CLN/TYP: remove unused (#46151)

Author: jbrockmendel

pandas/_libs/algos.pyi

@@ -61,67 +61,48 @@ def nancorr_spearman(
 
 # ----------------------------------------------------------------------
 
-# ctypedef fused algos_t:
-#    float64_t
-#    float32_t
-#    object
-#    int64_t
-#    int32_t
-#    int16_t
-#    int8_t
-#    uint64_t
-#    uint32_t
-#    uint16_t
-#    uint8_t
-
 def validate_limit(nobs: int | None, limit=...) -> int: ...
 def pad(
-    old: np.ndarray,  # ndarray[algos_t]
-    new: np.ndarray,  # ndarray[algos_t]
+    old: np.ndarray,  # ndarray[numeric_object_t]
+    new: np.ndarray,  # ndarray[numeric_object_t]
     limit=...,
 ) -> npt.NDArray[np.intp]: ...  # np.ndarray[np.intp, ndim=1]
 def pad_inplace(
-    values: np.ndarray,  # algos_t[:]
+    values: np.ndarray,  # numeric_object_t[:]
     mask: np.ndarray,  # uint8_t[:]
     limit=...,
 ) -> None: ...
 def pad_2d_inplace(
-    values: np.ndarray,  # algos_t[:, :]
+    values: np.ndarray,  # numeric_object_t[:, :]
     mask: np.ndarray,  # const uint8_t[:, :]
     limit=...,
 ) -> None: ...
 def backfill(
-    old: np.ndarray,  # ndarray[algos_t]
-    new: np.ndarray,  # ndarray[algos_t]
+    old: np.ndarray,  # ndarray[numeric_object_t]
+    new: np.ndarray,  # ndarray[numeric_object_t]
     limit=...,
 ) -> npt.NDArray[np.intp]: ...  # np.ndarray[np.intp, ndim=1]
 def backfill_inplace(
-    values: np.ndarray,  # algos_t[:]
+    values: np.ndarray,  # numeric_object_t[:]
     mask: np.ndarray,  # uint8_t[:]
     limit=...,
 ) -> None: ...
 def backfill_2d_inplace(
-    values: np.ndarray,  # algos_t[:, :]
+    values: np.ndarray,  # numeric_object_t[:, :]
     mask: np.ndarray,  # const uint8_t[:, :]
     limit=...,
 ) -> None: ...
 def is_monotonic(
-    arr: np.ndarray,  # ndarray[algos_t, ndim=1]
+    arr: np.ndarray,  # ndarray[numeric_object_t, ndim=1]
     timelike: bool,
 ) -> tuple[bool, bool, bool]: ...
 
 # ----------------------------------------------------------------------
 # rank_1d, rank_2d
 # ----------------------------------------------------------------------
 
-# ctypedef fused rank_t:
-#    object
-#    float64_t
-#    uint64_t
-#    int64_t
-
 def rank_1d(
-    values: np.ndarray,  # ndarray[rank_t, ndim=1]
+    values: np.ndarray,  # ndarray[iu_64_floating_obj_t, ndim=1]
     labels: np.ndarray | None = ...,  # const int64_t[:]=None
     is_datetimelike: bool = ...,
     ties_method=...,
@@ -130,7 +111,7 @@ def rank_1d(
     na_option=...,
 ) -> np.ndarray: ...  # np.ndarray[float64_t, ndim=1]
 def rank_2d(
-    in_arr: np.ndarray,  # ndarray[rank_t, ndim=2]
+    in_arr: np.ndarray,  # ndarray[iu_64_floating_obj_t, ndim=2]
     axis: int = ...,
     is_datetimelike: bool = ...,
     ties_method=...,

pandas/_libs/groupby.pyx

@@ -475,19 +475,16 @@ def group_any_all(int8_t[:, ::1] out,
 # group_add, group_prod, group_var, group_mean, group_ohlc
 # ----------------------------------------------------------------------
 
