Deterministic Train/Test Split

Problem

Split the ordered indices 0..n-1 into train and test sets without shuffling.

n_test = int(n * test_fraction) (floor) indices go to the test set at the end, and the rest go to train. Return [train_indices, test_indices] in ascending order.

Hint

Compute the test size with int(), then slice the index range.

Test cases

case 1

in: [10,0.2]

expected: [[0,1,2,3,4,5,6,7],[8,9]]

case 2

in: [5,0.5]

expected: [[0,1,2],[3,4]]

case 3

in: [7,0.3]

expected: [[0,1,2,3,4],[5,6]]

case 4

in: [4,0]

expected: [[0,1,2,3],[]]

Starter codePython

def train_test_split_ordered(n, test_fraction):
    # Returns [train_indices, test_indices]
    # Your code here
    pass

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