#!/usr/bin/env python 
# -*- coding: utf-8 -*- 
# @Time : 2017-03-12 15:11 
# @Author : CC 
# @File : net_load_data.py 
 
from numpy import * 
import numpy as np 
import cPickle 
def load_data(): 
 """載入解壓后的數據，并讀取""" 
 with open('data/mnist_pkl/mnist.pkl','rb') as f: 
  try: 
   train_data,validation_data,test_data = cPickle.load(f) 
   print " the file open sucessfully" 
   # print train_data[0].shape #(50000,784) 
   # print train_data[1].shape #(50000,) 
   return (train_data,validation_data,test_data) 
  except EOFError: 
   print 'the file open error' 
   return None 
 
def data_transform(): 
 """將數據轉化為計算格式""" 
 t_d,va_d,te_d = load_data() 
 # print t_d[0].shape # (50000,784) 
 # print te_d[0].shape # (10000,784) 
 # print va_d[0].shape # (10000,784) 
 # n1 = [np.reshape(x,784,1) for x in t_d[0]] # 將5萬個數據分別逐個取出化成（784,1），逐個排列 
 n = [np.reshape(x, (784, 1)) for x in t_d[0]] # 將5萬個數據分別逐個取出化成（784,1），逐個排列 
 # print 'n1',n1[0].shape 
 # print 'n',n[0].shape 
 m = [vectors(y) for y in t_d[1]] # 將5萬標簽（50000,1）化為（10,50000） 
 train_data = zip(n,m) # 將數據與標簽打包成元組形式 
 n = [np.reshape(x, (784, 1)) for x in va_d[0]] # 將5萬個數據分別逐個取出化成（784,1），排列 
 validation_data = zip(n,va_d[1]) # 沒有將標簽數據矢量化 
 n = [np.reshape(x, (784, 1)) for x in te_d[0]] # 將5萬個數據分別逐個取出化成（784,1），排列 
 test_data = zip(n, te_d[1]) # 沒有將標簽數據矢量化 
 # print train_data[0][0].shape #(784,） 
 # print "len(train_data[0])",len(train_data[0]) #2 
 # print "len(train_data[100])",len(train_data[100]) #2 
 # print "len(train_data[0][0])", len(train_data[0][0]) #784 
 # print "train_data[0][0].shape", train_data[0][0].shape #（784,1） 
 # print "len(train_data)", len(train_data) #50000 
 # print train_data[0][1].shape #(10,1) 
 # print test_data[0][1] # 7 
 return (train_data,validation_data,test_data) 
def vectors(y): 
 "賦予標簽" 
 label = np.zeros((10,1)) 
 label[y] = 1.0 #浮點計算 
 return label 

#!/usr/bin/env python 
# -*- coding: utf-8 -*- 
# @Time : 2017-03-28 10:18 
# @Author : CC 
# @File : net_network2.py 
 
from numpy import * 
import numpy as np 
import operator 
import json 
# import sys 
 
class QuadraticCost(): 
 """定義二次代價函數類的方法""" 
 @staticmethod 
 def fn(a,y): 
  cost = 0.5*np.linalg.norm(a-y)**2 
  return cost 
 @staticmethod 
 def delta(z,a,y): 
  delta = (a-y)*sig_derivate(z) 
  return delta 
 
class CrossEntroyCost(): 
 """定義交叉熵函數類的方法""" 
 @staticmethod 
 def fn(a, y): 
  cost = np.sum(np.nan_to_num(-y*np.log(a)-(1-y)*np.log(1-a))) # not a number---0, inf---larger number 
  return cost 
 @staticmethod 
 def delta(z, a, y): 
  delta = (a - y) 
  return delta 
 
class Network(object): 
 """定義網絡結構和方法""" 
 def __init__(self,sizes,cost): 
  self.num_layer = len(sizes) 
  self.sizes = sizes 
  self.cost = cost 
  # print "self.cost.__name__:",self.cost.__name__ # CrossEntropyCost 
  self.default_weight_initializer() 
 def default_weight_initializer(self): 
  """權值初始化""" 
  self.bias = [np.random.rand(x, 1) for x in self.sizes[1:]] 
  self.weight = [np.random.randn(y, x)/float(np.sqrt(x)) for (x, y) in zip(self.sizes[:-1], self.sizes[1:])] 
 
