How can you implement a basic recommendation system in Python using collaborative filtering and content-based filtering to suggest items based on user preferences? Provide a simple code example demonstrating how to calculate similarity between users or items, generate recommendations, and handle new user data.

import numpy as np
from sklearn.metrics.pairwise import cosine_similarity

# Sample user-item interaction matrix (rows: users, cols: items)
ratings = np.array([
    [5, 3, 0, 1, 4],
    [4, 0, 0, 1, 2],
    [1, 1, 0, 5, 1],
    [1, 0, 0, 5, 4]
])

# Simulated item features (e.g., genre, category)
item_features = {
    0: ["action", "adventure"],
    1: ["drama", "romance"],
    2: ["comedy", "fantasy"],
    3: ["action", "sci-fi"],
    4: ["drama", "thriller"]
}

def get_user_similarity(user_id, ratings):
    """Calculate similarity between users using cosine similarity."""
    return cosine_similarity(ratings[user_id].reshape(1, -1), ratings)[0]

def get_item_similarity(item_id, ratings):
    """Calculate similarity between items."""
    return cosine_similarity(ratings.T[item_id].reshape(1, -1), ratings.T)[0]

def recommend_items(user_id, ratings, item_features):
    """Generate recommendations for a user."""
    # Collaborative filtering: find similar users
    similarities = get_user_similarity(user_id, ratings)
    similar_users = np.argsort(similarities)[-3:]  # Top 3 similar users
    
    # Get items liked by similar users but not by current user
    recommended_items = set()
    for u in similar_users:
        if u != user_id:
            for i in range(len(ratings[u])):
                if ratings[u][i] > 0 and ratings[user_id][i] == 0:
                    recommended_items.add(i)
    
    # Content-based filtering: recommend similar items
    user_likes = []
    for i in range(len(ratings[user_id])):
        if ratings[user_id][i] > 0:
            user_likes.extend(item_features[i])
    
    for item_id, features in item_features.items():
        if item_id not in recommended_items:
            common = len(set(user_likes) & set(features))
            if common > 0:
                recommended_items.add(item_id)
    
    return list(recommended_items)

# Example usage
print("Recommendations for user 0:", recommend_items(0, ratings, item_features))

#AI #RecommendationSystem #CollaborativeFiltering #ContentBasedFiltering #MachineLearning #Python #BeginnerAI #UserPreferences #SimpleAlgorithm #BasicML

By: @DataScienceQ 🚀