feat(batching): unit 粒度切分——pair 整锁 + 单元级分桶 + 非 AR 独立 rng
build_batches 改以 QuestionUnit 为原子调度单元：孪生对 2 题整锁进同一 batch、 按单元级正确性（双向 AND）落 correct/error 桶，不再因 P 对 Q 错被劈或被 FFD 拆箱。 - 非 AR（single）用 random.Random(seed) 复现旧逐题算法确切 draw 序列，AR（pair） 用 _rng_ns(seed,"AR") SHA-256 派生独立流；二者 draw 流互不干扰，故 AR 折叠不改变 非 AR 抽样/洗牌序列——纯非 AR 输入 build_batches 结果与引入 QuestionUnit 前逐字节一致。 - FFD 容量按 unit.size（pair 占 2），round-robin 遇碎片新开 bin 兜底而非报错。 - _select_mixed_by_task_type 分流各跑一次后合并，大类洗牌按 kind 拆分各用对应 rng。 新增黄金测试 test_batching_pair_lock.py 覆盖三条铁律（同 batch / 单元分桶 / 非 AR byte-identical + draw 流独立）；既有 batching 测试全绿。
This commit is contained in:
+214
-103
@@ -1,13 +1,37 @@
|
||||
"""混合 mini-batch 切分：大类打散、小类整锁，供 runner 每 step 处理一个 batch。"""
|
||||
"""混合 mini-batch 切分：以 QuestionUnit 为最小调度粒度，大类打散、小类整锁。
|
||||
|
||||
供 runner 每 step 处理一个 batch。孪生对（AR pair）作为 2 题单元整锁不拆、按单元级
|
||||
正确性分桶；非 AR single 单元的抽样/洗牌 draw 流与"引入 QuestionUnit 前"的旧逐题算法
|
||||
逐字节一致（AR 折叠不干扰非 AR draw 流）。
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import hashlib
|
||||
import math
|
||||
import random
|
||||
from typing import TYPE_CHECKING
|
||||
|
||||
from app.harness.question_units import build_units, flatten_units, unit_correctness
|
||||
|
||||
if TYPE_CHECKING:
|
||||
from core.types import GeneratedQuestion
|
||||
from core.types import GeneratedQuestion, QuestionUnit
|
||||
|
||||
|
||||
def _rng_ns(seed: int, ns: str) -> random.Random:
|
||||
"""由 (seed, 命名空间) 稳定派生独立随机数发生器。
|
||||
|
||||
用 SHA-256 派生而非 Python 内置 ``hash()``——后者受 hash randomization 影响，
|
||||
跨进程不可复现。不同命名空间的 draw 流互不干扰，使 AR 单元折叠不扰动非 AR 抽样。
|
||||
|
||||
参数:
|
||||
seed: 实验随机种子。
|
||||
ns: 命名空间标签（如 "AR"）。
|
||||
返回:
|
||||
以 SHA-256(f"{ns}:{seed}") 前 8 字节为种子的 ``random.Random``。
|
||||
"""
|
||||
digest = hashlib.sha256(f"{ns}:{seed}".encode()).digest()
|
||||
return random.Random(int.from_bytes(digest[:8], "big"))
|
||||
|
||||
|
||||
def build_batches(
|
||||
@@ -18,55 +42,59 @@ def build_batches(
|
||||
seed: int,
|
||||
correct_ratio: float = 0.0,
|
||||
) -> tuple[list[list[GeneratedQuestion]], int]:
|
||||
"""把诊断池里的题目切成多个混合 mini-batch。
|
||||
"""把诊断池里的题目切成多个混合 mini-batch（以 QuestionUnit 为原子调度单元）。
|
||||
|
||||
当 ``correct_ratio > 0`` 时，按题型为每组错题配比一定数量的正确题，使 batch
|
||||
包含正误混合样本（"动量"机制）；``correct_ratio <= 0`` 时退化为纯错题模式。
|
||||
single 题为 1 题单元，AR pair 孪生对为 2 题单元；同一 pair 的两题整锁进同一 batch，
|
||||
按单元级正确性（双向 AND）分桶。当 ``correct_ratio > 0`` 时，按题型为每组错误单元配比
|
||||
一定数量的正确单元（"动量"机制）；``correct_ratio <= 0`` 时退化为纯错误单元模式。
|
||||
|
||||
参数:
|
||||
items: 候选题目全集。
|
||||
items: 候选题目全集（可混含 single 与孪生对成员）。
|
||||
correctness: question_id -> 基线是否答对。
|
||||
batch_size: 单个 batch 的样本数上限（> 0）。
|
||||
min_class_per_batch: 小类判定阈值——题目数 ≤ 此值的题型整组锁进单一
|
||||
batch_size: 单个 batch 的题目数上限（> 0，pair 占 2）。
|
||||
min_class_per_batch: 小类判定阈值——单元题目总数 ≤ 此值的题型整组锁进单一
|
||||
batch（> 0）。
|
||||
seed: 随机种子，保证相同输入产出完全一致的切分。
|
||||
correct_ratio: 正确题占比（0.0 ~ 1.0）。0.0 = 纯错题；0.5 = 错题:正确题 = 1:1。
|
||||
correct_ratio: 正确题占比（0.0 ~ 1.0）。0.0 = 纯错误单元；0.5 = 错:正 = 1:1。
|
||||
返回:
|
||||
(非空 mini-batch 列表, selected_count)；无错题时返回 ([], 0)。
|
||||
selected_count 是所有 batch 中题目总数。
|
||||
(非空 mini-batch 列表, selected_count)；无错误单元时返回 ([], 0)。
|
||||
selected_count 是所有 batch 中题目（展开后）总数。
|
||||
异常:
|
||||
ValueError: batch_size 或 min_class_per_batch < 1, 或
|
||||
min_class_per_batch >= batch_size（破坏小类整组装箱不超容的前提）。
|
||||
关键实现细节:
|
||||
装箱顺序为「先小类后大类」。小类整组用 first-fit-decreasing 装箱：按组大小
|
||||
降序处理（同大小再按 task_type 排序保证确定性），每组放进第一个剩余容量足够
|
||||
的 batch；若现有 batch 都装不下就新开一个空 batch——因小类组大小
|
||||
≤ min_class_per_batch < batch_size，新空 batch 必能容纳，故小类装箱永不抛
|
||||
ValueError，且保证整组不拆。再把大类样本（seed 确定性 shuffle 后）round-robin
|
||||
分发到所有现存 batch 填充剩余容量。这样小类聚集于单 batch、大类散布多 batch
|
||||
且与小类共箱，自然产生多类混合 batch（纯类切片会被 multiclass 断言拒绝）。
|
||||
nb = ceil(总题数/batch_size) 是初始 batch 数下界估计而非硬上限：小类装箱可能
|
||||
新开 bin 使实际 batch 数超过 nb。每次新开 bin 都意味着总容量随之增加，故总容量
|
||||
恒 ≥ 总题数，大类 round-robin 跳过满箱后仍能放下全部样本，不会违反 batch_size
|
||||
上限。题型按名称排序处理以保证跨运行确定性，不依赖 dict 遍历顺序。
|
||||
非 AR（single）与 AR（pair）各用独立稳定派生的 rng：非 AR 用 ``random.Random(seed)``
|
||||
（复现旧逐题算法的确切 draw 序列，保证纯非 AR 输入逐字节一致），AR 用
|
||||
``_rng_ns(seed, "AR")``；二者 draw 流互不干扰，故加入/移除 pair 不改变非 AR 的
|
||||
抽样/洗牌序列。抽样在合并前按流分别进行（``_select_mixed_by_task_type`` 各跑一次），
|
||||
大类洗牌按单元 kind 拆分后各用对应流。装箱顺序「先小类后大类」：小类整组
|
||||
first-fit-decreasing（容量按单元 ``size`` 计，pair 占 2）装入首个容得下的 batch，
|
||||
装不下新开 bin；大类洗牌后 round-robin 分发，遇碎片（size-2 单元放不进任一现存
|
||||
batch 的剩余容量）新开 bin 兜底而非报错。最终每个 batch 展开回题目列表。
|
||||
题型按名称排序处理以保证跨运行确定性。
|
||||
"""
|
||||
_validate_params(batch_size, min_class_per_batch)
|
||||
|
||||
rng = random.Random(seed)
|
||||
grouped = _select_mixed_by_task_type(items, correctness, correct_ratio, rng)
|
||||
