Python中计算相似度的方法详解

import numpy as np

def cosine_similarity(a, b):
    return np.dot(a, b) / (np.linalg.norm(a) * np.linalg.norm(b))

# 示例
vector_a = np.array([1, 2, 3])
vector_b = np.array([4, 5, 6])
similarity = cosine_similarity(vector_a, vector_b)
print(f'余弦相似度: {similarity}')

from scipy.spatial import distance

def euclidean_distance(a, b):
    return distance.euclidean(a, b)

# 示例
vector_a = np.array([1, 2, 3])
vector_b = np.array([4, 5, 6])
dist = euclidean_distance(vector_a, vector_b)
print(f'欧氏距离: {dist}')

def manhattan_distance(a, b):
    return np.sum(np.abs(a - b))# 示例
vector_a = np.array([1, 2, 3])


vector_b = np.array([4, 5, 6])
dist = manhattan_distance(vector_a, vector_b)
print(f'曼哈顿距离: {dist}')

def jaccard_similarity(set_a, set_b):
    intersection = len(set_a.intersection(set_b))
    union = len(set_a.union(set_b))
    return intersection / union

# 示例
set_a = {1, 2, 3}
set_b = {3, 4, 5}
similarity = jaccard_similarity(set_a, set_b)
print(f'杰卡德相似度: {similarity}')