Fix some typing errors (#57795)

* Fix some typing errors

* Fix some typing errors

* Fix some typing errors

* Fix some typing errors

* Fix some typing errors

* Fix some typing errors

* Fix some typing errors

* Fix some typing errors

* Fix some typing errors

* Fix some typing errors

* Fix some typing errors

* Fix some typing errors

* Review

* Review

Author: tqa236

pandas/compat/pickle_compat.py

@@ -64,7 +64,7 @@
 # our Unpickler sub-class to override methods and some dispatcher
 # functions for compat and uses a non-public class of the pickle module.
 class Unpickler(pickle._Unpickler):
-    def find_class(self, module, name):
+    def find_class(self, module: str, name: str) -> Any:
         key = (module, name)
         module, name = _class_locations_map.get(key, key)
         return super().find_class(module, name)

pandas/core/array_algos/datetimelike_accumulations.py

@@ -18,7 +18,7 @@ def _cum_func(
     values: np.ndarray,
     *,
     skipna: bool = True,
-):
+) -> np.ndarray:
     """
     Accumulations for 1D datetimelike arrays.
 
@@ -61,9 +61,9 @@ def cumsum(values: np.ndarray, *, skipna: bool = True) -> np.ndarray:
     return _cum_func(np.cumsum, values, skipna=skipna)
 
 
-def cummin(values: np.ndarray, *, skipna: bool = True):
+def cummin(values: np.ndarray, *, skipna: bool = True) -> np.ndarray:
     return _cum_func(np.minimum.accumulate, values, skipna=skipna)
 
 
-def cummax(values: np.ndarray, *, skipna: bool = True):
+def cummax(values: np.ndarray, *, skipna: bool = True) -> np.ndarray:
     return _cum_func(np.maximum.accumulate, values, skipna=skipna)

pandas/core/array_algos/masked_accumulations.py

@@ -22,7 +22,7 @@ def _cum_func(
     mask: npt.NDArray[np.bool_],
     *,
     skipna: bool = True,
-):
+) -> tuple[np.ndarray, npt.NDArray[np.bool_]]:
     """
     Accumulations for 1D masked array.
 
@@ -74,17 +74,25 @@ def _cum_func(
     return values, mask
 
 
-def cumsum(values: np.ndarray, mask: npt.NDArray[np.bool_], *, skipna: bool = True):
+def cumsum(
+    values: np.ndarray, mask: npt.NDArray[np.bool_], *, skipna: bool = True
+) -> tuple[np.ndarray, npt.NDArray[np.bool_]]:
     return _cum_func(np.cumsum, values, mask, skipna=skipna)
 
 
-def cumprod(values: np.ndarray, mask: npt.NDArray[np.bool_], *, skipna: bool = True):
+def cumprod(
+    values: np.ndarray, mask: npt.NDArray[np.bool_], *, skipna: bool = True
+) -> tuple[np.ndarray, npt.NDArray[np.bool_]]:
     return _cum_func(np.cumprod, values, mask, skipna=skipna)
 
 
-def cummin(values: np.ndarray, mask: npt.NDArray[np.bool_], *, skipna: bool = True):
+def cummin(
+    values: np.ndarray, mask: npt.NDArray[np.bool_], *, skipna: bool = True
+) -> tuple[np.ndarray, npt.NDArray[np.bool_]]:
     return _cum_func(np.minimum.accumulate, values, mask, skipna=skipna)
 
 
-def cummax(values: np.ndarray, mask: npt.NDArray[np.bool_], *, skipna: bool = True):
+def cummax(
+    values: np.ndarray, mask: npt.NDArray[np.bool_], *, skipna: bool = True
+) -> tuple[np.ndarray, npt.NDArray[np.bool_]]:
     return _cum_func(np.maximum.accumulate, values, mask, skipna=skipna)

pandas/core/config_init.py

@@ -37,7 +37,7 @@
 """
 
 
-def use_bottleneck_cb(key) -> None:
+def use_bottleneck_cb(key: str) -> None:
     from pandas.core import nanops
 
     nanops.set_use_bottleneck(cf.get_option(key))
@@ -51,7 +51,7 @@ def use_bottleneck_cb(key) -> None:
 """
 
 
-def use_numexpr_cb(key) -> None:
+def use_numexpr_cb(key: str) -> None:
     from pandas.core.computation import expressions
 
     expressions.set_use_numexpr(cf.get_option(key))
@@ -65,7 +65,7 @@ def use_numexpr_cb(key) -> None:
 """
 
 
-def use_numba_cb(key) -> None:
+def use_numba_cb(key: str) -> None:
     from pandas.core.util import numba_
 
     numba_.set_use_numba(cf.get_option(key))
@@ -287,7 +287,7 @@ def use_numba_cb(key) -> None:
 """
 