total = sum(len(g) for g in grouped.values())
|
||||
# 非 AR 复现旧版 random.Random(seed) 的确切序列以满足黄金 byte-identity；
|
||||
# AR 走独立命名空间派生流，二者互不干扰。
|
||||
rng_nonar = random.Random(seed)
|
||||
rng_ar = _rng_ns(seed, "AR")
|
||||
|
||||
grouped = _group_units_by_task_type(items, correctness, correct_ratio, rng_nonar, rng_ar)
|
||||
|
||||
total = sum(_group_load(g) for g in grouped.values())
|
||||
if total == 0:
|
||||
return [], 0
|
||||
|
||||
nb = max(1, math.ceil(total / batch_size))
|
||||
batches: list[list[GeneratedQuestion]] = [[] for _ in range(nb)]
|
||||
batches: list[list[QuestionUnit]] = [[] for _ in range(nb)]
|
||||
|
||||
small, large = _split_by_size(grouped, min_class_per_batch)
|
||||
for group in _small_groups_decreasing(small):
|
||||
_pack_small_class(batches, group, batch_size)
|
||||
_distribute_large_classes(batches, large, batch_size, rng)
|
||||
_distribute_large_classes(batches, large, batch_size, rng_nonar, rng_ar)
|
||||
|
||||
result = [b for b in batches if b]
|
||||
result = [flatten_units(b) for b in batches if b]
|
||||
selected_count = sum(len(b) for b in result)
|
||||
return result, selected_count
|
||||
|
||||
@@ -74,7 +102,7 @@ def build_batches(
|
||||
def _validate_params(batch_size: int, min_class_per_batch: int) -> None:
|
||||
"""校验切分参数，非法值直接报错而非用默认值掩盖。
|
||||
|
||||
除各自 >= 1 外，强制 min_class_per_batch < batch_size：小类组大小 ≤
|
||||
除各自 >= 1 外，强制 min_class_per_batch < batch_size：小类组题目总数 ≤
|
||||
min_class_per_batch，唯有此前提成立才能保证小类整组放入单一 batch 而不超容；否则
|
||||
_pack_small_class 新开的 bin 会装入超 batch_size 的整组，静默违反容量合约。此约束
|
||||
与 config._validate_minibatch 一致，是 build_batches 对自身前提的防御性自校验（P5）。
|
||||
@@ -91,52 +119,129 @@ def _validate_params(batch_size: int, min_class_per_batch: int) -> None:
|
||||
)
|
||||
|
||||
|
||||
def _split_by_size(
|
||||
grouped: dict[str, list[GeneratedQuestion]],
|
||||
min_class_per_batch: int,
|
||||
) -> tuple[dict[str, list[GeneratedQuestion]], dict[str, list[GeneratedQuestion]]]:
|
||||
"""按错题数把题型分为小类（≤ 阈值）与大类（> 阈值）两组。"""
|
||||
small = {t: g for t, g in grouped.items() if len(g) <= min_class_per_batch}
|
||||
large = {t: g for t, g in grouped.items() if len(g) > min_class_per_batch}
|
||||
return small, large
|
||||
|
||||
|
||||
def _select_mixed_by_task_type(
|
||||
def _group_units_by_task_type(
|
||||
items: list[GeneratedQuestion],
|
||||
correctness: dict[str, bool],
|
||||
correct_ratio: float,
|
||||
rng: random.Random,
|
||||
) -> dict[str, list[GeneratedQuestion]]:
|
||||
"""按题型分组，为每组错题按比例采样正确题混入。
|
||||
|
||||
只对有错题的题型做混合——无错题的题型不进 batch，即使有正确题。
|
||||
``correct_ratio <= 0`` 时退化为纯错题模式（向后兼容）。
|
||||
rng_nonar: random.Random,
|
||||
rng_ar: random.Random,
|
||||
) -> dict[str, list[QuestionUnit]]:
|
||||
"""把题目聚合为单元并按题型分组：非 AR 与 AR 各走独立 draw 流后合并。
|
||||
|
||||
参数:
|
||||
items: 候选题目全集。
|
||||
correctness: question_id -> 基线是否答对。
|
||||
correct_ratio: 正确题占比（0.0 ~ 1.0）。
|
||||
rng: 随机数发生器，用于采样正确题。
|
||||
correct_ratio: 正确题占比。
|
||||
rng_nonar: 非 AR（single 单元）抽样用 rng。
|
||||
rng_ar: AR（pair 单元）抽样用 rng。
|
||||
返回:
|
||||
task_type -> 该题型的混合题目列表（错题全部 + 按比例采样的正确题）。
|
||||
task_type -> 混合后的单元列表（single 单元在前、pair 单元在后）。
|
||||
"""
|
||||
errors_by_type: dict[str, list[GeneratedQuestion]] = {}
|
||||
correct_by_type: dict[str, list[GeneratedQuestion]] = {}
|
||||
for q in items:
|
||||
qid = q.question_id
|
||||
if correctness.get(qid) is False:
|
||||
errors_by_type.setdefault(q.task_type, []).append(q)
|
||||
elif correctness.get(qid, False):
|
||||
correct_by_type.setdefault(q.task_type, []).append(q)
|
||||
units = build_units(items)
|
||||
singles = [u for u in units if u.kind == "single"]
|
||||
pairs = [u for u in units if u.kind == "pair"]
|
||||
grouped_nonar = _select_mixed_by_task_type(singles, correctness, correct_ratio, rng_nonar)
|
||||
grouped_ar = _select_mixed_by_task_type(pairs, correctness, correct_ratio, rng_ar)
|
||||
return _merge_grouped(grouped_nonar, grouped_ar)
|
||||
|
||||
|
||||
def _group_load(group: list[QuestionUnit]) -> int:
|
||||
"""一组单元展开后的题目总数（single 计 1，pair 计 2），即占用的 batch 容量。"""
|
||||
return sum(u.size for u in group)
|
||||
|
||||
|
||||
def _batch_load(batch: list[QuestionUnit]) -> int:
|
||||
"""一个 batch 内单元展开后的题目总数，用于容量判断。"""
|
||||
return sum(u.size for u in batch)
|
||||
|
||||
|
||||
def _merge_grouped(
|
||||
grouped_nonar: dict[str, list[QuestionUnit]],
|
||||
grouped_ar: dict[str, list[QuestionUnit]],
|
||||
) -> dict[str, list[QuestionUnit]]:
|
||||
"""按 task_type 合并非 AR 与 AR 两条流的分组（single 在前、pair 在后）。
|
||||
|
||||
参数:
|
||||
grouped_nonar: 非 AR（single 单元）分组。
|
||||
grouped_ar: AR（pair 单元）分组。
|
||||
返回:
|
||||
task_type -> 合并后的单元列表；每类 single 单元在前、pair 单元在后，顺序稳定。
|
||||
"""
|
||||
