TYP: type all arguments with int default values (pandas-dev#48761)

* TYP: type all arguments with int default values

* multiindex

* _get_ordinal_range

* fix plotting/_matplotlib/hist.py

* mark only bins as keyword-only

Author: twoertwein

.pre-commit-config.yaml

@@ -268,7 +268,7 @@ repos:
             |/_testing/
     -   id: autotyping
         name: autotyping
-        entry: python -m libcst.tool codemod autotyping.AutotypeCommand --none-return --scalar-return --annotate-magics --annotate-imprecise-magics --bool-param --bytes-param --str-param --float-param
+        entry: python -m libcst.tool codemod autotyping.AutotypeCommand --aggressive
         types_or: [python, pyi]
         files: ^pandas
         exclude: ^(pandas/tests|pandas/_version.py|pandas/io/clipboard)

pandas/_config/config.py

@@ -704,7 +704,7 @@ def _build_option_description(k: str) -> str:
     return s
 
 
-def pp_options_list(keys: Iterable[str], width=80, _print: bool = False):
+def pp_options_list(keys: Iterable[str], width: int = 80, _print: bool = False):
     """Builds a concise listing of available options, grouped by prefix"""
     from itertools import groupby
     from textwrap import wrap

pandas/_testing/__init__.py

@@ -341,33 +341,35 @@ def getCols(k) -> str:
 
 
 # make index
-def makeStringIndex(k=10, name=None) -> Index:
+def makeStringIndex(k: int = 10, name=None) -> Index:
     return Index(rands_array(nchars=10, size=k), name=name)
 
 
-def makeCategoricalIndex(k=10, n=3, name=None, **kwargs) -> CategoricalIndex:
+def makeCategoricalIndex(
+    k: int = 10, n: int = 3, name=None, **kwargs
+) -> CategoricalIndex:
     """make a length k index or n categories"""
     x = rands_array(nchars=4, size=n, replace=False)
     return CategoricalIndex(
         Categorical.from_codes(np.arange(k) % n, categories=x), name=name, **kwargs
     )
 
 
-def makeIntervalIndex(k=10, name=None, **kwargs) -> IntervalIndex:
+def makeIntervalIndex(k: int = 10, name=None, **kwargs) -> IntervalIndex:
     """make a length k IntervalIndex"""
     x = np.linspace(0, 100, num=(k + 1))
     return IntervalIndex.from_breaks(x, name=name, **kwargs)
 
 
-def makeBoolIndex(k=10, name=None) -> Index:
+def makeBoolIndex(k: int = 10, name=None) -> Index:
     if k == 1:
         return Index([True], name=name)
     elif k == 2:
         return Index([False, True], name=name)
     return Index([False, True] + [False] * (k - 2), name=name)
 
 
-def makeNumericIndex(k=10, name=None, *, dtype) -> NumericIndex:
+def makeNumericIndex(k: int = 10, name=None, *, dtype) -> NumericIndex:
     dtype = pandas_dtype(dtype)
     assert isinstance(dtype, np.dtype)
 
@@ -385,21 +387,21 @@ def makeNumericIndex(k=10, name=None, *, dtype) -> NumericIndex:
     return NumericIndex(values, dtype=dtype, name=name)
 
 
-def makeIntIndex(k=10, name=None) -> Int64Index:
+def makeIntIndex(k: int = 10, name=None) -> Int64Index:
     base_idx = makeNumericIndex(k, name=name, dtype="int64")
     return Int64Index(base_idx)
 
 
-def makeUIntIndex(k=10, name=None) -> UInt64Index:
+def makeUIntIndex(k: int = 10, name=None) -> UInt64Index:
     base_idx = makeNumericIndex(k, name=name, dtype="uint64")
     return UInt64Index(base_idx)
 
 
-def makeRangeIndex(k=10, name=None, **kwargs) -> RangeIndex:
+def makeRangeIndex(k: int = 10, name=None, **kwargs) -> RangeIndex:
     return RangeIndex(0, k, 1, name=name, **kwargs)
 
