写出基于TF-IDF+KNN对txt文件格式的中文文本进行分类的代码

以下是基于TF-IDF+KNN对txt文件格式的中文文本进行分类的代码示例：

import os
import jieba
from sklearn.feature_extraction.text import TfidfVectorizer
from sklearn.neighbors import KNeighborsClassifier

# 读取数据集
def load_dataset(path):
    dataset = []
    labels = []
    for root, dirs, files in os.walk(path):
        for file in files:
            label = root.split("/")[-1]
            labels.append(label)
            file_path = os.path.join(root, file)
            with open(file_path, 'r', encoding='utf-8') as f:
                content = f.read()
                dataset.append(content)
    return dataset, labels

# 中文分词
def chinese_word_cut(text):
    return " ".join(jieba.cut(text))

# 计算TF-IDF值
def tf_idf(dataset):
    vectorizer = TfidfVectorizer(tokenizer=chinese_word_cut, max_features=5000)
    X = vectorizer.fit_transform(dataset)
    return X.toarray(), vectorizer

# KNN分类
def knn_classifier(X_train, y_train, X_test, k=3):
    knn = KNeighborsClassifier(n_neighbors=k)
    knn.fit(X_train, y_train)
    y_predict = knn.predict(X_test)
    return y_predict

if __name__ == "__main__":
    dataset, labels = load_dataset("data")
    X, vectorizer = tf_idf(dataset)
    y = labels
    
    # 分割训练集和测试集
    split_index = int(len(dataset) * 0.7)
    X_train, y_train = X[:split_index], y[:split_index]
    X_test, y_test = X[split_index:], y[split_index:]
    
    # KNN分类
    y_predict = knn_classifier(X_train, y_train, X_test)
    print("KNN分类结果：", y_predict)

代码中使用了jieba分词库对中文文本进行分词，使用sklearn库中的TfidfVectorizer计算TF-IDF值，使用sklearn库中的KNeighborsClassifier进行KNN分类。在main函数中，首先调用load_dataset函数读取数据集，然后调用tf_idf函数计算TF-IDF值。接着将数据集分割为训练集和测试集，最后调用knn_classifier函数进行KNN分类，并输出分类结果。