merged: dict[str, list[QuestionUnit]] = {}
|
||||
for task_type in sorted({*grouped_nonar, *grouped_ar}):
|
||||
merged[task_type] = grouped_nonar.get(task_type, []) + grouped_ar.get(task_type, [])
|
||||
return merged
|
||||
|
||||
|
||||
def _split_by_size(
|
||||
grouped: dict[str, list[QuestionUnit]],
|
||||
min_class_per_batch: int,
|
||||
) -> tuple[dict[str, list[QuestionUnit]], dict[str, list[QuestionUnit]]]:
|
||||
"""按题目总数（单元展开）把题型分为小类（≤ 阈值）与大类（> 阈值）两组。"""
|
||||
small = {t: g for t, g in grouped.items() if _group_load(g) <= min_class_per_batch}
|
||||
large = {t: g for t, g in grouped.items() if _group_load(g) > min_class_per_batch}
|
||||
return small, large
|
||||
|
||||
|
||||
def _classify_unit(unit: QuestionUnit, correctness: dict[str, bool]) -> str | None:
|
||||
"""判定单元落入哪个桶：error / correct / None（未知，跳过）。
|
||||
|
||||
参数:
|
||||
unit: 目标单元。
|
||||
correctness: question_id -> 是否答对（缺键视为未知）。
|
||||
返回:
|
||||
"error"（单元级正确性为 False）、"correct"（双向 AND 为 True）；单元内任一题
|
||||
未知（correctness 缺该键）返回 None，与旧逐题算法把未知题排除在错/对两桶之外
|
||||
的语义一致。
|
||||
关键实现:
|
||||
先探测是否有未知题（get 返回 None ⟺ 键缺失，因 correctness 值恒为 bool），
|
||||
全部已知后交由 unit_correctness 计双向 AND（此时 KeyError 不可达）。
|
||||
"""
|
||||
if any(correctness.get(q.question_id) is None for q in unit.questions):
|
||||
return None
|
||||
return "correct" if unit_correctness(unit, correctness) else "error"
|
||||
|
||||
|
||||
def _select_mixed_by_task_type(
|
||||
units: list[QuestionUnit],
|
||||
correctness: dict[str, bool],
|
||||
correct_ratio: float,
|
||||
rng: random.Random,
|
||||
) -> dict[str, list[QuestionUnit]]:
|
||||
"""按题型分组，为每组错误单元按比例采样正确单元混入（单元粒度）。
|
||||
|
||||
只对有错误单元的题型做混合——无错误单元的题型不进 batch，即使有正确单元。
|
||||
``correct_ratio <= 0`` 时退化为纯错误单元模式。本函数只处理单一 draw 流（全 single
|
||||
或全 pair），使非 AR 与 AR 的抽样互不干扰。
|
||||
|
||||
参数:
|
||||
units: 同一流的候选单元（全 single 或全 pair）。
|
||||
correctness: question_id -> 基线是否答对。
|
||||
correct_ratio: 正确题占比（0.0 ~ 1.0）。
|
||||
rng: 本流专用随机数发生器，用于采样正确单元。
|
||||
返回:
|
||||
task_type -> 该题型的混合单元列表（错误单元全部 + 按比例采样的正确单元）。
|
||||
关键实现:
|
||||
n_correct 按错误单元「题目总数」而非单元数计，与旧逐题语义对齐（纯 single 时
|
||||
单元数 == 题目数，采样序列逐字节一致）。
|
||||
"""
|
||||
errors_by_type: dict[str, list[QuestionUnit]] = {}
|
||||
correct_by_type: dict[str, list[QuestionUnit]] = {}
|
||||
for unit in units:
|
||||
bucket = _classify_unit(unit, correctness)
|
||||
if bucket == "error":
|
||||
errors_by_type.setdefault(unit.task_type, []).append(unit)
|
||||
elif bucket == "correct":
|
||||
correct_by_type.setdefault(unit.task_type, []).append(unit)
|
||||
|
||||
if correct_ratio <= 0:
|
||||
return errors_by_type
|
||||
|
||||
# 为每个有错题的 task_type 混入正确题
|
||||
grouped: dict[str, list[GeneratedQuestion]] = {}
|
||||
grouped: dict[str, list[QuestionUnit]] = {}
|
||||
for task_type in sorted(errors_by_type):
|
||||
errs = errors_by_type[task_type]
|
||||
n_correct = round(len(errs) * correct_ratio / (1 - correct_ratio))
|
||||
n_err = _group_load(errs)
|
||||
n_correct = round(n_err * correct_ratio / (1 - correct_ratio))
|
||||
available = correct_by_type.get(task_type, [])
|
||||
sampled = (
|
||||
list(available) if len(available) <= n_correct else rng.sample(available, n_correct)
|
||||
@@ -147,94 +252,100 @@ def _select_mixed_by_task_type(
|
||||
|
||||
|
||||
def _small_groups_decreasing(
|
||||
small: dict[str, list[GeneratedQuestion]],
|
||||
) -> list[list[GeneratedQuestion]]:
|
||||
"""按组大小降序、同大小按 task_type 升序排出小类组（first-fit-decreasing 顺序）。
|
||||
small: dict[str, list[QuestionUnit]],
|
||||
) -> list[list[QuestionUnit]]:
|
||||
"""按组题目总数降序、同大小按 task_type 升序排出小类组（first-fit-decreasing 顺序）。
|
||||
|
||||
参数:
|
||||
small: task_type -> 小类错题列表。
|
||||
small: task_type -> 小类单元列表。
|
||||
返回:
|
||||
排好序的小类组列表；降序处理可降低碎片，确定性 tie-break 保证跨运行一致。
|
||||
"""
|
||||
return [small[t] for t in sorted(small, key=lambda t: (-len(small[t]), t))]
|
||||
return [small[t] for t in sorted(small, key=lambda t: (-_group_load(small[t]), t))]
|
||||
|
||||
|
||||
def _pack_small_class(
|
||||
batches: list[list[GeneratedQuestion]],
|
||||
group: list[GeneratedQuestion],
|
||||
batches: list[list[QuestionUnit]],
|
||||
group: list[QuestionUnit],
|
||||
batch_size: int,
|
||||
) -> None:
|
||||
"""用 first-fit 把一个小类整组放入首个容得下的 batch，装不下则新开 bin（就地修改）。
|
||||
|
||||
因小类组大小 ≤ min_class_per_batch < batch_size，新开的空 batch 必能容纳整组，
|
||||
故此函数永不抛 ValueError，且整组不拆。
|
||||
因小类组题目总数 ≤ min_class_per_batch < batch_size，新开的空 batch 必能容纳整组，
|
||||
故此函数永不抛 ValueError，且整组（含内部 pair 单元）不拆。
|
||||
|
||||
参数:
|
||||
batches: 当前各 batch（就地追加，必要时 append 新空 batch）。
|
||||
group: 待锁定的小类错题（整组不拆）。
|
||||
batch_size: 单 batch 容量上限。
|
||||
group: 待锁定的小类单元组（整组不拆）。
|
||||
batch_size: 单 batch 题目容量上限。
|
||||
"""
|
||||
