K-Nearest Neighbors

Implement a simple K-Nearest Neighbors classifier from scratch.

Given training data as a list of (features, label) tuples, a query point, and k, return the most common label among the k nearest training points using Euclidean distance.

If there is a tie, return the label that appears first among the nearest neighbors (by distance, then by insertion order).

Example:

train = [([0, 0], "A"), ([1, 1], "A"), ([5, 5], "B"), ([6, 6], "B")]
knn_classify(train, [1, 0], k=3) → "A"