
_________________________________________________________________
Train on 7360 samples, validate on 1840 samples
Epoch 1/100
 - 0s - loss: 1.9573 - acc: 0.7432 - val_loss: 1.6758 - val_acc: 0.9098
Epoch 2/100
 - 0s - loss: 1.5837 - acc: 0.8760 - val_loss: 1.3641 - val_acc: 0.9332
Epoch 3/100
 - 0s - loss: 1.2899 - acc: 0.9201 - val_loss: 1.1060 - val_acc: 0.9424
Epoch 4/100
 - 0s - loss: 1.0525 - acc: 0.9404 - val_loss: 0.9179 - val_acc: 0.9446
Epoch 5/100
 - 0s - loss: 0.8831 - acc: 0.9466 - val_loss: 0.7754 - val_acc: 0.9484
Epoch 6/100
 - 0s - loss: 0.7291 - acc: 0.9552 - val_loss: 0.6513 - val_acc: 0.9538
Epoch 7/100
 - 0s - loss: 0.6149 - acc: 0.9572 - val_loss: 0.5541 - val_acc: 0.9495
Epoch 8/100
 - 0s - loss: 0.5232 - acc: 0.9558 - val_loss: 0.4717 - val_acc: 0.9484
Epoch 9/100
 - 0s - loss: 0.4443 - acc: 0.9595 - val_loss: 0.4118 - val_acc: 0.9489
Epoch 10/100
 - 0s - loss: 0.3921 - acc: 0.9590 - val_loss: 0.3667 - val_acc: 0.9554
Epoch 11/100
 - 0s - loss: 0.3579 - acc: 0.9553 - val_loss: 0.3348 - val_acc: 0.9565
Epoch 12/100
 - 0s - loss: 0.3302 - acc: 0.9572 - val_loss: 0.3209 - val_acc: 0.9473
Epoch 13/100
 - 0s - loss: 0.3154 - acc: 0.9546 - val_loss: 0.2988 - val_acc: 0.9560
Epoch 14/100
 - 0s - loss: 0.2956 - acc: 0.9596 - val_loss: 0.2899 - val_acc: 0.9500
Epoch 15/100
 - 0s - loss: 0.2907 - acc: 0.9565 - val_loss: 0.2786 - val_acc: 0.9500
Epoch 16/100
 - 0s - loss: 0.2794 - acc: 0.9607 - val_loss: 0.2665 - val_acc: 0.9560
Epoch 17/100
 - 0s - loss: 0.2712 - acc: 0.9588 - val_loss: 0.2636 - val_acc: 0.9598
Epoch 18/100
 - 0s - loss: 0.2665 - acc: 0.9603 - val_loss: 0.2532 - val_acc: 0.9533
Epoch 19/100
 - 0s - loss: 0.2659 - acc: 0.9569 - val_loss: 0.2473 - val_acc: 0.9538
Epoch 20/100
 - 0s - loss: 0.2569 - acc: 0.9591 - val_loss: 0.2451 - val_acc: 0.9614
Epoch 21/100
 - 0s - loss: 0.2464 - acc: 0.9614 - val_loss: 0.2402 - val_acc: 0.9625
Epoch 22/100
 - 0s - loss: 0.2470 - acc: 0.9598 - val_loss: 0.2453 - val_acc: 0.9538
Epoch 23/100
 - 0s - loss: 0.2498 - acc: 0.9601 - val_loss: 0.2408 - val_acc: 0.9538
Epoch 24/100
 - 0s - loss: 0.2433 - acc: 0.9587 - val_loss: 0.2421 - val_acc: 0.9505
Epoch 25/100
 - 0s - loss: 0.2406 - acc: 0.9613 - val_loss: 0.2307 - val_acc: 0.9538
Epoch 26/100
 - 0s - loss: 0.2372 - acc: 0.9601 - val_loss: 0.2301 - val_acc: 0.9538
Epoch 27/100
 - 0s - loss: 0.2294 - acc: 0.9615 - val_loss: 0.2287 - val_acc: 0.9598
Epoch 28/100
 - 0s - loss: 0.2349 - acc: 0.9613 - val_loss: 0.2255 - val_acc: 0.9571
Epoch 29/100
 - 0s - loss: 0.2326 - acc: 0.9579 - val_loss: 0.2206 - val_acc: 0.9554
Epoch 30/100
 - 0s - loss: 0.2257 - acc: 0.9614 - val_loss: 0.2180 - val_acc: 0.9571
Epoch 31/100
 - 0s - loss: 0.2258 - acc: 0.9618 - val_loss: 0.2200 - val_acc: 0.9609
Epoch 32/100
 - 0s - loss: 0.2236 - acc: 0.9611 - val_loss: 0.2213 - val_acc: 0.9538
Epoch 33/100