load = _group_load(group)
|
||||
for b in batches:
|
||||
if len(b) + len(group) <= batch_size:
|
||||
if _batch_load(b) + load <= batch_size:
|
||||
b.extend(group)
|
||||
return
|
||||
batches.append(list(group))
|
||||
|
||||
|
||||
def _distribute_large_classes(
|
||||
batches: list[list[GeneratedQuestion]],
|
||||
large: dict[str, list[GeneratedQuestion]],
|
||||
batches: list[list[QuestionUnit]],
|
||||
large: dict[str, list[QuestionUnit]],
|
||||
batch_size: int,
|
||||
rng: random.Random,
|
||||
rng_nonar: random.Random,
|
||||
rng_ar: random.Random,
|
||||
) -> None:
|
||||
"""将各大类样本 shuffle 后 round-robin 分发到所有现存 batch（就地修改）。
|
||||
"""将各大类单元洗牌后 round-robin 分发到所有现存 batch（就地修改）。
|
||||
|
||||
参数:
|
||||
batches: 当前各 batch（含小类装箱可能新开的 bin，就地追加）。
|
||||
large: task_type -> 大类错题列表。
|
||||
batch_size: 单 batch 容量上限。
|
||||
rng: 复用的随机数发生器，保证 shuffle 确定性。
|
||||
异常:
|
||||
ValueError: 所有 batch 均满仍有样本未放置（总容量估算异常，合法输入不可达）。
|
||||
large: task_type -> 大类单元列表。
|
||||
batch_size: 单 batch 题目容量上限。
|
||||
rng_nonar: 非 AR（single 单元）洗牌用 rng。
|
||||
rng_ar: AR（pair 单元）洗牌用 rng。
|
||||
关键实现细节:
|
||||
轮转范围是「所有现存 batch」而非固定 nb 个——小类装箱新开的 bin 也参与分发。
|
||||
总容量 = 现存 batch 数 × batch_size，每次新开 bin 都同步抬高总容量，故总容量恒
|
||||
≥ 总错题数，防御性 ValueError 在合法输入下不可达。全局指针在所有大类样本间持续
|
||||
轮转（不为每类重置），满箱即跳过，使大类充分散布并与已锁定的小类共箱。题型按名称
|
||||
排序以保证分发顺序确定。
|
||||
每组按单元 kind 拆成 single 子列与 pair 子列，分别用 rng_nonar / rng_ar 洗牌后
|
||||
拼接（single 在前），使非 AR 洗牌 draw 流不受 pair 存在与否影响（纯 single 时
|
||||
single 子列即整组，复现旧版单一 rng.shuffle 的序列）。全局指针在所有大类单元间
|
||||
持续轮转，遇满箱跳过、遇碎片新开 bin。题型按名称排序以保证分发顺序确定。
|
||||
"""
|
||||
nb = len(batches)
|
||||
pointer = 0
|
||||
for task_type in sorted(large):
|
||||
group = list(large[task_type])
|
||||
rng.shuffle(group)
|
||||
for q in group:
|
||||
pointer = _place_round_robin(batches, q, pointer, batch_size, nb)
|
||||
group = large[task_type]
|
||||
singles = [u for u in group if u.kind == "single"]
|
||||
pairs = [u for u in group if u.kind == "pair"]
|
||||
rng_nonar.shuffle(singles)
|
||||
rng_ar.shuffle(pairs)
|
||||
for unit in singles + pairs:
|
||||
pointer = _place_round_robin(batches, unit, pointer, batch_size)
|
||||
|
||||
|
||||
def _place_round_robin(
|
||||
batches: list[list[GeneratedQuestion]],
|
||||
q: GeneratedQuestion,
|
||||
batches: list[list[QuestionUnit]],
|
||||
unit: QuestionUnit,
|
||||
pointer: int,
|
||||
batch_size: int,
|
||||
nb: int,
|
||||
) -> int:
|
||||
"""从 pointer 起找第一个未满 batch 放入 q，返回下一次起始指针。
|
||||
"""从 pointer 起找第一个容量够放 unit 的 batch 放入，返回下一次起始指针。
|
||||
|
||||
参数:
|
||||
batches: 当前各 batch（就地追加）。
|
||||
q: 待放置的样本。
|
||||
unit: 待放置的单元（占用 unit.size 个容量）。
|
||||
pointer: 本次轮转起始 batch 下标。
|
||||
batch_size: 单 batch 容量上限。
|
||||
nb: batch 总数。
|
||||
batch_size: 单 batch 题目容量上限。
|
||||
返回:
|
||||
下一次轮转的起始指针（已前移一位）。
|
||||
异常:
|
||||
ValueError: 扫描一轮所有 batch 均满（总容量估算异常）。
|
||||
关键实现:
|
||||
单个单元容量 ≤ batch_size 是前提（pair 占 2，而 batch_size > min_class ≥ 1 ⇒
|
||||
batch_size ≥ 2），故此处断言防御。扫描一轮所有现存 batch 都放不下（size-2 单元
|
||||
遇满地碎片）时新开 bin 兜底而非报错——聚合容量足够但单箱剩余不足是合法碎片场景。
|
||||
纯 single（size 1）永不触发新开分支，故与旧逐题 round-robin 逐字节一致。
|
||||
"""
|
||||
assert unit.size <= batch_size, f"单元 size={unit.size} 超过 batch_size={batch_size}"
|
||||
nb = len(batches)
|
||||
for offset in range(nb):
|
||||
idx = (pointer + offset) % nb
|
||||
if len(batches[idx]) < batch_size:
|
||||
batches[idx].append(q)
|
||||
if _batch_load(batches[idx]) + unit.size <= batch_size:
|
||||
batches[idx].append(unit)
|
||||
return (idx + 1) % nb
|
||||
raise ValueError("所有 batch 均满仍有样本待放置, 总容量估算异常")
|
||||
batches.append([unit])
|
||||
return len(batches) % len(batches)
|
||||
|
||||
@@ -0,0 +1,304 @@
|
||||
"""app/harness/batching.py 的 unit 粒度切分测试（Task 5）。
|
||||
|
||||
覆盖 pair 契约在 mini-batch 构建中的三条铁律：
|
||||
- (a) 同 pair_id 两题整锁进同一 batch（像小类整组不拆）；
|
||||
- (b) pair 按 unit correctness（双向 AND）落 correct/error 桶，不因 P 对 Q 错被劈；
|
||||
- (c) 非 AR byte-identical：AR unit 折叠不改变非 AR 的 rng.sample/shuffle 抽样序列——
|
||||
纯非 AR 输入下 build_batches 结果与"引入 QuestionUnit 前"的旧算法逐字节一致。
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import math
|
||||
import random
|
||||
|
||||
from app.harness.batching import build_batches
|
||||
from core.types import GeneratedQuestion
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# 辅助构造
|
||||
# ---------------------------------------------------------------------------
|
||||
|
||||
|
||||
def _make_single(
|
||||
qid: str,
|
||||
task_type: str = "default",
|
||||
video_id: str = "v1",
|
||||
) -> GeneratedQuestion:
|
||||
"""构造最小 single GeneratedQuestion。"""
|
||||
return GeneratedQuestion(
|
||||
question_id=qid,
|
||||
video_id=video_id,
|
||||
task_type=task_type,
|
||||
question=f"question_{qid}",
|
