# 题目1
print("题目1：")
for c in "Hello":
    print(ord(c))
print(chr(65))

# 题目2 思考题答案
print("\n题目2：")
print("""1. 数据的表示形式：
图像是结构化的数值矩阵，每个像素都是数字，计算模型可以直接处理；
文本是非结构化的符号序列，每个字符/词的编码本身不包含直接可计算的数值关系。
2. 语义理解：
图像的数值矩阵直接对应像素信息，模型只需处理数值运算；
文本承载抽象语义、歧义、上下文依赖，无法直接用简单数值运算捕捉深层含义。""")

# 题目3
print("\n题目3：")
A = [3, 4]
B = [1, 2]
print("A + B =", [a + b for a, b in zip(A, B)])
print("2 × A =", [2 * x for x in A])
length_A = (A[0]**2 + A[1]**2) ** 0.5
print("A的长度（模） =", length_A)

# 题目4
print("\n题目4：")
A = [1, 2, 3]
B = [4, 5, 6]
dot_product = sum(a * b for a, b in zip(A, B))
mod_A = (sum(x**2 for x in A)) ** 0.5
mod_B = (sum(x**2 for x in B)) ** 0.5
cos_sim = dot_product / (mod_A * mod_B)
print("A · B =", dot_product)
print("余弦相似度 =", cos_sim)

A2 = [1, 0]
B2 = [0, 1]
dot2 = sum(a * b for a, b in zip(A2, B2))
mod_A2 = (sum(x**2 for x in A2)) ** 0.5
mod_B2 = (sum(x**2 for x in B2)) ** 0.5
cos_sim2 = dot2 / (mod_A2 * mod_B2)
print("A = [1,0], B = [0,1] 的余弦相似度 =", cos_sim2)
print("解释：两个向量正交，夹角为90度，余弦值为0，表示两者完全不相关。")

# 题目5
print("\n题目5：")
docs = ["Python 是 编程 语言", "Java 是 编程 语言", "Python Python Python"]
vocab = sorted(list(set(" ".join(docs).split())))
vec1 = [docs[0].split().count(word) for word in vocab]
vec2 = [docs[1].split().count(word) for word in vocab]
vec3 = [docs[2].split().count(word) for word in vocab]
print("词表：", vocab)
print("Doc1向量：", vec1)
print("Doc2向量：", vec2)
print("Doc3向量：", vec3)

# 题目6 思考题答案
print("\n题目6：")
print("""BoW模型的缺点：
1. 忽略词序：只统计词频，不考虑词的顺序，无法区分语义，如“我打你”和“你打我”向量完全相同，会造成语义混淆。
2. 不区分词的重要性：高频停用词（如“是”）和低频关键词权重一样，无法突出关键信息，降低文本区分度。""")

# 附加题（题目7，去掉sklearn依赖，改用纯Python实现TF-IDF核心逻辑）
print("\n题目7（纯Python实现TF-IDF）：")
docs = ["Python 编程", "Java 编程", "Python Python"]
vocab = sorted(list(set(" ".join(docs).split())))
N = len(docs)

def tf(word, doc):
    return doc.split().count(word) / len(doc.split())

def idf(word, docs):
    import math
    df = sum(1 for doc in docs if word in doc.split())
    return math.log(N / (1 + df))

tfidf_matrix = []
for doc in docs:
    row = []
    for word in vocab:
        row.append(tf(word, doc) * idf(word, docs))
    tfidf_matrix.append(row)

print("词表:", vocab)
print("TF-IDF矩阵:")
for row in tfidf_matrix:
    print(row)