推荐系统之基于物品的协同过滤算法（ItemCF）
推荐系统之基于物品的协同过滤算法（ItemCF）
前端时间已经把基于用户的推荐系统给弄出来了，详情见我的另一篇文章： 点击打开链接，（建议先看懂UserCF后再来看这篇文章，当然大佬可以忽视）
其实理解了基于用户的协同过滤算法，再来看基于物品的协同过滤算法，就会感觉没啥太大差异，
具体的思路，通俗的讲：
用户A 喜欢了一个物品s集合,那么推荐的时候就把与物品s集合里最相似的前N个物品推荐给用户A，结束。
是不是言简意赅？哈哈，其实道理都差不多，看懂了UserCF再来看ItemCF,就会感觉基本差不多。
具体的步骤呢：
一、计算物品之间的相似度。
二、根据物品的相似度和用户的历史行为给用户生成推荐列表
同样，计算相似度的时候公式用的也是余弦相似度，详情就看我写的UserCF吧： 点击打开链接，因为都差不多就不重复写了，对照着上一篇博客然后在看看书，就知道基本完全一样了
这里就贴上书上给的一个案例，最下面就是系统的推荐TOP N ，很好理解：
依旧是大牛的ItemCF 代码，贴上供大家学习：
#-*- coding: utf-8 -*-
'''
Created on 2015-06-22
@author: Lockvictor
'''
import sys
import random
import math
import os
from operator import itemgetter
random.seed(0)
class ItemBasedCF(object):
''' TopN recommendation - Item Based Collaborative Filtering '''
def __init__(self):
self.trainset = {}
self.testset = {}
self.n_sim_movie = 20
self.n_rec_movie = 10
self.movie_sim_mat = {}
self.movie_popular = {}
self.movie_count = 0
print('Similar movie number = %d' % self.n_sim_movie, file=sys.stderr)
print('Recommended movie number = %d' %
self.n_rec_movie, file=sys.stderr)
@staticmethod
def loadfile(filename):
''' load a file, return a generator. '''
fp = open(filename, 'r')
for i, line in enumerate(fp):
yield line.strip('\r\n')
if i % 100000 == 0:
print ('loading %s(%s)' % (filename, i), file=sys.stderr)
fp.close()
print ('load %s succ' % filename, file=sys.stderr)
def generate_dataset(self, filename, pivot=0.7):
''' load rating data and split it to training set and test set '''
trainset_len = 0
testset_len = 0
for line in self.loadfile(filename):
user, movie, rating, _ = line.split('::')
# split the data by pivot
if random.random() < pivot:
self.trainset.setdefault(user, {})
self.trainset[user][movie] = int(rating)
trainset_len += 1
else:
self.testset.setdefault(user, {})
self.testset[user][movie] = int(rating)
testset_len += 1
print ('split training set and test set succ', file=sys.stderr)
print ('train set = %s' % trainset_len, file=sys.stderr)
print ('test set = %s' % testset_len, file=sys.stderr)
def calc_movie_sim(self):
''' calculate movie similarity matrix '''
print('counting movies number and popularity...', file=sys.stderr)
for user, movies in self.trainset.items():
for movie in movies:
# count item popularity
if movie not in self.movie_popular:
self.movie_popular[movie] = 0
self.movie_popular[movie] += 1
print('count movies number and popularity succ', file=sys.stderr)
# save the total number of movies
self.movie_count = len(self.movie_popular)
print('total movie number = %d' % self.movie_count, file=sys.stderr)
# count co-rated users between items
itemsim_mat = self.movie_sim_mat
print('building co-rated users matrix...', file=sys.stderr)
for user, movies in self.trainset.items():
for m1 in movies:
for m2 in movies:
if m1 == m2:
continue
itemsim_mat.setdefault(m1, {})
itemsim_mat[m1].setdefault(m2, 0)
itemsim_mat[m1][m2] += 1
print('build co-rated users matrix succ', file=sys.stderr)
# calculate similarity matrix
print('calculating movie similarity matrix...', file=sys.stderr)
simfactor_count = 0
PRINT_STEP = 2000000
for m1, related_movies in itemsim_mat.items():
for m2, count in related_movies.items():
itemsim_mat[m1][m2] = count / math.sqrt(
self.movie_popular[m1] * self.movie_popular[m2])
simfactor_count += 1
if simfactor_count % PRINT_STEP == 0:
print('calculating movie similarity factor(%d)' %
simfactor_count, file=sys.stderr)
print('calculate movie similarity matrix(similarity factor) succ',
file=sys.stderr)
print('Total similarity factor number = %d' %
simfactor_count, file=sys.stderr)
def recommend(self, user):
''' Find K similar movies and recommend N movies. '''
K = self.n_sim_movie
N = self.n_rec_movie
rank = {}
watched_movies = self.trainset[user]
for movie, rating in watched_movies.items():
for related_movie, similarity_factor in sorted(self.movie_sim_mat[movie].items(),
key=itemgetter(1), reverse=True)[:K]:
if related_movie in watched_movies:
continue
rank.setdefault(related_movie, 0)
rank[related_movie] += similarity_factor * rating
# return the N best movies
return sorted(rank.items(), key=itemgetter(1), reverse=True)[:N]
def evaluate(self):
''' print evaluation result: precision, recall, coverage and popularity '''
print('Evaluation start...', file=sys.stderr)
N = self.n_rec_movie
# varables for precision and recall
hit = 0
rec_count = 0
test_count = 0
# varables for coverage
all_rec_movies = set()
# varables for popularity
popular_sum = 0
for i, user in enumerate(self.trainset):
if i % 500 == 0:
print ('recommended for %d users' % i, file=sys.stderr)
test_movies = self.testset.get(user, {})
rec_movies = self.recommend(user)
for movie, _ in rec_movies:
if movie in test_movies:
hit += 1
all_rec_movies.add(movie)
popular_sum += math.log(1 + self.movie_popular[movie])
rec_count += N
test_count += len(test_movies)
precision = hit / (1.0 * rec_count)
recall = hit / (1.0 * test_count)
coverage = len(all_rec_movies) / (1.0 * self.movie_count)
popularity = popular_sum / (1.0 * rec_count)
print ('precision=%.4f\trecall=%.4f\tcoverage=%.4f\tpopularity=%.4f' %
(precision, recall, coverage, popularity), file=sys.stderr)
if __name__ == '__main__':
ratingfile = os.path.join('ml-1m', 'ratings.dat')
itemcf = ItemBasedCF()
itemcf.generate_dataset(ratingfile)
itemcf.calc_movie_sim()
itemcf.evaluate()