Top-K Recommendations

Problem

Rank unseen items for a user.

scores is a list of predicted scores per item and rated lists the item indices the user has already rated. Return the k unseen item indices with the highest scores, breaking ties by smaller index, as a list.

Hint

Filter out rated items first, then sort by descending score.

Test cases

case 1

in: [[0.1,0.9,0.5,0.7],[0],2]

expected: [1,3]

case 2

in: [[1,2,3],[],3]

expected: [2,1,0]

case 3

in: [[1,2],[0,1],2]

expected: []

case 4

in: [[5,5,5],[],2]

expected: [0,1]

Starter codePython

def top_k_items(scores, rated, k):
    # Your code here
    pass

4 test cases · run your code against them in the editor