Open the context
Choose the project folder and name the files or behavior involved.
Workflows
Coding workflows · Machine-learning data splits
03
A concrete starting point
Split machine-learning data by the entity that could leak across sets. Keep each group on one side and fit preprocessing on training data before applying it to held-out rows.
Define the change
Describe the input, expected output and boundaries that must stay intact.
Inspect the work
Review the proposed edits and any commands before relying on their result.
Check the outcome
Compare actual behavior with the expected result. If a check fails, investigate it before applying more changes.
Machine-learning data splits
A concrete starting point
train_groups, test_groups = split_groups(group_ids)
assert not set(train_groups) & set(test_groups)
train = rows_in_groups(data, train_groups)
test = rows_in_groups(data, test_groups)The example is a starting point for a real project, not a claim that generated code is already tested. Adjust paths, dependencies and expected behavior to match your application.