分词与评价 任务1、利用Jieba对CDIAL-BIAS-race文件进行分词，并抽取词表。 任务2、利用上述词表，编写一个正向最大匹配分词程序。 任务3、编写一个评价程序，以结巴分词结果为标准答案，计算最大匹配分词结果的准确率、召回率、F测度。

任务1代码：

import jieba

# 读取CDIAL-BIAS-race数据集
with open("CDIAL-BIAS-race.txt", "r", encoding="utf-8") as f:
    text = f.read()

# 使用结巴分词进行分词，并抽取词表
seg_list = jieba.cut(text)
word_set = set(seg_list)

# 将词表写入文件
with open("CDIAL-BIAS-race-vocab.txt", "w", encoding="utf-8") as f:
    f.write("\n".join(word_set))

任务2代码：

# 读取CDIAL-BIAS-race数据集和词表
with open("CDIAL-BIAS-race.txt", "r", encoding="utf-8") as f:
    text = f.read()
with open("CDIAL-BIAS-race-vocab.txt", "r", encoding="utf-8") as f:
    word_set = set(line.strip() for line in f)

# 实现正向最大匹配分词算法
def max_match(text, word_set):
    seg_list = []
    while text:
        for i in range(len(text), 0, -1):
            if text[:i] in word_set:
                seg_list.append(text[:i])
                text = text[i:]
                break
        else:
            seg_list.append(text[0])
            text = text[1:]
    return seg_list

# 对CDIAL-BIAS-race数据集进行分词
seg_list = max_match(text, word_set)

# 将分词结果写入文件
with open("CDIAL-BIAS-race-seg-maxmatch.txt", "w", encoding="utf-8") as f:
    f.write(" ".join(seg_list))

任务3代码：

# 读取结巴分词结果和自己实现的正向最大匹配分词结果
with open("CDIAL-BIAS-race-seg.txt", "r", encoding="utf-8") as f:
    jieba_result = f.read().split()
with open("CDIAL-BIAS-race-seg-maxmatch.txt", "r", encoding="utf-8") as f:
    max_match_result = f.read().split()

# 计算准确率、召回率、F测度
tp = 0
fp = 0
fn = 0
for word in max_match_result:
    if word in jieba_result:
        tp += 1
    else:
        fp += 1
for word in jieba_result:
    if word not in max_match_result:
        fn += 1
precision = tp / (tp + fp)
recall = tp / (tp + fn)
f_measure = 2 * precision * recall / (precision + recall)

# 输出评价结果
print("准确率：", precision)
print("召回率：", recall)
print("F测度：", f_measure)