fix(auto-fixer): fix df.loc[instrument] DateParseError on MultiIndex frames

When LLM iterates over instruments via get_level_values('instrument').unique()
and then does df.loc[instrument], pandas tries to parse the instrument string
('EURUSD') as a datetime against level-0 of the (datetime, instrument) index,
raising DateParseError.

Fix: detect loop variables bound to get_level_values(1) or get_level_values('instrument')
and replace DF.loc[loop_var] (read) with DF.xs(loop_var, level=1). Assignment
write-backs are left untouched to avoid complex rewrites.

Adds 4 new tests (TestInstrumentLocMultiindex) — total 23 tests, all passing.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
This commit is contained in:
TPTBusiness
2026-04-27 15:31:35 +02:00
parent 17a2558339
commit 44f82b13d3
2 changed files with 90 additions and 9 deletions
+34
View File
@@ -122,6 +122,40 @@ class TestInstrumentColumnAccess:
assert "df['instrument']" not in result
class TestInstrumentLocMultiindex:
def test_loc_replaced_with_xs(self, fixer):
code = (
"for instrument in df.index.get_level_values('instrument').unique():\n"
" inst_df = df.loc[instrument].copy()\n"
)
result = fixer.fix(code)
assert "df.xs(instrument, level=1)" in result
assert "df.loc[instrument]" not in result
def test_loc_replaced_with_level1_int(self, fixer):
code = (
"for inst in df.index.get_level_values(1).unique():\n"
" data = df.loc[inst]\n"
)
result = fixer.fix(code)
assert "df.xs(inst, level=1)" in result
def test_loc_assignment_not_touched(self, fixer):
# Write-back df.loc[instrument] = ... must not be changed
code = (
"for instrument in df.index.get_level_values('instrument').unique():\n"
" df.loc[instrument] = modified\n"
)
result = fixer.fix(code)
assert "df.loc[instrument] = modified" in result
def test_non_instrument_loop_not_touched(self, fixer):
# for-loop not related to instrument levels must not be changed
code = "for date in dates:\n sub = df.loc[date]\n"
result = fixer.fix(code)
assert "df.loc[date]" in result
class TestRollingDdof:
def test_removes_ddof_from_rolling_args(self, fixer):
result = fixer.fix("df.rolling(20, min_periods=1, ddof=1).std()")