你可以在Python中使用简单的函数来实现:

def get_cosine(text1, text2):
  vec1 = text1
  vec2 = text2
  intersection = set(vec1.keys()) & set(vec2.keys())
  numerator = sum([vec1[x] * vec2[x] for x in intersection])
  sum1 = sum([vec1[x]**2 for x in vec1.keys()])
  sum2 = sum([vec2[x]**2 for x in vec2.keys()])
  denominator = math.sqrt(sum1) * math.sqrt(sum2)
  if not denominator:
     return 0.0
  else:
     return round(float(numerator) / denominator, 3)
dataSet1 = [3, 45, 7, 2]
dataSet2 = [2, 54, 13, 15]
get_cosine(dataSet1, dataSet2)

另一个版本，如果你有一个场景，你有一个向量列表和一个查询向量，你想要计算查询向量与列表中所有向量的余弦相似度，你可以用下面的方式一次性完成:

>>> import numpy as np

>>> A      # list of vectors, shape -> m x n
array([[ 3, 45,  7,  2],
       [ 1, 23,  3,  4]])

>>> B      # query vector, shape -> 1 x n
array([ 2, 54, 13, 15])

>>> similarity_scores = A.dot(B)/ (np.linalg.norm(A, axis=1) * np.linalg.norm(B))

>>> similarity_scores
array([0.97228425, 0.99026919])

你应该试试SciPy。它有一堆有用的科学例程，例如，“用于数值计算积分、求解微分方程、优化和稀疏矩阵的例程。”它使用超高速优化的NumPy进行数字处理。请参见此处安装。

注意，space .distance.cos计算距离，而不是相似度。所以，你必须用1减去这个值才能得到相似度。

from scipy import spatial

dataSetI = [3, 45, 7, 2]
dataSetII = [2, 54, 13, 15]
result = 1 - spatial.distance.cosine(dataSetI, dataSetII)

这里有一个实现，也适用于矩阵。它的行为完全像sklearn余弦相似度:

def cosine_similarity(a, b):    
    return np.divide(
        np.dot(a, b.T),
        np.linalg.norm(
            a,
            axis=1,
            keepdims=True
        ) 
        @ # matrix multiplication
        np.linalg.norm(
            b,
            axis=1,
            keepdims=True
        ).T
    )

符号@代表矩阵乘法。看到 “at”(@)符号在Python中有什么作用?

Python代码计算:

余弦距离 余弦相似度 角距离 角相似

import math

from scipy import spatial


def calculate_cosine_distance(a, b):
    cosine_distance = float(spatial.distance.cosine(a, b))
    return cosine_distance


def calculate_cosine_similarity(a, b):
    cosine_similarity = 1 - calculate_cosine_distance(a, b)
    return cosine_similarity


def calculate_angular_distance(a, b):
    cosine_similarity = calculate_cosine_similarity(a, b)
    angular_distance = math.acos(cosine_similarity) / math.pi
    return angular_distance


def calculate_angular_similarity(a, b):
    angular_similarity = 1 - calculate_angular_distance(a, b)
    return angular_similarity

相似性搜索:

如果你想在嵌入数组中找到最接近的余弦相似度，你可以使用Tensorflow，就像下面的代码。

在我的测试中，在不到一秒钟(使用GPU)的时间内，在1M嵌入(1' 000,000 '000 x512)中找到形状为1x512的嵌入的最接近值。

import time

import numpy as np  # np.__version__ == '1.23.5'
import tensorflow as tf  # tf.__version__ == '2.11.0'

EMBEDDINGS_LENGTH = 512
NUMBER_OF_EMBEDDINGS = 1000 * 1000


def calculate_cosine_similarities(x, embeddings):
    cosine_similarities = -1 * tf.keras.losses.cosine_similarity(x, embeddings)
    return cosine_similarities.numpy()


def find_closest_embeddings(x, embeddings, top_k=1):
    cosine_similarities = calculate_cosine_similarities(x, embeddings)
    values, indices = tf.math.top_k(cosine_similarities, k=top_k)
    return values.numpy(), indices.numpy()


def main():
    # x shape: (512)
    # Embeddings shape: (1000000, 512)
    x = np.random.rand(EMBEDDINGS_LENGTH).astype(np.float32)
    embeddings = np.random.rand(NUMBER_OF_EMBEDDINGS, EMBEDDINGS_LENGTH).astype(np.float32)

    print('Embeddings shape: ', embeddings.shape)

    n = 100
    sum_duration = 0
    for i in range(n):
        start = time.time()
        best_values, best_indices = find_closest_embeddings(x, embeddings, top_k=1)
        end = time.time()

        duration = end - start
        sum_duration += duration

        print('Duration (seconds): {}, Best value: {}, Best index: {}'.format(duration, best_values[0], best_indices[0]))

    # Average duration (seconds): 1.707 for Intel(R) Core(TM) i7-10700 CPU @ 2.90GHz
    # Average duration (seconds): 0.961 for NVIDIA 1080 ti
    print('Average duration (seconds): ', sum_duration / n)


if __name__ == '__main__':
    main()

对于更高级的相似度搜索，你可以使用Milvus, Weaviate或Faiss。

https://en.wikipedia.org/wiki/Cosine_similarity https://gist.github.com/amir-saniyan/e102de09b01c4ed1632e3d1a1a1cbf64

使用numpy比较一个数字列表和多个列表(矩阵):

def cosine_similarity(vector,matrix):
   return ( np.sum(vector*matrix,axis=1) / ( np.sqrt(np.sum(matrix**2,axis=1)) * np.sqrt(np.sum(vector**2)) ) )[::-1]