||||
options=("A. a", "B. b", "C. c", "D. d"),
|
||||
answer="A",
|
||||
source_nodes=("n1",),
|
||||
difficulty="medium",
|
||||
question_role="single",
|
||||
)
|
||||
|
||||
|
||||
def _make_pair(
|
||||
pair_id: str,
|
||||
task_type: str = "AR",
|
||||
video_id: str = "v1",
|
||||
) -> tuple[GeneratedQuestion, GeneratedQuestion]:
|
||||
"""构造一个孪生对（original + mirror），共享 pair_id / flip_axis。"""
|
||||
common = {
|
||||
"video_id": video_id,
|
||||
"task_type": task_type,
|
||||
"question": "?",
|
||||
"options": ("A. a", "B. b", "C. c", "D. d"),
|
||||
"answer": "A",
|
||||
"source_nodes": ("n1",),
|
||||
"difficulty": "medium",
|
||||
"pair_id": pair_id,
|
||||
"flip_axis": "before_after",
|
||||
}
|
||||
original = GeneratedQuestion(
|
||||
question_id=f"{pair_id}_o", question_role="pair_original", **common
|
||||
)
|
||||
mirror = GeneratedQuestion(question_id=f"{pair_id}_m", question_role="pair_mirror", **common)
|
||||
return original, mirror
|
||||
|
||||
|
||||
def _batch_of(batches: list[list[GeneratedQuestion]], qid: str) -> int:
|
||||
"""返回 qid 所在 batch 的下标；不存在返回 -1。"""
|
||||
for i, b in enumerate(batches):
|
||||
if any(q.question_id == qid for q in b):
|
||||
return i
|
||||
return -1
|
||||
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# (a) 同 pair_id 两题落同一 batch（整锁不拆）
|
||||
# ---------------------------------------------------------------------------
|
||||
|
||||
|
||||
class TestPairStaysInSameBatch:
|
||||
"""孪生对两题必须整锁进同一 batch，无论散布在多少 single 之间。"""
|
||||
|
||||
def test_single_pair_same_batch(self) -> None:
|
||||
po, pm = _make_pair("pairA", task_type="AR")
|
||||
singles = [_make_single(f"s{i}", task_type="RETRIEVAL") for i in range(10)]
|
||||
items = [*singles, po, pm]
|
||||
correctness = {q.question_id: False for q in items}
|
||||
batches, count = build_batches(
|
||||
items, correctness, batch_size=4, min_class_per_batch=2, seed=3
|
||||
)
|
||||
assert count == 12
|
||||
idx_o = _batch_of(batches, "pairA_o")
|
||||
idx_m = _batch_of(batches, "pairA_m")
|
||||
assert idx_o != -1 and idx_o == idx_m
|
||||
|
||||
def test_many_pairs_each_intact(self) -> None:
|
||||
items: list[GeneratedQuestion] = []
|
||||
for k in range(5):
|
||||
po, pm = _make_pair(f"p{k}", task_type="AR")
|
||||
items.extend([po, pm])
|
||||
items.extend(_make_single(f"s{i}", task_type="SPATIAL") for i in range(6))
|
||||
correctness = {q.question_id: False for q in items}
|
||||
batches, _ = build_batches(items, correctness, batch_size=6, min_class_per_batch=2, seed=11)
|
||||
for k in range(5):
|
||||
idx_o = _batch_of(batches, f"p{k}_o")
|
||||
idx_m = _batch_of(batches, f"p{k}_m")
|
||||
assert idx_o != -1 and idx_o == idx_m, f"pair p{k} 被拆到不同 batch"
|
||||
# 每个 batch 容量不超限（pair 占 2）
|
||||
for b in batches:
|
||||
assert len(b) <= 6
|
||||
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# (b) pair 按 unit correctness（双向 AND）分桶
|
||||
# ---------------------------------------------------------------------------
|
||||
|
||||
|
||||
class TestPairBucketedByUnitCorrectness:
|
||||
"""P 对 Q 错的 pair 是 error 单元，不因单题分歧被劈到两个桶。"""
|
||||
|
||||
def test_p_correct_q_wrong_pair_is_error_unit(self) -> None:
|
||||
po, pm = _make_pair("pairErr", task_type="AR")
|
||||
# 混一个 single 错题避免空池边界
|
||||
s0 = _make_single("s0", task_type="AR")
|
||||
items = [po, pm, s0]
|
||||
# original 对、mirror 错 → 单元级 AND = 错 → 应作为 error 单元整体进 batch
|
||||
correctness = {"pairErr_o": True, "pairErr_m": False, "s0": False}
|
||||
batches, count = build_batches(
|
||||
items, correctness, batch_size=6, min_class_per_batch=2, seed=0, correct_ratio=0.0
|
||||
)
|
||||
idx_o = _batch_of(batches, "pairErr_o")
|
||||
idx_m = _batch_of(batches, "pairErr_m")
|
||||
# 两题都在（未被"P 对"劈掉）且同 batch
|
||||
assert idx_o != -1 and idx_o == idx_m
|
||||
# 纯错题模式下 pair 单元整体被选入
|
||||
assert count == 3
|
||||
|
||||
def test_both_correct_pair_excluded_in_pure_error_mode(self) -> None:
|
||||
po, pm = _make_pair("pairOk", task_type="AR")
|
||||
s_err = _make_single("s_err", task_type="AR")
|
||||
items = [po, pm, s_err]
|
||||
correctness = {"pairOk_o": True, "pairOk_m": True, "s_err": False}
|
||||
batches, count = build_batches(
|
||||
items, correctness, batch_size=6, min_class_per_batch=2, seed=0, correct_ratio=0.0
|
||||
)
|
||||
# both-correct pair 是 correct 单元，纯错题模式下不入池
|
||||
assert count == 1
|
||||
assert _batch_of(batches, "pairOk_o") == -1
|
||||
assert _batch_of(batches, "pairOk_m") == -1
|
||||
assert _batch_of(batches, "s_err") != -1
|
||||
|
||||
def test_both_correct_pair_stays_intact_when_mixed(self) -> None:
|
||||
"""correct_ratio>0 时 both-correct pair 可作为整体 correct 单元混入。"""
|
||||
errs = [_make_single(f"e{i}", task_type="AR") for i in range(4)]
