根据单词索引更改搜索顺序

from sklearn.feature_extraction.text import TfidfVectorizer
from sklearn.metrics.pairwise import cosine_similarity

# 示例文档
documents = [
    "This is the first document.",
    "This document is the second document.",
    "And this is the third one.",
    "Is this the first document?"
]

# 创建TF-IDF向量化器
vectorizer = TfidfVectorizer()

# 计算TF-IDF矩阵
tfidf_matrix = vectorizer.fit_transform(documents)

# 示例查询
query = "first document"

# 将查询转换为TF-IDF向量
query_vector = vectorizer.transform([query])

# 计算查询与文档的相似度
similarity_scores = cosine_similarity(query_vector, tfidf_matrix).flatten()

# 根据相似度排序文档
sorted_indices = similarity_scores.argsort()[::-1]

# 输出排序后的文档
for idx in sorted_indices:
    print(f"Document {idx + 1}: {documents[idx]}")