 - 0s - loss: 0.2201 - acc: 0.9622 - val_loss: 0.2112 - val_acc: 0.9587
Epoch 34/100
 - 0s - loss: 0.2253 - acc: 0.9617 - val_loss: 0.2159 - val_acc: 0.9549
Epoch 35/100
 - 0s - loss: 0.2207 - acc: 0.9629 - val_loss: 0.2114 - val_acc: 0.9598
Epoch 36/100
 - 0s - loss: 0.2228 - acc: 0.9606 - val_loss: 0.2136 - val_acc: 0.9592
Epoch 37/100
 - 0s - loss: 0.2163 - acc: 0.9617 - val_loss: 0.2098 - val_acc: 0.9620
Epoch 38/100
 - 0s - loss: 0.2167 - acc: 0.9621 - val_loss: 0.2179 - val_acc: 0.9560
Epoch 39/100
 - 0s - loss: 0.2137 - acc: 0.9611 - val_loss: 0.2120 - val_acc: 0.9576
Epoch 40/100
 - 0s - loss: 0.2093 - acc: 0.9636 - val_loss: 0.2003 - val_acc: 0.9658
Epoch 41/100
 - 0s - loss: 0.2155 - acc: 0.9621 - val_loss: 0.2016 - val_acc: 0.9625
Epoch 42/100
 - 0s - loss: 0.2076 - acc: 0.9652 - val_loss: 0.1994 - val_acc: 0.9598
Epoch 43/100
 - 0s - loss: 0.2128 - acc: 0.9626 - val_loss: 0.2053 - val_acc: 0.9587
Epoch 44/100
 - 0s - loss: 0.2071 - acc: 0.9643 - val_loss: 0.1974 - val_acc: 0.9630
Epoch 45/100
 - 0s - loss: 0.2078 - acc: 0.9637 - val_loss: 0.2047 - val_acc: 0.9592
Epoch 46/100
 - 0s - loss: 0.2130 - acc: 0.9615 - val_loss: 0.2089 - val_acc: 0.9538
Epoch 47/100
 - 0s - loss: 0.2113 - acc: 0.9617 - val_loss: 0.2007 - val_acc: 0.9582
Epoch 48/100
 - 0s - loss: 0.2072 - acc: 0.9656 - val_loss: 0.2026 - val_acc: 0.9538
Epoch 49/100
 - 0s - loss: 0.2055 - acc: 0.9636 - val_loss: 0.2013 - val_acc: 0.9565
Epoch 50/100
 - 0s - loss: 0.2089 - acc: 0.9610 - val_loss: 0.1974 - val_acc: 0.9582
Epoch 51/100
 - 0s - loss: 0.2033 - acc: 0.9632 - val_loss: 0.1946 - val_acc: 0.9587
Epoch 52/100
 - 0s - loss: 0.2075 - acc: 0.9626 - val_loss: 0.1995 - val_acc: 0.9625
Epoch 53/100
 - 0s - loss: 0.2030 - acc: 0.9635 - val_loss: 0.1948 - val_acc: 0.9603
Epoch 54/100
 - 0s - loss: 0.2038 - acc: 0.9641 - val_loss: 0.1939 - val_acc: 0.9679
Epoch 55/100
 - 0s - loss: 0.2048 - acc: 0.9636 - val_loss: 0.1950 - val_acc: 0.9592
Epoch 56/100
 - 0s - loss: 0.2037 - acc: 0.9637 - val_loss: 0.1917 - val_acc: 0.9636
Epoch 57/100
 - 0s - loss: 0.2014 - acc: 0.9647 - val_loss: 0.1909 - val_acc: 0.9620
Epoch 58/100
 - 0s - loss: 0.1979 - acc: 0.9651 - val_loss: 0.1896 - val_acc: 0.9614
Epoch 59/100
 - 0s - loss: 0.2068 - acc: 0.9629 - val_loss: 0.1909 - val_acc: 0.9609
Epoch 60/100
 - 0s - loss: 0.1990 - acc: 0.9633 - val_loss: 0.1908 - val_acc: 0.9614
Epoch 61/100
 - 0s - loss: 0.1921 - acc: 0.9666 - val_loss: 0.1904 - val_acc: 0.9620
Epoch 62/100
 - 0s - loss: 0.2018 - acc: 0.9629 - val_loss: 0.1896 - val_acc: 0.9614
Epoch 63/100
 - 0s - loss: 0.2041 - acc: 0.9620 - val_loss: 0.1917 - val_acc: 0.9625
Epoch 64/100
 - 0s - loss: 0.2000 - acc: 0.9652 - val_loss: 0.1891 - val_acc: 0.9620
Epoch 65/100
 - 0s - loss: 0.1967 - acc: 0.9656 - val_loss: 0.1916 - val_acc: 0.9609
Epoch 66/100
 - 0s - loss: 0.1961 - acc: 0.9639 - val_loss: 0.1854 - val_acc: 0.9641
Epoch 67/100
