commands: m2d-log + backtest + batch + stats slash commands (124 tests pass)

tests/test_stats_ci.py

@@ -0,0 +1,83 @@
+"""Pure-math tests for stats CI primitives (no I/O)."""
+
+from __future__ import annotations
+
+import sys
+from pathlib import Path
+
+import pytest
+
+sys.path.insert(0, str(Path(__file__).resolve().parent.parent))
+
+from scripts.stats import bootstrap_expectancy_ci, wilson_ci  # noqa: E402
+
+
+# ---------------------------------------------------------------------------
+# Wilson CI
+# ---------------------------------------------------------------------------
+
+
+class TestWilsonCI:
+    def test_wilson_n_zero(self) -> None:
+        assert wilson_ci(0, 0) == (0.0, 0.0)
+
+    def test_wilson_perfect_winrate(self) -> None:
+        lo, hi = wilson_ci(10, 10)
+        assert lo > 0.65
+        assert hi == pytest.approx(1.0, abs=1e-12)
+
+    def test_wilson_reference_15_55(self) -> None:
+        """wins=8, n=15 (WR≈53%) → CI approximately [29%, 76%] ±2%."""
+        lo, hi = wilson_ci(8, 15)
+        assert lo == pytest.approx(0.29, abs=0.02)
+        assert hi == pytest.approx(0.76, abs=0.02)
+
+    def test_wilson_all_losses(self) -> None:
+        lo, hi = wilson_ci(0, 10)
+        assert lo == pytest.approx(0.0, abs=1e-12)
+        assert hi < 0.35
+
+    def test_wilson_wins_out_of_range(self) -> None:
+        with pytest.raises(ValueError):
+            wilson_ci(11, 10)
+        with pytest.raises(ValueError):
+            wilson_ci(-1, 10)
+
+    def test_wilson_clamps_at_50pct_n40(self) -> None:
+        """Reference at WR=50%, N=40: CI ≈ [35.2%, 64.8%]."""
+        lo, hi = wilson_ci(20, 40)
+        assert lo == pytest.approx(0.352, abs=0.005)
+        assert hi == pytest.approx(0.648, abs=0.005)
+
+
+# ---------------------------------------------------------------------------
+# Bootstrap CI
+# ---------------------------------------------------------------------------
+
+
+class TestBootstrap:
+    def test_bootstrap_deterministic(self) -> None:
+        values = [1.0, -0.5, 0.5, -1.0]
+        a = bootstrap_expectancy_ci(values, n_resamples=1000, seed=42)
+        b = bootstrap_expectancy_ci(values, n_resamples=1000, seed=42)
+        assert a == b
+
+    def test_bootstrap_different_seed_different_result(self) -> None:
+        values = [1.0, -0.5, 0.5, -1.0, 0.2, -0.3, 0.5]
+        a = bootstrap_expectancy_ci(values, n_resamples=1000, seed=1)
+        b = bootstrap_expectancy_ci(values, n_resamples=1000, seed=2)
+        assert a != b
+
+    def test_bootstrap_empty(self) -> None:
+        assert bootstrap_expectancy_ci([], n_resamples=100, seed=0) == (0.0, 0.0)
+
+    def test_bootstrap_single_value(self) -> None:
+        lo, hi = bootstrap_expectancy_ci([0.5], n_resamples=100, seed=0)
+        assert lo == pytest.approx(0.5, abs=1e-9)
+        assert hi == pytest.approx(0.5, abs=1e-9)
+
+    def test_bootstrap_brackets_the_mean(self) -> None:
+        values = [0.5, -1.0, 0.5, 0.5, -1.0, 0.2, -0.3, 0.5, -1.0, 0.5] * 5
+        mean = sum(values) / len(values)
+        lo, hi = bootstrap_expectancy_ci(values, n_resamples=1000, seed=7)
+        assert lo <= mean <= hi