如何在Python中统计数据帧中每个句子中特定单词的出现次数

import pandas as pd
import nltk
from nltk.tokenize import word_tokenize
from nltk.corpus import stopwords

data = {'句子': ['这是一个示例句子。', '这个句子包含特定单词。', '句子中的单词需要被统计。']}
df = pd.DataFrame(data)

def count_word_occurrences(sentence, word):
    tokens = word_tokenize(sentence)  # 将句子分词
    tokens = [token.lower() for token in tokens if token.isalpha()]  # 去除标点符号和数字，并转为小写
    tokens = [token for token in tokens if token not in stopwords.words('english')]  # 去除停用词
    return tokens.count(word)  # 统计特定单词的出现次数

word = '特定'  # 要统计的特定单词
df['特定单词出现次数'] = df['句子'].apply(lambda x: count_word_occurrences(x, word))