几种相似度计算代码

from math import sqrt
"""
余弦相似度
"""
def sim_distance_cos(p1,p2):
    c = set(p1.keys())&set(p2.keys())
    if not c:
        return 0
    ss = sum([p1.get(sk)*p2.get(sk) for sk in c])
    sq1 = sqrt(sum([pow(p1.get(sk),2) for sk in p1.values()]))
    sq2 = sqrt(sum([pow(p2.get(sk),2) for sk in p2.values()]))
    p = float(ss)/(sq1*sq2)
    return p

from math import sqrt
"""
皮尔逊相关度
"""
def sim_distance_pearson(p1,p2):
    c = set(p1.keys())&set(p2.keys())
    if not c:
        return 0
    s1 = sum([p1.get(sk) for sk in c])
    s2 = sum([p2.get(sk) for sk in c])
    sq1 = sum([pow(p1.get(sk),2) for sk in c])
    sq2 = sum([pow(p2.get(sk),2) for sk in c])
    ss = sum([p1.get(sk)*p2.get(sk) for sk in c])
    n = len(c)
    num = ss-s1*s2/n
    den = sqrt((sq1-pow(s1,2)/n)*(sq2-pow(s2-2)/n))
    if den == 0:
        return 0
    p = num/den
    return p

from math import sqrt
"""
欧几里得空间法 计算相似度
"""
def sim_distance(p1, p2):
    c = set(p1.keys())&set(p2.keys())
    if not c:
        return 0
    sum_of_squares = sum([pow(p1.get(sk)-p2.get(sk),2) for sk in c])
    p = 1/(1+sqrt(sum_of_squares))
    return p

"""
Jaccard系数
"""
def sim_distance_jaccard(p1,p2):
    c = set(p1.keys())&set(p2.keys())
    if not c:
        return 0
    ss = sum([p1.get(sk)*p2.get(sk) for sk in c])
    sq1 = sum([pow(sk,2) for sk in p1.values()])
    sq2 = sum([pow(sk,2) for sk in p2.values()])
    p = float(ss)/(sq1+sq2-ss)
    return p