fix(auto-fixer): replace zero \$volume with price-range proxy for FX data

EUR/USD synthetic data has \$volume=0 for all rows, causing any VWAP or
volume-weighted factor to produce all-NaN output. Insert a guard after
pd.read_hdf() that replaces zero volume with (\$high - \$low) range proxy
so volume-dependent factors produce meaningful signals.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

rdagent/components/coder/factor_coder/auto_fixer.py

@@ -58,15 +58,16 @@ class FactorAutoFixer:
         fix_methods = [
             self._fix_instrument_column_access,     # First: fix df['instrument'] on MultiIndex
             self._fix_instrument_loc_multiindex,    # Second: fix df.loc[instrument_var] on MultiIndex
-            self._fix_reset_index_groupby,          # Third: fix groupby(level=N) after reset_index()
-            self._fix_groupby_mixed_levels,         # Fourth: fix groupby(level=[int, str])
-            self._fix_groupby_column_on_multiindex, # Fifth: fix groupby(['instrument','date']) on MultiIndex
-            self._fix_chained_groupby,              # Sixth: fix groupby(level=N).groupby('date') chain
-            self._fix_rolling_ddof,                 # Seventh: remove unsupported ddof kwarg
-            self._fix_groupby_apply_to_transform,   # Eighth: fix groupby patterns
-            self._fix_inf_nan_handling,             # Ninth: add inf/nan handling
-            self._fix_data_range_processing,        # Tenth: ensure full data range
-            self._fix_multiindex_groupby,           # Eleventh: ensure groupby on MultiIndex
+            self._fix_zero_volume_proxy,            # Third: replace zero $volume with range proxy
+            self._fix_reset_index_groupby,          # Fourth: fix groupby(level=N) after reset_index()
+            self._fix_groupby_mixed_levels,         # Fifth: fix groupby(level=[int, str])
+            self._fix_groupby_column_on_multiindex, # Sixth: fix groupby(['instrument','date']) on MultiIndex
+            self._fix_chained_groupby,              # Seventh: fix groupby(level=N).groupby('date') chain
+            self._fix_rolling_ddof,                 # Eighth: remove unsupported ddof kwarg
+            self._fix_groupby_apply_to_transform,   # Ninth: fix groupby patterns
+            self._fix_inf_nan_handling,             # Tenth: add inf/nan handling
+            self._fix_data_range_processing,        # Eleventh: ensure full data range
+            self._fix_multiindex_groupby,           # Twelfth: ensure groupby on MultiIndex
         ]
 
         for fix_method in fix_methods:
@@ -164,6 +165,52 @@ class FactorAutoFixer:
 
         return fixed_code
 
+    def _fix_zero_volume_proxy(self, code: str) -> str:
+        """
+        Fix: $volume is always 0 in our EUR/USD dataset (FX has no real volume).
+        Any factor using $volume (VWAP, volume-weighted returns, etc.) produces
+        all-NaN output because 0*price=0 and sum(0)/sum(0)=NaN.
+
+        Insert a guard right after pd.read_hdf() that replaces zero volume with
+        the intraday price-range proxy ($high - $low) so volume-weighted factors
+        produce meaningful signals.
+        """
+        if "'$volume'" not in code and '"$volume"' not in code:
+            return code
+
+        # Already patched
+        if "volume proxy" in code:
+            return code
+
+        lines = code.splitlines()
+        insert_after = -1
+        df_var = "df"
+        indent = "    "
+
+        for i, line in enumerate(lines):
+            if "read_hdf(" in line:
+                m = re.match(r"(\s*)(\w+)\s*=\s*", line)
+                if m:
+                    indent = m.group(1)
+                    df_var = m.group(2)
+                else:
+                    m2 = re.match(r"(\s*)", line)
+                    indent = m2.group(1) if m2 else "    "
+                insert_after = i
+                break
+
+        if insert_after == -1:
+            return code
+
+        proxy_lines = [
+            f"{indent}# volume proxy: $volume is always 0 in FX data — use price-range as proxy",
+            f"{indent}if ({df_var}['$volume'] == 0).all():",
+            f"{indent}    {df_var}['$volume'] = {df_var}['$high'] - {df_var}['$low']",
+        ]
+        lines = lines[: insert_after + 1] + proxy_lines + lines[insert_after + 1 :]
+        self.fixes_applied.append("volume_proxy: replaced zero $volume with ($high - $low)")
+        return "\n".join(lines)
+
     def _fix_reset_index_groupby(self, code: str) -> str:
         """
         Fix: groupby(level=N) on a variable created by .reset_index() fails because

test/qlib/test_auto_fixer.py

@@ -205,6 +205,40 @@ class TestGroupbyApplyToTransform:
         assert ".transform(" in result
 
 
+class TestZeroVolumeProxy:
+    def test_injects_proxy_when_volume_used(self, fixer):
+        code = (
+            "def calc():\n"
+            "    df = pd.read_hdf('data.h5', key='data')\n"
+            "    df['pv'] = df['$close'] * df['$volume']\n"
+            "    return df[['pv']]\n"
+        )
+        result = fixer.fix(code)
+        assert "volume proxy" in result
+        assert "df['$volume'] = df['$high'] - df['$low']" in result
+        # Proxy must come right after read_hdf line
+        lines = result.splitlines()
+        hdf_idx = next(i for i, l in enumerate(lines) if "read_hdf" in l)
+        assert "volume proxy" in lines[hdf_idx + 1]
+
+    def test_no_injection_when_volume_absent(self, fixer):
+        code = "df = pd.read_hdf('data.h5', key='data')\ndf['x'] = df['$close'].pct_change()\n"
+        result = fixer.fix(code)
+        assert "volume proxy" not in result
+
+    def test_no_double_injection(self, fixer):
+        code = (
+            "def calc():\n"
+            "    df = pd.read_hdf('data.h5', key='data')\n"
+            "    # volume proxy: $volume is always 0 in FX data — use price-range as proxy\n"
+            "    if (df['$volume'] == 0).all():\n"
+            "        df['$volume'] = df['$high'] - df['$low']\n"
+            "    df['pv'] = df['$close'] * df['$volume']\n"
+        )
+        result = fixer.fix(code)
+        assert result.count("volume proxy") == 1
+
+
 class TestRollingDdof:
     def test_removes_ddof_from_rolling_args(self, fixer):
         result = fixer.fix("df.rolling(20, min_periods=1, ddof=1).std()")