 
-def makeFloatIndex(k=10, name=None) -> Float64Index:
+def makeFloatIndex(k: int = 10, name=None) -> Float64Index:
     base_idx = makeNumericIndex(k, name=name, dtype="float64")
     return Float64Index(base_idx)
 
@@ -423,7 +425,7 @@ def makePeriodIndex(k: int = 10, name=None, **kwargs) -> PeriodIndex:
     return pd.period_range(start=dt, periods=k, freq="B", name=name, **kwargs)
 
 
-def makeMultiIndex(k=10, names=None, **kwargs):
+def makeMultiIndex(k: int = 10, names=None, **kwargs):
     N = (k // 2) + 1
     rng = range(N)
     mi = MultiIndex.from_product([("foo", "bar"), rng], names=names, **kwargs)
@@ -665,8 +667,8 @@ def makeCustomDataframe(
     ncols,
     c_idx_names: bool | list[str] = True,
     r_idx_names: bool | list[str] = True,
-    c_idx_nlevels=1,
-    r_idx_nlevels=1,
+    c_idx_nlevels: int = 1,
+    r_idx_nlevels: int = 1,
     data_gen_f=None,
     c_ndupe_l=None,
     r_ndupe_l=None,

pandas/core/arrays/_mixins.py

@@ -250,7 +250,7 @@ def _validate_searchsorted_value(
             return value
 
     @doc(ExtensionArray.shift)
-    def shift(self, periods=1, fill_value=None, axis=0):
+    def shift(self, periods: int = 1, fill_value=None, axis: AxisInt = 0):
 
         fill_value = self._validate_shift_value(fill_value)
         new_values = shift(self._ndarray, periods, axis, fill_value)

pandas/core/arrays/masked.py

@@ -1062,7 +1062,12 @@ def _wrap_reduction_result(self, name: str, result, skipna, **kwargs):
         return result
 
     def sum(
-        self, *, skipna: bool = True, min_count=0, axis: AxisInt | None = 0, **kwargs
+        self,
+        *,
+        skipna: bool = True,
+        min_count: int = 0,
+        axis: AxisInt | None = 0,
+        **kwargs,
     ):
         nv.validate_sum((), kwargs)
 
@@ -1085,7 +1090,12 @@ def sum(
         )
 
     def prod(
-        self, *, skipna: bool = True, min_count=0, axis: AxisInt | None = 0, **kwargs
+        self,
+        *,
+        skipna: bool = True,
+        min_count: int = 0,
+        axis: AxisInt | None = 0,
+        **kwargs,
     ):
         nv.validate_prod((), kwargs)
         result = masked_reductions.prod(

pandas/core/arrays/numpy_.py

@@ -243,7 +243,12 @@ def max(
         return self._wrap_reduction_result(axis, result)
 
     def sum(
-        self, *, axis: AxisInt | None = None, skipna: bool = True, min_count=0, **kwargs
+        self,
+        *,
+        axis: AxisInt | None = None,
+        skipna: bool = True,
+        min_count: int = 0,
+        **kwargs,
     ) -> Scalar:
         nv.validate_sum((), kwargs)
         result = nanops.nansum(
@@ -252,7 +257,12 @@ def sum(
         return self._wrap_reduction_result(axis, result)
 
     def prod(
-        self, *, axis: AxisInt | None = None, skipna: bool = True, min_count=0, **kwargs
+        self,
+        *,
+        axis: AxisInt | None = None,
+        skipna: bool = True,
+        min_count: int = 0,
+        **kwargs,
     ) -> Scalar:
         nv.validate_prod((), kwargs)
         result = nanops.nanprod(
@@ -294,7 +304,7 @@ def std(
         axis: AxisInt | None = None,
         dtype: NpDtype | None = None,
         out=None,
-        ddof=1,
+        ddof: int = 1,
         keepdims: bool = False,
         skipna: bool = True,
     ):
@@ -310,7 +320,7 @@ def var(
         axis: AxisInt | None = None,
         dtype: NpDtype | None = None,
         out=None,
-        ddof=1,
+        ddof: int = 1,
         keepdims: bool = False,
         skipna: bool = True,
     ):
@@ -326,7 +336,7 @@ def sem(
         axis: AxisInt | None = None,
         dtype: NpDtype | None = None,
         out=None,
-        ddof=1,
+        ddof: int = 1,
         keepdims: bool = False,
         skipna: bool = True,
     ):

