Created
December 28, 2012 04:16
-
-
Save rmacy/4394410 to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
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 Seymoud': { | |
'Lady in the water': 3.0, | |
'Snakes on a plane': 3.5, | |
'Just my luck': 3.0, | |
'Superman returns': 5.0, | |
'You, Me and Dupree': 3.5, | |
'The night listener': 3.0, | |
}, | |
'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, | |
}, | |
} | |
from math import sqrt | |
def sim_distance(prefs, person1, person2): | |
si = {} | |
for item in prefs[person1]: | |
if item in prefs[person2]: | |
si[item] = 1 | |
if len(si) == 0: | |
return 0 | |
sum_of_squares = sum([pow(prefs[person1][item]-prefs[person2][item],2) for item in si]) | |
return 1/(1+sqrt(sum_of_squares)) | |
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 0 | |
sum1 = sum([prefs[p1][it] for it in si]) | |
sum2 = sum([prefs[p2][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 | |
def topMatches(prefs, person, n=5, similarity=sim_pearson): | |
scores = [(similarity(prefs, person, other), other) | |
for other in prefs if other != person] | |
scores.sort() | |
scores.reverse() | |
return scores[0:n] |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment