ENH: Allow performance warnings to be disabled (#56921)

* ENH: Allow performance warnings to be disabled

* ENH: Allow performance warnings to be disabled

* Add tests

* fixup

Author: rhshadrach

doc/source/whatsnew/v3.0.0.rst

@@ -33,6 +33,7 @@ Other enhancements
 - :meth:`Styler.set_tooltips` provides alternative method to storing tooltips by using title attribute of td elements. (:issue:`56981`)
 - Allow dictionaries to be passed to :meth:`pandas.Series.str.replace` via ``pat`` parameter (:issue:`51748`)
 - Support passing a :class:`Series` input to :func:`json_normalize` that retains the :class:`Series` :class:`Index` (:issue:`51452`)
+- Users can globally disable any ``PerformanceWarning`` by setting the option ``mode.performance_warnings`` to ``False`` (:issue:`56920`)
 -
 
 .. ---------------------------------------------------------------------------

pandas/conftest.py

@@ -1983,6 +1983,16 @@ def indexer_ial(request):
     return request.param
 
 
+@pytest.fixture(params=[True, False])
+def performance_warning(request) -> Iterator[bool | type[Warning]]:
+    """
+    Fixture to check if performance warnings are enabled. Either produces
+    ``PerformanceWarning`` if they are enabled, otherwise ``False``.
+    """
+    with pd.option_context("mode.performance_warnings", request.param):
+        yield pd.errors.PerformanceWarning if request.param else False
+
+
 @pytest.fixture
 def using_infer_string() -> bool:
     """

pandas/core/arrays/arrow/_arrow_utils.py

@@ -5,6 +5,8 @@
 import numpy as np
 import pyarrow
 
+from pandas._config.config import _get_option
+
 from pandas.errors import PerformanceWarning
 from pandas.util._exceptions import find_stack_level
 
@@ -14,10 +16,11 @@ def fallback_performancewarning(version: str | None = None) -> None:
     Raise a PerformanceWarning for falling back to ExtensionArray's
     non-pyarrow method
     """
-    msg = "Falling back on a non-pyarrow code path which may decrease performance."
-    if version is not None:
-        msg += f" Upgrade to pyarrow >={version} to possibly suppress this warning."
-    warnings.warn(msg, PerformanceWarning, stacklevel=find_stack_level())
+    if _get_option("performance_warnings"):
+        msg = "Falling back on a non-pyarrow code path which may decrease performance."
+        if version is not None:
+            msg += f" Upgrade to pyarrow >={version} to possibly suppress this warning."
+        warnings.warn(msg, PerformanceWarning, stacklevel=find_stack_level())
 
 
 def pyarrow_array_to_numpy_and_mask(

pandas/core/arrays/datetimelike.py

@@ -20,6 +20,8 @@
 
 import numpy as np
 
+from pandas._config.config import _get_option
+
 from pandas._libs import (
     algos,
     lib,
@@ -1332,12 +1334,13 @@ def _addsub_object_array(self, other: npt.NDArray[np.object_], op) -> np.ndarray
             # If both 1D then broadcasting is unambiguous
             return op(self, other[0])
 
-        warnings.warn(
-            "Adding/subtracting object-dtype array to "
-            f"{type(self).__name__} not vectorized.",
-            PerformanceWarning,
-            stacklevel=find_stack_level(),
-        )
+        if _get_option("performance_warnings"):
+            warnings.warn(
+                "Adding/subtracting object-dtype array to "
+                f"{type(self).__name__} not vectorized.",
+                PerformanceWarning,
+                stacklevel=find_stack_level(),
+            )
 
