Question

我有一个默认的示例字典，如下所示：

critics = {'Lisa Rose': {'Lady in the Water': 2.5, 'Snakes on a Plane': 3.5,
'Just My Luck': 3.0, 'Superman Returns': 3.5, 'You, Me and Dupree': 2.5,
'The Night Listener': 3.0},
           'Gene Seymour': {'Lady in the Water': 3.0, 'Snakes on a Plane': 3.5,
'Just My Luck': 1.5, 'Superman Returns': 5.0, 'The Night Listener': 3.0,
'You, Me and Dupree': 3.5},
           'Michael Phillips': {'Lady in the Water': 2.5, 'Snakes on a Plane': 3.0,
'Superman Returns': 3.5, 'The Night Listener': 4.0},
'Claudia Puig': {'Snakes on a Plane': 3.5, 'Just My Luck': 3.0,
'The Night Listener': 4.5, 'Superman Returns': 4.0,
'You, Me and Dupree': 2.5},
           'Mick LaSalle': {'Lady in the Water': 3.0, 'Snakes on a Plane': 4.0,
'Just My Luck': 2.0, 'Superman Returns': 3.0, 'The Night Listener': 3.0,
'You, Me and Dupree': 2.0},
'Jack Matthews': {'Lady in the Water': 3.0, 'Snakes on a Plane': 4.0,
'The Night Listener': 3.0, 'Superman Returns': 5.0, 'You, Me and Dupree': 3.5},
           'Toby': {'Snakes on a Plane':4.5,'You, Me and Dupree':1.0,'Superman Returns':4.0}}

我使用一个函数，使用Pearson相关系数返回字典中最相似的人，如下所示：

from math import sqrt
def sim_pearson(prefs,p1,p2):
# lista na zaednichki tochki
    si={}
    for item in prefs[p1]:
        if item in prefs[p2]: si[item]=1
# najdi go brojot na elementi
    n=len(si)
# ako nemaat zaednichki tochki vrati 0
    if n==0: return 0
# dodadi gi site
    sum1=sum([prefs[p1][it] for it in si])
    sum2=sum([prefs[p2][it] for it in si])
# sumiraj gi kvadratite
    sum1Sq=sum([pow(prefs[p1][it],2) for it in si])
    sum2Sq=sum([pow(prefs[p2][it],2) for it in si])
# sumiraj gi proizvodite
    pSum=sum([prefs[p1][it]*prefs[p2][it] for it in si])
# presmetka na Pirsonoviot koeficient
    num=pSum-(sum1*sum2/n)
    den=sqrt((sum1Sq-pow(sum1,2)/n)*(sum2Sq-pow(sum2,2)/n))
    if den==0: return 0
    r=num/den
    return r

