基于用户的最近邻推荐

__author__ = 'LiFeiteng(Email: lifeiteng0422@gmail.com)'
# -*- coding: utf-8 -*-
import numpy as np

class	UserUserRec:
	def __init__(self):
		self.U = 0  # user number
		self.M = 0  # movie number
		self.user_dict = {}
		self.movie_dict = {}
		self.movie_title = {}
		self.user_ratings = np.matrix([])

	def GetRatingData(self, ratings_file):
		for line in open(ratings_file):
			user, movie, rating = line.split(",")
			if not self.user_dict.has_key(user):
				self.user_dict[user] = self.U
				self.U += 1
			if not self.movie_dict.has_key(movie):
				self.movie_dict[movie] = self.M
				self.M += 1
		print self.U, self.M
		self.user_ratings = np.matrix(np.zeros([self.U, self.M]))
		for line in open("ratings.csv", "r"):
			user, movie, rating = line.split(",")
			self.user_ratings[self.user_dict[user], self.movie_dict[movie]] = np.double(rating)

	def GetMovieTitles(self, movie_titles_file):
		for line in open(movie_titles_file):
			movie, title = line.split(",")
			#delete '\n'
			self.movie_title[movie] = title[:-1]

	def CosineUserSim(self, user1, user2): 
		'''用户相似性计算 useri 为评分矩阵对应的行号'''
		user_rat = self.user_ratings[user1,:].copy()
		u1 = user_rat - np.mean(user_rat[user_rat>0.0])
		u1 = np.array(u1)*np.array(np.where(user_rat>0, 1, 0))

		user_rat = self.user_ratings[user2,:].copy()
		u2 = user_rat - np.mean(user_rat[user_rat>0.0])
		u2 = np.array(u2)*np.array(np.where(user_rat>0, 1, 0))

		if (np.linalg.norm(u1[0,:])*np.linalg.norm(u2[0,:])) == 0:
			sim = 0.0
		else:
			sim = np.dot(u1[0,:],u2[0,:])/(np.linalg.norm(u1[0,:])*np.linalg.norm(u2[0,:]))
		return np.double(sim)

	def MovieScore4User(self, user, movie):
		'''基于用户的推荐，根据user最相似的30位其他用户预测user对movie的rating'''
		rating4movie = self.user_ratings[:, self.movie_dict[movie]]
		Temp = []
		userID = 0
		for rating in rating4movie:
			if rating != 0.0:
				Temp.append([userID, rating, self.CosineUserSim(self.user_dict[user], userID)])
			userID += 1
		Temp = sorted(Temp, key=lambda e:e[2], reverse=True)
		n = 0
		sim_add = 0.0
		score4movie = 0.0
		for data in Temp:
			if n >= 30:
				break
			userID = data[0]
			rat = data[1]
			if userID != self.user_dict[user] and rat != 0.0:
				sim = data[2]
				user_rat = self.user_ratings[userID,:].copy()
				mu = np.mean(user_rat[user_rat > 0.0])
				score4movie += (rat-mu) * sim
				sim_add += np.abs(sim)
				n += 1

		score4movie /= sim_add
		user_rat = self.user_ratings[self.user_dict[user],:].copy()
		score4movie += np.mean(user_rat[user_rat > 0.0])
		score4movie = np.double(score4movie)
		print ",".join([user, movie, format(score4movie,".4f"), self.movie_title[movie]])
		return score4movie
# end of class UserUserRec

if __name__ == '__main__':
	#### PA3
	user_user_rec = UserUserRec()
	user_user_rec.GetRatingData("ratings.csv")
	user_user_rec.GetMovieTitles("movie-titles.csv")

	outfile = open("outfile.txt","w")
	for line in open("input.txt"):# input
		user, movie = line.split(":")
		movie = str(int(movie))
		score = user_user_rec.MovieScore4User(user, movie)
		str1 = ",".join([user, movie, format(score, ".4f"), user_user_rec.movie_title[movie]])
		outfile.write(str1+"\n")
	outfile.close()