直接看结果：

代码：

import re
from collections import defaultdict
import random
import matplotlib.pyplot as plt
import numpy as np

import pandas as pd
import numpy as np
import re
from sklearn.feature_extraction.text import CountVectorizer
from nltk.corpus import stopwords
from nltk.tokenize import word_tokenize
import matplotlib.pyplot as plt
import seaborn as sns
def STM(text):

    cleaned_text = re.sub(r'\W+', ' ', text)
    cleaned_text = re.sub(r'\d+', '', cleaned_text)


    tokens = cleaned_text.lower().split()


    stop_words = {'the', 'is', 'in', 'and', 'to', 'of', 'a', 'with&