微瓴视图推荐

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电影信息的DataFrame
movies = pd.DataFrame({
    'title': ['Movie A', 'Movie B', 'Movie C'],
    'description': ['Action-packed adventure', 'Heartwarming romance', 'Sci-fi thriller']
})

# 使用TF-IDF向量化描述
tfidf = TfidfVectorizer(stop_words='english')
movies['description'] = movies['description'].fillna('')
tfidf_matrix = tfidf.fit_transform(movies['description'])

# 计算余弦相似度
cosine_sim = linear_kernel(tfidf_matrix, tfidf_matrix)

def get_recommendations(title, cosine_sim=cosine_sim):
    idx = movies.index[movies['title'] == 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
    movie_indices = [i[0] for i in sim_scores]
    return movies['title'].iloc[movie_indices]

print(get_recommendations('Movie A'))