From 0e315ac98db8b4ad90f26cf11a5cab4e6439a8a6 Mon Sep 17 00:00:00 2001
From: 2509165028 <2509165028@student.edu.cn>
Date: Thu, 23 Apr 2026 16:06:54 +0800
Subject: [PATCH] 3-2-1

---
 260421_2509165028.py | 23 +++++++++++++++++++++++
 1 file changed, 23 insertions(+)

diff --git a/260421_2509165028.py b/260421_2509165028.py
index ece70c4..85c6720 100644
--- a/260421_2509165028.py
+++ b/260421_2509165028.py
@@ -3,6 +3,7 @@ import numpy as np
 s="Hello"
 print("ASCII码分别为：",[ord(o) for o in s])
 print(f"ASCII码65对应的字符是：{chr(65)}")
+
 # 第二部分题目3
 A=np.array([3,4])
 B=np.array([1,2])
@@ -10,9 +11,31 @@ print(f"计算A+B的结果为：{A+B}")
 print(f"计算A*2的结果为：{A*2}")
 length=np.linalg.norm(A)
 print(f"向量A的长度为：{length}")
+
 # 第二部分题目4
 A=np.array([1,2,3])
 B=np.array([4,5,6])
 dot=np.dot(A,B)
 print(f"A·B点积为：{dot}")
+def cosine_similarity(A, B):
+    dot = np.dot(A, B)
+    norm_a = np.linalg.norm(A)
+    norm_b = np.linalg.norm(B)
+    return dot / (norm_a * norm_b)
 print(f"相似度 = {cosine_similarity(A, B):.3f}")
+
+# 第三部分题目5
+from sklearn.feature_extraction.text import CountVectorizer
+docs = [
+    "Python 是 编程 语言",
+    "Java  是 编程 语言",
+    "Python Python Python"
+]
+vectorizer = CountVectorizer()
+bow_matrix = vectorizer.fit_transform(docs)
+print("词表:", vectorizer.get_feature_names_out())
+print("BoW矩阵:")
+print(bow_matrix.toarray())
+
+# 第三部分题目6
+print("BoW模型的缺点：忽略词序，所有词同等重要")
\ No newline at end of file