Python:统计单词和过滤出现频率最低的单词的最快方法

import re
import heapq

def find_least_frequent_words(text, k):
    # 使用正则表达式将文本拆分为单词列表
    words = re.findall(r'\w+', text.lower())
    
    # 使用字典统计每个单词的出现次数
    word_count = {}
    for word in words:
        if word in word_count:
            word_count[word] += 1
        else:
            word_count[word] = 1
    
    # 使用堆找到出现频率最低的k个单词
    least_frequent_words = heapq.nsmallest(k, word_count, key=word_count.get)
    
    return least_frequent_words

# 测试示例
text = "This is a sample text. This text contains some repeated words. This is a sample."
k = 2
result = find_least_frequent_words(text, k)
print(result)

['repeated', 'contains']