import numpy as np
vocab = ["Python", "学习", "数据", "人工智能", "编程"]
doc1 = "Python学习编程"
doc2 = "Python人工智能数据"

def text_to_vector(text, vocab):
    words = text.split()
    vector = np.zeros(len(vocab))
    for i, word in enumerate(vocab):
        vector[i] = words.count(word)
    return vector

v1 = text_to_vector(doc1, vocab)
v2 = text_to_vector(doc2, vocab)

print("doc1向量:", v1)
print("doc2向量:", v2)