-ctypedef fused add_t:
-    float64_t
-    float32_t
-    complex64_t
-    complex128_t
-    object
-
 ctypedef fused mean_t:
     float64_t
     float32_t
     complex64_t
     complex128_t
 
+ctypedef fused add_t:
+    mean_t
+    object
+
 
 @cython.wraparound(False)
 @cython.boundscheck(False)

pandas/_libs/hashtable.pyx

@@ -27,6 +27,7 @@ cnp.import_array()
 
 
 from pandas._libs cimport util
+from pandas._libs.dtypes cimport numeric_object_t
 from pandas._libs.khash cimport (
     KHASH_TRACE_DOMAIN,
     are_equivalent_float32_t,

pandas/_libs/hashtable_func_helper.pxi.in

@@ -301,19 +301,9 @@ cdef mode_{{dtype}}(const {{dtype}}_t[:] values, bint dropna):
 
 
 ctypedef fused htfunc_t:
+    numeric_object_t
     complex128_t
     complex64_t
-    float64_t
-    float32_t
-    uint64_t
-    uint32_t
-    uint16_t
-    uint8_t
-    int64_t
-    int32_t
-    int16_t
-    int8_t
-    object
 
 
 cpdef value_count(ndarray[htfunc_t] values, bint dropna):

pandas/core/arrays/_arrow_utils.py

@@ -6,7 +6,7 @@
 from pandas.core.arrays.interval import VALID_CLOSED
 
 
-def pyarrow_array_to_numpy_and_mask(arr, dtype):
+def pyarrow_array_to_numpy_and_mask(arr, dtype: np.dtype):
     """
     Convert a primitive pyarrow.Array to a numpy array and boolean mask based
     on the buffers of the Array.

pandas/core/arrays/_mixins.py

@@ -313,11 +313,12 @@ def fillna(
                 # TODO: check value is None
                 # (for now) when self.ndim == 2, we assume axis=0
                 func = missing.get_fill_func(method, ndim=self.ndim)
-                new_values, _ = func(self._ndarray.T.copy(), limit=limit, mask=mask.T)
-                new_values = new_values.T
+                npvalues = self._ndarray.T.copy()
+                func(npvalues, limit=limit, mask=mask.T)
+                npvalues = npvalues.T
 
                 # TODO: PandasArray didn't used to copy, need tests for this
-                new_values = self._from_backing_data(new_values)
+                new_values = self._from_backing_data(npvalues)
             else:
                 # fill with value
                 new_values = self.copy()

pandas/core/arrays/base.py

@@ -789,8 +789,9 @@ def fillna(
         if mask.any():
             if method is not None:
                 func = missing.get_fill_func(method)
-                new_values, _ = func(self.astype(object), limit=limit, mask=mask)
-                new_values = self._from_sequence(new_values, dtype=self.dtype)
+                npvalues = self.astype(object)
+                func(npvalues, limit=limit, mask=mask)
+                new_values = self._from_sequence(npvalues, dtype=self.dtype)
             else:
                 # fill with value
                 new_values = self.copy()
@@ -1397,7 +1398,8 @@ def _reduce(self, name: str, *, skipna: bool = True, **kwargs):
     __hash__: None  # type: ignore[assignment]
 
     # ------------------------------------------------------------------------
-    # Non-Optimized Default Methods
+    # Non-Optimized Default Methods; in the case of the private methods here,
+    #  these are not guaranteeed to be stable across pandas versions.
 
