Python 中的 NLP 特征工程
Rounak Banik
Data Scientist
设两个向量，
$$V = (v_1, v_2, \cdots, v_n), W = (w_1, w_2, \cdots, w_n)$$
则 V 与 W 的点积为：
$$V \cdot W = (v_1 \times w_1) + (v_2 \times w_2) + \cdots + (v_n \times w_n) $$
示例：
$$A = (4, 7, 1) \; , \; B = (5, 2, 3)$$
$$A \cdot B = (4 \times 5) + (7 \times 2) + \cdots (1 \times 3)$$
$$= 20 + 14 + 3 = 37 \color{white}{A \cdot B d}$$
$$$$
对任意向量，
$$V = (v_1, v_2, \cdots, v_n)$$
其模长定义为：
$$||\mathbf{V}|| = \sqrt{(v_1)^{2} + (v_2)^{2} + ... + (v_n)^{2}} $$
$$||\mathbf{A}|| = \sqrt{(4)^{2} + (7)^{2} + (1)^{2}} $$
$$ \color{white}{filler} = \sqrt{16 + 49 + 1} = \sqrt{66}$$
$$
$$A: (4, 7, 1)$$
$$B: (5, 2, 3)$$
余弦分数，
$$cos(A,B) = \frac{A \cdot B}{|A| \cdot |B|}$$
$$\color{white}{fillers lorem}= \frac{37}{\sqrt{66} \times \sqrt{38}}$$
$$\color{white}{fillers l}= 0.7388$$
# 导入 cosine_similarity from sklearn.metrics.pairwise import cosine_similarity
# 定义两个三维向量 A 和 B A = (4,7,1) B = (5,2,3) # 计算 A 与 B 的余弦分数 score = cosine_similarity([A], [B]) # 打印余弦分数 print(score)
array([[ 0.73881883]])
$$
$$
$$$$
Preparing Video For Download...
