STYLE: enable pylint warnings for cell-var-from-loop (pandas-dev#49445)

* STYLE: Refactored one loop, suppressed three false positives.

* Oooh, didn't think of that.

* I need to get better at spotting this stuff.

* Yeah, let's not suppress those after all.

* Accidentally removed a newline.

* Helps to revert to correct version of file.

* OK, backing slowly away from the git client now.

* OK, backing slowly away from the git client now.

* Resolve autotyper find

* Added type hints per reviewer note.

* Update pandas/core/strings/object_array.py

Co-authored-by: Marco Edward Gorelli <[email protected]>

* Update pandas/tests/io/parser/test_c_parser_only.py

Co-authored-by: Marco Edward Gorelli <[email protected]>

Co-authored-by: William Blum <[email protected]>
Co-authored-by: Marco Edward Gorelli <[email protected]>

Author: 3 people

pandas/core/strings/object_array.py

@@ -1,6 +1,7 @@
 from __future__ import annotations
 
 from collections.abc import Callable  # noqa: PDF001
+import functools
 import re
 import textwrap
 from typing import (
@@ -380,9 +381,14 @@ def _str_get_dummies(self, sep: str = "|"):
 
         dummies = np.empty((len(arr), len(tags2)), dtype=np.int64)
 
+        def _isin(test_elements: str, element: str) -> bool:
+            return element in test_elements
+
         for i, t in enumerate(tags2):
             pat = sep + t + sep
-            dummies[:, i] = lib.map_infer(arr.to_numpy(), lambda x: pat in x)
+            dummies[:, i] = lib.map_infer(
+                arr.to_numpy(), functools.partial(_isin, element=pat)
+            )
         return dummies, tags2
 
     def _str_upper(self):

pandas/io/pytables.py

@@ -4094,44 +4094,44 @@ def process_axes(self, obj, selection: Selection, columns=None) -> DataFrame:
         for axis, labels in self.non_index_axes:
             obj = _reindex_axis(obj, axis, labels, columns)
 
-        # apply the selection filters (but keep in the same order)
-        if selection.filter is not None:
-            for field, op, filt in selection.filter.format():
+            def process_filter(field, filt, op):
 
-                def process_filter(field, filt):
+                for axis_name in obj._AXIS_ORDERS:
+                    axis_number = obj._get_axis_number(axis_name)
+                    axis_values = obj._get_axis(axis_name)
+                    assert axis_number is not None
 
-                    for axis_name in obj._AXIS_ORDERS:
-                        axis_number = obj._get_axis_number(axis_name)
-                        axis_values = obj._get_axis(axis_name)
-                        assert axis_number is not None
+                    # see if the field is the name of an axis
+                    if field == axis_name:
 
-                        # see if the field is the name of an axis
-                        if field == axis_name:
+                        # if we have a multi-index, then need to include
+                        # the levels
+                        if self.is_multi_index:
+                            filt = filt.union(Index(self.levels))
 
-                            # if we have a multi-index, then need to include
-                            # the levels
-                            if self.is_multi_index:
-                                filt = filt.union(Index(self.levels))
+                        takers = op(axis_values, filt)
+                        return obj.loc(axis=axis_number)[takers]
 
-                            takers = op(axis_values, filt)
-                            return obj.loc(axis=axis_number)[takers]
+                    # this might be the name of a file IN an axis
+                    elif field in axis_values:
 
-                        # this might be the name of a file IN an axis
-                        elif field in axis_values:
+                        # we need to filter on this dimension
+                        values = ensure_index(getattr(obj, field).values)
+                        filt = ensure_index(filt)
 
-                            # we need to filter on this dimension
-                            values = ensure_index(getattr(obj, field).values)
-                            filt = ensure_index(filt)
+                        # hack until we support reversed dim flags
+                        if isinstance(obj, DataFrame):
+                            axis_number = 1 - axis_number
 
-                            # hack until we support reversed dim flags
-                            if isinstance(obj, DataFrame):
-                                axis_number = 1 - axis_number
-                            takers = op(values, filt)
-                            return obj.loc(axis=axis_number)[takers]
+                        takers = op(values, filt)
+                        return obj.loc(axis=axis_number)[takers]
 
-                    raise ValueError(f"cannot find the field [{field}] for filtering!")
+                raise ValueError(f"cannot find the field [{field}] for filtering!")
 
-                obj = process_filter(field, filt)
+        # apply the selection filters (but keep in the same order)
+        if selection.filter is not None:
+            for field, op, filt in selection.filter.format():
+                obj = process_filter(field, filt, op)
 
         return obj
 

pandas/tests/io/parser/test_c_parser_only.py

@@ -176,6 +176,9 @@ def test_precise_conversion(c_parser_only):
     normal_errors = []
     precise_errors = []
 
+    def error(val: float, actual_val: Decimal) -> Decimal:
+        return abs(Decimal(f"{val:.100}") - actual_val)
+
     # test numbers between 1 and 2
     for num in np.linspace(1.0, 2.0, num=500):
         # 25 decimal digits of precision
@@ -192,11 +195,8 @@ def test_precise_conversion(c_parser_only):
         )
         actual_val = Decimal(text[2:])
 
-        def error(val):
-            return abs(Decimal(f"{val:.100}") - actual_val)
-
-        normal_errors.append(error(normal_val))
-        precise_errors.append(error(precise_val))
+        normal_errors.append(error(normal_val, actual_val))
+        precise_errors.append(error(precise_val, actual_val))
 
         # round-trip should match float()
         assert roundtrip_val == float(text[2:])

pyproject.toml

@@ -137,7 +137,6 @@ disable = [
   "arguments-renamed",
   "attribute-defined-outside-init",
   "broad-except",
-  "cell-var-from-loop",
   "comparison-with-callable",
   "confusing-with-statement",
   "dangerous-default-value",