基于用户的推荐算法余弦相似性实现

1. [文件]     cosine.py 

#-*- coding: utf-8 -*-
'''
Created on 2012-9-3

@author: Jekey
余弦相关性，如果数据稀疏，考虑使用该算法
'''
import codecs
from math import sqrt

users = {"Angelica": {"Blues Traveler": 3.5, "Broken Bells": 2.0, "Norah Jones": 4.5, "Phoenix": 5.0, "Slightly Stoopid": 1.5, "The Strokes": 2.5, "Vampire Weekend": 2.0},
         "Bill":{"Blues Traveler": 2.0, "Broken Bells": 3.5, "Deadmau5": 4.0, "Phoenix": 2.0, "Slightly Stoopid": 3.5, "Vampire Weekend": 3.0},
         "Chan": {"Blues Traveler": 5.0, "Broken Bells": 1.0, "Deadmau5": 1.0, "Norah Jones": 3.0, "Phoenix": 5, "Slightly Stoopid": 1.0},
         "Dan": {"Blues Traveler": 3.0, "Broken Bells": 4.0, "Deadmau5": 4.5, "Phoenix": 3.0, "Slightly Stoopid": 4.5, "The Strokes": 4.0, "Vampire Weekend": 2.0},
         "Hailey": {"Broken Bells": 4.0, "Deadmau5": 1.0, "Norah Jones": 4.0, "The Strokes": 4.0, "Vampire Weekend": 1.0},
         "Jordyn":  {"Broken Bells": 4.5, "Deadmau5": 4.0, "Norah Jones": 5.0, "Phoenix": 5.0, "Slightly Stoopid": 4.5, "The Strokes": 4.0, "Vampire Weekend": 4.0},
         "Sam": {"Blues Traveler": 5.0, "Broken Bells": 2.0, "Norah Jones": 3.0, "Phoenix": 5.0, "Slightly Stoopid": 4.0, "The Strokes": 5.0},
         "Veronica": {"Blues Traveler": 3.0, "Norah Jones": 5.0, "Phoenix": 4.0, "Slightly Stoopid": 2.5, "The Strokes": 3.0}
        }

#cosine 距离

def cosine(rate1,rate2):
    sum_xy = 0
    sum_x=0
    sum_y=0
    n=0  
    for key in rate1:
        if key in rate2:
            n+=1
            x=rate1[key]
            y=rate2[key]
            sum_xy += x*y
            sum_x +=x*x
            sum_y +=y*y
    #计算距离
    if n==0:
        return 0
    else:
        sx=pow(sum_x,1/2)
        sy=pow(sum_y,1/2)
        if sum_xy<>0:
            denominator=sx*sy/sum_xy
        else:
            denominator=0
    return denominator

#返回最近距离用户
def computeNearestNeighbor(username,users):
    distances = []
    for key in users:
        if key<>username:
            distance = cosine(users[username],users[key])
            distances.append((distance,key)) 
    distances.sort()          
    return distances
#推荐
def recommend(username,users):
    #获得最近用户的name
    nearest = computeNearestNeighbor(username,users)[0][1]
    recommendations =[]
    #得到最近用户的推荐列表
    neighborRatings = users[nearest]
    for key in neighborRatings:
        if not key in users[username]:
            recommendations.append((key,neighborRatings[key]))
    recommendations.sort(key=lambda rat:rat[1], reverse=True)
    return recommendations


    
    
if __name__ == &#39;__main__&#39;:
    print recommend(&#39;Hailey&#39;, users)