读书笔记：集体智慧编程（1）

  1 # -*- coding: utf-8 -*-  
  2 
  3 # A dictionary of movie critics and their ratings of a small
  4 # set of movies
  5 critics = {‘Lisa Rose‘: {‘Lady in the Water‘: 2.5, ‘Snakes on a Plane‘: 3.5,
  6                          ‘Just My Luck‘: 3.0, ‘Superman Returns‘: 3.5, ‘You, Me and Dupree‘: 2.5,
  7                          ‘The Night Listener‘: 3.0},
  8            ‘Gene Seymour‘: {‘Lady in the Water‘: 3.0, ‘Snakes on a Plane‘: 3.5,
  9                             ‘Just My Luck‘: 1.5, ‘Superman Returns‘: 5.0, ‘The Night Listener‘: 3.0,
 10                             ‘You, Me and Dupree‘: 3.5},
 11            ‘Michael Phillips‘: {‘Lady in the Water‘: 2.5, ‘Snakes on a Plane‘: 3.0,
 12                                 ‘Superman Returns‘: 3.5, ‘The Night Listener‘: 4.0},
 13            ‘Claudia Puig‘: {‘Snakes on a Plane‘: 3.5, ‘Just My Luck‘: 3.0,
 14                             ‘The Night Listener‘: 4.5, ‘Superman Returns‘: 4.0,
 15                             ‘You, Me and Dupree‘: 2.5},
 16            ‘Mick LaSalle‘: {‘Lady in the Water‘: 3.0, ‘Snakes on a Plane‘: 4.0,
 17                             ‘Just My Luck‘: 2.0, ‘Superman Returns‘: 3.0, ‘The Night Listener‘: 3.0,
 18                             ‘You, Me and Dupree‘: 2.0},
 19            ‘Jack Matthews‘: {‘Lady in the Water‘: 3.0, ‘Snakes on a Plane‘: 4.0,
 20                              ‘The Night Listener‘: 3.0, ‘Superman Returns‘: 5.0, ‘You, Me and Dupree‘: 3.5},
 21            ‘Toby‘: {‘Snakes on a Plane‘: 4.5, ‘You, Me and Dupree‘: 1.0, ‘Superman Returns‘: 4.0}}
 22 
 23 from math import sqrt
 24 
 25 def sim_distance(prefs, person1, person2):
 26     si = {}
 27     for item in prefs[person1]:
 28         if item in prefs[person2]:
 29             si[item] = 1
 30 
 31     if len(si) == 0: return 0
 32     sum_of_squares = sum(
 33         [pow(prefs[person1][item] - prefs[person2][item], 2) for item in prefs[person1] if item in prefs[person2]])
 34     return 1 / (1 + sqrt(sum_of_squares))
 35 
 36 
 37 def sim_pearson(prefs, person1, person2):
 38     si = {}
 39     for item in prefs[person1]:
 40         if item in prefs[person2]:
 41             si[item] = 1
 42 
 43     n = len(si)
 44     if n == 0: return 1
 45 
 46     sum1 = sum([prefs[person1][it] for it in si])
 47     sum2 = sum([prefs[person2][it] for it in si])
 48 
 49     sum1Sq = sum([pow(prefs[person1][it], 2) for it in si])
 50     sum2Sq = sum([pow(prefs[person2][it], 2) for it in si])
 51 
 52     pSum = sum([prefs[person1][it] * prefs[person2][it] for it in si])
 53 
 54     num = pSum - (sum1 * sum2 / n)
 55     den = sqrt((sum1Sq - pow(sum1, 2) / n) * (sum2Sq - pow(sum2, 2) / n))
 56     if den == 0: return 0
 57 
 58     r = num / den
 59     return r
 60 
 61 
 62 # Returns the best matches for person from the prefs dictionary.
 63 # Number of results and similarity function are optional params.
 64 def topMatches(prefs, person, n=5, similarity=sim_pearson):
 65     scores = [(similarity(prefs, person, other), other) for other in prefs if other != person]
 66     # Sort the list so the highest scores appear at the top
 67     scores.sort()
 68     scores.reverse()
 69     return scores[0:n]
 70 
 71 
 72 # Gets recommendations for a person by using a weighted average
 73 # of every other user‘s rankings
 74 def getRecommendations(prefs, person, similarity=sim_pearson):
 75     totals = {}
 76     simSums = {}
 77     for other in prefs:
 78         # don‘t compare me to myself
 79         if other == person: continue
 80         sim = similarity(prefs, person, other)
 81         # ignore scores of zero or lower
 82         if sim <= 0: continue
 83         for item in prefs[other]:
 84             # only score movies I haven‘t seen yet
 85             if item not in prefs[person] or prefs[person][item] == 0:
 86                 # Similarity * Score
 87                 totals.setdefault(item, 0)
 88                 totals[item] += prefs[other][item] * sim
 89                 # Sum of similarities
 90                 simSums.setdefault(item, 0)
 91                 simSums[item] += sim
 92     # Create the normalized list
 93     rankings = [(total / simSums[item], item) for item, total in totals.items()]
 94     # Return the sorted list
 95     rankings.sort()
 96     rankings.reverse()
 97     return rankings
 98 
 99 if __name__ == ‘__main__‘:
100     print getRecommendations(critics,‘Toby‘,similarity=sim_pearson)