Merge remote-tracking branch 'upstream/master' into move-metadata-to-cfg

Author: fangchenli

.pre-commit-config.yaml

@@ -150,7 +150,6 @@ repos:
             (?x)
             \#\ type:\ (?!ignore)
             |\#\ type:\s?ignore(?!\[)
-            |\)\ ->\ \"
         language: pygrep
         types: [python]
     -   id: np-bool
@@ -185,3 +184,7 @@ repos:
     -   id: codespell
         types_or: [python, rst, markdown]
         files: ^pandas/core/
+-   repo: https://github.com/MarcoGorelli/no-string-hints
+    rev: v0.1.5
+    hooks:
+    -   id: no-string-hints

doc/source/whatsnew/v1.3.0.rst

@@ -235,6 +235,7 @@ Datetimelike
 - Bug in :meth:`DatetimeIndex.intersection`, :meth:`DatetimeIndex.symmetric_difference`, :meth:`PeriodIndex.intersection`, :meth:`PeriodIndex.symmetric_difference` always returning object-dtype when operating with :class:`CategoricalIndex` (:issue:`38741`)
 - Bug in :meth:`Series.where` incorrectly casting ``datetime64`` values to ``int64`` (:issue:`37682`)
 - Bug in :class:`Categorical` incorrectly typecasting ``datetime`` object to ``Timestamp`` (:issue:`38878`)
+- Bug in :func:`date_range` incorrectly creating :class:`DatetimeIndex` containing ``NaT`` instead of raising ``OutOfBoundsDatetime`` in corner cases (:issue:`24124`)
 
 Timedelta
 ^^^^^^^^^

pandas/core/aggregation.py

@@ -3,6 +3,8 @@
 kwarg aggregations in groupby and DataFrame/Series aggregation
 """
 
+from __future__ import annotations
+
 from collections import defaultdict
 from functools import partial
 from typing import (
@@ -296,7 +298,7 @@ def relabel_result(
     func: Dict[str, List[Union[Callable, str]]],
     columns: Iterable[Hashable],
     order: Iterable[int],
-) -> Dict[Hashable, "Series"]:
+) -> Dict[Hashable, Series]:
     """
     Internal function to reorder result if relabelling is True for
     dataframe.agg, and return the reordered result in dict.
@@ -323,7 +325,7 @@ def relabel_result(
     reordered_indexes = [
         pair[0] for pair in sorted(zip(columns, order), key=lambda t: t[1])
     ]
-    reordered_result_in_dict: Dict[Hashable, "Series"] = {}
+    reordered_result_in_dict: Dict[Hashable, Series] = {}
     idx = 0
 
     reorder_mask = not isinstance(result, ABCSeries) and len(result.columns) > 1

pandas/core/algorithms.py

@@ -559,7 +559,7 @@ def factorize(
     sort: bool = False,
     na_sentinel: Optional[int] = -1,
     size_hint: Optional[int] = None,
-) -> Tuple[np.ndarray, Union[np.ndarray, "Index"]]:
+) -> Tuple[np.ndarray, Union[np.ndarray, Index]]:
     """
     Encode the object as an enumerated type or categorical variable.
 

pandas/core/arrays/_ranges.py

@@ -7,7 +7,13 @@
 
 import numpy as np
 
-from pandas._libs.tslibs import BaseOffset, OutOfBoundsDatetime, Timedelta, Timestamp
+from pandas._libs.tslibs import (
+    BaseOffset,
+    OutOfBoundsDatetime,
+    Timedelta,
+    Timestamp,
+    iNaT,
+)
 
 
 def generate_regular_range(
@@ -150,7 +156,12 @@ def _generate_range_overflow_safe_signed(
         addend = np.int64(periods) * np.int64(stride)
         try:
             # easy case with no overflows
-            return np.int64(endpoint) + addend
+            result = np.int64(endpoint) + addend
+            if result == iNaT:
+                # Putting this into a DatetimeArray/TimedeltaArray
+                #  would incorrectly be interpreted as NaT
+                raise OverflowError
+            return result
         except (FloatingPointError, OverflowError):
             # with endpoint negative and addend positive we risk
             #  FloatingPointError; with reversed signed we risk OverflowError

pandas/core/arrays/boolean.py

@@ -72,7 +72,7 @@ def numpy_dtype(self) -> np.dtype:
         return np.dtype("bool")
 
     @classmethod
-    def construct_array_type(cls) -> Type["BooleanArray"]:
+    def construct_array_type(cls) -> Type[BooleanArray]:
         """
         Return the array type associated with this dtype.
 
