在Python中可视化文本数据集中最常用的单词

import re
from collections import Counter
import matplotlib.pyplot as plt

# 文本数据
text = "This is a sample text. It contains some words that will be visualized."

# 数据预处理
text = re.sub(r'[^\w\s]', '', text)  # 去除标点符号
text = text.lower()  # 转换为小写字母

# 单词统计
words = text.split()
word_counts = Counter(words)

# 可视化
top_n = 10  # 只展示出现频率最高的前10个单词
top_words = dict(word_counts.most_common(top_n))

plt.bar(top_words.keys(), top_words.values())
plt.xlabel('Words')
plt.ylabel('Frequency')
plt.title('Top {} Most Common Words'.format(top_n))
plt.show()