         # Caller is responsible for broadcasting if necessary
         assert self.shape == other.shape, (self.shape, other.shape)

pandas/core/arrays/datetimes.py

@@ -15,6 +15,8 @@
 
 import numpy as np
 
+from pandas._config.config import _get_option
+
 from pandas._libs import (
     lib,
     tslib,
@@ -818,11 +820,13 @@ def _add_offset(self, offset: BaseOffset) -> Self:
                 # "dtype[Any] | type[Any] | _SupportsDType[dtype[Any]]"
                 res_values = res_values.view(values.dtype)  # type: ignore[arg-type]
         except NotImplementedError:
-            warnings.warn(
-                "Non-vectorized DateOffset being applied to Series or DatetimeIndex.",
-                PerformanceWarning,
-                stacklevel=find_stack_level(),
-            )
+            if _get_option("performance_warnings"):
+                warnings.warn(
+                    "Non-vectorized DateOffset being applied to Series or "
+                    "DatetimeIndex.",
+                    PerformanceWarning,
+                    stacklevel=find_stack_level(),
+                )
             res_values = self.astype("O") + offset
             # TODO(GH#55564): as_unit will be unnecessary
             result = type(self)._from_sequence(res_values).as_unit(self.unit)

pandas/core/arrays/sparse/array.py

@@ -18,6 +18,8 @@
 
 import numpy as np
 
+from pandas._config.config import _get_option
+
 from pandas._libs import lib
 import pandas._libs.sparse as splib
 from pandas._libs.sparse import (
@@ -1154,8 +1156,9 @@ def searchsorted(
         side: Literal["left", "right"] = "left",
         sorter: NumpySorter | None = None,
     ) -> npt.NDArray[np.intp] | np.intp:
-        msg = "searchsorted requires high memory usage."
-        warnings.warn(msg, PerformanceWarning, stacklevel=find_stack_level())
+        if _get_option("performance_warnings"):
+            msg = "searchsorted requires high memory usage."
+            warnings.warn(msg, PerformanceWarning, stacklevel=find_stack_level())
         v = np.asarray(v)
         return np.asarray(self, dtype=self.dtype.subtype).searchsorted(v, side, sorter)
 

pandas/core/arrays/string_arrow.py

@@ -12,6 +12,8 @@
 
 import numpy as np
 
+from pandas._config.config import _get_option
+
 from pandas._libs import (
     lib,
     missing as libmissing,
@@ -343,7 +345,8 @@ def _str_contains(
         self, pat, case: bool = True, flags: int = 0, na=np.nan, regex: bool = True
     ):
         if flags:
-            fallback_performancewarning()
+            if _get_option("mode.performance_warnings"):
+                fallback_performancewarning()
             return super()._str_contains(pat, case, flags, na, regex)
 
         if regex:
@@ -403,7 +406,8 @@ def _str_replace(
         regex: bool = True,
     ):
         if isinstance(pat, re.Pattern) or callable(repl) or not case or flags:
-            fallback_performancewarning()
+            if _get_option("mode.performance_warnings"):
+                fallback_performancewarning()
             return super()._str_replace(pat, repl, n, case, flags, regex)
 
         func = pc.replace_substring_regex if regex else pc.replace_substring

pandas/core/computation/align.py

@@ -15,6 +15,8 @@
 
 import numpy as np
 
+from pandas._config.config import _get_option
+
 from pandas.errors import PerformanceWarning
 from pandas.util._exceptions import find_stack_level
 
@@ -124,7 +126,11 @@ def _align_core(terms):
                 reindexer_size = len(reindexer)
 
                 ordm = np.log10(max(1, abs(reindexer_size - term_axis_size)))
-                if ordm >= 1 and reindexer_size >= 10000:
+                if (
+                    _get_option("performance_warnings")
+                    and ordm >= 1
+                    and reindexer_size >= 10000
+                ):
                     w = (
                         f"Alignment difference on axis {axis} is larger "
                         f"than an order of magnitude on term {terms[i].name!r}, "

pandas/core/config_init.py

@@ -444,6 +444,19 @@ def is_terminal() -> bool:
         validator=is_one_of_factory([None, "warn", "raise"]),
     )
 
+performance_warnings = """
+: boolean
+    Whether to show or hide PerformanceWarnings.
+"""
+
+with cf.config_prefix("mode"):
+    cf.register_option(
+        "performance_warnings",
+        True,
+        performance_warnings,
+        validator=is_bool,
+    )
+
 
 string_storage_doc = """
 : string

pandas/core/dtypes/dtypes.py

@@ -21,6 +21,8 @@
 import numpy as np
 import pytz
 
+from pandas._config.config import _get_option
+
 from pandas._libs import (
     lib,
     missing as libmissing,
@@ -2028,7 +2030,9 @@ def _get_common_dtype(self, dtypes: list[DtypeObj]) -> DtypeObj | None:
 
