在python上从多个文本文件构建向量

import os
import numpy as np
from sklearn.feature_extraction.text import CountVectorizer

def text_to_vector(file_path):
    with open(file_path, 'r') as file:
        text = file.read()
        # 进行文本处理，如分词、去除停用词、词干提取等
        # ...
        # 将文本转换为向量表示
        vectorizer = CountVectorizer()
        vector = vectorizer.fit_transform([text]).toarray()
        return vector

def build_vectors_from_files(directory):
    vectors = []
    for root, dirs, files in os.walk(directory):
        for file in files:
            if file.endswith('.txt'):
                file_path = os.path.join(root, file)
                vector = text_to_vector(file_path)
                vectors.append(vector)
    return np.concatenate(vectors, axis=0)

# 示例用法
directory = '/path/to/text/files'
vectors = build_vectors_from_files(directory)
print(vectors)