写出基于TF-IDF+KNN进行txt文件格式的中文文本分类的代码

以下是基于TF-IDF和KNN的中文文本分类代码示例：

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

# 读取文件，返回文本和标签列表
def load_data(path):
    texts = []
    labels = []
    for label in os.listdir(path):
        label_path = os.path.join(path, label)
        for file_name in os.listdir(label_path):
            file_path = os.path.join(label_path, file_name)
            with open(file_path, 'r', encoding='utf-8') as f:
                text = f.read()
            texts.append(text)
            labels.append(label)
    return texts, labels

# 分词
def cut_words(texts):
    cut_texts = []
    for text in texts:
        cut_text = ' '.join(jieba.cut(text))
        cut_texts.append(cut_text)
    return cut_texts

# 构建词向量
def build_tfidf_vectorizer(texts):
    tfidf_vectorizer = TfidfVectorizer()
    tfidf_vectorizer.fit_transform(texts)
    return tfidf_vectorizer

# 计算相似度矩阵
def compute_similarity(tfidf_vectorizer, texts):
    tfidf_matrix = tfidf_vectorizer.transform(texts)
    similarity_matrix = tfidf_matrix * tfidf_matrix.T
    return similarity_matrix.toarray()

# 基于KNN的文本分类
def text_classification(train_texts, train_labels, test_texts, n_neighbors=5):
    # 分词
    train_cut_texts = cut_words(train_texts)
    test_cut_texts = cut_words(test_texts)
    # 构建词向量
    tfidf_vectorizer = build_tfidf_vectorizer(train_cut_texts)
    # 计算相似度矩阵
    similarity_matrix = compute_similarity(tfidf_vectorizer, train_cut_texts)
    # 构建KNN模型
    knn_model = KNeighborsClassifier(n_neighbors=n_neighbors, metric='precomputed')
    # 训练KNN模型
    knn_model.fit(similarity_matrix, train_labels)
    # 预测测试集标签
    test_similarity_matrix = compute_similarity(tfidf_vectorizer, test_cut_texts)
    predict_labels = knn_model.predict(test_similarity_matrix)
    return predict_labels

# 测试代码
if __name__ == '__main__':
    path = 'data'  # 数据集路径
    train_texts, train_labels = load_data(os.path.join(path, 'train'))
    test_texts, test_labels = load_data(os.path.join(path, 'test'))
    predict_labels = text_classification(train_texts, train_labels, test_texts)
    print(predict_labels)  # 输出预测的标签

需要注意的是，该代码中使用的是基于文件夹的数据集格式，即每个文件夹代表一个类别，文件夹中包含若干个文本文件。如果您的数据集格式不同，需要根据实际情况进行修改。