import numpy as np
import pandas as pd
from scipy.sparse import csr_matrix
from sklearn.metrics.pairwise import cosine_similarity

# Build a sparse user × article matrix (1 = clicked, 0 = didn't)
matrix = csr_matrix((np.ones(len(clicks)), (user_rows, article_cols)),
                    shape=(n_users, n_articles))
def recommend(user_id, matrix, top_n=15, n_neighbors=50):
    """Find 50 most similar users and rank the articles
    they clicked that our user hasn't seen yet."""
    u = user_idx[user_id]
    
    # Cosine similarity between this user and everyone else
    sims = cosine_similarity(matrix[u], matrix).flatten()
    sims[u] = 0  # don't recommend to yourself
    
    # Take the top 50 most similar users
    top_neighbors = np.argsort(sims)[-n_neighbors:][::-1]
    weights = sims[top_neighbors]
    
    # Score articles by weighted sum of neighbour clicks
    scores = np.asarray(matrix[top_neighbors].T.dot(weights)).flatten()
    
    # Zero out articles the user already clicked
    scores[matrix[u].toarray().flatten() > 0] = 0
    
    # Return the top-scoring articles
    top_articles = np.argsort(scores)[-top_n:][::-1]
    return top_articles