Files
task-3-2-1-Text-Processing-…/作业/文本数据处理.py
2026-04-21 11:20:11 +08:00

56 lines
1.6 KiB
Python
Raw Blame History

This file contains ambiguous Unicode characters

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

# ========== 题目1文本数据基础 ==========
# 1. 打印"Hello"每个字符的ASCII码
print("===== 题目1-1打印Hello的ASCII码 =====")
s = "Hello"
for char in s:
print(f"字符 '{char}' 的ASCII码{ord(char)}")
# 2. 验证chr(65)是大写字母A
print("\n===== 题目1-2chr(65)验证 =====")
print(f"ASCII码65对应的字符是{chr(65)}")
# ========== 题目3向量基础A=[3,4], B=[1,2] ==========
print("\n===== 题目3向量A=[3,4], B=[1,2] =====")
A = [3, 4]
B = [1, 2]
# 1. A + B
add_result = [A[0]+B[0], A[1]+B[1]]
print(f"1. A + B = {add_result}")
# 2. 2 × A
mul_result = [2 * A[0], 2 * A[1]]
print(f"2. 2 × A = {mul_result}")
# 3. A的长度
import math
norm_A = math.sqrt(A[0]**2 + A[1]**2)
print(f"3. A的长度 = {norm_A}")
# ========== 题目4向量点积与余弦相似度 ==========
print("\n===== 题目4向量A=[1,2,3], B=[4,5,6] =====")
A = [1, 2, 3]
B = [4, 5, 6]
# 1. 点积
dot_product = sum(a * b for a, b in zip(A, B))
print(f"1. 点积 A·B = {dot_product}")
# 2. 余弦相似度
norm_A = math.sqrt(sum(a**2 for a in A))
norm_B = math.sqrt(sum(b**2 for b in B))
cos_sim = dot_product / (norm_A * norm_B)
print(f"2. 余弦相似度 = {cos_sim:.3f}")
# 3. 特殊情况A=[1,0], B=[0,1]的余弦相似度
print("\n===== 题目4-3向量A=[1,0], B=[0,1] =====")
A = [1, 0]
B = [0, 1]
dot_product2 = sum(a * b for a, b in zip(A, B))
norm_A2 = math.sqrt(sum(a**2 for a in A))
norm_B2 = math.sqrt(sum(b**2 for b in B))
cos_sim2 = dot_product2 / (norm_A2 * norm_B2)
print(f"余弦相似度 = {cos_sim2}")
print("解释两个向量互相垂直夹角为90°余弦值为0")