|
||||
po, pm = _make_pair("pairOk", task_type="AR")
|
||||
items = [*errs, po, pm]
|
||||
correctness = {f"e{i}": False for i in range(4)}
|
||||
correctness["pairOk_o"] = True
|
||||
correctness["pairOk_m"] = True
|
||||
batches, _ = build_batches(
|
||||
items, correctness, batch_size=10, min_class_per_batch=2, seed=1, correct_ratio=0.5
|
||||
)
|
||||
idx_o = _batch_of(batches, "pairOk_o")
|
||||
idx_m = _batch_of(batches, "pairOk_m")
|
||||
# 若被混入，两题必须整体同 batch；若未被采样，两题都不在
|
||||
if idx_o == -1:
|
||||
assert idx_m == -1
|
||||
else:
|
||||
assert idx_o == idx_m
|
||||
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# (c) 非 AR byte-identical：与"引入 QuestionUnit 前"旧算法逐字节一致
|
||||
# ---------------------------------------------------------------------------
|
||||
|
||||
|
||||
def _reference_select_mixed(
|
||||
items: list[GeneratedQuestion],
|
||||
correctness: dict[str, bool],
|
||||
correct_ratio: float,
|
||||
rng: random.Random,
|
||||
) -> dict[str, list[GeneratedQuestion]]:
|
||||
"""旧版 _select_mixed_by_task_type 的忠实副本（逐题、单一 rng）。"""
|
||||
errors_by_type: dict[str, list[GeneratedQuestion]] = {}
|
||||
correct_by_type: dict[str, list[GeneratedQuestion]] = {}
|
||||
for q in items:
|
||||
qid = q.question_id
|
||||
if correctness.get(qid) is False:
|
||||
errors_by_type.setdefault(q.task_type, []).append(q)
|
||||
elif correctness.get(qid, False):
|
||||
correct_by_type.setdefault(q.task_type, []).append(q)
|
||||
if correct_ratio <= 0:
|
||||
return errors_by_type
|
||||
grouped: dict[str, list[GeneratedQuestion]] = {}
|
||||
for task_type in sorted(errors_by_type):
|
||||
errs = errors_by_type[task_type]
|
||||
n_correct = round(len(errs) * correct_ratio / (1 - correct_ratio))
|
||||
available = correct_by_type.get(task_type, [])
|
||||
sampled = (
|
||||
list(available) if len(available) <= n_correct else rng.sample(available, n_correct)
|
||||
)
|
||||
grouped[task_type] = errs + sampled
|
||||
return grouped
|
||||
|
||||
|
||||
def _reference_build_batches(
|
||||
items: list[GeneratedQuestion],
|
||||
correctness: dict[str, bool],
|
||||
batch_size: int,
|
||||
min_class_per_batch: int,
|
||||
seed: int,
|
||||
correct_ratio: float = 0.0,
|
||||
) -> tuple[list[list[GeneratedQuestion]], int]:
|
||||
"""引入 QuestionUnit 前的旧版 build_batches 的忠实副本（逐题、单一 rng）。"""
|
||||
rng = random.Random(seed)
|
||||
grouped = _reference_select_mixed(items, correctness, correct_ratio, rng)
|
||||
total = sum(len(g) for g in grouped.values())
|
||||
if total == 0:
|
||||
return [], 0
|
||||
nb = max(1, math.ceil(total / batch_size))
|
||||
batches: list[list[GeneratedQuestion]] = [[] for _ in range(nb)]
|
||||
small = {t: g for t, g in grouped.items() if len(g) <= min_class_per_batch}
|
||||
large = {t: g for t, g in grouped.items() if len(g) > min_class_per_batch}
|
||||
for t in sorted(small, key=lambda t: (-len(small[t]), t)):
|
||||
group = small[t]
|
||||
placed = False
|
||||
for b in batches:
|
||||
if len(b) + len(group) <= batch_size:
|
||||
b.extend(group)
|
||||
placed = True
|
||||
break
|
||||
if not placed:
|
||||
batches.append(list(group))
|
||||
nb_live = len(batches)
|
||||
pointer = 0
|
||||
for task_type in sorted(large):
|
||||
group = list(large[task_type])
|
||||
rng.shuffle(group)
|
||||
for q in group:
|
||||
for offset in range(nb_live):
|
||||
idx = (pointer + offset) % nb_live
|
||||
if len(batches[idx]) < batch_size:
|
||||
batches[idx].append(q)
|
||||
pointer = (idx + 1) % nb_live
|
||||
break
|
||||
result = [b for b in batches if b]
|
||||
return result, sum(len(b) for b in result)
|
||||
|
||||
|
||||
class TestNonARByteIdentical:
|
||||
"""纯 single 输入下 build_batches 与旧逐题算法逐字节一致（黄金对照）。"""
|
||||
|
||||
def _assert_identical(
|
||||
self,
|
||||
items: list[GeneratedQuestion],
|
||||
correctness: dict[str, bool],
|
||||
batch_size: int,
|
||||
min_class_per_batch: int,
|
||||
seed: int,
|
||||
correct_ratio: float,
|
||||
) -> None:
|
||||
got_batches, got_count = build_batches(
|
||||
items, correctness, batch_size, min_class_per_batch, seed, correct_ratio
|
||||
)
|
||||
ref_batches, ref_count = _reference_build_batches(
|
||||
items, correctness, batch_size, min_class_per_batch, seed, correct_ratio
|
||||
)
|
||||
got_ids = [[q.question_id for q in b] for b in got_batches]
|
||||
ref_ids = [[q.question_id for q in b] for b in ref_batches]
|
||||
assert got_ids == ref_ids
|
||||
assert got_count == ref_count
|
||||
|
||||
def test_pure_errors_identical(self) -> None:
|
||||
items = [_make_single(f"q{i}", task_type=f"type_{i % 3}") for i in range(20)]
|
||||
correctness = {f"q{i}": False for i in range(20)}
|
||||
