Merge branch 'master' into mask_pos_args_deprecation

doc/source/whatsnew/v1.3.0.rst

@@ -228,7 +228,7 @@ Other enhancements
 - Constructing a :class:`DataFrame` or :class:`Series` with the ``data`` argument being a Python iterable that is *not* a NumPy ``ndarray`` consisting of NumPy scalars will now result in a dtype with a precision the maximum of the NumPy scalars; this was already the case when ``data`` is a NumPy ``ndarray`` (:issue:`40908`)
 - Add keyword ``sort`` to :func:`pivot_table` to allow non-sorting of the result (:issue:`39143`)
 - Add keyword ``dropna`` to :meth:`DataFrame.value_counts` to allow counting rows that include ``NA`` values (:issue:`41325`)
--
+- :meth:`Series.replace` will now cast results to ``PeriodDtype`` where possible instead of ``object`` dtype (:issue:`41526`)
 
 .. ---------------------------------------------------------------------------
 
@@ -649,6 +649,7 @@ Deprecations
 - Deprecated behavior of :meth:`DatetimeIndex.union` with mixed timezones; in a future version both will be cast to UTC instead of object dtype (:issue:`39328`)
 - Deprecated using ``usecols`` with out of bounds indices for ``read_csv`` with ``engine="c"`` (:issue:`25623`)
 - Deprecated passing arguments (apart from ``cond``) as positional in :meth:`DataFrame.mask` (:issue:`41485`)
+- Deprecated passing arguments as positional (except for ``"method"``) in :meth:`DataFrame.interpolate` and :meth:`Series.interpolate` (:issue:`41485`)
 
 .. ---------------------------------------------------------------------------
 

pandas/_libs/lib.pyi

@@ -40,7 +40,6 @@ def is_integer(val: object) -> bool: ...
 def is_float(val: object) -> bool: ...
 
 def is_interval_array(values: np.ndarray) -> bool: ...
-def is_period_array(values: np.ndarray) -> bool: ...
 def is_datetime64_array(values: np.ndarray) -> bool: ...
 def is_timedelta_or_timedelta64_array(values: np.ndarray) -> bool: ...
 def is_datetime_with_singletz_array(values: np.ndarray) -> bool: ...
@@ -67,50 +66,60 @@ def map_infer(
 @overload  # both convert_datetime and convert_to_nullable_integer False -> np.ndarray
 def maybe_convert_objects(
     objects: np.ndarray,  # np.ndarray[object]
+    *,
     try_float: bool = ...,
     safe: bool = ...,
     convert_datetime: Literal[False] = ...,
     convert_timedelta: bool = ...,
+    convert_period: Literal[False] = ...,
     convert_to_nullable_integer: Literal[False] = ...,
 ) -> np.ndarray: ...
 
 @overload
 def maybe_convert_objects(
     objects: np.ndarray,  # np.ndarray[object]
+    *,
     try_float: bool = ...,
     safe: bool = ...,
-    convert_datetime: Literal[False] = False,
+    convert_datetime: bool = ...,
     convert_timedelta: bool = ...,
+    convert_period: bool = ...,
     convert_to_nullable_integer: Literal[True] = ...,
 ) -> ArrayLike: ...
 
 @overload
 def maybe_convert_objects(
     objects: np.ndarray,  # np.ndarray[object]
+    *,
     try_float: bool = ...,
     safe: bool = ...,
     convert_datetime: Literal[True] = ...,
     convert_timedelta: bool = ...,
-    convert_to_nullable_integer: Literal[False] = ...,
+    convert_period: bool = ...,
+    convert_to_nullable_integer: bool = ...,
 ) -> ArrayLike: ...
 
 @overload
 def maybe_convert_objects(
     objects: np.ndarray,  # np.ndarray[object]
+    *,
     try_float: bool = ...,
     safe: bool = ...,
-    convert_datetime: Literal[True] = ...,
+    convert_datetime: bool = ...,
     convert_timedelta: bool = ...,
-    convert_to_nullable_integer: Literal[True] = ...,
+    convert_period: Literal[True] = ...,
+    convert_to_nullable_integer: bool = ...,
 ) -> ArrayLike: ...
 
