python实现Pearson相似度/皮尔逊相关系数

 pearson相似度的计算公式：

 

 其中  是均值， 是指 x 的均值。

 代码如下所示：

def mean_processed(a):
    b = np.zeros_like(a)
    num = 0
    for i,j in enumerate(a):
        if j != 0:
            num += 1
   
    for i,j in enumerate(a):
        if j != 0:
            b[i] = np.sum(a) / num
#     print(np.sum(a) / num)
#     print(b)
    return b



def Pearson_similar(item1_score, item2_score):
    # 将列表转换为可计算的np.array类型
    item1_score = np.array(item1_score)
    item2_score = np.array(item2_score)
    
    # 计算item中有值的数量，以及他们的平均值
    item1_score_mean = mean_processed(item1_score)
    item2_score_mean = mean_processed(item2_score)
    
    # 计算item减去均值
    item1_chazhi =  item1_score - item1_score_mean
    item2_chazhi =  item2_score - item2_score_mean
    
    fenzi = np.sum(item1_chazhi * item2_chazhi)
    print(fenzi)
    
    # 计算差值的平方
    item1_chazhi_squre = np.power(item1_chazhi, 2)
    item2_chazhi_squre = np.power(item2_chazhi, 2)
    
    fenmu = np.sqrt(np.sum(item1_chazhi_squre)) * np.sqrt(np.sum(item2_chazhi_squre))
    print(fenmu)
    similar = fenzi / fenmu
    return similar


a = [1.0, 0.0, 3.0, 0.0, 0.0, 5.0, 0.0, 0.0, 5.0, 0.0, 4.0, 0.0]
# b1 = [0.0, 0.0, 5.0, 4.0, 0.0, 0.0, 4.0, 0.0, 0.0, 2.0, 1.0, 3.0]
b2 = [1.0, 0.0, 3.0, 0.0, 3.0, 0.0, 0.0, 2.0, 0.0, 0.0, 4.0, 0.0]

Pearson_similar(a, b2)

b1的结果是  -0.179

b2的结果是  0.587