self._assert_identical(items, correctness, 5, 2, 42, 0.0)
|
||||
|
||||
def test_mixed_ratio_identical(self) -> None:
|
||||
items = [_make_single(f"q{i}", task_type=f"type_{i % 4}") for i in range(40)]
|
||||
correctness = {f"q{i}": (i % 3 == 0) for i in range(40)}
|
||||
self._assert_identical(items, correctness, 8, 3, 7, 0.5)
|
||||
|
||||
def test_large_round_robin_identical(self) -> None:
|
||||
items = [_make_single(f"q{i}", task_type="big") for i in range(30)]
|
||||
correctness = {f"q{i}": False for i in range(30)}
|
||||
self._assert_identical(items, correctness, 6, 2, 99, 0.0)
|
||||
|
||||
def test_ar_folding_does_not_shift_nonar_draws(self) -> None:
|
||||
"""加入 AR pair 不改变非 AR single 的抽样序列（draw 流独立）。"""
|
||||
singles = [_make_single(f"q{i}", task_type=f"type_{i % 3}") for i in range(24)]
|
||||
s_correctness = {f"q{i}": (i % 4 == 0) for i in range(24)}
|
||||
base, _ = build_batches(singles, s_correctness, 6, 2, 5, 0.5)
|
||||
base_ids = {q.question_id for b in base for q in b}
|
||||
|
||||
# 追加若干 AR pair（不同 task_type），非 AR single 的入选集合应不变
|
||||
items = list(singles)
|
||||
correctness = dict(s_correctness)
|
||||
for k in range(3):
|
||||
po, pm = _make_pair(f"p{k}", task_type="AR")
|
||||
items.extend([po, pm])
|
||||
correctness[po.question_id] = False
|
||||
correctness[pm.question_id] = False
|
||||
with_ar, _ = build_batches(items, correctness, 6, 2, 5, 0.5)
|
||||
with_ar_single_ids = {q.question_id for b in with_ar for q in b if q.pair_id is None}
|
||||
assert with_ar_single_ids == base_ids
|
||||
@@ -7,22 +7,23 @@ correctness False vs None 精确匹配。
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import pytest
|
||||
|
||||
from core.types import GeneratedQuestion
|
||||
from app.harness.batching import (
|
||||
build_batches,
|
||||
_validate_params,
|
||||
_select_mixed_by_task_type,
|
||||
)
|
||||
|
||||
import random
|
||||
|
||||
import pytest
|
||||
|
||||
from app.harness.batching import (
|
||||
_select_mixed_by_task_type,
|
||||
_validate_params,
|
||||
build_batches,
|
||||
)
|
||||
from app.harness.question_units import build_units
|
||||
from core.types import GeneratedQuestion
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# 辅助构造
|
||||
# ---------------------------------------------------------------------------
|
||||
|
||||
|
||||
def _make_q(
|
||||
qid: str,
|
||||
task_type: str = "default",
|
||||
@@ -45,6 +46,7 @@ def _make_q(
|
||||
# test_build_batches_deterministic
|
||||
# ---------------------------------------------------------------------------
|
||||
|
||||
|
||||
class TestBuildBatchesDeterministic:
|
||||
"""相同输入 + 相同 seed 产出完全一致的切分。"""
|
||||
|
||||
@@ -73,6 +75,7 @@ class TestBuildBatchesDeterministic:
|
||||
# test_small_class_not_split
|
||||
# ---------------------------------------------------------------------------
|
||||
|
||||
|
||||
class TestSmallClassNotSplit:
|
||||
"""小类（≤ min_class_per_batch）整组不拆，锁在同一 batch。"""
|
||||
|
||||
@@ -90,10 +93,7 @@ class TestSmallClassNotSplit:
|
||||
)
|
||||
assert count == 10
|
||||
# 找到包含 small_type 的 batch
|
||||
small_batch = [
|
||||
b for b in batches
|
||||
if any(q.task_type == "small_type" for q in b)
|
||||
]
|
||||
small_batch = [b for b in batches if any(q.task_type == "small_type" for q in b)]
|
||||
assert len(small_batch) == 1 # 整组在同一个 batch
|
||||
small_ids = {q.question_id for q in small_batch[0] if q.task_type == "small_type"}
|
||||
assert small_ids == {"s1", "s2"}
|
||||
@@ -103,6 +103,7 @@ class TestSmallClassNotSplit:
|
||||
# test_large_class_round_robin
|
||||
# ---------------------------------------------------------------------------
|
||||
|
||||
|
||||
class TestLargeClassRoundRobin:
|
||||
"""大类样本 round-robin 散布到多个 batch，不集中于单一 batch。"""
|
||||
|
||||
@@ -124,6 +125,7 @@ class TestLargeClassRoundRobin:
|
||||
# test_correct_ratio_mixing
|
||||
# ---------------------------------------------------------------------------
|
||||
|
||||
|
||||
class TestCorrectRatioMixing:
|
||||
"""correct_ratio > 0 时混入正确题。"""
|
||||
|
||||
@@ -137,7 +139,11 @@ class TestCorrectRatioMixing:
|
||||
]
|
||||
correctness = {"e1": False, "e2": False, "c1": True, "c2": True, "c3": True}
|
||||
batches, count = build_batches(
|
||||
items, correctness, batch_size=10, min_class_per_batch=2, seed=0,
|
||||
items,
|
||||
correctness,
|
||||
batch_size=10,
|
||||
min_class_per_batch=2,
|
||||
seed=0,
|
||||
correct_ratio=0.5,
|
||||
)
|
||||
# correct_ratio=0.5 → 错:正 = 1:1 → 2 错 + 2 正 = 4 题
|
||||
@@ -155,7 +161,11 @@ class TestCorrectRatioMixing:
|
||||
]
|
||||
correctness = {"e1": False, "c1": True}
|
||||
batches, count = build_batches(
|
||||
items, correctness, batch_size=10, min_class_per_batch=2, seed=0,
