gavindiaz/NexQuant
1
0
Fork 0
mirror of https://github.com/NicolasBohn/NexQuant.git synced 2026-07-27 23:47:46 +00:00
Code Issues Packages Projects Releases Wiki Activity

fix(auto-fixer): preserve date dimension in groupby(['instrument','date']) fix

Browse Source 
The previous fixer converted groupby(['instrument','date']) → groupby(level=1),
stripping the date level. This caused intraday calculations (VWAP, rolling-std,
cumsum) to accumulate across trading days instead of resetting daily, producing
all-NaN factor output — causing 100% failure rate on intraday factors.

New behaviour: capture the DataFrame variable name and emit:
  var.groupby([var.index.get_level_values(1),
               var.index.get_level_values(0).normalize()])
which groups by (instrument, day) as originally intended.

Adds test/qlib/test_auto_fixer.py covering all fixer cases.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
This commit is contained in:
TPTBusiness
2026-04-26 11:50:52 +02:00
parent bd5a5e0fd5
commit f4deda99b5
2 changed files with 109 additions and 15 deletions
Download Patch File Download Diff File Expand all files Collapse all files
rdagent/components/coder/factor_coder/auto_fixer.py
+41 -15
View File
@@ -129,25 +129,51 @@ class FactorAutoFixer:
def _fix_groupby_column_on_multiindex(self, code: str) -> str:
"""
Fix: groupby(['instrument', 'date']) on a MultiIndex DataFrame fails with
KeyError because 'instrument' and 'date' are index levels, not columns.
Fix: groupby(['instrument', 'date']) on a MultiIndex (datetime, instrument)
DataFrame fails with KeyError because those are index levels, not columns.
Replace with groupby(level=1) (instrument is level 1).
Also handle groupby(['date', 'instrument']) and single groupby('instrument').
Correct replacement preserves BOTH dimensions so intraday calculations reset
per day:
var.groupby(['instrument', 'date'])
→ var.groupby([var.index.get_level_values(1), var.index.get_level_values(0).normalize()])
Single-column groupby(['instrument']) is correctly replaced with groupby(level=1).
Note: do NOT convert groupby('instrument') → groupby(level=1) here — that would
undo the reset_index_groupby fix which correctly emits groupby('instrument').
"""
fixed_code = code
# groupby(['instrument', 'date']) or groupby(['date', 'instrument'])
# Note: do NOT convert groupby('instrument') → groupby(level=1) here —
# that would undo the reset_index_groupby fix which correctly emits groupby('instrument').
for pat, repl in [
(r"\.groupby\(\['instrument',\s*'date'\]\)", ".groupby(level=1)"),
(r"\.groupby\(\['date',\s*'instrument'\]\)", ".groupby(level=1)"),
(r"\.groupby\(\['instrument'\]\)", ".groupby(level=1)"),
]:
if re.search(pat, fixed_code):
fixed_code = re.sub(pat, repl, fixed_code)
self.fixes_applied.append(f"multiindex_groupby: {pat} → {repl}")
def _replace_two_col_groupby(m: re.Match, order: str) -> str:
var = m.group(1)
if order == "instrument_date":
repl = (
f"{var}.groupby([{var}.index.get_level_values(1), "
f"{var}.index.get_level_values(0).normalize()])"
)
else: # date_instrument
repl = (
f"{var}.groupby([{var}.index.get_level_values(0).normalize(), "
f"{var}.index.get_level_values(1)])"
)
self.fixes_applied.append(f"multiindex_groupby: {m.group(0)[:60]} → two-level")
return repl
# groupby(['instrument', 'date']) — capture variable name before .groupby
fixed_code = re.sub(
r'(\w+)\.groupby\(\[\'instrument\',\s*\'date\'\]\)',
lambda m: _replace_two_col_groupby(m, "instrument_date"),
fixed_code,
)
# groupby(['date', 'instrument'])
fixed_code = re.sub(
r'(\w+)\.groupby\(\[\'date\',\s*\'instrument\'\]\)',
lambda m: _replace_two_col_groupby(m, "date_instrument"),
fixed_code,
)
# single: groupby(['instrument']) → groupby(level=1)
if re.search(r"\.groupby\(\['instrument'\]\)", fixed_code):
fixed_code = re.sub(r"\.groupby\(\['instrument'\]\)", ".groupby(level=1)", fixed_code)
self.fixes_applied.append("multiindex_groupby: groupby(['instrument']) → groupby(level=1)")
return fixed_code