如何在Jupyter Notebook中绘制假新闻中最常见的30个单词的柱状图

import pandas as pd
import matplotlib.pyplot as plt
import nltk
from nltk.corpus import stopwords
from collections import Counter

df = pd.read_csv('fake_news.csv')  # 假设假新闻数据保存在fake_news.csv文件中

# 将文本转换为小写
df['text'] = df['text'].str.lower()

# 分词
df['text'] = df['text'].apply(nltk.word_tokenize)

# 去除停用词
stop_words = set(stopwords.words('english'))
df['text'] = df['text'].apply(lambda x: [word for word in x if word not in stop_words])

# 统计词频
word_freq = Counter([word for text in df['text'] for word in text])

# 获取最常见的30个单词及其频率
top_words = word_freq.most_common(30)

# 提取单词和频率
words = [word[0] for word in top_words]
freqs = [word[1] for word in top_words]

# 创建柱状图
plt.figure(figsize=(12, 6))
plt.bar(words, freqs)
plt.xlabel('Words')
plt.ylabel('Frequency')
plt.title('Top 30 Words in Fake News')
plt.xticks(rotation=90)
plt.show()