11.11视频点播推荐

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的DataFrame
data = {
    'title': ['Video A', 'Video B', 'Video C'],
    'description': ['This is a comedy.', 'A thrilling adventure.', 'An educational video.']
}
df = pd.DataFrame(data)

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

# 计算余弦相似度
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
    video_indices = [i[0] for i in sim_scores]
    return df['title'].iloc[video_indices]

# 示例调用
print(get_recommendations('Video A'))