Python词频统计宋词三百首

以下是Python词频统计宋词三百首的例子：

# 读取文件
with open('song.txt', 'r', encoding='utf-8') as f:
    text = f.read()

# 分词
import jieba
words = jieba.lcut(text)

# 去除停用词
stopwords = ['，', '。', '？', '！', '、', '：', '；', '「', '」', '『', '』', '（', '）', '—', '…', '·', '《', '》', '\n']
words_clean = []
for word in words:
    if word not in stopwords:
        words_clean.append(word)

# 统计词频
from collections import Counter
word_counts = Counter(words_clean)

# 获取前10个高频词
top_10 = word_counts.most_common(10)
print(top_10)