皮尔逊相关度评价

皮尔逊相关系数是判断两组数据与某一直线的拟合程度的一种度量。

critics={'Lisa Rose':{'Lady in Water':2.5,'Snacks on a Plane':3.5,'Just My Luck':3.0,'Superman Returns':5.0,'The Night Listener':3.0,
'You,Me and Dupree':3.0},
'Gene':{'Lady in Water':3.0,'Snacks 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':{'Lady in Water':2.5,'Snacks on a Plane':3.0,'Superman Returns':3.5,'The Night Listener':4.0},
'Claudia':{'Snacks on a Plane':3.5,'Just My Luck':3.0,'Superman Returns':4.5,'The Night Listener':3.0,
'You,Me and Dupree':2.5},
'Mick':{'Lady in Water':3.0,'Snacks 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':{'Lady in Water':3.0,'Snacks on a Plane':4.0,'Superman Returns':3.0,'The Night Listener':3.0,
'You,Me and Dupree':3.5},
'Toby':{'Snacks on a Plane':4.5,'Superman Returns':4.0,'You,Me and Dupree':1.0}}
from math import sqrt
def sim_pearson(prefs,p1,p2):
si={}
for item in prefs[p1]:
if item in prefs[p2]: si[item]=1


n=len(si)
if n==0: return 1
sum1=sum([prefs[p1][it] for it in si])
sum2=sum([prefs[p1][it] for it in si])


sum1Sq=sum([pow(prefs[p1][it],2) for it in si])
sum2Sq=sum([pow(prefs[p2][it],2) for it in si])


pSum=sum([prefs[p1][it]*prefs[p2][it] for it in si])


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