Fix proxy attribution benchmark and labeling

factor_attribution.py

@@ -32,17 +32,18 @@ PROXY_FACTOR_COLUMNS = [
     "CMA_PROXY",
 ] + EXTENSION_FACTOR_COLUMNS
 TRADING_DAYS_PER_YEAR = 252
+MISSING_BENCHMARK_SENTINEL = "__missing_benchmark__"
 SUMMARY_BETA_COLUMN_BY_FACTOR = {
     "MKT_RF": "beta_mkt",
     "MKT": "beta_mkt",
     "SMB": "beta_smb",
-    "SMB_PROXY": "beta_smb",
+    "SMB_PROXY": "beta_smb_proxy",
     "HML": "beta_hml",
-    "HML_PROXY": "beta_hml",
+    "HML_PROXY": "beta_hml_proxy",
     "RMW": "beta_rmw",
-    "RMW_PROXY": "beta_rmw",
+    "RMW_PROXY": "beta_rmw_proxy",
     "CMA": "beta_cma",
-    "CMA_PROXY": "beta_cma",
+    "CMA_PROXY": "beta_cma_proxy",
     "MOM": "beta_mom",
     "LOWVOL": "beta_lowvol",
     "RECOVERY": "beta_recovery",
@@ -68,6 +69,10 @@ SUMMARY_COLUMNS = [
     "beta_hml",
     "beta_rmw",
     "beta_cma",
+    "beta_smb_proxy",
+    "beta_hml_proxy",
+    "beta_rmw_proxy",
+    "beta_cma_proxy",
     "beta_mom",
     "beta_lowvol",
     "beta_recovery",
@@ -429,6 +434,12 @@ def _select_model_names(
     return list(available_models)
 
 
+def _resolve_benchmark_symbol(benchmark: str | None) -> str:
+    if benchmark is None:
+        return MISSING_BENCHMARK_SENTINEL
+    return benchmark
+
+
 def attribute_strategies(
     results_df: pd.DataFrame,
     benchmark_label: str,
@@ -438,10 +449,7 @@ def attribute_strategies(
     benchmark: str | None = None,
     external_factors: pd.DataFrame | None = None,
 ) -> tuple[pd.DataFrame, pd.DataFrame]:
-    benchmark_symbol = benchmark
+    benchmark_symbol = _resolve_benchmark_symbol(benchmark)
-    if benchmark_symbol is None:
-        matching_columns = [column for column in price_data.columns if column in benchmark_label]
-        benchmark_symbol = matching_columns[0] if matching_columns else price_data.columns[-1]
 
     extension_factors = build_extension_factors(price_data, benchmark=benchmark_symbol, market=market)
 
@@ -518,6 +526,10 @@ def attribute_strategies(
                 "beta_hml": np.nan,
                 "beta_rmw": np.nan,
                 "beta_cma": np.nan,
+                "beta_smb_proxy": np.nan,
+                "beta_hml_proxy": np.nan,
+                "beta_rmw_proxy": np.nan,
+                "beta_cma_proxy": np.nan,
                 "beta_mom": np.nan,
                 "beta_lowvol": np.nan,
                 "beta_recovery": np.nan,
@@ -575,7 +587,7 @@ def _describe_fit(r_squared: float) -> str:
 
 
 def _top_loading_descriptions(row: pd.Series, limit: int = 2) -> str:
-    beta_columns = [column for column in SUMMARY_COLUMNS if column.startswith("beta_")]
+    beta_columns = [column for column in row.index if column.startswith("beta_")]
     present = []
     for column in beta_columns:
         value = row.get(column)
@@ -606,11 +618,15 @@ def print_attribution_summary(summary_df: pd.DataFrame) -> None:
         "beta_hml",
         "beta_rmw",
         "beta_cma",
+        "beta_smb_proxy",
+        "beta_hml_proxy",
+        "beta_rmw_proxy",
+        "beta_cma_proxy",
         "beta_mom",
         "beta_lowvol",
         "beta_recovery",
     ]
-    table = summary_df.loc[:, display_columns].copy()
+    table = summary_df.reindex(columns=display_columns).copy()
     numeric_columns = [column for column in display_columns if column not in {"strategy", "market", "model"}]
     table.loc[:, numeric_columns] = table.loc[:, numeric_columns].round(4)
 

tests/test_factor_attribution.py

@@ -655,6 +655,10 @@ class AttributionIntegrationTests(unittest.TestCase):
                 "beta_hml",
                 "beta_rmw",
                 "beta_cma",
+                "beta_smb_proxy",
+                "beta_hml_proxy",
+                "beta_rmw_proxy",
+                "beta_cma_proxy",
                 "beta_mom",
                 "beta_lowvol",
                 "beta_recovery",
@@ -667,6 +671,7 @@ class AttributionIntegrationTests(unittest.TestCase):
         self.assertAlmostEqual(summary.loc[0, "beta_mkt"], 1.10, places=3)
         self.assertAlmostEqual(summary.loc[0, "beta_smb"], -0.25, places=3)
         self.assertAlmostEqual(summary.loc[0, "beta_hml"], 0.35, places=3)
+        self.assertTrue(np.isnan(summary.loc[0, "beta_smb_proxy"]))
         self.assertTrue(np.isnan(summary.loc[0, "beta_mom"]))
 
