#coding=utf-8

 #1.数据预处理

 import numpy as np             #导入模块，numpy是扩展链接库

 import pandas as pd

 import tensorflow

 import keras

 from keras.utils import np_utils

 np.random.seed(10)            #设置seed可以产生的随机数据

 from keras.datasets import mnist  #导入模块，下载读取mnist数据

 (x_train_image,y_train_label),\

 (x_test_image,y_test_label)=mnist.load_data() #下载读取mnist数据

 print('train data=',len(x_train_image))

 print('test data=',len(x_test_image))

 print('x_train_image:',x_train_image.shape)

 print('y_train_label:',y_train_label.shape)

 import matplotlib.pyplot as plt

 def plot_image(image):

     fig=plt.gcf()

     fig.set_size_inches(2,2)

     plt.imshow(image,cmap='binary')

     plt.show()

 y_train_label[0]

 import matplotlib.pyplot as plt

 def plot_image_labels_prediction(image,lables,prediction,idx,num=10):

     fig=plt.gcf()

     fig.set_size_inches(12,14)

     if num>25:num=25

     for i in range(0,num):

         ax=plt.subplot(5,5,i+1)

         ax.imshow(image[idx],cmap='binary')

         title="lable="+str(lables[idx])

         if len(prediction)>0:

             title+=",predict="+str(prediction[idx])

         ax.set_title(title,fontsize=10)

         ax.set_xticks([]);ax.set_yticks([])

         idx+=1

     plt.show()

 plot_image_labels_prediction(x_train_image,y_train_label,[],0,10)

 plot_image_labels_prediction(x_test_image,y_test_label,[],0,10)

 x_Train=x_train_image.reshape(60000,784).astype('float32') #以reshape转化成784个float

 x_Test=x_test_image.reshape(10000,784).astype('float32')

 x_Train_normalize=x_Train/255    #将features标准化

 x_Test_normalize=x_Test/255

 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

 y_Test_OneHot=np_utils.to_categorical(y_test_label)

 #2.建立模型

 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

 from keras.layers import Dense    #全连接层

 from keras.layers import Dropout  #避免过度拟合

 model=Sequential()

 #建立输入层、隐藏层

 model.add(Dense(units=1000,

                 input_dim=784,

                 kernel_initializer='normal',

                 activation='relu'))

 model.add(Dropout(0.5))

 model.add(Dense(units=1000,

                 kernel_initializer='normal',

                 activation='relu'))

 model.add(Dropout(0.5))

 #建立输出层

 model.add(Dense(units=10,

                 kernel_initializer='normal',

                 activation='softmax'))

 print(model.summary())   #查看模型的摘要

 #3、进行训练

 #对训练模型进行设置，损失函数、优化器、权值

 model.compile(loss='categorical_crossentropy',

               optimizer='adam',metrics=['accuracy'])

 # 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

 train_history=model.fit(x=x_Train_normalize,

                         y=y_Train_OneHot,validation_split=0.2,

                         epochs=10,batch_size=200,verbose=2)

 #显示训练过程

 import matplotlib.pyplot as plt

 def show_train_history(train_history,train,validation):

     plt.plot(train_history.history[train])

     plt.plot(train_history.history[validation])

     plt.title('Train History')

     plt.ylabel(train)

     plt.xlabel('Epoch')

     plt.legend(['train','validation'],loc='upper left')    #显示左上角标签

     plt.show()

 show_train_history(train_history,'acc','val_acc')   #画出准确率评估结果

 show_train_history(train_history,'loss','val_loss') #画出误差执行结果

 #以测试数据评估模型准确率

 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）

 print()

 print('accuracy',scores[1])

 #进行预测

 prediction=model.predict_classes(x_Test)

 prediction

 plot_image_labels_prediction(x_test_image,y_test_label,prediction,idx=340)

 #4、建立模型提高预测准确率

 #建立混淆矩阵

 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

 pd.crosstab(y_test_label,prediction,

             rownames=['label'],colnames=['predict'])

 #建立真实值与预测值dataFrame

 df=pd.DataFrame({'label':y_test_label,'predict':prediction})

 df[:2]

 df[(df.label==5)&(df.predict==3)]

 plot_image_labels_prediction(x_test_image,y_test_label,prediction,idx=340,num=1)