 @overload
 def maybe_convert_objects(
     objects: np.ndarray,  # np.ndarray[object]
+    *,
     try_float: bool = ...,
     safe: bool = ...,
     convert_datetime: bool = ...,
     convert_timedelta: bool = ...,
+    convert_period: bool = ...,
     convert_to_nullable_integer: bool = ...,
 ) -> ArrayLike: ...
 

pandas/_libs/lib.pyx

@@ -1186,6 +1186,7 @@ cdef class Seen:
         bint coerce_numeric   # coerce data to numeric
         bint timedelta_       # seen_timedelta
         bint datetimetz_      # seen_datetimetz
+        bint period_          # seen_period
 
     def __cinit__(self, bint coerce_numeric=False):
         """
@@ -1210,6 +1211,7 @@ cdef class Seen:
         self.datetime_ = False
         self.timedelta_ = False
         self.datetimetz_ = False
+        self.period_ = False
         self.coerce_numeric = coerce_numeric
 
     cdef inline bint check_uint64_conflict(self) except -1:
@@ -1996,18 +1998,35 @@ cpdef bint is_time_array(ndarray values, bint skipna=False):
     return validator.validate(values)
 
 
-cdef class PeriodValidator(TemporalValidator):
-    cdef inline bint is_value_typed(self, object value) except -1:
-        return is_period_object(value)
+cdef bint is_period_array(ndarray[object] values):
+    """
+    Is this an ndarray of Period objects (or NaT) with a single `freq`?
+    """
+    cdef:
+        Py_ssize_t i, n = len(values)
+        int dtype_code = -10000  # i.e. c_FreqGroup.FR_UND
+        object val
 
-    cdef inline bint is_valid_null(self, object value) except -1:
-        return checknull_with_nat(value)
+    if len(values) == 0:
+        return False
 
+    for val in values:
+        if is_period_object(val):
+            if dtype_code == -10000:
+                dtype_code = val._dtype._dtype_code
+            elif dtype_code != val._dtype._dtype_code:
+                # mismatched freqs
+                return False
+        elif checknull_with_nat(val):
+            pass
+        else:
+            # Not a Period or NaT-like
+            return False
 
-cpdef bint is_period_array(ndarray values):
-    cdef:
-        PeriodValidator validator = PeriodValidator(len(values), skipna=True)
-    return validator.validate(values)
+    if dtype_code == -10000:
+        # we saw all-NaTs, no actual Periods
+        return False
+    return True
 
 
 cdef class IntervalValidator(Validator):
@@ -2249,9 +2268,13 @@ def maybe_convert_numeric(
 
 @cython.boundscheck(False)
 @cython.wraparound(False)
-def maybe_convert_objects(ndarray[object] objects, bint try_float=False,
-                          bint safe=False, bint convert_datetime=False,
+def maybe_convert_objects(ndarray[object] objects,
+                          *,
+                          bint try_float=False,
+                          bint safe=False,
+                          bint convert_datetime=False,
                           bint convert_timedelta=False,
+                          bint convert_period=False,
                           bint convert_to_nullable_integer=False) -> "ArrayLike":
     """
     Type inference function-- convert object array to proper dtype
@@ -2272,6 +2295,9 @@ def maybe_convert_objects(ndarray[object] objects, bint try_float=False,
     convert_timedelta : bool, default False
         If an array-like object contains only timedelta values or NaT is
         encountered, whether to convert and return an array of m8[ns] dtype.
+    convert_period : bool, default False
+        If an array-like object contains only (homogeneous-freq) Period values
+        or NaT, whether to convert and return a PeriodArray.
     convert_to_nullable_integer : bool, default False
         If an array-like object contains only integer values (and NaN) is
         encountered, whether to convert and return an IntegerArray.
@@ -2292,7 +2318,7 @@ def maybe_convert_objects(ndarray[object] objects, bint try_float=False,
         int64_t[:] itimedeltas
         Seen seen = Seen()
         object val
-        float64_t fval, fnan
+        float64_t fval, fnan = np.nan
 
     n = len(objects)
 
@@ -2311,8 +2337,6 @@ def maybe_convert_objects(ndarray[object] objects, bint try_float=False,
         timedeltas = np.empty(n, dtype='m8[ns]')
         itimedeltas = timedeltas.view(np.int64)
 
