双12实时音视频推荐

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视频信息和用户观看记录的数据集
data = {
    'video_id': [1, 2, 3],
    'title': ['Video A', 'Video B', 'Video C'],
    'description': ['Description A', 'Description B', 'Description C']
}
df = pd.DataFrame(data)

# 用户观看记录
user_history = ['Video A', 'Video B']

# 使用TF-IDF向量化视频描述
tfidf = TfidfVectorizer(stop_words='english')
df['description'] = df['description'].fillna('')
tfidf_matrix = tfidf.fit_transform(df['description'])

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

# 推荐函数
def get_recommendations(title, cosine_sim=cosine_sim):
    idx = df.index[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]  # 获取最相似的两个视频
    video_indices = [i[0] for i in sim_scores]
    return df['title'].iloc[video_indices]

# 获取推荐
recommendations = get_recommendations('Video A')
print(recommendations)