|
||||
items,
|
||||
correctness,
|
||||
batch_size=10,
|
||||
min_class_per_batch=2,
|
||||
seed=0,
|
||||
correct_ratio=0.0,
|
||||
)
|
||||
assert count == 1
|
||||
@@ -166,6 +176,7 @@ class TestCorrectRatioMixing:
|
||||
# test_no_wrong_answers_empty
|
||||
# ---------------------------------------------------------------------------
|
||||
|
||||
|
||||
class TestNoWrongAnswersEmpty:
|
||||
"""无错题时返回空列表。"""
|
||||
|
||||
@@ -173,14 +184,22 @@ class TestNoWrongAnswersEmpty:
|
||||
items = [_make_q(f"q{i}") for i in range(5)]
|
||||
correctness = {f"q{i}": True for i in range(5)}
|
||||
batches, count = build_batches(
|
||||
items, correctness, batch_size=3, min_class_per_batch=1, seed=0,
|
||||
items,
|
||||
correctness,
|
||||
batch_size=3,
|
||||
min_class_per_batch=1,
|
||||
seed=0,
|
||||
)
|
||||
assert batches == []
|
||||
assert count == 0
|
||||
|
||||
def test_empty_items_returns_empty(self) -> None:
|
||||
batches, count = build_batches(
|
||||
[], {}, batch_size=3, min_class_per_batch=1, seed=0,
|
||||
[],
|
||||
{},
|
||||
batch_size=3,
|
||||
min_class_per_batch=1,
|
||||
seed=0,
|
||||
)
|
||||
assert batches == []
|
||||
assert count == 0
|
||||
@@ -190,6 +209,7 @@ class TestNoWrongAnswersEmpty:
|
||||
# test_validate_params_strict
|
||||
# ---------------------------------------------------------------------------
|
||||
|
||||
|
||||
class TestValidateParamsStrict:
|
||||
"""参数校验：batch_size < 1、min_class < 1、min_class >= batch_size 都报错。"""
|
||||
|
||||
@@ -221,6 +241,7 @@ class TestValidateParamsStrict:
|
||||
# test_correctness_false_vs_none
|
||||
# ---------------------------------------------------------------------------
|
||||
|
||||
|
||||
class TestCorrectnessFalseVsNone:
|
||||
"""correctness.get(qid) is False 精确匹配：None（未知题）不算错题。"""
|
||||
|
||||
@@ -233,7 +254,11 @@ class TestCorrectnessFalseVsNone:
|
||||
# wrong=False（错题），right=True（正确题），unknown 不在 correctness（None）
|
||||
correctness: dict[str, bool] = {"wrong": False, "right": True}
|
||||
batches, count = build_batches(
|
||||
items, correctness, batch_size=10, min_class_per_batch=2, seed=0,
|
||||
items,
|
||||
correctness,
|
||||
batch_size=10,
|
||||
min_class_per_batch=2,
|
||||
seed=0,
|
||||
correct_ratio=0.0,
|
||||
)
|
||||
# 仅 wrong 进入 batch，unknown 不算错题
|
||||
@@ -241,7 +266,7 @@ class TestCorrectnessFalseVsNone:
|
||||
assert batches[0][0].question_id == "wrong"
|
||||
|
||||
def test_explicit_false_only(self) -> None:
|
||||
"""直接测试 _select_mixed_by_task_type 内部逻辑。"""
|
||||
"""直接测试 _select_mixed_by_task_type 内部逻辑（single 单元粒度）。"""
|
||||
items = [
|
||||
_make_q("f1", task_type="t1"),
|
||||
_make_q("n1", task_type="t1"), # None（未知）
|
||||
@@ -249,19 +274,19 @@ class TestCorrectnessFalseVsNone:
|
||||
]
|
||||
correctness: dict[str, bool] = {"f1": False, "t1": True}
|
||||
rng = random.Random(0)
|
||||
result = _select_mixed_by_task_type(items, correctness, 0.0, rng)
|
||||
result = _select_mixed_by_task_type(build_units(items), correctness, 0.0, rng)
|
||||
assert "t1" in result
|
||||
assert len(result["t1"]) == 1
|
||||
assert result["t1"][0].question_id == "f1"
|
||||
assert result["t1"][0].unit_id == "f1"
|
||||
|
||||
def test_none_not_treated_as_correct(self) -> None:
|
||||
"""None（未知）不进正确组，不被 correct_ratio 采样。"""
|
||||
"""None（未知）不进正确组，不被 correct_ratio 采样（single 单元粒度）。"""
|
||||
items = [
|
||||
_make_q("err", task_type="t1"),
|
||||
_make_q("unk", task_type="t1"),
|
||||
]
|
||||
correctness: dict[str, bool] = {"err": False}
|
||||
rng = random.Random(0)
|
||||
result = _select_mixed_by_task_type(items, correctness, 0.5, rng)
|
||||
result = _select_mixed_by_task_type(build_units(items), correctness, 0.5, rng)
|
||||
# 只有 err 一题错题，unk 不在 correctness 中 → get 返回 None → 不进 correct 组
|
||||
assert len(result["t1"]) == 1 # 只有错题，无正确题可混入
|
||||
|
||||
@@ -53,7 +53,7 @@ class _FakeInferenceResult:
|
||||
|
||||
@dataclass(frozen=True)
|
||||
class _FakeQuestion:
|
||||
"""GeneratedQuestion 替身。"""
|
||||
"""GeneratedQuestion 替身（含 pair 契约字段，供 build_units 聚合）。"""
|
||||
|
||||
question_id: str
|
||||
video_id: str = "v1"
|
||||
@@ -63,6 +63,15 @@ class _FakeQuestion:
|
||||
answer: str = "A"
|
||||
source_nodes: tuple = ()
|
||||
difficulty: str = "medium"
|
||||
pair_id: str | None = None
|
||||
question_role: str = "single"
|
||||
unit_id: str = ""
|
||||
flip_axis: str | None = None
|
||||
|
||||
def __post_init__(self) -> None:
|
||||
"""缺省 unit_id 回填为 pair_id 或 question_id，对齐真实 GeneratedQuestion。"""
|
||||
if not self.unit_id:
|
||||
object.__setattr__(self, "unit_id", self.pair_id or self.question_id)
|
||||
|
||||
|
||||
@dataclass
|
||||
|
||||
Reference in New Issue
Block a user