双十一汽车相关识别选购

import pandas as pd
from sklearn.feature_extraction.text import TfidfVectorizer
from sklearn.metrics.pairwise import linear_kernel

# 假设我们有一个包含车型信息和用户偏好的数据集
data = {
    'Car_Model': ['Model S', 'Model X', 'Model 3', 'Model Y'],
    'Description': [
        '豪华电动车，高性能',
        '大型SUV，家庭友好',
        '经济实惠，日常出行',
        '紧凑型SUV，灵活多变'
    ]
}

df = pd.DataFrame(data)

# 使用TF-IDF向量化文本描述
tfidf = TfidfVectorizer(stop_words='english')
df['Description'] = df['Description'].fillna('')
tfidf_matrix = tfidf.fit_transform(df['Description'])

# 计算相似度矩阵
cosine_sim = linear_kernel(tfidf_matrix, tfidf_matrix)

# 推荐函数
def get_recommendations(title, cosine_sim=cosine_sim):
    idx = df.index[df['Car_Model'] == title].tolist()[0]
    sim_scores = list(enumerate(cosine_sim[idx]))
    sim_scores = sorted(sim_scores, key=lambda x: x[1], reverse=True)
    sim_scores = sim_scores[1:3]  # 获取最相似的两个车型
    car_indices = [i[0] for i in sim_scores]
    return df['Car_Model'].iloc[car_indices]

# 示例调用
print(get_recommendations('Model S'))