#!/usr/bin/python3 
# -*- coding: utf-8 -*- 
#20170916號(hào)協(xié)同過(guò)濾電影推薦基稿 
#字典等格式數(shù)據(jù)處理及直接寫(xiě)入文件 
 
 
##from numpy import * 
import time 
from math import sqrt 
##from texttable import Texttable 
 
 
class CF: 
 
 def __init__(self, movies, ratings, k=5, n=20): 
  self.movies = movies#[MovieID,Title,Genres] 
  (self.train_data,self.test_data) = (ratings[0], ratings[1])#[UserID::MovieID::Rating::Timestamp] 
  # 鄰居個(gè)數(shù) 
  self.k = k 
  # 推薦個(gè)數(shù) 
  self.n = n 
  # 用戶(hù)對(duì)電影的評(píng)分 
  # 數(shù)據(jù)格式{'UserID用戶(hù)ID':[(MovieID電影ID,Rating用戶(hù)對(duì)電影的評(píng)星)]} 
  self.userDict = {} 
  # 對(duì)某電影評(píng)分的用戶(hù) 
  # 數(shù)據(jù)格式：{'MovieID電影ID':[UserID,用戶(hù)ID]} 
  # {'1',[1,2,3..],...} 
  self.ItemUser = {} 
  # 鄰居的信息 
  self.neighbors = [] 
  # 推薦列表 
  self.recommandList = []#包含dist和電影id 
  self.recommand = [] #訓(xùn)練集合測(cè)試集的交集，且僅有電影id 
  #用戶(hù)評(píng)過(guò)電影信息 
  self.train_user = [] 
  self.test_user = [] 
  #給用戶(hù)的推薦列表，僅含movieid 
  self.train_rec =[] 
  self.test_rec = [] 
  #test中的電影評(píng)分預(yù)測(cè)數(shù)據(jù)集合, 
  self.forecast = {}#前k個(gè)近鄰的評(píng)分集合 
  self.score = {}#最終加權(quán)平均后的評(píng)分集合{“電影id”：預(yù)測(cè)評(píng)分} 
  #召回率和準(zhǔn)確率 
  self.pre = [0.0,0.0] 
  self.z = [0.0, 0.0] 
 ''''' 
 userDict數(shù)據(jù)格式： 
 '3': [('3421', 0.8), ('1641', 0.4), ('648', 0.6), ('1394', 0.8), ('3534', 0.6), ('104', 0.8), 
 ('2735', 0.8), ('1210', 0.8), ('1431', 0.6), ('3868', 0.6), ('1079', 1.0), ('2997', 0.6), 
 ('1615', 1.0), ('1291', 0.8), ('1259', 1.0), ('653', 0.8), ('2167', 1.0), ('1580', 0.6), 
 ('3619', 0.4), ('260', 1.0), ('2858', 0.8), ('3114', 0.6), ('1049', 0.8), ('1261', 0.2), 
 ('552', 0.8), ('480', 0.8), ('1265', 0.4), ('1266', 1.0), ('733', 1.0), ('1196', 0.8), 
 ('590', 0.8), ('2355', 1.0), ('1197', 1.0), ('1198', 1.0), ('1378', 1.0), ('593', 0.6), 
 ('1379', 0.8), ('3552', 1.0), ('1304', 1.0), ('1270', 0.6), ('2470', 0.8), ('3168', 0.8), 
 ('2617', 0.4), ('1961', 0.8), ('3671', 1.0), ('2006', 0.8), ('2871', 0.8), ('2115', 0.8), 
 ('1968', 0.8), ('1136', 1.0), ('2081', 0.8)]} 
 ItemUser數(shù)據(jù)格式： 
 {'42': ['8'], '2746': ['10'], '2797': ['1'], '2987': ['5'], '1653': ['5', '8', '9'], 
 '194': ['5'], '3500': ['8', '10'], '3753': ['6', '7'], '1610': ['2', '5', '7'], 
 '1022': ['1', '10'], '1244': ['2'], '25': ['8', '9'] 
 ''' 
  