@@ -94,7 +94,7 @@ def _is_numeric(self) -> bool:
         return True
 
     def __from_arrow__(
-        self, array: Union["pyarrow.Array", "pyarrow.ChunkedArray"]
+        self, array: Union[pyarrow.Array, pyarrow.ChunkedArray]
     ) -> BooleanArray:
         """
         Construct BooleanArray from pyarrow Array/ChunkedArray.

pandas/core/arrays/categorical.py

@@ -422,7 +422,7 @@ def dtype(self) -> CategoricalDtype:
         return self._dtype
 
     @property
-    def _constructor(self) -> Type["Categorical"]:
+    def _constructor(self) -> Type[Categorical]:
         return Categorical
 
     @classmethod
@@ -2162,7 +2162,7 @@ def _concat_same_type(
 
     # ------------------------------------------------------------------
 
-    def _encode_with_my_categories(self, other: "Categorical") -> Categorical:
+    def _encode_with_my_categories(self, other: Categorical) -> Categorical:
         """
         Re-encode another categorical using this Categorical's categories.
 
@@ -2179,7 +2179,7 @@ def _encode_with_my_categories(self, other: "Categorical") -> Categorical:
         )
         return self._from_backing_data(codes)
 
-    def _categories_match_up_to_permutation(self, other: "Categorical") -> bool:
+    def _categories_match_up_to_permutation(self, other: Categorical) -> bool:
         """
         Returns True if categoricals are the same dtype
           same categories, and same ordered
@@ -2527,7 +2527,7 @@ def _delegate_method(self, name, *args, **kwargs):
 # utility routines
 
 
-def _get_codes_for_values(values, categories: "Index") -> np.ndarray:
+def _get_codes_for_values(values, categories: Index) -> np.ndarray:
     """
     utility routine to turn values into codes given the specified categories
 

pandas/core/arrays/floating.py

@@ -47,7 +47,7 @@ def _is_numeric(self) -> bool:
         return True
 
     @classmethod
-    def construct_array_type(cls) -> Type["FloatingArray"]:
+    def construct_array_type(cls) -> Type[FloatingArray]:
         """
         Return the array type associated with this dtype.
 

pandas/core/arrays/integer.py

@@ -57,7 +57,7 @@ def _is_numeric(self) -> bool:
         return True
 
     @classmethod
-    def construct_array_type(cls) -> Type["IntegerArray"]:
+    def construct_array_type(cls) -> Type[IntegerArray]:
         """
         Return the array type associated with this dtype.
 

pandas/core/arrays/numeric.py

@@ -1,3 +1,5 @@
+from __future__ import annotations
+
 import datetime
 import numbers
 from typing import TYPE_CHECKING, Any, List, Union
@@ -25,7 +27,7 @@
 
 class NumericDtype(BaseMaskedDtype):
     def __from_arrow__(
-        self, array: Union["pyarrow.Array", "pyarrow.ChunkedArray"]
+        self, array: Union[pyarrow.Array, pyarrow.ChunkedArray]
     ) -> BaseMaskedArray:
         """
         Construct IntegerArray/FloatingArray from pyarrow Array/ChunkedArray.

pandas/core/arrays/numpy_.py

@@ -89,7 +89,7 @@ def construct_from_string(cls, string: str) -> PandasDtype:
         return cls(dtype)
 
     @classmethod
-    def construct_array_type(cls) -> Type["PandasArray"]:
+    def construct_array_type(cls) -> Type[PandasArray]:
         """
         Return the array type associated with this dtype.
 
@@ -155,7 +155,7 @@ class PandasArray(
     # ------------------------------------------------------------------------
     # Constructors
 
-    def __init__(self, values: Union[np.ndarray, "PandasArray"], copy: bool = False):
+    def __init__(self, values: Union[np.ndarray, PandasArray], copy: bool = False):
         if isinstance(values, type(self)):
             values = values._ndarray
         if not isinstance(values, np.ndarray):

pandas/core/arrays/period.py

@@ -201,7 +201,7 @@ def _simple_new(
 
     @classmethod
     def _from_sequence(
-        cls: Type["PeriodArray"],
+        cls: Type[PeriodArray],
         scalars: Union[Sequence[Optional[Period]], AnyArrayLike],
         *,
         dtype: Optional[Dtype] = None,

pandas/core/arrays/sparse/array.py

@@ -62,7 +62,7 @@
 _sparray_doc_kwargs = {"klass": "SparseArray"}
 
 
-def _get_fill(arr: "SparseArray") -> np.ndarray:
+def _get_fill(arr: SparseArray) -> np.ndarray:
     """
     Create a 0-dim ndarray containing the fill value
 
@@ -87,7 +87,7 @@ def _get_fill(arr: "SparseArray") -> np.ndarray:
 
 
 def _sparse_array_op(
-    left: "SparseArray", right: "SparseArray", op: Callable, name: str
+    left: SparseArray, right: SparseArray, op: Callable, name: str
 ) -> Any:
     """
     Perform a binary operation between two arrays.
@@ -896,7 +896,7 @@ def _take_with_fill(self, indices, fill_value=None) -> np.ndarray:
 
         return taken
 
-    def _take_without_fill(self, indices) -> Union[np.ndarray, "SparseArray"]:
+    def _take_without_fill(self, indices) -> Union[np.ndarray, SparseArray]:
         to_shift = indices < 0
         indices = indices.copy()
 

pandas/core/arrays/sparse/dtype.py

@@ -173,7 +173,7 @@ def __repr__(self) -> str:
         return self.name
 
     @classmethod
-    def construct_array_type(cls) -> Type["SparseArray"]:
+    def construct_array_type(cls) -> Type[SparseArray]:
         """
         Return the array type associated with this dtype.
 

pandas/core/arrays/string_.py

@@ -71,7 +71,7 @@ def type(self) -> Type[str]:
         return str
 
     @classmethod
-    def construct_array_type(cls) -> Type["StringArray"]:
+    def construct_array_type(cls) -> Type[StringArray]:
         """
         Return the array type associated with this dtype.
 
@@ -85,7 +85,7 @@ def __repr__(self) -> str:
         return "StringDtype"
 
     def __from_arrow__(
-        self, array: Union["pyarrow.Array", "pyarrow.ChunkedArray"]
+        self, array: Union[pyarrow.Array, pyarrow.ChunkedArray]
     ) -> StringArray:
         """
         Construct StringArray from pyarrow Array/ChunkedArray.

pandas/core/arrays/string_arrow.py

@@ -87,7 +87,7 @@ def type(self) -> Type[str]:
         return str
 
     @classmethod
-    def construct_array_type(cls) -> Type["ArrowStringArray"]:
+    def construct_array_type(cls) -> Type[ArrowStringArray]:
         """
         Return the array type associated with this dtype.
 
@@ -104,7 +104,7 @@ def __repr__(self) -> str:
         return "ArrowStringDtype"
 
     def __from_arrow__(
-        self, array: Union["pa.Array", "pa.ChunkedArray"]
+        self, array: Union[pa.Array, pa.ChunkedArray]
     ) -> ArrowStringArray:
         """
         Construct StringArray from pyarrow Array/ChunkedArray.

pandas/core/computation/ops.py

@@ -2,6 +2,8 @@
 Operator classes for eval.
 """
 