 def large_weight_initializer(self): 
  """權值另一種初始化""" 
  self.bias = [np.random.rand(x, 1) for x in self.sizes[1:]] 
  self.weight = [np.random.randn(y, x) for x, y in zip(self.sizes[:-1], self.sizes[1:])] 
 def forward(self,a): 
  """forward the network""" 
  for w,b in zip(self.weight,self.bias): 
   a=sigmoid(np.dot(w,a)+b) 
  return a 
 
 def SGD(self,train_data,min_batch_size,epochs,eta,test_data=False, 
   lambd = 0, 
   monitor_train_cost = False, 
   monitor_train_accuracy = False, 
   monitor_test_cost=False, 
   monitor_test_accuracy=False 
   ): 
  """1)Set the train_data,shuffle; 
   2) loop the epoches, 
   3) set the min_batches,and rule of update""" 
  if test_data: n_test=len(test_data) 
  n = len(train_data) 
  for i in xrange(epochs): 
   random.shuffle(train_data) 
   min_batches = [train_data[k:k+min_batch_size] for k in xrange(0,n,min_batch_size)] 
 
   for min_batch in min_batches: # 每次提取一個批次的樣本 
    self.update_minbatch_parameter(min_batch,eta,lambd,n) 
   train_cost = [] 
   if monitor_train_cost: 
    cost1 = self.total_cost(train_data,lambd,cont=False) 
    train_cost.append(cost1) 
    print "epoche {0},train_cost: {1}".format(i,cost1) 
   if monitor_train_accuracy: 
    accuracy = self.accuracy(train_data,cont=True) 
    train_cost.append(accuracy) 
    print "epoche {0}/{1},train_accuracy: {2}".format(i,epochs,accuracy) 
   test_cost = [] 
   if monitor_test_cost: 
    cost1 = self.total_cost(test_data,lambd) 
    test_cost.append(cost1) 
    print "epoche {0},test_cost: {1}".format(i,cost1) 
   test_accuracy = [] 
   if monitor_test_accuracy: 
    accuracy = self.accuracy(test_data) 
    test_cost.append(accuracy) 
    print "epoche:{0}/{1},test_accuracy:{2}".format(i,epochs,accuracy) 
  self.save(filename= "net_save") #保存網絡網絡參數 
 
 def total_cost(self,train_data,lambd,cont=True): 
  cost1 = 0.0 
  for x,y in train_data: 
   a = self.forward(x) 
   if cont: y = vectors(y) #將測試樣本標簽化為矩陣 
   cost1 += (self.cost).fn(a,y)/len(train_data) 
  cost1 += lambd/len(train_data)*np.sum(np.linalg.norm(weight)**2 for weight in self.weight) #加上權值項 
  return cost1 
 def accuracy(self,train_data,cont=False): 
  if cont: 
   output1 = [(np.argmax(self.forward(x)),np.argmax(y)) for (x,y) in train_data] 
  else: 
   output1 = [(np.argmax(self.forward(x)), y) for (x, y) in train_data] 
  return sum(int(out1 == y) for (out1, y) in output1) 
 def update_minbatch_parameter(self,min_batch, eta,lambd,n): 
  """1) determine the weight and bias 
   2) calculate the the delta 
   3) update the data """ 
  able_b = [np.zeros(b.shape) for b in self.bias] 
  able_w=[np.zeros(w.shape) for w in self.weight] 
  for x,y in min_batch: #每次只取一個樣本？ 
   deltab,deltaw = self.backprop(x,y) 
   able_b =[a_b+dab for a_b, dab in zip(able_b,deltab)] #實際上對dw,db做批次累加，最后小批次取平均 
   able_w = [a_w + daw for a_w, daw in zip(able_w, deltaw)] 
  self.weight = [weight - eta * (dw) / len(min_batch)- eta*(lambd*weight)/n for weight, dw in zip(self.weight,able_w) ] 
  #增加正則化項：eta*lambda/m *weight 
  self.bias = [bias - eta * db / len(min_batch) for bias, db in zip(self.bias, able_b)] 
 
