用python编写朴素贝叶斯中文文本分类器，训练集和数据集五五分，并输出精确率、召回率和f值

好的，我可以给你提供一个基于Python实现的朴素贝叶斯中文文本分类器的代码，你可以在此基础上进行训练和测试。

import os
import jieba
import random
from sklearn.naive_bayes import MultinomialNB
from sklearn.metrics import precision_score, recall_score, f1_score

# 加载停用词
def load_stopwords(filename):
    stopwords = set()
    with open(filename, 'r', encoding='utf-8') as f:
        for line in f:
            stopwords.add(line.strip())
    return stopwords

# 加载数据
def load_data(path):
    all_data = []
    for filename in os.listdir(path):
        label = filename.split('.')[0]
        with open(os.path.join(path, filename), 'r', encoding='utf-8') as f:
            content = f.read().strip()
        all_data.append((label, content))
    return all_data

# 分词
def cut_words(data, stopwords):
    all_words = []
    for label, content in data:
        words = [word for word in jieba.cut(content) if word not in stopwords]
        all_words.extend(words)
    return all_words

# 获取特征
def get_features(data, stopwords, feature_count):
    word_count = {}
    for label, content in data:
        words = [word for word in jieba.cut(content) if word not in stopwords]
        for word in words:
            if word not in word_count:
                word_count[word] = 0
            word_count[word] += 1
    word_count_list = sorted(word_count.items(), key=lambda x: x[1], reverse=True)
    features = [word for word, count in word_count_list[:feature_count]]
    return features

# 特征向量化
def vectorize(data, features, stopwords):
    vectors = []
    for label, content in data:
        words = [word for word in jieba.cut(content) if word not in stopwords]
        vector = [words.count(feature) for feature in features]
        vectors.append((label, vector))
    return vectors

# 训练模型
def train_model(train_data, features):
    X_train = [vector for label, vector in train_data]
    y_train = [label for label, vector in train_data]
    clf = MultinomialNB()
    clf.fit(X_train, y_train)
    return clf

# 测试模型
def test_model(test_data, clf):
    X_test = [vector for label, vector in test_data]
    y_test = [label for label, vector in test_data]
    y_pred = clf.predict(X_test)
    precision = precision_score(y_test, y_pred, average='macro')
    recall = recall_score(y_test, y_pred, average='macro')
    f1 = f1_score(y_test, y_pred, average='macro')
    return precision, recall, f1

if __name__ == '__main__':
    # 加载停用词
    stopwords = load_stopwords('stopwords.txt')

    # 加载数据，进行分词
    all_data = load_data('data')
    random.shuffle(all_data)
    train_data = all_data[:len(all_data) // 2]
    test_data = all_data[len(all_data) // 2:]
    all_words = cut_words(all_data, stopwords)

    # 获取特征
    features = get_features(train_data, stopwords, 5000)

    # 特征向量化
    train_vectors = vectorize(train_data, features, stopwords)
    test_vectors = vectorize(test_data, features, stopwords)

    # 训练模型
    clf = train_model(train_vectors, features)

    # 测试模型，输出精确率、召回率和f值
    precision, recall, f1 = test_model(test_vectors, clf)
    print('Precision:', precision)
    print('Recall:', recall)
    print('F1:', f1)

请注意，这是一个简单的中文文本分类器示例代码。如果要将其用于实际应用，还需要对其进行优化，比如使用更好的分词工具、增加特征数量、增加训练数据等等。