Stacked Predictions

Build the meta-feature matrix used to train the second-level model in stacking. predictions is a list with one prediction vector per base model, each of length n_samples.

Implement solve(predictions).

Returns. Return a NumPy array of shape (n_samples, n_models) where column $jj$ holds the predictions of base model $jj$.

Examples

Example 1

Input:

solve([[1.0, 2.0], [3.0, 4.0]])

Output:

[[1.0, 3.0], [2.0, 4.0]]

Example 2

Input:

solve([[0.1, 0.9, 0.5], [0.2, 0.8, 0.4], [0.0, 1.0, 0.6]])

Output:

[[0.1, 0.2, 0.0], [0.9, 0.8, 1.0], [0.5, 0.4, 0.6]]