 
-def table_schema_cb(key) -> None:
+def table_schema_cb(key: str) -> None:
     from pandas.io.formats.printing import enable_data_resource_formatter
 
     enable_data_resource_formatter(cf.get_option(key))
@@ -612,7 +612,7 @@ def is_terminal() -> bool:
 """
 
 
-def register_plotting_backend_cb(key) -> None:
+def register_plotting_backend_cb(key: str | None) -> None:
     if key == "matplotlib":
         # We defer matplotlib validation, since it's the default
         return
@@ -626,7 +626,7 @@ def register_plotting_backend_cb(key) -> None:
         "backend",
         defval="matplotlib",
         doc=plotting_backend_doc,
-        validator=register_plotting_backend_cb,
+        validator=register_plotting_backend_cb,  # type: ignore[arg-type]
     )
 
 
@@ -638,7 +638,7 @@ def register_plotting_backend_cb(key) -> None:
 """
 
 
-def register_converter_cb(key) -> None:
+def register_converter_cb(key: str) -> None:
     from pandas.plotting import (
         deregister_matplotlib_converters,
         register_matplotlib_converters,

pandas/core/dtypes/concat.py

@@ -42,7 +42,7 @@
     )
 
 
-def _is_nonempty(x, axis) -> bool:
+def _is_nonempty(x: ArrayLike, axis: AxisInt) -> bool:
     # filter empty arrays
     # 1-d dtypes always are included here
     if x.ndim <= axis:

pandas/core/groupby/categorical.py

@@ -50,7 +50,7 @@ def recode_for_groupby(
         # In cases with c.ordered, this is equivalent to
         #  return c.remove_unused_categories(), c
 
-        unique_codes = unique1d(c.codes)
+        unique_codes = unique1d(c.codes)  # type: ignore[no-untyped-call]
 
         take_codes = unique_codes[unique_codes != -1]
         if sort:
@@ -74,7 +74,7 @@ def recode_for_groupby(
     # xref GH:46909: Re-ordering codes faster than using (set|add|reorder)_categories
     all_codes = np.arange(c.categories.nunique())
     # GH 38140: exclude nan from indexer for categories
-    unique_notnan_codes = unique1d(c.codes[c.codes != -1])
+    unique_notnan_codes = unique1d(c.codes[c.codes != -1])  # type: ignore[no-untyped-call]
     if sort:
         unique_notnan_codes = np.sort(unique_notnan_codes)
     if len(all_codes) > len(unique_notnan_codes):

pandas/core/ops/mask_ops.py

@@ -190,6 +190,6 @@ def kleene_and(
     return result, mask
 
 
-def raise_for_nan(value, method: str) -> None:
+def raise_for_nan(value: object, method: str) -> None:
     if lib.is_float(value) and np.isnan(value):
         raise ValueError(f"Cannot perform logical '{method}' with floating NaN")

pandas/io/formats/console.py

@@ -63,7 +63,7 @@ def in_interactive_session() -> bool:
     """
     from pandas import get_option
 
-    def check_main():
+    def check_main() -> bool:
         try:
             import __main__ as main
         except ModuleNotFoundError:

pandas/io/formats/css.py

@@ -36,7 +36,7 @@ def _side_expander(prop_fmt: str) -> Callable:
         function: Return to call when a 'border(-{side}): {value}' string is encountered
     """
 
-    def expand(self, prop, value: str) -> Generator[tuple[str, str], None, None]:
+    def expand(self, prop: str, value: str) -> Generator[tuple[str, str], None, None]:
         """
         Expand shorthand property into side-specific property (top, right, bottom, left)
 
@@ -81,7 +81,7 @@ def _border_expander(side: str = "") -> Callable:
     if side != "":
         side = f"-{side}"
 
-    def expand(self, prop, value: str) -> Generator[tuple[str, str], None, None]:
+    def expand(self, prop: str, value: str) -> Generator[tuple[str, str], None, None]:
         """
         Expand border into color, style, and width tuples
 

pandas/io/stata.py

@@ -1835,7 +1835,7 @@ def _do_select_columns(self, data: DataFrame, columns: Sequence[str]) -> DataFra
             fmtlist = []
             lbllist = []
             for col in columns:
-                i = data.columns.get_loc(col)
+                i = data.columns.get_loc(col)  # type: ignore[no-untyped-call]
                 dtyplist.append(self._dtyplist[i])
                 typlist.append(self._typlist[i])
                 fmtlist.append(self._fmtlist[i])
@@ -2155,7 +2155,7 @@ def _dtype_to_stata_type(dtype: np.dtype, column: Series) -> int:
 
 
 def _dtype_to_default_stata_fmt(
-    dtype, column: Series, dta_version: int = 114, force_strl: bool = False
+    dtype: np.dtype, column: Series, dta_version: int = 114, force_strl: bool = False
 ) -> str:
     """
     Map numpy dtype to stata's default format for this type. Not terribly
@@ -3467,7 +3467,7 @@ def _write_characteristics(self) -> None:
         self._update_map("characteristics")
         self._write_bytes(self._tag(b"", "characteristics"))
 
