#!/usr/bin/python3
# -*- coding: utf-8 -*-
from numpy import *
import time
from texttable import Texttable
class CF:
  def __init__(self, movies, ratings, k=5, n=10):
    self.movies = movies
    self.ratings = ratings
    # 鄰居個數
    self.k = k
    # 推薦個數
    self.n = n
    # 用戶對電影的評分
    # 數據格式{'UserID：用戶ID':[(MovieID：電影ID,Rating：用戶對電影的評星)]}
    self.userDict = {}
    # 對某電影評分的用戶
    # 數據格式：{'MovieID：電影ID',[UserID：用戶ID]}
    # {'1',[1,2,3..],...}
    self.ItemUser = {}
    # 鄰居的信息
    self.neighbors = []
    # 推薦列表
    self.recommandList = []
    self.cost = 0.0

  # 基于用戶的推薦
  # 根據對電影的評分計算用戶之間的相似度
  def recommendByUser(self, userId):
    self.formatRate()
    # 推薦個數 等于 本身評分電影個數，用戶計算準確率
    self.n = len(self.userDict[userId])
    self.getNearestNeighbor(userId)
    self.getrecommandList(userId)
    self.getPrecision(userId)

  # 獲取推薦列表
  def getrecommandList(self, userId):
    self.recommandList = []
    # 建立推薦字典
    recommandDict = {}
    for neighbor in self.neighbors:
      movies = self.userDict[neighbor[1]]
      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:
      self.recommandList.append([recommandDict[key], key])
    self.recommandList.sort(reverse=True)
    self.recommandList = self.recommandList[:self.n]

  # 將ratings轉換為userDict和ItemUser
  def formatRate(self):
    self.userDict = {}
    self.ItemUser = {}
    for i in self.ratings:
      # 評分最高為5 除以5 進行數據歸一化
      temp = (i[1], float(i[2]) / 5)
      # 計算userDict {'1':[(1,5),(2,5)...],'2':[...]...}
      if(i[0] in self.userDict):
        self.userDict[i[0]].append(temp)
      else:
        self.userDict[i[0]] = [temp]
      # 計算ItemUser {'1',[1,2,3..],...}
      if(i[1] in self.ItemUser):
        self.ItemUser[i[1]].append(i[0])
      else:
        self.ItemUser[i[1]] = [i[0]]

  # 找到某用戶的相鄰用戶
  def getNearestNeighbor(self, userId):
    neighbors = []
    self.neighbors = []
    # 獲取userId評分的電影都有那些用戶也評過分
    for i in self.userDict[userId]:
      for j in self.ItemUser[i[0]]:
        if(j != userId and j not in neighbors):
          neighbors.append(j)
    # 計算這些用戶與userId的相似度并排序
    for i in neighbors:
      dist = self.getCost(userId, i)
      self.neighbors.append([dist, i])
    # 排序默認是升序，reverse=True表示降序
    self.neighbors.sort(reverse=True)
    self.neighbors = self.neighbors[:self.k]

  # 格式化userDict數據
  def formatuserDict(self, userId, l):
    user = {}
    for i in self.userDict[userId]:
      user[i[0]] = [i[1], 0]
    for j in self.userDict[l]:
      if(j[0] not in user):
        user[j[0]] = [0, j[1]]
      else:
        user[j[0]][1] = j[1]
    return user

  # 計算余弦距離
  def getCost(self, userId, l):
    # 獲取用戶userId和l評分電影的并集
    # {'電影ID'：[userId的評分，l的評分]} 沒有評分為0
    user = self.formatuserDict(userId, l)
    x = 0.0
    y = 0.0
    z = 0.0
    for k, v in user.items():
      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)

  # 推薦的準確率
  def getPrecision(self, userId):
    user = [i[0] for i in self.userDict[userId]]
    recommand = [i[1] for i in self.recommandList]
    count = 0.0
    if(len(user) >= len(recommand)):
      for i in recommand:
        if(i in user):
          count += 1.0
      self.cost = count / len(recommand)
    else:
      for i in user:
        if(i in recommand):
          count += 1.0
      self.cost = count / len(user)

  # 顯示推薦列表
  def showTable(self):
    neighbors_id = [i[1] for i in self.neighbors]
    table = Texttable()
    table.set_deco(Texttable.HEADER)
    table.set_cols_dtype(["t", "t", "t", "t"])
    table.set_cols_align(["l", "l", "l", "l"])
    rows = []
    rows.append([u"movie ID", u"Name", u"release", u"from userID"])
    for item in self.recommandList:
      fromID = []
      for i in self.movies:
        if i[0] == item[1]:
          movie = i
          break
      for i in self.ItemUser[item[1]]:
        if i in neighbors_id:
          fromID.append(i)
      movie.append(fromID)
      rows.append(movie)
    table.add_rows(rows)
    print(table.draw())
# 獲取數據
def readFile(filename):
  files = open(filename, "r", encoding="utf-8")
  # 如果讀取不成功試一下
  # files = open(filename, "r", encoding="iso-8859-15")
  data = []
  for line in files.readlines():
    item = line.strip().split("::")
    data.append(item)
  return data

# -------------------------開始-------------------------------
start = time.clock()
movies = readFile("/home/hadoop/Python/CF/movies.dat")
ratings = readFile("/home/hadoop/Python/CF/ratings.dat")
demo = CF(movies, ratings, k=20)
demo.recommendByUser("100")
print("推薦列表為：")
demo.showTable()
print("處理的數據為%d條" % (len(demo.ratings)))
print("準確率： %.2f %%" % (demo.cost * 100))
end = time.clock()
print("耗費時間： %f s" % (end - start))