【推荐系统notes】python实现最简单的推荐系统(附完整代码)

数据介绍

影片csv格式数据

相似度系数使用场景比较

• 如果数据存在“分数膨胀”问题,就使用皮尔逊相关系数。
• 如果数据比较“密集”,变量之间基本都存在公有值,且这些距离数据是非常重要的,那就使用欧几里得或曼哈顿距离。
• 如果数据是稀疏的,则使用余弦相似度。
  本次实验使用皮尔逊相关系数。

皮尔逊相关系数

皮尔逊相关系数的计算公式是:

上面的公式除了看起来比较复杂,另一个问题是要获得计算结果必须对数据做多次遍历。好
在我们有另外一个公式,能够计算皮尔逊相关系数的近似值:

这个公式虽然看起来更加复杂,而且其计算结果会不太稳定,有一定误差存在,但它最大的优点是,用代码实现的时候可以只需遍历一次数据。代码如下：

def pearson_distance(self,usr1,usr2):
        sum_x_y = 0
        sum_x = 0
        sum_y = 0
        sum_x_2 = 0
        sum_y_2 = 0
        n = 0
        for movie in usr1.keys():
            if movie in usr2.keys():
                n += 1
                x = usr1[movie]
                y = usr2[movie]
                sum_x_y += x*y
                sum_x += x
                sum_y += y
                sum_x_2 += x**2
                sum_y_2 += y**2
        if n==0:return 0
        denominator = math.sqrt(sum_x_2-float(sum_x**2)/n) * math.sqrt(sum_y_2-float(sum_y**2)/n)
        if denominator==0:return 0
        return (sum_x_y - float(sum_x*sum_y)/n)/denominator

完整代码

import math

class recommender(object):
    def o_distance(self,usr1,usr2):
        distance = 0
        for movie in usr1.keys():
            if movie in usr2.keys():
                distance += abs(usr1[movie]-usr2[movie])**2
        return math.sqrt(distance)

    def pearson_distance(self,usr1,usr2):
        sum_x_y = 0
        sum_x = 0
        sum_y = 0
        sum_x_2 = 0
        sum_y_2 = 0
        n = 0
        for movie in usr1.keys():
            if movie in usr2.keys():
                n += 1
                x = usr1[movie]
                y = usr2[movie]
                sum_x_y += x*y
                sum_x += x
                sum_y += y
                sum_x_2 += x**2
                sum_y_2 += y**2
        if n==0:return 0
        denominator = math.sqrt(sum_x_2-float(sum_x**2)/n) * math.sqrt(sum_y_2-float(sum_y**2)/n)
        if denominator==0:return 0
        return (sum_x_y - float(sum_x*sum_y)/n)/denominator
                    
    def k_nearst(self,k):
        distances = []
        for usr,rate in self.usr_rating.items():
            if not usr == self.usr:
                distance = self.pearson_distance(self.usr_rating[self.usr],self.usr_rating[usr])
                if distance != 0:distances.append((usr,distance))        
        distances.sort(key=lambda item:item[1],reverse=True)
        #print(distances)
        if k>len(distances):return distances
        else:return distances[:k]
        
    def load_data(self,path):
        with open(path) as f:
             lines = f.readlines()
        usr_name = [i.strip('"') for i in lines[0].strip().split(',')[1:]]
        for line in lines[1:]:
            items = line.strip().split(',')
            movie = items[0].strip('"')
            for index in range(1,len(items)):
                if not items[index]=='':
                    if usr_name[index-1] not in self.usr_rating:
                        self.usr_rating[usr_name[index-1]]={movie:int(items[index])}
                    else:self.usr_rating[usr_name[index-1]][movie] = int(items[index])
                    

    def recomend_k(self,nearst,k):
        recommend = {}
        total_distance = 0
        for item in nearst: 
            total_distance+=item[1]
        for item in nearst:
            u_name = item[0]
            weight = float(item[1])/total_distance
            for movie,rate in self.usr_rating[u_name].items():
                if movie not in self.usr_rating[self.usr].keys():
                    if movie not in recommend.keys():
                        recommend[movie] = rate*weight
                    else:
                        recommend[movie] += rate*weight
        print(recommend)   
        top_k = list(recommend.items())
        top_k.sort(key=lambda x:x[1],reverse=True)
        if k>len(top_k):return top_k
        else:return top_k[:k]

    def __init__(self,path,usr):
        self.path=path
        #'/home/ant2017/Downloads/Movie_Ratings.csv'
        self.usr = usr
        self.usr_rating = {}
        self.load_data(path)
        
    def run(self):
        nearst = self.k_nearst(5)
        print(nearst)
        top_k = self.recomend_k(nearst,5)
        for item in top_k:
            print("为您推荐影片:"+item[0]+"\t推荐指数:"+str(item[1]))  
        
path = '/home/ant2017/Downloads/Movie_Ratings.csv'
r = recommender(path,'vanessa')
r.run()