python中的jieba实现对一个文件夹中的所有文档进行分词，根据停用词表去除停用词，基于文档中的非停用词及其TF-IDF值，生成该文档的词向量，具体代码...

好的，以下是基于Python中jieba库、sklearn库和numpy库的代码实现：

import os
import jieba
import numpy as np
from sklearn.feature_extraction.text import TfidfVectorizer

# 加载停用词表
stopwords_path = 'stopwords.txt'
stopwords = [line.strip() for line in open(stopwords_path, 'r', encoding='utf-8').readlines()]

def cut_words(file_path):
    """
    对文本进行分词，去除停用词
    """
    with open(file_path, 'r', encoding='utf-8') as f:
        content = f.read()
        word_list = jieba.cut(content)
        word_list = [word.strip() for word in word_list if word.strip() not in stopwords]
        return ' '.join(word_list)

def load_files(file_dir):
    """
    加载文件夹中的所有文本
    """
    file_list = []
    for root, dirs, files in os.walk(file_dir):
        for file in files:
            file_list.append(os.path.join(root, file))
    return file_list

def get_tfidf(file_list):
    """
    计算tf-idf权重矩阵
    """
    corpus = []
    for file in file_list:
        corpus.append(cut_words(file))
    vectorizer = TfidfVectorizer()
    tfidf = vectorizer.fit_transform(corpus)
    return tfidf.toarray(), vectorizer.get_feature_names()

def get_word_vector(file_path, tfidf_weight, feature_names):
    """
    根据文档中的非停用词及其TF-IDF值生成该文档的词向量
    """
    word_dict = {}
    with open(file_path, 'r', encoding='utf-8') as f:
        content = f.read()
        word_list = jieba.cut(content)
        for word in word_list:
            if word.strip() not in stopwords:
                if word.strip() in word_dict:
                    word_dict[word.strip()] += 1
                else:
                    word_dict[word.strip()] = 1
    word_vector = np.zeros(len(feature_names))
    for word, count in word_dict.items():
        if word in feature_names:
            index = feature_names.index(word)
            word_vector[index] = count * tfidf_weight[index]
    return word_vector

if __name__ == '__main__':
    file_dir = 'data'
    file_list = load_files(file_dir)
    tfidf_weight, feature_names = get_tfidf(file_list)
    for file_path in file_list:
        word_vector = get_word_vector(file_path, tfidf_weight, feature_names)
        print(f'{file_path} 的词向量为：{word_vector}')

其中，假设文本文件夹为`data`，停用词表为`stopwords.txt`，代码中的`cut_words`函数用于对文本进行分词并去除停用词，`load_files`函数用于加载文件夹中的所有文本，`get_tfidf`函数用于计算tf-idf权重矩阵，`get_word_vector`函数用于根据文档中的非停用词及其TF-IDF值生成该文档的词向量。最后，遍历所有文本文件，分别输出其对应的词向量。