perf(factor): fast_ops v2 去over化——rolling.over(vt_symbol)在10M行分组滚动分钟级/算子(py-spy实锤ts_mean),改符号内shift展开统一模式(ts_mean/std/min/max/sum/corr/cov),等价性测试对齐原版+1M行速度护栏 [vps]

tests/factor/test_fast_ops.py

@@ -28,6 +28,13 @@ from sanguo_factor.fast_ops import (
     fast_ts_rsquare,
     fast_ts_resi,
     fast_ts_quantile,
+    fast_ts_mean,
+    fast_ts_std,
+    fast_ts_sum,
+    fast_ts_min,
+    fast_ts_max,
+    fast_ts_corr_v2,
+    fast_ts_cov_v2,
 )
 
 
@@ -282,6 +289,161 @@ class TestFastTsQuantile:
             assert_dataproxy_equal(original, fast, rtol=1e-9)
 
 
+class TestFastTsMean:
+    """Test fast_ts_mean equivalence."""
+
+    def test_random_data(self):
+        """Exact match on random data."""
+        np.random.seed(42)
+        values = np.random.randn(100) * 10 + 50
+        feature = create_dataproxy(values)
+
+        original = ts_function.ts_mean(feature, window=10)
+        fast = fast_ts_mean(feature, window=10)
+
+        assert_dataproxy_equal(original, fast, rtol=1e-9)
+
+    def test_with_nan(self):
+        """Handle NaN correctly."""
+        values = np.array([1.0, np.nan, 3.0, np.nan, 5.0] * 20)
+        feature = create_dataproxy(values)
+
+        original = ts_function.ts_mean(feature, window=5)
+        fast = fast_ts_mean(feature, window=5)
+
+        assert_dataproxy_equal(original, fast, check_nan=False)
+
+
+class TestFastTsStd:
+    """Test fast_ts_std equivalence."""
+
+    def test_random_data(self):
+        """Exact match on random data."""
+        np.random.seed(42)
+        values = np.random.randn(100) * 10 + 50
+        feature = create_dataproxy(values)
+
+        original = ts_function.ts_std(feature, window=10)
+        fast = fast_ts_std(feature, window=10)
+
+        assert_dataproxy_equal(original, fast, rtol=1e-7)
+
+    def test_constant_values(self):
+        """Constant values should have std = 0."""
+        values = np.array([5.0] * 100)
+        feature = create_dataproxy(values)
+
+        result = fast_ts_std(feature, window=10)
+        df = result.df
+        std_values = df.filter(pl.col("data").is_not_null())["data"].to_numpy()
+
+        assert np.all(std_values < 1e-10), "Std of constant values should be ~0"
+
+
+class TestFastTsSum:
+    """Test fast_ts_sum equivalence."""
+
+    def test_random_data(self):
+        """Exact match on random data (ts_sum has no min_samples, so partial windows are NaN)."""
+        np.random.seed(42)
+        values = np.random.randn(100) * 10 + 50
+        feature = create_dataproxy(values)
+
+        original = ts_function.ts_sum(feature, window=10)
+        fast = fast_ts_sum(feature, window=10)
+
+        assert_dataproxy_equal(original, fast, rtol=1e-9)
+
+    def test_partial_windows_nan(self):
+        """ts_sum returns NaN for partial windows (no min_samples=1)."""
+        values = np.array([1.0, 2.0, 3.0, 4.0, 5.0, 6.0, 7.0, 8.0, 9.0, 10.0] * 10)
+        feature = create_dataproxy(values)
+
+        result = fast_ts_sum(feature, window=5)
+
+        # First 4 values should be NaN (partial window)
+        df = result.df
+        first_four = df["data"].to_numpy()[:4]
+        assert all(np.isnan(first_four)), "Partial windows should be NaN"
+
+
+class TestFastTsMin:
+    """Test fast_ts_min equivalence."""
+
+    def test_random_data(self):
+        """Exact match on random data."""
+        np.random.seed(42)
+        values = np.random.randn(100) * 10 + 50
+        feature = create_dataproxy(values)
+
+        original = ts_function.ts_min(feature, window=10)
+        fast = fast_ts_min(feature, window=10)
+
+        assert_dataproxy_equal(original, fast, rtol=1e-9)
+
+
+class TestFastTsMax:
+    """Test fast_ts_max equivalence."""
+
+    def test_random_data(self):
+        """Exact match on random data."""
+        np.random.seed(42)
+        values = np.random.randn(100) * 10 + 50
+        feature = create_dataproxy(values)
+
+        original = ts_function.ts_max(feature, window=10)
+        fast = fast_ts_max(feature, window=10)
+
+        assert_dataproxy_equal(original, fast, rtol=1e-9)
+
+
+class TestFastTsCorrV2:
+    """Test fast_ts_corr_v2 (over-free) equivalence."""
+
+    def test_random_data(self):
+        """Exact match on random data."""
+        np.random.seed(42)
+        values1 = np.random.randn(100) * 10 + 50
+        values2 = np.random.randn(100) * 10 + 50
+
+        feature1 = create_dataproxy(values1)
+        feature2 = create_dataproxy(values2)
+
+        original = ts_function.ts_corr(feature1, feature2, window=10)
+        fast = fast_ts_corr_v2(feature1, feature2, window=10)
+
+        assert_dataproxy_equal(original, fast, rtol=1e-7)
+
+    def test_perfect_correlation(self):
+        """Perfect correlation should be exactly 1.0."""
+        values = np.random.randn(100) * 10 + 50
+        feature1 = create_dataproxy(values)
+        feature2 = create_dataproxy(values * 2 + 10)
+
+        result = fast_ts_corr_v2(feature1, feature2, window=10)
+
+        df = result.df
+        assert (df.filter(pl.col("data").is_not_null())["data"] - 1.0).abs().max() < 1e-6
+
+
+class TestFastTsCovV2:
+    """Test fast_ts_cov_v2 (over-free) equivalence."""
+
+    def test_random_data(self):
+        """Exact match on random data."""
+        np.random.seed(42)
+        values1 = np.random.randn(100) * 10 + 50
+        values2 = np.random.randn(100) * 10 + 50
+
+        feature1 = create_dataproxy(values1)
+        feature2 = create_dataproxy(values2)
+
+        original = ts_function.ts_cov(feature1, feature2, window=10)
+        fast = fast_ts_cov_v2(feature1, feature2, window=10)
+
+        assert_dataproxy_equal(original, fast, rtol=1e-7)
+
+
 class TestRegistrationAndIntegration:
     """Test registration and vnpy integration."""
 