         # np.nan isn't a singleton, so we may end up with multiple
         # NaNs here, so we ignore the all NA case too.
-        if not (len(set(fill_values)) == 1 or isna(fill_values).all()):
+        if _get_option("performance_warnings") and (
+            not (len(set(fill_values)) == 1 or isna(fill_values).all())
+        ):
             warnings.warn(
                 "Concatenating sparse arrays with multiple fill "
                 f"values: '{fill_values}'. Picking the first and "

pandas/core/indexes/multi.py

@@ -21,6 +21,7 @@
 import numpy as np
 
 from pandas._config import get_option
+from pandas._config.config import _get_option
 
 from pandas._libs import (
     algos as libalgos,
@@ -2356,7 +2357,7 @@ def drop(  # type: ignore[override]
                     step = loc.step if loc.step is not None else 1
                     inds.extend(range(loc.start, loc.stop, step))
                 elif com.is_bool_indexer(loc):
-                    if self._lexsort_depth == 0:
+                    if _get_option("performance_warnings") and self._lexsort_depth == 0:
                         warnings.warn(
                             "dropping on a non-lexsorted multi-index "
                             "without a level parameter may impact performance.",
@@ -3018,11 +3019,12 @@ def _maybe_to_slice(loc):
         if not follow_key:
             return slice(start, stop)
 
-        warnings.warn(
-            "indexing past lexsort depth may impact performance.",
-            PerformanceWarning,
-            stacklevel=find_stack_level(),
-        )
+        if _get_option("performance_warnings"):
+            warnings.warn(
+                "indexing past lexsort depth may impact performance.",
+                PerformanceWarning,
+                stacklevel=find_stack_level(),
+            )
 
         loc = np.arange(start, stop, dtype=np.intp)
 

pandas/core/internals/managers.py

@@ -18,6 +18,8 @@
 
 import numpy as np
 
+from pandas._config.config import _get_option
+
 from pandas._libs import (
     algos as libalgos,
     internals as libinternals,
@@ -1526,7 +1528,10 @@ def insert(self, loc: int, item: Hashable, value: ArrayLike, refs=None) -> None:
 
         self._known_consolidated = False
 
-        if sum(not block.is_extension for block in self.blocks) > 100:
+        if (
+            _get_option("performance_warnings")
+            and sum(not block.is_extension for block in self.blocks) > 100
+        ):
             warnings.warn(
                 "DataFrame is highly fragmented.  This is usually the result "
                 "of calling `frame.insert` many times, which has poor performance.  "

pandas/core/reshape/reshape.py

@@ -10,6 +10,8 @@
 
 import numpy as np
 
+from pandas._config.config import _get_option
+
 import pandas._libs.reshape as libreshape
 from pandas.errors import PerformanceWarning
 from pandas.util._decorators import cache_readonly
@@ -144,7 +146,7 @@ def __init__(
         num_cells = num_rows * num_columns
 
         # GH 26314: Previous ValueError raised was too restrictive for many users.
-        if num_cells > np.iinfo(np.int32).max:
+        if _get_option("performance_warnings") and num_cells > np.iinfo(np.int32).max:
             warnings.warn(
                 f"The following operation may generate {num_cells} cells "
                 f"in the resulting pandas object.",

pandas/io/pytables.py

@@ -32,6 +32,7 @@
     get_option,
     using_pyarrow_string_dtype,
 )
+from pandas._config.config import _get_option
 
 from pandas._libs import (
     lib,
@@ -3143,7 +3144,7 @@ def write_array(
                 pass
             elif inferred_type == "string":
                 pass
-            else:
+            elif _get_option("performance_warnings"):
                 ws = performance_doc % (inferred_type, key, items)
                 warnings.warn(ws, PerformanceWarning, stacklevel=find_stack_level())