它有效。例如，对于调用print sim_pearson(critics, 'Toby', 'Lisa Rose')，我得到系数0.991240707162。

但是，当我用我的词典尝试相同的功能时：

tests = {'dzam': {'ag1yYW5kb20tcmFuZG9tcg8LEghib29rbWFyaxiKAgw': 5.0,
'ag1yYW5kb20tcmFuZG9tcg8LEghib29rbWFyaxjvAQw': 1.0, 
'ag1yYW5kb20tcmFuZG9tcg8LEghib29rbWFyaxj3AQw': 1.0, 
'ag1yYW5kb20tcmFuZG9tcg8LEghib29rbWFyaxiMAgw': 5.0, 
'ag1yYW5kb20tcmFuZG9tcg8LEghib29rbWFyaxiBAgw': 1.0, 
'ag1yYW5kb20tcmFuZG9tcg8LEghib29rbWFyaxjtAQw': 1.0, 
'ag1yYW5kb20tcmFuZG9tcg8LEghib29rbWFyaxj_AQw': 1.0, 
'ag1yYW5kb20tcmFuZG9tcg8LEghib29rbWFyaxiIAgw': 5.0, 
'ag1yYW5kb20tcmFuZG9tcg8LEghib29rbWFyaxj9AQw': 1.0, 
'ag1yYW5kb20tcmFuZG9tcg8LEghib29rbWFyaxiqAgw': 3.0, 
'ag1yYW5kb20tcmFuZG9tcg8LEghib29rbWFyaxjzAQw': 5.0, 
'ag1yYW5kb20tcmFuZG9tcg8LEghib29rbWFyaxikAgw': 3.0, 
'ag1yYW5kb20tcmFuZG9tcg8LEghib29rbWFyaxiaAgw': 5.0, 
'ag1yYW5kb20tcmFuZG9tcg8LEghib29rbWFyaxj1AQw': 1.0, 
'ag1yYW5kb20tcmFuZG9tcg8LEghib29rbWFyaxjxAQw': 5.0, 
'ag1yYW5kb20tcmFuZG9tcg8LEghib29rbWFyaxiYAgw': 5.0}, 
         'kex': {'ag1yYW5kb20tcmFuZG9tcg8LEghib29rbWFyaxiKAgw': 5.0, 
'ag1yYW5kb20tcmFuZG9tcg8LEghib29rbWFyaxjvAQw': 1.0, 
'ag1yYW5kb20tcmFuZG9tcg8LEghib29rbWFyaxj3AQw': 1.0, 
'ag1yYW5kb20tcmFuZG9tcg8LEghib29rbWFyaxiMAgw': 5.0, 
'ag1yYW5kb20tcmFuZG9tcg8LEghib29rbWFyaxiBAgw': 1.0, 
'ag1yYW5kb20tcmFuZG9tcg8LEghib29rbWFyaxjtAQw': 1.0, 
'ag1yYW5kb20tcmFuZG9tcg8LEghib29rbWFyaxj_AQw': 1.0, 
'ag1yYW5kb20tcmFuZG9tcg8LEghib29rbWFyaxiIAgw': 5.0, 
'ag1yYW5kb20tcmFuZG9tcg8LEghib29rbWFyaxj9AQw': 1.0, 
'ag1yYW5kb20tcmFuZG9tcg8LEghib29rbWFyaxiqAgw': 3.0, 
'ag1yYW5kb20tcmFuZG9tcg8LEghib29rbWFyaxjzAQw': 5.0, 
'ag1yYW5kb20tcmFuZG9tcg8LEghib29rbWFyaxikAgw': 3.0, 
'ag1yYW5kb20tcmFuZG9tcg8LEghib29rbWFyaxiaAgw': 5.0, 
'ag1yYW5kb20tcmFuZG9tcg8LEghib29rbWFyaxj1AQw': 1.0, 
'ag1yYW5kb20tcmFuZG9tcg8LEghib29rbWFyaxjxAQw': 5.0, 
'ag1yYW5kb20tcmFuZG9tcg8LEghib29rbWFyaxiYAgw': 5.0}, 
         'rokoko': {'ag1yYW5kb20tcmFuZG9tcg8LEghib29rbWFyaxiKAgw': 5.0, 
'ag1yYW5kb20tcmFuZG9tcg8LEghib29rbWFyaxjvAQw': 1.0, 
'ag1yYW5kb20tcmFuZG9tcg8LEghib29rbWFyaxj3AQw': 1.0, 