+from __future__ import annotations
+
 from datetime import datetime
 from distutils.version import LooseVersion
 from functools import partial
@@ -203,7 +205,7 @@ class Op:
 
     op: str
 
-    def __init__(self, op: str, operands: Iterable[Union[Term, "Op"]], encoding=None):
+    def __init__(self, op: str, operands: Iterable[Union[Term, Op]], encoding=None):
         self.op = _bool_op_map.get(op, op)
         self.operands = operands
         self.encoding = encoding

pandas/core/describe.py

@@ -92,7 +92,7 @@ class NDFrameDescriberAbstract(ABC):
         Whether to treat datetime dtypes as numeric.
     """
 
-    def __init__(self, obj: "FrameOrSeriesUnion", datetime_is_numeric: bool):
+    def __init__(self, obj: FrameOrSeriesUnion, datetime_is_numeric: bool):
         self.obj = obj
         self.datetime_is_numeric = datetime_is_numeric
 
@@ -110,7 +110,7 @@ def describe(self, percentiles: Sequence[float]) -> FrameOrSeriesUnion:
 class SeriesDescriber(NDFrameDescriberAbstract):
     """Class responsible for creating series description."""
 
-    obj: "Series"
+    obj: Series
 
     def describe(self, percentiles: Sequence[float]) -> Series:
         describe_func = select_describe_func(
@@ -137,7 +137,7 @@ class DataFrameDescriber(NDFrameDescriberAbstract):
 
     def __init__(
         self,
-        obj: "DataFrame",
+        obj: DataFrame,
         *,
         include: Optional[Union[str, Sequence[str]]],
         exclude: Optional[Union[str, Sequence[str]]],
@@ -154,7 +154,7 @@ def __init__(
     def describe(self, percentiles: Sequence[float]) -> DataFrame:
         data = self._select_data()
 
-        ldesc: List["Series"] = []
+        ldesc: List[Series] = []
         for _, series in data.items():
             describe_func = select_describe_func(series, self.datetime_is_numeric)
             ldesc.append(describe_func(series, percentiles))
@@ -191,7 +191,7 @@ def _select_data(self):
         return data
 
 
-def reorder_columns(ldesc: Sequence["Series"]) -> List[Hashable]:
+def reorder_columns(ldesc: Sequence[Series]) -> List[Hashable]:
     """Set a convenient order for rows for display."""
     names: List[Hashable] = []
     ldesc_indexes = sorted((x.index for x in ldesc), key=len)
@@ -202,7 +202,7 @@ def reorder_columns(ldesc: Sequence["Series"]) -> List[Hashable]:
     return names
 
 
-def describe_numeric_1d(series: "Series", percentiles: Sequence[float]) -> Series:
+def describe_numeric_1d(series: Series, percentiles: Sequence[float]) -> Series:
     """Describe series containing numerical data.
 
     Parameters
@@ -226,7 +226,7 @@ def describe_numeric_1d(series: "Series", percentiles: Sequence[float]) -> Serie
 
 
 def describe_categorical_1d(
-    data: "Series",
+    data: Series,
     percentiles_ignored: Sequence[float],
 ) -> Series:
     """Describe series containing categorical data.
@@ -258,7 +258,7 @@ def describe_categorical_1d(
 
 
 def describe_timestamp_as_categorical_1d(
-    data: "Series",
+    data: Series,
     percentiles_ignored: Sequence[float],
 ) -> Series:
     """Describe series containing timestamp data treated as categorical.
@@ -305,7 +305,7 @@ def describe_timestamp_as_categorical_1d(
     return Series(result, index=names, name=data.name, dtype=dtype)
 
 
-def describe_timestamp_1d(data: "Series", percentiles: Sequence[float]) -> Series:
+def describe_timestamp_1d(data: Series, percentiles: Sequence[float]) -> Series:
     """Describe series containing datetime64 dtype.
 
     Parameters
@@ -330,7 +330,7 @@ def describe_timestamp_1d(data: "Series", percentiles: Sequence[float]) -> Serie
 
 
 def select_describe_func(
-    data: "Series",
+    data: Series,
     datetime_is_numeric: bool,
 ) -> Callable:
     """Select proper function for describing series based on data type.