# 將ratings轉(zhuǎn)換為userDict和ItemUser 
 def formatRate(self,train_or_test): 
  self.userDict = {} 
  self.ItemUser = {} 
  for i in train_or_test:#[UserID,MovieID,Rating,Timestamp] 
   # 評(píng)分最高為5 除以5 進(jìn)行數(shù)據(jù)歸一化 
##   temp = (i[1], float(i[2]) / 5) 
   temp = (i[1], float(i[2])) 
##   temp = (i[1], i[2]) 
   # 計(jì)算userDict {'用戶(hù)id':[(電影id,評(píng)分),(2,5)...],'2':[...]...}一個(gè)觀(guān)眾對(duì)每一部電影的評(píng)分集合 
   if(i[0] in self.userDict): 
    self.userDict[i[0]].append(temp) 
   else: 
    self.userDict[i[0]] = [temp] 
   # 計(jì)算ItemUser {'電影id',[用戶(hù)id..],...}同一部電影的觀(guān)眾集合 
   if(i[1] in self.ItemUser): 
    self.ItemUser[i[1]].append(i[0]) 
   else: 
    self.ItemUser[i[1]] = [i[0]]   
 
 # 格式化userDict數(shù)據(jù) 
 def formatuserDict(self, userId, p):#userID為待查詢(xún)目標(biāo)，p為近鄰對(duì)象 
  user = {} 
  #user數(shù)據(jù)格式為：電影id：[userID的評(píng)分，近鄰用戶(hù)的評(píng)分] 
  for i in self.userDict[userId]:#i為userDict數(shù)據(jù)中的每個(gè)括號(hào)同81行 
   user[i[0]] = [i[1], 0] 
  for j in self.userDict[p]: 
   if(j[0] not in user): 
    user[j[0]] = [0, j[1]]#說(shuō)明目標(biāo)用戶(hù)和近鄰用戶(hù)沒(méi)有同時(shí)對(duì)一部電影評(píng)分 
   else: 
    user[j[0]][1] = j[1]#說(shuō)明兩者對(duì)同一部電影都有評(píng)分 
  return user 
  
   
 
 # 計(jì)算余弦距離 
 def getCost(self, userId, p): 
  # 獲取用戶(hù)userId和p評(píng)分電影的并集 
  # {'電影ID'：[userId的評(píng)分，p的評(píng)分]} 沒(méi)有評(píng)分為0 
  user = self.formatuserDict(userId, p) 
  x = 0.0 
  y = 0.0 
  z = 0.0 
  for k, v in user.items():#k是鍵，v是值 
   x += float(v[0]) * float(v[0]) 
   y += float(v[1]) * float(v[1]) 
   z += float(v[0]) * float(v[1]) 
  if(z == 0.0): 
   return 0 
  return z / sqrt(x * y) 
 #計(jì)算皮爾遜相似度 
##  def getCost(self, userId, p): 
##   # 獲取用戶(hù)userId和l評(píng)分電影的并集 
##   # {'電影ID'：[userId的評(píng)分，l的評(píng)分]} 沒(méi)有評(píng)分為0 
##   user = self.formatuserDict(userId, p) 
##   sumxsq = 0.0 
##   sumysq = 0.0 
##   sumxy = 0.0 
##   sumx = 0.0 
##   sumy = 0.0 
##   n = len(user) 
##   for k, v in user.items(): 
##    sumx +=float(v[0]) 
##    sumy +=float(v[1]) 
##    sumxsq += float(v[0]) * float(v[0]) 
##    sumysq += float(v[1]) * float(v[1]) 
##    sumxy += float(v[0]) * float(v[1]) 
##   up = sumxy -sumx*sumy/n 
##   down = sqrt((sumxsq - pow(sumxsq,2)/n)*(sumysq - pow(sumysq,2)/n)) 
##   if(down == 0.0): 
##    return 0 
##   return up/down 
 