@@ -291,7 +453,7 @@ class TestRegistrationAndIntegration:
         overrides2 = register_fast_ops()
 
         assert overrides1 == overrides2
-        assert len(overrides1) == 8
+        assert len(overrides1) == 13
 
     def test_expression_override(self):
         """Test that registered functions override vnpy defaults."""
@@ -325,8 +487,9 @@ class TestRegistrationAndIntegration:
         overrides = register_fast_ops()
 
         expected = {
-            "ts_rank", "ts_corr", "ts_cov",
-            "ts_decay_linear", "ts_slope", "ts_rsquare", "ts_resi", "ts_quantile"
+            "ts_mean", "ts_std", "ts_sum", "ts_min", "ts_max",
+            "ts_corr", "ts_cov",
+            "ts_rank", "ts_decay_linear", "ts_slope", "ts_rsquare", "ts_resi", "ts_quantile"
         }
 
         assert set(overrides) == expected
@@ -390,6 +553,24 @@ class TestEdgeCases:
         # Should complete in under 10 seconds for 200k rows
         assert elapsed < 10, f"Performance regression: {elapsed:.2f}s > 10s"
 
+    def test_ts_mean_overfree_speed_guard(self):
+        """Speed guard for over-free ts_mean (critical hot path)."""
+        import time
+        n = 1_000_000  # 1M rows (1/10 of full 10M dataset)
+        df = pl.DataFrame({
+            "vt_symbol": ["A"] * (n // 2) + ["B"] * (n // 2),
+            "datetime": list(range(n // 2)) * 2,
+            "data": [((i * 37) % 997) / 997 for i in range(n // 2)] * 2
+        })
+        feature = DataProxy(df)
+
+        t0 = time.time()
+        fast_ts_mean(feature, 20)
+        elapsed = time.time() - t0
+
+        # .over() version would take minutes; target is <10 seconds
+        assert elapsed < 10, f"Performance regression: {elapsed:.2f}s > 10s"
+
 
 if __name__ == "__main__":
     pytest.main([__file__, "-v"])