from math import sqrt critics Lisa Rose Lady in the Water Snakes on Pl

  1
  2
  3
  4
  5
  6
  7
  8
  9
 10
 11
 12
 13
 14
 15
 16
 17
 18
 19
 20
 21
 22
 23
 24
 25
 26
 27
 28
 29
 30
 31
 32
 33
 34
 35
 36
 37
 38
 39
 40
 41
 42
 43
 44
 45
 46
 47
 48
 49
 50
 51
 52
 53
 54
 55
 56
 57
 58
 59
 60
 61
 62
 63
 64
 65
 66
 67
 68
 69
 70
 71
 72
 73
 74
 75
 76
 77
 78
 79
 80
 81
 82
 83
 84
 85
 86
 87
 88
 89
 90
 91
 92
 93
 94
 95
 96
 97
 98
 99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
from math import sqrt
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}}
def sim_distance(prefs, person1, person2):
# Get the list of shared items
si = {}
for item in prefs[person1]:
if item in prefs[person2]:
si[item] = 1
# if they have no rating in common, return 0
if len(si) == 0:
return 0
# Add up the squaresof all the differences
sum_of_squares = sum(pow(prefs[person1][item] - prefs[person2][item], 2)
for item in prefs[person1] if item in prefs[person2])
return 1/(1+sum_of_squares)
def sim_pearson(prefs,p1,p2):
# Get the list of mutually rated items
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]
def getRecommendations(prefs, person, similarity=sim_pearson):
totals = {}
simSums = {}
for other in prefs:
if other == person: continue
sim = similarity(prefs, person, other)
if sim <= 0: continue
for item in prefs[other]:
if item not in prefs[person] or prefs[person][item] == 0:
totals.setdefault(item, 0)
totals[item] += prefs[other][item] * sim
simSums.setdefault(item, 0)
simSums[item] += sim
rankings = [(totals/simSums[item], item) for (item, totals) in totals.items()]
rankings.sort()
rankings.reverse()
return rankings
def transformPrefs(prefs):
result = {}
for person in prefs:
for item in prefs[person]:
result.setdefault(item, {})
result[item][person] = prefs[person][item]
return result
def calculateSimiliarItems(prefs, n=10):
result = {}
itemPrefs = transformPrefs(prefs)
c = 0
for item in itemPrefs:
c += 1
if c % 100 == 0:
print "%d / %d" % (c, len(itemPrefs))
scores = topMatches(itemPrefs, item, n=n, similarity=sim_distance)
result[item] = scores
return result
def getRecommendedItems(prefs, itemMatch, user):
userRatings = prefs[user]
scores = {}
totalSim = {}
for (item, rating) in userRatings.items():
for (similarity, item2) in itemMatch[item]:
if item2 in userRatings: continue
scores.setdefault(item2, 0)
scores[item2] += similarity * rating
totalSim.setdefault(item2, 0)
totalSim[item2] += similarity
rankings = [(score/totalSim[item], item) for item,score in scores.items()]
rankings.sort()
rankings.reverse()
return rankings
def loadMovieLens(path='/home/xa4a/merc/c_i/ml-data'):
movies = {}
for line in open(path + '/u.item'):
(id, title) = line.split('|')[0:2]
movies[id] = title
prefs = {}
for line in open(path + '/u.data'):
(user, movieid, rating, ts) = line.split('\t')
prefs.setdefault(user,{})
prefs[user][movies[movieid]] = float(rating)
return prefs