# 找到某用戶(hù)的相鄰用戶(hù) 
 def getNearestNeighbor(self, userId): 
  neighbors = [] 
  self.neighbors = [] 
  # 獲取userId評(píng)分的電影都有那些用戶(hù)也評(píng)過(guò)分 
  for i in self.userDict[userId]:#i為userDict數(shù)據(jù)中的每個(gè)括號(hào)同95行#user數(shù)據(jù)格式為：電影id：[userID的評(píng)分，近鄰用戶(hù)的評(píng)分] 
   for j in self.ItemUser[i[0]]:#i[0]為電影編號(hào)，j為看同一部電影的每位用戶(hù) 
    if(j != userId and j not in neighbors): 
     neighbors.append(j) 
  # 計(jì)算這些用戶(hù)與userId的相似度并排序 
  for i in neighbors:#i為用戶(hù)id 
   dist = self.getCost(userId, i) 
   self.neighbors.append([dist, i]) 
  # 排序默認(rèn)是升序，reverse=True表示降序 
  self.neighbors.sort(reverse=True) 
  self.neighbors = self.neighbors[:self.k]#切片操作，取前k個(gè) 
##  print('neighbors',len(neighbors)) 
 
  # 獲取推薦列表 
 def getrecommandList(self, userId): 
  self.recommandList = [] 
  # 建立推薦字典 
  recommandDict = {} 
  for neighbor in self.neighbors:#這里的neighbor數(shù)據(jù)格式為[[dist，用戶(hù)id],[],....] 
   movies = self.userDict[neighbor[1]]#movies數(shù)據(jù)格式為[(電影id，評(píng)分),()，。。。。] 
   for movie in movies: 
    if(movie[0] in recommandDict): 
     recommandDict[movie[0]] += neighbor[0]####？？？？ 
    else: 
     recommandDict[movie[0]] = neighbor[0] 
 
  # 建立推薦列表 
  for key in recommandDict:#recommandDict數(shù)據(jù)格式{電影id：累計(jì)dist，。。。} 
   self.recommandList.append([recommandDict[key], key])#recommandList數(shù)據(jù)格式【【累計(jì)dist，電影id】，【】，。。。?！?
  self.recommandList.sort(reverse=True) 
##  print(len(self.recommandList)) 
  self.recommandList = self.recommandList[:self.n] 
##  print(len(self.recommandList)) 
 # 推薦的準(zhǔn)確率 
 def getPrecision(self, userId): 
##  print("開(kāi)始！??！") 
#先運(yùn)算test_data，這樣最終self.neighbors等保留的是后來(lái)計(jì)算train_data后的數(shù)據(jù)(不交換位置的話(huà)就得在gR函數(shù)中增加參數(shù)保留各自的neighbor) 
  (self.test_user,self.test_rec) = self.getRecommand(self.test_data,userId)#測(cè)試集的用戶(hù)userId所評(píng)價(jià)的電影和給該用戶(hù)推薦的電影列表 
  (self.train_user,self.train_rec) = self.getRecommand(self.train_data,userId)#訓(xùn)練集的用戶(hù)userId所評(píng)價(jià)的所有電影集合(self.train_user)和給該用戶(hù)推薦的電影列表(self.train_rec) 
#西安電大的張海朋：基于協(xié)同過(guò)濾的電影推薦系統(tǒng)的構(gòu)建（2015）中的準(zhǔn)確率召回率計(jì)算 
  for i in self.test_rec: 
   if i in self.train_rec: 
    self.recommand.append(i) 
  self.pre[0] = len(self.recommand)/len(self.train_rec) 
  self.z[0] = len(self.recommand)/len(self.test_rec) 
  #北京交大黃宇：基于協(xié)同過(guò)濾的推薦系統(tǒng)設(shè)計(jì)與實(shí)現(xiàn)（2015）中的準(zhǔn)、召計(jì)算 
  self.recommand = []#這里沒(méi)有歸零的話(huà)，下面計(jì)算初始recommand不為空 
  for i in self.train_rec: 
   if i in self.test_user: 
    self.recommand.append(i) 
  self.pre[1] = len(self.recommand)/len(self.train_rec) 
  self.z[1] = len(self.recommand)/len(self.test_user) 
##  print(self.train_rec,self.test_rec,"20",len(self.train_rec),len(self.train_rec)) 
  #對(duì)同一用戶(hù)分別通過(guò)訓(xùn)練集和測(cè)試集處理 
 def getRecommand(self,train_or_test,userId): 
  self.formatRate(train_or_test) 
  self.getNearestNeighbor(userId) 
  self.getrecommandList(userId) 
  user = [i[0] for i in self.userDict[userId]]#用戶(hù)userId評(píng)分的所有電影集合 
  recommand = [i[1] for i in self.recommandList]#推薦列表僅有電影id的集合，區(qū)別于recommandList（還含有dist） 
##  print("userid該用戶(hù)已通過(guò)訓(xùn)練集測(cè)試集處理") 
  return (user,recommand) 
 #對(duì)test的電影進(jìn)行評(píng)分預(yù)測(cè) 
 def foreCast(self): 
  self.forecast = {}#？？？？？前面變量統(tǒng)一定義初始化后，函數(shù)內(nèi)部是否需要該初始化？？？？ 
  same_movie_id = [] 
  neighbors_id = [i[1] for i in self.neighbors] #近鄰用戶(hù)數(shù)據(jù)僅含用戶(hù)id的集合  
     
  for i in self.test_user:#i為電影id，即在test里的i有被推薦到 
   if i in self.train_rec: 
    same_movie_id.append(i) 
    for j in self.ItemUser[i]:#j為用戶(hù)id,即尋找近鄰用戶(hù)的評(píng)分和相似度 
     if j in neighbors_id: 
      user = [i[0] for i in self.userDict[j]]#self.userDict[userId]數(shù)據(jù)格式：數(shù)據(jù)格式為[(電影id，評(píng)分),()，。。。。]；這里的userid應(yīng)為近鄰用戶(hù)p 
      a = self.neighbors[neighbors_id.index(j)]#找到該近鄰用戶(hù)的數(shù)據(jù)【dist，用戶(hù)id】 
      b = self.userDict[j][user.index(i)]#找到該近鄰用戶(hù)的數(shù)據(jù)【電影id，用戶(hù)id】 
      c = [a[0], b[1], a[1]] 
      if (i in self.forecast): 
       self.forecast[i].append(c) 
      else: 
       self.forecast[i] = [c]#數(shù)據(jù)格式：字典{“電影id”：【dist，評(píng)分，用戶(hù)id】【】}{'589': [[0.22655856915174025, 0.6, '419'], [0.36264561173211646, 1.0, '1349']。。。} 
##  print(same_movie_id) 
  #每個(gè)近鄰用戶(hù)的評(píng)分加權(quán)平均計(jì)算得預(yù)測(cè)評(píng)分 
  self.score = {} 
  if same_movie_id :#在test里的電影是否有在推薦列表里，如果為空不做判斷，下面的處理會(huì)報(bào)錯(cuò) 
   for movieid in same_movie_id: 
    total_d = 0 
    total_down = 0 
    for d in self.forecast[movieid]:#此時(shí)的d已經(jīng)是最里層的列表了【】；self.forecast[movieid]的數(shù)據(jù)格式[[]] 
     total_d += d[0]*d[1] 
     total_down += d[0] 
    self.score[movieid] = [round(total_d/total_down,3)]#加權(quán)平均后取3位小數(shù)的精度 
   #在test里但是推薦沒(méi)有的電影id,這里先按零計(jì)算 
   for i in self.test_user: 
    if i not in movieid: 
     self.score[i] = [0] 
  else: 
   for i in self.test_user: 
    self.score[i] = [0] 
##  return self.score 
 #計(jì)算平均絕對(duì)誤差MAE 
 def cal_Mae(self,userId): 
  self.formatRate(self.test_data) 
##  print(self.userDict) 
  for item in self.userDict[userId]: 
   if item[0] in self.score: 
    self.score[item[0]].append(item[1])#self.score數(shù)據(jù)格式[[預(yù)測(cè)分，實(shí)際分]] 
##  #過(guò)渡代碼 
##  for i in self.score: 
##   pass 
  return self.score 
    # 基于用戶(hù)的推薦 
 # 根據(jù)對(duì)電影的評(píng)分計(jì)算用戶(hù)之間的相似度 
## def recommendByUser(self, userId): 
##  print("親，請(qǐng)稍等片刻，系統(tǒng)正在快馬加鞭為你運(yùn)作中")   #人機(jī)交互輔助解讀， 
##  self.getPrecision(self,userId) 
 
