【Python】ItemBasedCF的游戏推荐系统

参考

• 《集体智慧编程》

---

代码

# -*- coding: utf-8 -*-
from math import sqrt

# Returns a distance-based similarity score for person1 and person2
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 ratings in common, return 0
    if len(si) == 0: return 0

    # Add up the squares of 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)

#计算皮尔逊相关度(1为完全正相关，-1为完成负相关)
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

    # if they are no ratings in common, return 0
    if len(si) == 0:
        return 0

    # Sum calculations
    n = len(si)

    # Sums of all the preferences
    sum1 = sum([prefs[p1][it] for it in si])
    sum2 = sum([prefs[p2][it] for it in si])

    # Sums of the squares
    sum1Sq = sum([pow(prefs[p1][it], 2) for it in si])
    sum2Sq = sum([pow(prefs[p2][it], 2) for it in si])

    # Sum of the products
    pSum = sum([prefs[p1][it] * prefs[p2][it] for it in si])

    # Calculate r (Pearson score)
    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]

# 矩阵转置
def transformPrefs(prefs):
    result = {}
    for person in prefs:
        for item in prefs[person]:
            result.setdefault(item, {})

            # Flip item and person
            result[item][person] = prefs[person][item]
    return result

# 计算item之间的相似度
def calculateSimilarItems(prefs, n=10):
    # Create a dictionary of items showing which other items they
    # are most similar to.
    result = {}
    # Invert the preference matrix to be item-centric
    itemPrefs = transformPrefs(prefs)
    c = 0
    for item in itemPrefs:
        # Status updates for large datasets
        c += 1
        if c % 100 == 0: print("%d / %d" % (c,len(itemPrefs)))
        # Find the most similar items to this one
        scores=topMatches(itemPrefs, item, n=n, similarity=sim_distance)
        result[item] = scores
    return result


def getRecommendedItems(prefs, itemMatch, user):
    userRatings = prefs[user]
    scores = {}
    totalSim = {}
    # Loop over items rated by this user
    for (item, rating) in userRatings.items( ):
        # Loop over items similar to this one
        for (similarity, item2) in itemMatch[item]:

          # Ignore if this user has already rated this item
          if item2 in userRatings: continue
          # Weighted sum of rating times similarity
          scores.setdefault(item2, 0)
          scores[item2] += similarity*rating
          # Sum of all the similarities
          totalSim.setdefault(item2, 0)
          totalSim[item2] += similarity

    # Divide each total score by total weighting to get an average
    rankings = [(score/totalSim[item], item) for item, score in scores.items()]

    # Return the rankings from highest to lowest
    rankings.sort()
    rankings.reverse()
    return rankings

if __name__ == "__main__":
    # 原始数据, 评分范围为1-5，对应不喜欢到非常喜欢
    data = {
        'user1': {"Dota2": 1, "League of Legends": 2, "Hearthstone": 3, "World of Warcraft": 4},
        'user2': {"Dota2": 1, "League of Legends": 3, "Hearthstone": 2, "World of Warcraft": 1},
        'user3': {"Dota2": 2, "League of Legends": 2, "Hearthstone": 1, "World of Warcraft": 4}
    }

    # 插入待推荐用户的数据(ns2250225)
    data['ns2250225'] = {'Dota2': 1, 'League of Legends': 2}

    # 计算所有游戏间的相似度
    # 可以把计算好的结果用pickle模块持久化到本地
    # 下次就直接加载，不用重新计算
    itemSim = calculateSimilarItems(data)

    # 获取推荐的结果列表
    recommend_item = getRecommendedItems(data, itemSim, "ns2250225")

    print(str(recommend_item))
    # [(1.6363636363636362, 'Hearthstone'), (1.5185185185185186, 'World of Warcraft')]