'ag1yYW5kb20tcmFuZG9tcg8LEghib29rbWFyaxiMAgw': 5.0, 
'ag1yYW5kb20tcmFuZG9tcg8LEghib29rbWFyaxiBAgw': 1.0, 
'ag1yYW5kb20tcmFuZG9tcg8LEghib29rbWFyaxjtAQw': 1.0, 
'ag1yYW5kb20tcmFuZG9tcg8LEghib29rbWFyaxj_AQw': 1.0, 
'ag1yYW5kb20tcmFuZG9tcg8LEghib29rbWFyaxiIAgw': 5.0, 
'ag1yYW5kb20tcmFuZG9tcg8LEghib29rbWFyaxj9AQw': 1.0, 
'ag1yYW5kb20tcmFuZG9tcg8LEghib29rbWFyaxiqAgw': 3.0, 
'ag1yYW5kb20tcmFuZG9tcg8LEghib29rbWFyaxjzAQw': 5.0, 
'ag1yYW5kb20tcmFuZG9tcg8LEghib29rbWFyaxikAgw': 3.0, 
'ag1yYW5kb20tcmFuZG9tcg8LEghib29rbWFyaxiaAgw': 5.0, 
'ag1yYW5kb20tcmFuZG9tcg8LEghib29rbWFyaxj1AQw': 1.0, 
'ag1yYW5kb20tcmFuZG9tcg8LEghib29rbWFyaxjxAQw': 5.0, 
'ag1yYW5kb20tcmFuZG9tcg8LEghib29rbWFyaxiYAgw': 5.0}, 
         'test@example.com': {'ag1yYW5kb20tcmFuZG9tcg8LEghib29rbWFyaxiKAgw': 5.0, 
'ag1yYW5kb20tcmFuZG9tcg8LEghib29rbWFyaxjvAQw': 1.0, 
'ag1yYW5kb20tcmFuZG9tcg8LEghib29rbWFyaxj3AQw': 1.0, 
'ag1yYW5kb20tcmFuZG9tcg8LEghib29rbWFyaxiMAgw': 5.0, 
'ag1yYW5kb20tcmFuZG9tcg8LEghib29rbWFyaxiBAgw': 1.0, 
'ag1yYW5kb20tcmFuZG9tcg8LEghib29rbWFyaxjtAQw': 1.0, 
'ag1yYW5kb20tcmFuZG9tcg8LEghib29rbWFyaxj_AQw': 1.0, 
'ag1yYW5kb20tcmFuZG9tcg8LEghib29rbWFyaxiIAgw': 5.0, 
'ag1yYW5kb20tcmFuZG9tcg8LEghib29rbWFyaxj9AQw': 1.0, 
'ag1yYW5kb20tcmFuZG9tcg8LEghib29rbWFyaxiqAgw': 3.0, 
'ag1yYW5kb20tcmFuZG9tcg8LEghib29rbWFyaxjzAQw': 5.0, 
'ag1yYW5kb20tcmFuZG9tcg8LEghib29rbWFyaxikAgw': 3.0, 
'ag1yYW5kb20tcmFuZG9tcg8LEghib29rbWFyaxiaAgw': 5.0, 
'ag1yYW5kb20tcmFuZG9tcg8LEghib29rbWFyaxj1AQw': 1.0, 
'ag1yYW5kb20tcmFuZG9tcg8LEghib29rbWFyaxjxAQw': 5.0, 
'ag1yYW5kb20tcmFuZG9tcg8LEghib29rbWFyaxiYAgw': 5.0}, 
         'seljak': {'ag1yYW5kb20tcmFuZG9tcg8LEghib29rbWFyaxiKAgw': 5.0, 
'ag1yYW5kb20tcmFuZG9tcg8LEghib29rbWFyaxjvAQw': 1.0, 
'ag1yYW5kb20tcmFuZG9tcg8LEghib29rbWFyaxiKAgw': 5.0, 
'ag1yYW5kb20tcmFuZG9tcg8LEghib29rbWFyaxjvAQw': 1.0, }}

我总是得到1.0，不管我在词典中有匹配，为什么会这样？

顺便说一下，我正在使用哈希，所以我的词典必须有这么长的字符串。：）

Answer 1

你可能被躲在眼睛上的长键愚弄了，这些长串不同。

尝试将所有值设置为测试0中的'seljak'，然后与其进行关联。您会看到0相关性：

print sim_pearson(tests, 'test@example.com', 'seljak')

将测试'seljak'的最后一个值更改为1，您将看到重新运行脚本的负相关。

为什么函数不适合我的输入？

1 个答案: