使用Python计算文本中的单词(甚至是倍数

import re
from collections import Counter

def count_words(text):
    # 使用正则表达式去除标点符号并分割文本为单词列表
    words = re.findall(r'\b\w+\b', text.lower())
    
    # 统计每个单词的出现次数
    word_counts = Counter(words)
    
    return word_counts

# 示例文本
text = "Python is a powerful programming language. Python is also easy to learn."

# 计算单词数量
word_counts = count_words(text)

# 输出结果
for word, count in word_counts.items():
    print(f"{word}: {count}")

import nltk
from nltk.stem import PorterStemmer, WordNetLemmatizer

nltk.download('punkt')
nltk.download('wordnet')

stemmer = PorterStemmer()
lemmatizer = WordNetLemmatizer()

def stem_words(words):
    return [stemmer.stem(word) for word in words]

def lemmatize_words(words):
    return [lemmatizer.lemmatize(word) for word in words]