1 #coding=utf-8
  2 #1.数据预处理
  3 import numpy as np             #导入模块，numpy是扩展链接库
  4 import pandas as pd
  5 import tensorflow
  6 import keras
  7 from keras.utils import np_utils
  8 np.random.seed(10)            #设置seed可以产生的随机数据
  9 from keras.datasets import mnist  #导入模块，下载读取mnist数据
 10 (x_train_image,y_train_label),\
 11 (x_test_image,y_test_label)=mnist.load_data() #下载读取mnist数据
 12 print('train data=',len(x_train_image))
 13 print('test data=',len(x_test_image))
 14 print('x_train_image:',x_train_image.shape)
 15 print('y_train_label:',y_train_label.shape)
 16 import matplotlib.pyplot as plt
 17 def plot_image(image):
 18     fig=plt.gcf()
 19     fig.set_size_inches(2,2)
 20     plt.imshow(image,cmap='binary')
 21     plt.show()
 22 y_train_label[0]
 23 import matplotlib.pyplot as plt
 24 def plot_image_labels_prediction(image,lables,prediction,idx,num=10):
 25     fig=plt.gcf()
 26     fig.set_size_inches(12,14)
 27     if num>25:num=25
 28     for i in range(0,num):
 29         ax=plt.subplot(5,5,i+1)
 30         ax.imshow(image[idx],cmap='binary')
 31         title="lable="+str(lables[idx])
 32         if len(prediction)>0:
 33             title+=",predict="+str(prediction[idx])
 34         ax.set_title(title,fontsize=10)
 35         ax.set_xticks([]);ax.set_yticks([])
 36         idx+=1
 37     plt.show()
 38 plot_image_labels_prediction(x_train_image,y_train_label,[],0,10)
 39 plot_image_labels_prediction(x_test_image,y_test_label,[],0,10)
 40 x_Train=x_train_image.reshape(60000,784).astype('float32') #以reshape转化成784个float
 41 x_Test=x_test_image.reshape(10000,784).astype('float32')
 42 x_Train_normalize=x_Train/255    #将features标准化
 43 x_Test_normalize=x_Test/255
 44 y_Train_OneHot=np_utils.to_categorical(y_train_label)#将训练数据和测试数据的label进行one-hot encoding转化
 45 y_Test_OneHot=np_utils.to_categorical(y_test_label)
 46 #2.建立模型
 47 from keras.models import Sequential #可以通过Sequential模型传递一个layer的list来构造该模型,序惯模型是多个网络层的线性堆叠
 48 from keras.layers import Dense    #全连接层
 49 from keras.layers import Dropout  #避免过度拟合
 50 model=Sequential()
 51 #建立输入层、隐藏层
 52 model.add(Dense(units=1000,
 53                 input_dim=784,
 54                 kernel_initializer='normal',
 55                 activation='relu'))
 56 model.add(Dropout(0.5))
 57 model.add(Dense(units=1000,
 58                 kernel_initializer='normal',
 59                 activation='relu'))
 60 model.add(Dropout(0.5))
 61 #建立输出层
 62 model.add(Dense(units=10,
 63                 kernel_initializer='normal',
 64                 activation='softmax'))
 65 print(model.summary())   #查看模型的摘要
 66 #3、进行训练
 67 #对训练模型进行设置，损失函数、优化器、权值
 68 model.compile(loss='categorical_crossentropy',
 69               optimizer='adam',metrics=['accuracy'])
 70 # 设置训练与验证数据比例，80%训练，20%测试，执行10个训练周期，每一个周期200个数据，显示训练过程2次
 71 train_history=model.fit(x=x_Train_normalize,
 72                         y=y_Train_OneHot,validation_split=0.2,
 73                         epochs=10,batch_size=200,verbose=2)
 74 #显示训练过程
 75 import matplotlib.pyplot as plt
 76 def show_train_history(train_history,train,validation):
 77     plt.plot(train_history.history[train])
 78     plt.plot(train_history.history[validation])
 79     plt.title('Train History')
 80     plt.ylabel(train)
 81     plt.xlabel('Epoch')
 82     plt.legend(['train','validation'],loc='upper left')    #显示左上角标签
 83     plt.show()
 84 show_train_history(train_history,'acc','val_acc')   #画出准确率评估结果
 85 show_train_history(train_history,'loss','val_loss') #画出误差执行结果
 86 #以测试数据评估模型准确率
 87 scores=model.evaluate(x_Test_normalize,y_Test_OneHot)   #创建变量存储评估后的准确率数据，（特征值，真实值）
 88 print()
 89 print('accuracy',scores[1])
 90 #进行预测
 91 prediction=model.predict_classes(x_Test)
 92 prediction
 93 plot_image_labels_prediction(x_test_image,y_test_label,prediction,idx=340)
 94 #4、建立模型提高预测准确率
 95 #建立混淆矩阵
 96 import pandas as pd   #pandas 是基于NumPy 的一种工具，该工具是为了解决数据分析任务而创建的
 97 pd.crosstab(y_test_label,prediction,
 98             rownames=['label'],colnames=['predict'])
 99 #建立真实值与预测值dataFrame
100 df=pd.DataFrame({'label':y_test_label,'predict':prediction})
101 df[:2]
102 df[(df.label==5)&(df.predict==3)]
103 plot_image_labels_prediction(x_test_image,y_test_label,prediction,idx=340,num=1)