 - 0s - loss: 0.1969 - acc: 0.9648 - val_loss: 0.1887 - val_acc: 0.9592
Epoch 68/100
 - 0s - loss: 0.1990 - acc: 0.9630 - val_loss: 0.1874 - val_acc: 0.9636
Epoch 69/100
 - 0s - loss: 0.1923 - acc: 0.9662 - val_loss: 0.1893 - val_acc: 0.9614
Epoch 70/100
 - 0s - loss: 0.1925 - acc: 0.9645 - val_loss: 0.1853 - val_acc: 0.9641
Epoch 71/100
 - 0s - loss: 0.1948 - acc: 0.9622 - val_loss: 0.1905 - val_acc: 0.9592
Epoch 72/100
 - 0s - loss: 0.1994 - acc: 0.9628 - val_loss: 0.1852 - val_acc: 0.9641
Epoch 73/100
 - 0s - loss: 0.1953 - acc: 0.9651 - val_loss: 0.1834 - val_acc: 0.9641
Epoch 74/100
 - 0s - loss: 0.1888 - acc: 0.9670 - val_loss: 0.1816 - val_acc: 0.9620
Epoch 75/100
 - 0s - loss: 0.1933 - acc: 0.9659 - val_loss: 0.1860 - val_acc: 0.9620
Epoch 76/100
 - 0s - loss: 0.1917 - acc: 0.9635 - val_loss: 0.1828 - val_acc: 0.9625
Epoch 77/100
 - 0s - loss: 0.1907 - acc: 0.9677 - val_loss: 0.1828 - val_acc: 0.9603
Epoch 78/100
 - 0s - loss: 0.1990 - acc: 0.9637 - val_loss: 0.1805 - val_acc: 0.9652
Epoch 79/100
 - 0s - loss: 0.1934 - acc: 0.9652 - val_loss: 0.1864 - val_acc: 0.9614
Epoch 80/100
 - 0s - loss: 0.1870 - acc: 0.9667 - val_loss: 0.1808 - val_acc: 0.9674
Epoch 81/100
 - 0s - loss: 0.1901 - acc: 0.9660 - val_loss: 0.1825 - val_acc: 0.9625
Epoch 82/100
 - 0s - loss: 0.1880 - acc: 0.9649 - val_loss: 0.1871 - val_acc: 0.9663
Epoch 83/100
 - 0s - loss: 0.1901 - acc: 0.9677 - val_loss: 0.1808 - val_acc: 0.9620
Epoch 84/100
 - 0s - loss: 0.1941 - acc: 0.9620 - val_loss: 0.1853 - val_acc: 0.9647

Epoch 85/100
 - 0s - loss: 0.1867 - acc: 0.9674 - val_loss: 0.1825 - val_acc: 0.9620
Epoch 86/100
 - 0s - loss: 0.1940 - acc: 0.9651 - val_loss: 0.1877 - val_acc: 0.9576
Epoch 87/100
 - 0s - loss: 0.1913 - acc: 0.9633 - val_loss: 0.1817 - val_acc: 0.9620
Epoch 88/100
 - 0s - loss: 0.1940 - acc: 0.9649 - val_loss: 0.1834 - val_acc: 0.9636
Epoch 89/100
 - 0s - loss: 0.1886 - acc: 0.9656 - val_loss: 0.1844 - val_acc: 0.9625
Epoch 90/100
 - 0s - loss: 0.1835 - acc: 0.9677 - val_loss: 0.1899 - val_acc: 0.9641
Epoch 91/100
 - 0s - loss: 0.1884 - acc: 0.9674 - val_loss: 0.1894 - val_acc: 0.9587
Epoch 92/100
 - 0s - loss: 0.1855 - acc: 0.9675 - val_loss: 0.1894 - val_acc: 0.9582
Epoch 93/100
 - 0s - loss: 0.1864 - acc: 0.9655 - val_loss: 0.1808 - val_acc: 0.9641
Epoch 94/100
 - 0s - loss: 0.1878 - acc: 0.9671 - val_loss: 0.1865 - val_acc: 0.9609
Epoch 95/100
 - 0s - loss: 0.1901 - acc: 0.9662 - val_loss: 0.1859 - val_acc: 0.9641
Epoch 96/100
 - 0s - loss: 0.1836 - acc: 0.9670 - val_loss: 0.1823 - val_acc: 0.9647
Epoch 97/100
 - 0s - loss: 0.1876 - acc: 0.9664 - val_loss: 0.1799 - val_acc: 0.9668
Epoch 98/100
 - 0s - loss: 0.1854 - acc: 0.9675 - val_loss: 0.1912 - val_acc: 0.9565
Epoch 99/100
 - 0s - loss: 0.1881 - acc: 0.9673 - val_loss: 0.1801 - val_acc: 0.9668
Epoch 100/100
 - 0s - loss: 0.1821 - acc: 0.9674 - val_loss: 0.1758 - val_acc: 0.9701