feat(#42): 模型框架模板化PoC（真实数据验证·降RISK，Ti+树脂场景端到端验证R1精度/R2配方切换/R3阶段回滚）

2026-08-05 01:21:27 +08:00
parent 793dd0a3b8
commit 2151265f36
7 changed files with 764 additions and 0 deletions
@@ -0,0 +1 @@
+# -*- coding: utf-8 -*-
@@ -0,0 +1,23 @@
+# -*- coding: utf-8 -*-
+"""测试引导：把连字符目录 ``core/model-framework`` 加载为可导入包
+``model_framework``，使测试可 ``from model_framework import ...``。
+"""
+import importlib.util
+import os
+import sys
+
+PKG_DIR = os.path.dirname(os.path.dirname(os.path.abspath(__file__)))
+
+
+def _load_package(name: str, path: str) -> None:
+    if name in sys.modules:
+        return
+    init_py = os.path.join(path, "__init__.py")
+    spec = importlib.util.spec_from_file_location(
+        name, init_py, submodule_search_locations=[path])
+    module = importlib.util.module_from_spec(spec)
+    sys.modules[name] = module
+    spec.loader.exec_module(module)
+
+
+_load_package("model_framework", PKG_DIR)
@@ -0,0 +1,170 @@
+# -*- coding: utf-8 -*-
+"""模型框架模板化 PoC 单元测试（issue #42）。
+
+覆盖：
+- 轻量主干（_LinearBackbone / _MeanBackbone）训练预测 + _solve_linear 正确性；
+- _MiniRegistry 注册 / promote / rollback / serving；
+- PoCScenario 构造 + _gen_linear_samples 确定性；
+- TemplatePoC.run 端到端链路 + PoCReport 三条 RISK 验收口径（R1/R2/R3）；
+- 内置 Ti + 树脂场景跑通且 all_passed。
+"""
+import math
+import os
+import sys
+import unittest
+
+HERE = os.path.dirname(os.path.abspath(__file__))
+if HERE not in sys.path:
+    sys.path.insert(0, HERE)
+
+import _bootstrap  # noqa: E402  加载 model_framework 包
+
+from model_framework import (  # noqa: E402
+    PoCError,
+    PoCReport,
+    PoCScenario,
+    TemplatePoC,
+    resin_quality_scenario,
+    run_poc,
+    ti_quality_scenario,
+)
+from model_framework.template_poc import (  # noqa: E402
+    BACKBONES,
+    _Artifact,
+    _gen_linear_samples,
+    _LinearBackbone,
+    _MeanBackbone,
+    _MiniRegistry,
+    _solve_linear,
+)
+
+
+class TestSolveLinear(unittest.TestCase):
+    def test_simple(self):
+        # 2x + 3y = 8; x - y = 1 => x=2.2, y=1.2
+        w = _solve_linear([[2, 3], [1, -1]], [8, 1])
+        self.assertAlmostEqual(w[0], 2.2, places=6)
+        self.assertAlmostEqual(w[1], 1.2, places=6)
+
+    def test_identity(self):
+        w = _solve_linear([[1, 0], [0, 1]], [3, 5])
+        self.assertEqual(w, [3.0, 5.0])
+
+
+class TestBackbones(unittest.TestCase):
+    def test_linear_fits_linear_data(self):
+        # y = 1 + 2*x1 + 3*x2
+        X = [[0, 0], [1, 0], [0, 1], [1, 1], [2, 3]]
+        y = [1 + 2 * x1 + 3 * x2 for x1, x2 in X]
+        bb = _LinearBackbone({"lambda": 0.0})
+        bb.fit(X, y)
+        preds = bb.predict([[1, 1], [2, 2]])
+        self.assertAlmostEqual(preds[0], 6.0, places=4)
+        self.assertAlmostEqual(preds[1], 11.0, places=4)
+
+    def test_mean_backbone(self):
+        bb = _MeanBackbone({})
+        bb.fit([[1], [2], [3]], [10, 20, 30])
+        self.assertEqual(bb.predict([[9]]), [20.0])
+
+    def test_backbones_registered(self):
+        self.assertIn("linear", BACKBONES)
+        self.assertIn("mean", BACKBONES)
+
+
+class TestMiniRegistry(unittest.TestCase):
+    def test_register_promote_rollback(self):
+        reg = _MiniRegistry()
+        reg.register(_Artifact("m", "v1", "linear", {"mae": 1.0}))
+        self.assertEqual(reg.serving("m", "dev"), "v1")
+        reg.promote("m", "v1")  # dev->staging
+        reg.promote("m", "v1")  # staging->prod
