KNN Classification

Predict the class of a query point by a majority vote among its k nearest training rows (squared Euclidean distance). Distance ties are resolved in favour of the earlier training row, and a tied vote goes to the class that sorts first.

Implement solve(X, labels, q, k).

Returns. Return the winning class label, taken from labels.

Examples

Example 1

Input:

solve([[0.0], [1.0], [10.0], [11.0]], [0, 0, 1, 1], [0.5], 3)

Output:

0

Example 2

Input:

solve([[0.0], [2.0]], ['a', 'b'], [1.0], 2)

Output:

'a'