Deriva — Derive the Algorithm

← Projectsmetrics-lab / L2Precision, Recall, F1~12 min

one move: preserve an invariant

Report more than accuracy: compute precision, recall, F1, and confusion counts for a binary classifier. In the Metrics Lab system, implement this level as a deterministic contract before composing it with the next service.

Required API

def classification_report(y_true, y_pred, positive=1):
    return {'accuracy': ..., 'precision': ..., 'recall': ..., 'f1': ..., 'confusion': ...}

Behavior

count true and false positives and negatives
guard zero denominators
return rounded ratios with the confusion matrix

Examples — tap to reveal

Constraints

Use only the Python standard library.
Return deterministic values so every run can be compared with the contract.
Do not mutate caller-owned inputs.

Opening…