+        self.assertEqual(reg.serving("m", "prod"), "v1")
+        reg.register(_Artifact("m", "v2", "linear", {"mae": 0.8}))
+        reg.promote("m", "v2")
+        reg.promote("m", "v2")
+        reg.rollback("m", "prod", "v1")
+        self.assertEqual(reg.serving("m", "prod"), "v1")
+
+    def test_promote_prod_raises(self):
+        reg = _MiniRegistry()
+        reg.register(_Artifact("m", "v1", "linear", {}))
+        reg.promote("m", "v1")
+        reg.promote("m", "v1")
+        with self.assertRaises(PoCError):
+            reg.promote("m", "v1")
+
+
+class TestGenSamples(unittest.TestCase):
+    def test_deterministic(self):
+        s1 = _gen_linear_samples(10, 3, seed=42)
+        s2 = _gen_linear_samples(10, 3, seed=42)
+        self.assertEqual(s1, s2)
+
+    def test_shape(self):
+        s = _gen_linear_samples(20, 4, seed=1)
+        self.assertEqual(len(s), 20)
+        self.assertEqual(len(s[0]), 5)  # 4 feat + 1 target
+
+
+class TestTemplatePoC(unittest.TestCase):
+    def test_run_two_scenarios_all_passed(self):
+        report = run_poc()
+        self.assertIsInstance(report, PoCReport)
+        self.assertEqual(len(report.scenario_results), 2)
+        self.assertTrue(report.all_passed, report.summary())
+        self.assertTrue(report.r1_precision_ok)
+        self.assertTrue(report.r2_recipe_switch_ok)
+        self.assertTrue(report.r3_stage_rollback_ok)
+
+    def test_r1_precision_fails_on_bad_acceptance(self):
+        # 把验收线设极小，强制 R1 失败
+        sc = ti_quality_scenario()
+        sc.acceptance_mae = 0.0001  # 不可能达到
+        report = TemplatePoC([sc]).run()
+        self.assertFalse(report.r1_precision_ok)
+
+    def test_r2_recipe_switch_detects_mixed_backbone(self):
+        sc1 = ti_quality_scenario()
+        sc2 = resin_quality_scenario()
+        sc2.backbone = "mean"  # 故意用不同主干
+        report = TemplatePoC([sc1, sc2]).run()
+        self.assertFalse(report.r2_recipe_switch_ok)
+
+    def test_r3_rollback_serving_correct(self):
+        report = run_poc()
+        for sr in report.scenario_results:
+            self.assertTrue(sr["serving_is_v1"])
+
+    def test_to_dict_serializable(self):
+        import json
+        report = run_poc()
+        d = report.to_dict()
+        json.dumps(d)  # 可序列化
+        self.assertIn("R1_precision_ok", d)
+
+    def test_insufficient_samples_raises(self):
+        sc = PoCScenario(name="x", industry="t",
+                         feature_columns=("a",), target_column="y",
+                         samples=[[1, 2]])  # 不足
+        with self.assertRaises(PoCError):
+            TemplatePoC([sc]).run()
+
+    def test_unknown_backbone_raises(self):
+        sc = PoCScenario(name="x", industry="t",
+                         feature_columns=("a",), target_column="y",
+                         backbone="voodoo",
+                         samples=_gen_linear_samples(20, 1, seed=1))
+        with self.assertRaises(PoCError):
+            TemplatePoC([sc]).run()
+
+    def test_builtin_scenarios_distinct(self):
+        ti = ti_quality_scenario()
+        resin = resin_quality_scenario()
+        self.assertNotEqual(ti.feature_columns, resin.feature_columns)
+        self.assertEqual(ti.backbone, resin.backbone)  # 共用主干（R2）
+        self.assertNotEqual(ti.hyperparams, resin.hyperparams)  # 配方不同
+
+
+if __name__ == "__main__":
+    unittest.main()