如何在python中对大数据集(csv文件)中的单个列运行TF-IDF？

import pandas as pd
from sklearn.feature_extraction.text import TfidfVectorizer

data = pd.read_csv('your_file.csv')
column_data = data['column_name']

# 示例：使用NLTK库进行停用词移除
from nltk.corpus import stopwords
stop_words = set(stopwords.words('english'))

processed_data = column_data.apply(lambda x: ' '.join([word for word in x.split() if word.lower() not in stop_words]))

vectorizer = TfidfVectorizer()
tfidf_matrix = vectorizer.fit_transform(processed_data)

feature_names = vectorizer.get_feature_names()
tfidf_values = tfidf_matrix.toarray()

doc_index = 0
for word_index, word in enumerate(feature_names):
    tfidf_value = tfidf_values[doc_index][word_index]
    print(f"Word: {word}, TF-IDF: {tfidf_value}")