 
# 獲取數(shù)據(jù) 
def readFile(filename): 
 files = open(filename, "r", encoding = "utf-8") 
 data = [] 
 for line in files.readlines(): 
  item = line.strip().split("::") 
  data.append(item) 
 return data 
 files.close() 
def load_dict_from_file(filepath): 
 _dict = {} 
 try: 
  with open(filepath, 'r',encoding = "utf -8") as dict_file: 
   for line in dict_file.readlines(): 
    (key, value) = line.strip().split(':') 
    _dict[key] = value 
 except IOError as ioerr: 
  print ("文件 %s 不存在" % (filepath)) 
 return _dict 
def save_dict_to_file(_dict, filepath): 
 try: 
  with open(filepath, 'w',encoding = "utf - 8") as dict_file: 
   for (key,value) in _dict.items(): 
    dict_file.write('%s:%s\n' % (key, value)) 
 
 except IOError as ioerr: 
  print ("文件 %s 無(wú)法創(chuàng)建" % (filepath)) 
def writeFile(data,filename): 
 with open(filename, 'w', encoding = "utf-8")as f: 
  f.write(data) 
 
 
# -------------------------開(kāi)始------------------------------- 
 
def start3(): 
 start1 = time.clock() 
 movies = readFile("D:/d/movies.dat") 
 ratings = [readFile("D:/d/201709train.txt"),readFile("D:/d/201709test.txt")] 
 demo = CF(movies, ratings, k=20) 
 userId = '1000' 
 demo.getPrecision(userId) 
## print(demo.foreCast()) 
 demo.foreCast() 
 print(demo.cal_Mae(userId)) 
## demo.recommendByUser(ID)  #上一句只能實(shí)現(xiàn)固定用戶(hù)查詢(xún)，這句可以實(shí)現(xiàn)“想查哪個(gè)查哪個(gè)”，后期可以加個(gè)循環(huán)，挨個(gè)查，查到你不想查 
 print("處理的數(shù)據(jù)為%d條" % (len(ratings[0])+len(ratings[1]))) 
## print("____---",len(ratings[0]),len(ratings[1])) 
## print("準(zhǔn)確率： %.2f %%" % (demo.pre * 100)) 
## print("召回率： %.2f %%" % (demo.z * 100)) 
 print(demo.pre) 
 print(demo.z) 
 end1 = time.clock() 
 print("耗費(fèi)時(shí)間： %f s" % (end1 - start1)) 
def start1(): 
 start1 = time.clock() 
 movies = readFile("D:/d/movies.dat") 
 ratings = [readFile("D:/d/201709train.txt"),readFile("D:/d/201709test.txt")] 
 demo = CF(movies, ratings, k = 20) 
 demo.formatRate(ratings[0]) 
 writeFile(str(demo.userDict),"D:/d/dd/userDict.txt") 
 writeFile(str(demo.ItemUser), "D:/d/dd/ItemUser.txt") 
## save_dict_to_file(demo.userDict,"D:/d/dd/userDict.txt") 
## save_dict_to_file(demo.ItemUser,"D:/d/dd/ItemUser.txt") 
 print("處理結(jié)束") 
## with open("D:/d/dd/userDict.txt",'r',encoding = 'utf-8') as f: 
##  diction = f.read() 
##  i = 0 
##  for j in eval(diction): 
##   print(j) 
##   i += 1 
##   if i == 4: 
##    break 
def start2(): 
 start1 = time.clock() 
 movies = readFile("D:/d/movies.dat") 
 ratings = [readFile("D:/d/201709train.txt"),readFile("D:/d/201709test.txt")] 
 demo = CF(movies, ratings, k = 20) 
 demo.formatRate_toMovie(ratings[0]) 
 writeFile(str(demo.movieDict),"D:/d/dd/movieDict.txt") 
## writeFile(str(demo.userDict),"D:/d/dd/userDict.txt") 
## writeFile(str(demo.ItemUser), "D:/d/dd/ItemUser.txt") 
## save_dict_to_file(demo.userDict,"D:/d/dd/userDict.txt") 
## save_dict_to_file(demo.ItemUser,"D:/d/dd/ItemUser.txt") 
 print("處理結(jié)束")  
 
if __name__ == '__main__': 
 start1()