用python编写贝叶斯中文文本分类器，训练集和测试集五五分，并输出精确率、召回率和f值

好的，下面是一个简单的贝叶斯中文文本分类器的代码，并计算精确率、召回率和f值：

import os
import jieba
import math

# 停用词文件路径
stop_words_file = 'stop_words.txt'

# 计算先验概率
def calc_prior_prob(train_path):
    num_docs = 0
    class_word_count = {}
    class_doc_count = {}

    # 遍历训练集
    for root, dirs, files in os.walk(train_path):
        for file in files:
            num_docs += 1
            class_name = os.path.basename(root)
            if class_name not in class_word_count:
                class_word_count[class_name] = {}
                class_doc_count[class_name] = 0

            # 统计词频
            with open(os.path.join(root, file), 'r', encoding='utf-8') as f:
                for line in f:
                    words = jieba.cut(line.strip())
                    for word in words:
                        # 去停用词
                        if word in stop_words:
                            continue
                        if word not in class_word_count[class_name]:
                            class_word_count[class_name][word] = 1
                        else:
                            class_word_count[class_name][word] += 1
            class_doc_count[class_name] += 1

    # 计算每个类别的先验概率
    prior_prob = {}
    for class_name in class_doc_count:
        prior_prob[class_name] = class_doc_count[class_name] / num_docs

    return class_word_count, prior_prob

# 计算条件概率
def calc_conditional_prob(class_word_count):
    conditional_prob = {}
    for class_name in class_word_count:
        conditional_prob[class_name] = {}
        total_words = sum(class_word_count[class_name].values())
        for word in class_word_count[class_name]:
            conditional_prob[class_name][word] = (class_word_count[class_name][word] + 1) / (total_words + len(vocab))
    return conditional_prob

# 文本分类
def classify(test_path, class_word_count, prior_prob, conditional_prob):
    correct = 0
    total = 0
    TP = 0
    FP = 0
    FN = 0

    # 遍历测试集
    for root, dirs, files in os.walk(test_path):
        for file in files:
            total += 1
            class_name = os.path.basename(root)
            scores = {}
            # 统计词频
            with open(os.path.join(root, file), 'r', encoding='utf-8') as f:
                for line in f:
                    words = jieba.cut(line.strip())
                    for word in words:
                        # 去停用词
                        if word in stop_words:
                            continue
                        for c in class_word_count:
                            if word not in scores[c]:
                                scores[c][word] = 0
                            scores[c][word] += math.log(conditional_prob[c][word])

            # 计算每个类别的得分
            for c in class_word_count:
                scores[c] = math.log(prior_prob[c]) + sum(scores[c].values())

            # 取得分最大的类别
            predict_class = max(scores, key=scores.get)

            # 计算精确率、召回率和f值
            if predict_class == class_name:
                correct += 1
                TP += 1
            else:
                FP += 1
                FN += 1

    precision = TP / (TP + FP)
    recall = TP / (TP + FN)
    f1_score = 2 * precision * recall / (precision + recall)

    print('Precision:', precision)
    print('Recall:', recall)
    print('F1 score:', f1_score)

# 加载停用词
stop_words = set()
with open(stop_words_file, 'r', encoding='utf-8') as f:
    for line in f:
        stop_words.add(line.strip())

# 训练集和测试集路径
train_path = 'train'
test_path = 'test'

# 统计词汇表
vocab = set()
for root, dirs, files in os.walk(train_path):
    for file in files:
        with open(os.path.join(root, file), 'r', encoding='utf-8') as f:
            for line in f:
                words = jieba.cut(line.strip())
                for word in words:
                    # 去停用词
                    if word in stop_words:
                        continue
                    vocab.add(word)

# 计算先验概率
class_word_count, prior_prob = calc_prior_prob(train_path)

# 计算条件概率
conditional_prob = calc_conditional_prob(class_word_count)

# 文本分类
classify(test_path, class_word_count, prior_prob, conditional_prob)

其中，假设训练集和测试集的路径分别为 `train` 和 `test`。`calc_prior_prob` 函数用于计算先验概率，`calc_conditional_prob` 函数用于计算条件概率，`classify` 函数用于进行文本分类，并计算精确率、召回率和f值。

注意，由于中文文本的特殊性，我们需要使用中文分词工具 `jieba` 进行分词。同时，为了提高分类器的性能，我们还需要使用停用词表进行去停用词处理。

以上代码可能还需要进行一些细节的调整，但是基本的思路应该是可以参考的。