         self.assertListEqual(
@@ -704,11 +709,53 @@ class AttributionIntegrationTests(unittest.TestCase):
         self.assertEqual(summary.loc[0, "model"], "proxy")
         self.assertEqual(summary.loc[0, "factor_source"], "proxy_only")
         self.assertTrue(bool(summary.loc[0, "proxy_only"]))
+        self.assertIn("beta_smb_proxy", summary.columns)
+        self.assertIn("beta_hml_proxy", summary.columns)
+        self.assertIn("beta_rmw_proxy", summary.columns)
+        self.assertIn("beta_cma_proxy", summary.columns)
+        self.assertTrue(np.isnan(summary.loc[0, "beta_smb"]))
+        self.assertTrue(np.isnan(summary.loc[0, "beta_hml"]))
+        self.assertTrue(np.isnan(summary.loc[0, "beta_rmw"]))
+        self.assertTrue(np.isnan(summary.loc[0, "beta_cma"]))
         self.assertEqual(
             set(loadings["factor"]),
             {"MKT", "SMB_PROXY", "HML_PROXY", "RMW_PROXY", "CMA_PROXY", "MOM", "LOWVOL", "RECOVERY"},
         )
 
+    def test_attribute_strategies_without_benchmark_uses_equal_weight_proxy_market(self):
+        dates = pd.date_range("2025-01-01", periods=320, freq="B")
+        prices = self._make_price_frame(dates, benchmark="000300.SS").drop(columns=["000300.SS"])
+        equal_weight_returns = prices.pct_change().mean(axis=1).fillna(0.0)
+        results = pd.DataFrame(
+            {
+                "Strategy": 100_000.0 * (1.0 + 0.0002 + 0.8 * equal_weight_returns).cumprod(),
+                "External Benchmark": 100_000.0 * (1.0 + 0.0001 + 0.6 * equal_weight_returns).cumprod(),
+            },
+            index=dates,
+        )
+
+        summary_missing, loadings_missing = attribute_strategies(
+            results_df=results,
+            benchmark_label="External Benchmark",
+            benchmark=None,
+            price_data=prices,
+            market="cn",
+            model_selection="ff5",
+            external_factors=None,
+        )
+        summary_explicit, loadings_explicit = attribute_strategies(
+            results_df=results,
+            benchmark_label="External Benchmark",
+            benchmark="MISSING_BENCHMARK",
+            price_data=prices,
+            market="cn",
+            model_selection="ff5",
+            external_factors=None,
+        )
+
+        pd.testing.assert_frame_equal(summary_missing, summary_explicit, check_dtype=False)
+        pd.testing.assert_frame_equal(loadings_missing, loadings_explicit, check_dtype=False)
+
     def test_print_attribution_summary_prints_compact_table_and_interpretation(self):
         summary = pd.DataFrame(
             [
@@ -751,6 +798,50 @@ class AttributionIntegrationTests(unittest.TestCase):
         self.assertIn("alpha_ann", output)
         self.assertIn("Interpretation", output)
 
+    def test_print_attribution_summary_keeps_proxy_factor_labels_in_output(self):
+        summary = pd.DataFrame(
+            [
+                {
+                    "strategy": "Strategy",
+                    "market": "cn",
+                    "model": "proxy",
+                    "factor_source": "proxy_only",
+                    "proxy_only": True,
+                    "start_date": "2025-01-02",
+                    "end_date": "2026-03-24",
+                    "n_obs": 319,
+                    "alpha_daily": 0.0002,
+                    "alpha_ann": 0.0504,
+                    "alpha_t_stat": 1.5,
+                    "alpha_p_value": 0.12,
+                    "r_squared": 0.72,
+                    "adj_r_squared": 0.70,
+                    "residual_vol_ann": 0.14,
+                    "beta_mkt": 0.85,
+                    "beta_smb": np.nan,
+                    "beta_hml": np.nan,
+                    "beta_rmw": np.nan,
+                    "beta_cma": np.nan,
+                    "beta_smb_proxy": -0.30,
+                    "beta_hml_proxy": 0.25,
+                    "beta_rmw_proxy": 0.10,
+                    "beta_cma_proxy": -0.05,
+                    "beta_mom": 0.20,
+                    "beta_lowvol": np.nan,
+                    "beta_recovery": np.nan,
+                }
+            ]
+        )
+
+        buffer = io.StringIO()
+        with contextlib.redirect_stdout(buffer):
+            print_attribution_summary(summary)
+
+        output = buffer.getvalue()
+        self.assertIn("beta_smb_proxy", output)
+        self.assertIn("beta_hml_proxy", output)
+        self.assertIn("SMB_PROXY", output)
+
     def _make_price_frame(self, dates: pd.DatetimeIndex, benchmark: str) -> pd.DataFrame:
         steps = np.arange(len(dates), dtype=float)
         data = {}