-    def _write_data(self, records) -> None:
+    def _write_data(self, records: np.rec.recarray) -> None:
         self._update_map("data")
         self._write_bytes(b"<data>")
         self._write_bytes(records.tobytes())

pandas/util/__init__.py

@@ -25,5 +25,5 @@ def __getattr__(key: str):
     raise AttributeError(f"module 'pandas.util' has no attribute '{key}'")
 
 
-def __dir__():
+def __dir__() -> list[str]:
     return list(globals().keys()) + ["hash_array", "hash_pandas_object"]

pandas/util/_print_versions.py

@@ -33,7 +33,7 @@ def _get_commit_hash() -> str | None:
     except ImportError:
         from pandas._version import get_versions
 
-        versions = get_versions()
+        versions = get_versions()  # type: ignore[no-untyped-call]
         return versions["full-revisionid"]
 
 

pyproject.toml

@@ -567,13 +567,9 @@ module = [
   "pandas._config.config", # TODO
   "pandas._libs.*",
   "pandas._testing.*", # TODO
-  "pandas.arrays", # TODO
   "pandas.compat.numpy.function", # TODO
   "pandas.compat.compressors", # TODO
-  "pandas.compat.pickle_compat", # TODO
   "pandas.core._numba.executor", # TODO
-  "pandas.core.array_algos.datetimelike_accumulations", # TODO
-  "pandas.core.array_algos.masked_accumulations", # TODO
   "pandas.core.array_algos.masked_reductions", # TODO
   "pandas.core.array_algos.putmask", # TODO
   "pandas.core.array_algos.quantile", # TODO
@@ -588,7 +584,6 @@ module = [
   "pandas.core.dtypes.dtypes", # TODO
   "pandas.core.dtypes.generic", # TODO
   "pandas.core.dtypes.missing", # TODO
-  "pandas.core.groupby.categorical", # TODO
   "pandas.core.groupby.generic", # TODO
   "pandas.core.groupby.grouper", # TODO
   "pandas.core.groupby.groupby", # TODO
@@ -603,7 +598,6 @@ module = [
   "pandas.core.ops.array_ops", # TODO
   "pandas.core.ops.common", # TODO
   "pandas.core.ops.invalid", # TODO
-  "pandas.core.ops.mask_ops", # TODO
   "pandas.core.ops.missing", # TODO
   "pandas.core.reshape.*", # TODO
   "pandas.core.strings.*", # TODO
@@ -620,7 +614,6 @@ module = [
   "pandas.core.arraylike", # TODO
   "pandas.core.base", # TODO
   "pandas.core.common", # TODO
-  "pandas.core.config_init", # TODO
   "pandas.core.construction", # TODO
   "pandas.core.flags", # TODO
   "pandas.core.frame", # TODO
@@ -642,11 +635,9 @@ module = [
   "pandas.io.excel._pyxlsb", # TODO
   "pandas.io.excel._xlrd", # TODO
   "pandas.io.excel._xlsxwriter", # TODO
-  "pandas.io.formats.console", # TODO
   "pandas.io.formats.css", # TODO
   "pandas.io.formats.excel", # TODO
   "pandas.io.formats.format", # TODO
-  "pandas.io.formats.info", # TODO
   "pandas.io.formats.printing", # TODO
   "pandas.io.formats.style", # TODO
   "pandas.io.formats.style_render", # TODO
@@ -661,15 +652,13 @@ module = [
   "pandas.io.parquet", # TODO
   "pandas.io.pytables", # TODO
   "pandas.io.sql", # TODO
-  "pandas.io.stata", # TODO
   "pandas.io.xml", # TODO
   "pandas.plotting.*", # TODO
   "pandas.tests.*",
   "pandas.tseries.frequencies", # TODO
   "pandas.tseries.holiday", # TODO
   "pandas.util._decorators", # TODO
   "pandas.util._doctools", # TODO
-  "pandas.util._print_versions", # TODO
   "pandas.util._test_decorators", # TODO
   "pandas.util._validators", # TODO
   "pandas.util", # TODO