我用的Keras版本为2.2.0，部分参数有变化，再参考Keras文档后，进行修改，得出结果。仅供参考。

import pandas as pd
from keras.models import Sequential
from keras.layers.core import Dense, Activation
from cm_plot import *
import pandas as pd


inputfile = r'E:\Downloads\1662557648_Lbbweibo\python数据分析与挖掘实战配套资料' \
            r'\图书配套数据、代码\chapter5\demo\data\sales_data.xls'
data = pd.read_excel(inputfile, index_col='序号')  # 导入数据

data[data == u'好'] = 1
data[data == u'是'] = 1
data[data == u'高'] = 1
data[data != 1] = 0
x = data.iloc[:, :3].as_matrix().astype(int)
y = data.iloc[:, 3].as_matrix().astype(int)

model = Sequential()
model.add(Dense(input_dim=3, output_dim=10))
model.add(Activation('relu'))
model.add(Dense(input_dim=10, output_dim=1))
model.add(Activation('sigmoid'))

model.compile(loss='binary_crossentropy', optimizer='rmsprop', metrics=['accuracy'])

model.fit(x, y, nb_epoch=1000, batch_size=10)
yp = model.predict_classes(x).reshape(len(y))

cm_plot(y, yp).savefig(r'E:\python数据分析与挖掘实战配套资料\图书配套数据、代码\chapter5\demo\data\cm.png')

最后得到的混淆矩阵图为：