 def backprop(self,x,y): 
  """" 1) clacu the forward value 
   2) calcu the delta： delta =(y-f(z)); deltak = delta*w(k)*fz(k-1)' 
   3) clacu the delta in every layer: deltab=delta; deltaw=delta*fz(k-1)""" 
  deltab = [np.zeros(b.shape) for b in self.bias] 
  deltaw = [np.zeros(w.shape) for w in self.weight] 
  zs = [] 
  activate = x 
  activates = [x] 
  for w,b in zip(self.weight,self.bias): 
   z =np.dot(w, activate) +b 
   zs.append(z) 
   activate = sigmoid(z) 
   activates.append(activate) 
   # backprop 
  delta = self.cost.delta(zs[-1],activates[-1],y) #調用不同代價函數的方法求梯度 
  deltab[-1] = delta 
  deltaw[-1] = np.dot(delta ,activates[-2].transpose()) 
  for i in xrange(2,self.num_layer): 
   z = zs[-i] 
   delta = np.dot(self.weight[-i+1].transpose(),delta)* sig_derivate(z) 
   deltab[-i] = delta 
   deltaw[-i] = np.dot(delta,activates[-i-1].transpose()) 
  return (deltab,deltaw) 
 
 def save(self,filename): 
  """將訓練好的網絡采用json(java script object notation)將對象保存成字符串保存，用于生產部署 
  encoder=json.dumps(data) 
  python 原始類型(沒有數組類型)向 json 類型的轉化對照表： 
   python    json 
   dict    object 
  list/tuple   arrary 
  int/long/float  number 
  .tolist() 將數組轉化為列表 
  >>> a = np.array([[1, 2], [3, 4]]) 
  >>> list(a) 
  [array([1, 2]), array([3, 4])] 
  >>> a.tolist() 
  [[1, 2], [3, 4]] 
  """ 
  data = {"sizes": self.sizes,"weight": [weight.tolist() for weight in self.weight], 
    "bias": ([bias.tolist() for bias in self.bias]), 
    "cost": str(self.cost.__name__)} 
  # 保存網絡訓練好的權值，偏置，交叉熵參數。 
  f = open(filename, "w") 
  json.dump(data,f) 
  f.close() 
 
def load_net(filename): 
 """采用data=json.load(json.dumps(data))進行解碼， 
 decoder = json.load(encoder) 
 編碼后和解碼后鍵不會按照原始data的鍵順序排列，但每個鍵對應的值不會變 
 載入訓練好的網絡用于測試""" 
 f = open(filename,"r") 
 data = json.load(f) 
 f.close() 
 # print "data[cost]", getattr(sys.modules[__name__], data["cost"])#獲得屬性__main__.CrossEntropyCost 
 # print "data[cost]", data["cost"], data["sizes"] 
 net = Network(data["sizes"], cost=data["cost"]) #網絡初始化 
 net.weight = [np.array(w) for w in data["weight"]] #賦予訓練好的權值,并將list--->array 
 net.bias = [np.array(b) for b in data["bias"]] 
 return net 
 
def sig_derivate(z): 
 """derivate sigmoid""" 
 return sigmoid(z) * (1-sigmoid(z)) 
 
def sigmoid(x): 
 sigm=1.0/(1.0+exp(-x)) 
 return sigm 
 
def vectors(y): 
 """賦予標簽""" 
 label = np.zeros((10,1)) 
 label[y] = 1.0 #浮點計算 
 return label 

#!/usr/bin/env python 
# -*- coding: utf-8 -*- 
# @Time : 2017-03-12 15:24 
# @Author : CC 
# @File : net_test.py 
 
import net_load_data 
# net_load_data.load_data() 
train_data,validation_data,test_data = net_load_data.data_transform() 
 
import net_network2 as net 
cost = net.QuadraticCost 
cost = net.CrossEntroyCost 
lambd = 0 
net1 = net.Network([784,50,10],cost) 
min_batch_size = 30 
eta = 3.0 
epoches = 2 
net1.SGD(train_data,min_batch_size,epoches,eta,test_data, 
   lambd, 
   monitor_train_cost=True, 
   monitor_train_accuracy=True, 
   monitor_test_cost=True, 
   monitor_test_accuracy=True 
   ) 
print "complete" 

#!/usr/bin/env python 
# -*- coding: utf-8 -*- 
# @Time : 2017-03-28 17:27 
# @Author : CC 
# @File : forward_test.py 
 
import numpy as np 
# 對訓練好的網絡直接進行調用，并用測試樣本進行測試 
import net_load_data #導入測試數據 
import net_network2 as net 
train_data,validation_data,test_data = net_load_data.data_transform() 
net = net.load_net(filename= "net_save")  #導入網絡 
output = [(np.argmax(net.forward(x)),y) for (x,y) in test_data] #測試 
print sum(int(y1 == y2) for (y1,y2) in output)  #輸出最終值