K-Fold Splits (Index-Based)

Split the indices $0,\dots ,n-10,\backslash dots,n-1$ into k consecutive, near-equal validation folds and return, for each fold, the sorted training indices (all others) and the validation indices. No labels are given, so the split is index-based and does not stratify.

Implement solve(n, k).

Returns. Return a list of k tuples (train_indices, validation_indices) of NumPy arrays in fold order. The first $nkn\backslash bmod\; k$ folds are one element larger (np.array_split).

Examples

Example 1

Input:

solve(5, 3)

Output:

[([2, 3, 4], [0, 1]), ([0, 1, 4], [2, 3]), ([0, 1, 2, 3], [4])]

Example 2

Input:

solve(4, 2)

Output:

[([2, 3], [0, 1]), ([0, 1], [2, 3])]