import re
import matplotlib.pyplot as plt
from collections import Counter
word_counts = {}
with open('E:\自然语言处理\Hamlet(2).txt') as f:
    for line in f:
        words = line.strip().lower().split()
        for word in words:
            word = re.sub(r'[^a-zA-Z]+','',word)
            if word in word_counts:
                word_counts[word] += 1
            else:
                word_counts[word] = 1
top_words = Counter(word_counts).most_common(10)
top_words_list = [word[0] for word in top_words]
top_words_counts = [word[1] for word in top_words]
plt.bar(top_words_list, top_words_counts)
plt.xlabel('单词')
plt.ylabel('出现次数')
plt.title('前10个出现次数最多的单词')
plt.xticks(rotation=45)
plt.rcParams['font.sans-serif'] = ['SimHei']  # 指定使用中文字体
for i, count in enumerate(top_words_counts):
    plt.text(i, count, str(count), ha='center', va='bottom')
plt.show()
print(word_counts)

我们假设我们获取了一个哈姆雷特文本，要进行每个单词的统计