pandas/core/arrays/period.py

@@ -1067,7 +1067,7 @@ def dt64arr_to_periodarr(
     return c_dt64arr_to_periodarr(data.view("i8"), base, tz, reso=reso), freq
 
 
-def _get_ordinal_range(start, end, periods, freq, mult=1):
+def _get_ordinal_range(start, end, periods, freq, mult: int = 1):
     if com.count_not_none(start, end, periods) != 2:
         raise ValueError(
             "Of the three parameters: start, end, and periods, "

pandas/core/arrays/sparse/array.py

@@ -32,6 +32,7 @@
 from pandas._typing import (
     ArrayLike,
     AstypeArg,
+    Axis,
     AxisInt,
     Dtype,
     NpDtype,
@@ -1479,7 +1480,7 @@ def all(self, axis=None, *args, **kwargs):
 
         return values.all()
 
-    def any(self, axis=0, *args, **kwargs):
+    def any(self, axis: AxisInt = 0, *args, **kwargs):
         """
         Tests whether at least one of elements evaluate True
 
@@ -1576,7 +1577,7 @@ def cumsum(self, axis: AxisInt = 0, *args, **kwargs) -> SparseArray:
             fill_value=self.fill_value,
         )
 
-    def mean(self, axis=0, *args, **kwargs):
+    def mean(self, axis: Axis = 0, *args, **kwargs):
         """
         Mean of non-NA/null values
 

pandas/core/arrays/string_arrow.py

@@ -310,7 +310,7 @@ def _str_map(
             return lib.map_infer_mask(arr, f, mask.view("uint8"))
 
     def _str_contains(
-        self, pat, case: bool = True, flags=0, na=np.nan, regex: bool = True
+        self, pat, case: bool = True, flags: int = 0, na=np.nan, regex: bool = True
     ):
         if flags:
             fallback_performancewarning()

pandas/core/base.py

@@ -25,6 +25,7 @@
 import pandas._libs.lib as lib
 from pandas._typing import (
     ArrayLike,
+    Axis,
     AxisInt,
     DtypeObj,
     IndexLabel,
@@ -784,7 +785,7 @@ def _reduce(
         op,
         name: str,
         *,
-        axis=0,
+        axis: Axis = 0,
         skipna: bool = True,
         numeric_only=None,
         filter_type=None,

pandas/core/computation/eval.py

@@ -176,7 +176,7 @@ def eval(
     local_dict=None,
     global_dict=None,
     resolvers=(),
-    level=0,
+    level: int = 0,
     target=None,
     inplace: bool = False,
 ):

pandas/core/dtypes/concat.py

@@ -337,7 +337,7 @@ def _concatenate_2d(to_concat, axis: AxisInt):
     return np.concatenate(to_concat, axis=axis)
 
 
-def _concat_datetime(to_concat, axis=0):
+def _concat_datetime(to_concat, axis: AxisInt = 0):
     """
     provide concatenation of an datetimelike array of arrays each of which is a
     single M8[ns], datetime64[ns, tz] or m8[ns] dtype

pandas/core/frame.py

@@ -10867,7 +10867,7 @@ def func(values: np.ndarray):
             # We only use this in the case that operates on self.values
             return op(values, axis=axis, skipna=skipna, **kwds)
 
-        def blk_func(values, axis=1):
+        def blk_func(values, axis: Axis = 1):
             if isinstance(values, ExtensionArray):
                 if not is_1d_only_ea_dtype(values.dtype) and not isinstance(
                     self._mgr, ArrayManager