class Video: def __init__(self, video_id, title, views, likes, shares, watch_time): self.video_id = video_id self.title = title self.views = views self.likes = likes self.shares = shares self.watch_time = watch_time # average watch time in seconds def calculate_score(self): # Weighted sum of engagement metrics score = (0.1 * self.views) + (1 * self.likes) + (1.5 * self.shares) + (0.05 * self.watch_time) return score class User: def __init__(self, user_id, interests): self.user_id = user_id self.interests = interests # list of interest keywords class RecommendationSystem: def __init__(self, videos, users): self.videos = videos self.users = users def recommend(self, user): scored_videos = [] for video in self.videos: score = video.calculate_score() # Check if any interest keyword matches the video title interest_match = any(keyword.lower() in video.title.lower() for keyword in user.interests) if interest_match: scored_videos.append((score, video.title)) # Sort by score descending scored_videos.sort(reverse=True, key=lambda x: x[0]) # Return top 3 recommendations return [title for score, title in scored_videos[:3]] # Sample data videos = [ Video(1, "Amazing dance video", 1000, 150, 20, 180), Video(2, "Funny cat compilation", 1500, 300, 50, 200), Video(3, "Learn Python coding", 500, 200, 30, 240), Video(4, "Motivational speech", 800, 100, 10, 300), ] users = [ User(1, ["dance", "funny", "coding"]), User(2, ["motivational", "speech"]), ] rec_sys = RecommendationSystem(videos, users) # Get recommendations for user 1 recommendations_user_1 = rec_sys.recommend(users[0]) print(recommendations_user_1) # Output: ['Funny cat compilation', 'Learn Python coding', 'Amazing dance video'] #❤️Love You ज़िंदगी ❤️ #🥰Express Emotion #🚀SC बूस्ट के साथ Views को सुपरचार्ज करें #👫चैटरूम चिटचैट✨ #🎁चैटरूम: अर्न & लर्न🤑