التقسيم والإتاحة وحدود تسرب المعلومات

rows = [{"id":"a", "prediction_time":1, "label_available":3},
        {"id":"b", "prediction_time":2, "label_available":4},
        {"id":"c", "prediction_time":4, "label_available":6},
        {"id":"d", "prediction_time":5, "label_available":7}]
cutoff = 5
train = [r["id"] for r in rows if r["label_available"] < cutoff]
future = [r["id"] for r in rows if r["prediction_time"] >= cutoff]
excluded = [r["id"] for r in rows if r["id"] not in train + future]
print("train", train)
print("future cohort", future)
print("boundary exclusion", excluded)

train ['a', 'b']
future cohort ['d']
boundary exclusion ['c']

يستخدم حد التدريب الصارم إتاحة الوسم، بينما يستخدم مجتمع التقييم المستقبلي وقت التنبؤ؛ ولا يمكن حساب درجته إلا بعد نضج وسومه.

train = [{"id":"a1", "group":"x"}, {"id":"b1", "group":"y"}]
evaluation = [{"id":"a2", "group":"x"}, {"id":"c1", "group":"z"}]
train_groups = {r["group"] for r in train}
evaluation_groups = {r["group"] for r in evaluation}
overlap = sorted(train_groups & evaluation_groups)
print("shared groups", overlap)
print("valid for declared unseen-group task", not overlap)

shared groups ['x']
valid for declared unseen-group task False

لا يمنع اختلاف معرّفات الصفوف تداخل المجموعات؛ ويكشف هذا الفحص مخالفة واحدة لعقد تقييم معلن لمجموعات لم تر في التدريب.