-    fnan = np.nan
-
     for i in range(n):
         val = objects[i]
         if itemsize_max != -1:
@@ -2330,7 +2354,7 @@ def maybe_convert_objects(ndarray[object] objects, bint try_float=False,
                 idatetimes[i] = NPY_NAT
             if convert_timedelta:
                 itimedeltas[i] = NPY_NAT
-            if not (convert_datetime or convert_timedelta):
+            if not (convert_datetime or convert_timedelta or convert_period):
                 seen.object_ = True
                 break
         elif val is np.nan:
@@ -2343,14 +2367,6 @@ def maybe_convert_objects(ndarray[object] objects, bint try_float=False,
         elif util.is_float_object(val):
             floats[i] = complexes[i] = val
             seen.float_ = True
-        elif util.is_datetime64_object(val):
-            if convert_datetime:
-                idatetimes[i] = convert_to_tsobject(
-                    val, None, None, 0, 0).value
-                seen.datetime_ = True
-            else:
-                seen.object_ = True
-                break
         elif is_timedelta(val):
             if convert_timedelta:
                 itimedeltas[i] = convert_to_timedelta64(val, "ns").view("i8")
@@ -2396,6 +2412,13 @@ def maybe_convert_objects(ndarray[object] objects, bint try_float=False,
             else:
                 seen.object_ = True
                 break
+        elif is_period_object(val):
+            if convert_period:
+                seen.period_ = True
+                break
+            else:
+                seen.object_ = True
+                break
         elif try_float and not isinstance(val, str):
             # this will convert Decimal objects
             try:
@@ -2419,6 +2442,14 @@ def maybe_convert_objects(ndarray[object] objects, bint try_float=False,
             return dti._data
         seen.object_ = True
 
+    if seen.period_:
+        if is_period_array(objects):
+            from pandas import PeriodIndex
+            pi = PeriodIndex(objects)
+
+            # unbox to PeriodArray
+            return pi._data
+
     if not seen.object_:
         result = None
         if not safe:

pandas/_libs/tslib.pyx

@@ -235,7 +235,10 @@ def array_with_unit_to_datetime(
         if issubclass(values.dtype.type, (np.integer, np.float_)):
             result = values.astype("M8[ns]", copy=False)
         else:
-            result, tz = array_to_datetime(values.astype(object), errors=errors)
+            result, tz = array_to_datetime(
+                values.astype(object, copy=False),
+                errors=errors,
+            )
         return result, tz
 
     m, p = precision_from_unit(unit)

pandas/core/arrays/datetimelike.py

@@ -261,7 +261,7 @@ def _box_values(self, values) -> np.ndarray:
         """
         apply box func to passed values
         """
-        return lib.map_infer(values, self._box_func)
+        return lib.map_infer(values, self._box_func, convert=False)
 
     def __iter__(self):
         if self.ndim > 1:
@@ -599,7 +599,9 @@ def _validate_shift_value(self, fill_value):
                 "will raise in a future version, pass "
                 f"{self._scalar_type.__name__} instead.",
                 FutureWarning,
-                stacklevel=8,
+                # There is no way to hard-code the level since this might be
+                #  reached directly or called from the Index or Block method
+                stacklevel=find_stack_level(),
             )
             fill_value = new_fill
 

pandas/core/arrays/datetimes.py

@@ -1175,6 +1175,7 @@ def to_perioddelta(self, freq) -> TimedeltaArray:
             "future version.  "
             "Use `dtindex - dtindex.to_period(freq).to_timestamp()` instead",
             FutureWarning,
+            # stacklevel chosen to be correct for when called from DatetimeIndex
             stacklevel=3,
         )
         from pandas.core.arrays.timedeltas import TimedeltaArray

pandas/core/base.py

@@ -196,6 +196,7 @@ def _selected_obj(self):
         else:
             return self.obj[self._selection]
 
+    @final
     @cache_readonly
     def ndim(self) -> int:
         return self._selected_obj.ndim

pandas/core/construction.py

@@ -682,17 +682,21 @@ def _try_cast(
         subarr = construct_1d_object_array_from_listlike(arr)
         return subarr
 
+    if dtype is None and isinstance(arr, list):
+        # filter out cases that we _dont_ want to go through maybe_cast_to_datetime
+        varr = np.array(arr, copy=False)
+        if varr.dtype != object or varr.size == 0:
+            return varr
+        arr = varr
+
     try:
         # GH#15832: Check if we are requesting a numeric dtype and
         # that we can convert the data to the requested dtype.
         if is_integer_dtype(dtype):
             # this will raise if we have e.g. floats
 
-            # error: Argument 2 to "maybe_cast_to_integer_array" has incompatible type
-            # "Union[dtype, ExtensionDtype, None]"; expected "Union[ExtensionDtype, str,
-            # dtype, Type[str], Type[float], Type[int], Type[complex], Type[bool],
-            # Type[object]]"
-            maybe_cast_to_integer_array(arr, dtype)  # type: ignore[arg-type]
+            dtype = cast(np.dtype, dtype)
+            maybe_cast_to_integer_array(arr, dtype)
             subarr = arr
         else:
             subarr = maybe_cast_to_datetime(arr, dtype)