text = "Hello"
print([ord(c) for c in text])
print(chr(65))

import numpy as np
A = np.array([3, 4])
B = np.array([1, 2])
print(A + B)
print(2 * A)
print(np.linalg.norm(A))
A = np.array([1, 2, 3])
B = np.array([4, 5, 6])
print(np.dot(A, B))
cos = np.dot(A,B)/(np.linalg.norm(A)*np.linalg.norm(B))
print(cos)
A2 = np.array([1,0])
B2 = np.array([0,1])
print(np.dot(A2,B2)/(np.linalg.norm(A2)*np.linalg.norm(B2)))
from sklearn.feature_extraction.text import CountVectorizer
docs = ["Python 是 编程 语言","Java 是 编程 语言","Python Python Python"]
vec = CountVectorizer()
print(vec.fit_transform(docs).toarray())
print(vec.get_feature_names_out())

from sklearn.feature_extraction.text import TfidfVectorizer
docs = ["Python 编程","Java 编程","Python Python"]
tfidf = TfidfVectorizer()
matrix = tfidf.fit_transform(docs)
print("词表:", tfidf.get_feature_names_out())
print("矩阵:\n", matrix.toarray())