皮尔逊相关度评价

代码实现：

a.数据集

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}}

b.算法实现

import recommenfations
from math import sqrt


# 返回p1和p2的皮尔逊相关系数
def persion_person(prefs, person1, person2):
    # 得到双方都曾评价过的物品列表
    share_item = {}
    for item in prefs[person1]:
        if item in prefs[person2]:
            share_item[item] = 1

    # 得到列表元素的个数
    n = len(share_item)

    # 如果没用共同之处，则返回1
    if n == 0:
        return 1
    
    # 对所有偏好求和 
    sum_person1 = sum([prefs[person1][item] for item in share_item])
    sum_person2 = sum([prefs[person2][item] for item in share_item])

    # 求平方和
    sum_person1_Sq = sum([pow(prefs[person1][item], 2) for item in share_item])
    sum_person2_Sq = sum([pow(prefs[person2][item], 2) for item in share_item])

    # 求乘积之和 E(XY)
    pSum = sum([prefs[person1][item] * prefs[person2][item] for item in share_item])

    # 计算皮尔逊评价值
    num = pSum - (sum_person1 * sum_person2 / n)
    den = sqrt((sum_person1_Sq - pow(sum_person1, 2) / n) * (sum_person2_Sq - pow(sum_person2, 2) / n))
    if den == 0:
        return 0
    
    r = num / den

    return r