智能识别推荐

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标题和描述的DataFrame
movies_df = pd.DataFrame({
    'title': ['Movie A', 'Movie B', 'Movie C'],
    'description': ['A thrilling adventure.', 'A romantic comedy.', 'An action-packed blockbuster.']
})

# 使用TF-IDF向量化电影描述
tfidf = TfidfVectorizer(stop_words='english')
movies_df['description'] = movies_df['description'].fillna('')
tfidf_matrix = tfidf.fit_transform(movies_df['description'])

# 计算电影之间的相似度
cosine_sim = linear_kernel(tfidf_matrix, tfidf_matrix)

# 推荐函数
def get_recommendations(title, cosine_sim=cosine_sim):
    idx = movies_df.index[movies_df['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]  # 获取最相似的两个电影（排除自身）
    movie_indices = [i[0] for i in sim_scores]
    return movies_df['title'].iloc[movie_indices]

# 使用示例
print(get_recommendations('Movie A'))