63 lines
1.6 KiB
Python
63 lines
1.6 KiB
Python
# -------------------- 题目3 --------------------
|
||
import math
|
||
|
||
A = [3, 4]
|
||
B = [1, 2]
|
||
|
||
print("题目3")
|
||
print("A + B =", [A[0]+B[0], A[1]+B[1]])
|
||
print("2 × A =", [2*A[0], 2*A[1]])
|
||
print("A 的长度 =", math.sqrt(A[0]**2 + A[1]**2))
|
||
print()
|
||
|
||
# -------------------- 题目4 --------------------
|
||
A = [1,2,3]
|
||
B = [4,5,6]
|
||
|
||
dot = sum(a*b for a,b in zip(A,B))
|
||
normA = math.sqrt(sum(x**2 for x in A))
|
||
normB = math.sqrt(sum(x**2 for x in B))
|
||
cos = dot / (normA * normB)
|
||
|
||
print("题目4")
|
||
print("点积 =", dot)
|
||
print("余弦相似度 =", round(cos, 4))
|
||
|
||
A2 = [1,0]
|
||
B2 = [0,1]
|
||
dot2 = A2[0]*B2[0] + A2[1]*B2[1]
|
||
normA2 = math.sqrt(A2[0]**2 + A2[1]**2)
|
||
normB2 = math.sqrt(B2[0]**2 + B2[1]**2)
|
||
cos2 = dot2 / (normA2 * normB2)
|
||
print("A=[1,0], B=[0,1] 余弦相似度 =", cos2)
|
||
print()
|
||
|
||
# -------------------- 题目5 BoW --------------------
|
||
from sklearn.feature_extraction.text import CountVectorizer
|
||
|
||
docs = [
|
||
"Python 是 编程 语言",
|
||
"Java 是 编程 语言",
|
||
"Python Python Python"
|
||
]
|
||
|
||
bow = CountVectorizer()
|
||
matrix = bow.fit_transform(docs)
|
||
|
||
print("题目5")
|
||
print("词表 =", list(bow.get_feature_names_out()))
|
||
print("文档向量：")
|
||
print(matrix.toarray())
|
||
print()
|
||
|
||
# -------------------- 题目7 TF-IDF --------------------
|
||
from sklearn.feature_extraction.text import TfidfVectorizer
|
||
|
||
docs = ["Python 编程", "Java 编程", "Python Python"]
|
||
tfidf = TfidfVectorizer()
|
||
matrix = tfidf.fit_transform(docs)
|
||
|
||
print("题目7")
|
||
print("词表:", tfidf.get_feature_names_out())
|
||
print("TF-IDF矩阵:")
|
||
print(matrix.toarray().round(4)) |