     def tolist(self) -> list:
         """
@@ -1510,10 +1512,11 @@ def _fill_mask_inplace(
         ExtensionArray.fillna
         """
         func = missing.get_fill_func(method)
+        npvalues = self.astype(object)
         # NB: if we don't copy mask here, it may be altered inplace, which
         #  would mess up the `self[mask] = ...` below.
-        new_values, _ = func(self.astype(object), limit=limit, mask=mask.copy())
-        new_values = self._from_sequence(new_values, dtype=self.dtype)
+        func(npvalues, limit=limit, mask=mask.copy())
+        new_values = self._from_sequence(npvalues, dtype=self.dtype)
         self[mask] = new_values[mask]
         return
 

pandas/core/arrays/masked.py

@@ -174,12 +174,10 @@ def fillna(
         if mask.any():
             if method is not None:
                 func = missing.get_fill_func(method, ndim=self.ndim)
-                new_values, new_mask = func(
-                    self._data.copy().T,
-                    limit=limit,
-                    mask=mask.copy().T,
-                )
-                return type(self)(new_values.T, new_mask.view(np.bool_).T)
+                npvalues = self._data.copy().T
+                new_mask = mask.copy().T
+                func(npvalues, limit=limit, mask=new_mask)
+                return type(self)(npvalues.T, new_mask.T)
             else:
                 # fill with value
                 new_values = self.copy()

pandas/core/arrays/numeric.py

@@ -95,7 +95,7 @@ def __from_arrow__(
 
         results = []
         for arr in chunks:
-            data, mask = pyarrow_array_to_numpy_and_mask(arr, dtype=self.type)
+            data, mask = pyarrow_array_to_numpy_and_mask(arr, dtype=self.numpy_dtype)
             num_arr = array_class(data.copy(), ~mask, copy=False)
             results.append(num_arr)
 

pandas/core/dtypes/dtypes.py

@@ -1006,7 +1006,7 @@ def __from_arrow__(
 
         results = []
         for arr in chunks:
-            data, mask = pyarrow_array_to_numpy_and_mask(arr, dtype="int64")
+            data, mask = pyarrow_array_to_numpy_and_mask(arr, dtype=np.dtype(np.int64))
             parr = PeriodArray(data.copy(), freq=self.freq, copy=False)
             parr[~mask] = NaT
             results.append(parr)

pandas/core/groupby/groupby.py

@@ -3687,6 +3687,7 @@ def _reindex_output(
         index, _ = MultiIndex.from_product(levels_list, names=names).sortlevel()
 
         if self.as_index:
+            # Always holds for SeriesGroupBy unless GH#36507 is implemented
             d = {
                 self.obj._get_axis_name(self.axis): index,
                 "copy": False,

pandas/core/groupby/grouper.py

@@ -680,7 +680,7 @@ def _codes_and_uniques(self) -> tuple[np.ndarray, ArrayLike]:
         elif isinstance(self.grouping_vector, ops.BaseGrouper):
             # we have a list of groupers
             codes = self.grouping_vector.codes_info
-            uniques = self.grouping_vector.result_arraylike
+            uniques = self.grouping_vector.result_index._values
         else:
             # GH35667, replace dropna=False with na_sentinel=None
             if not self._dropna:

pandas/core/groupby/ops.py

@@ -868,21 +868,6 @@ def reconstructed_codes(self) -> list[np.ndarray]:
         ids, obs_ids, _ = self.group_info
         return decons_obs_group_ids(ids, obs_ids, self.shape, codes, xnull=True)
 
-    @final
-    @cache_readonly
-    def result_arraylike(self) -> ArrayLike:
-        """
-        Analogous to result_index, but returning an ndarray/ExtensionArray
-        allowing us to retain ExtensionDtypes not supported by Index.
-        """
-        # TODO(ExtensionIndex): once Index supports arbitrary EAs, this can
-        #  be removed in favor of result_index
-        if len(self.groupings) == 1:
-            return self.groupings[0].group_arraylike
-
-        # result_index is MultiIndex
-        return self.result_index._values
-
     @cache_readonly
     def result_index(self) -> Index:
         if len(self.groupings) == 1:
@@ -1147,7 +1132,7 @@ def reconstructed_codes(self) -> list[np.ndarray]:
         return [np.r_[0, np.flatnonzero(self.bins[1:] != self.bins[:-1]) + 1]]
 
     @cache_readonly
-    def result_index(self):
+    def result_index(self) -> Index:
         if len(self.binlabels) != 0 and isna(self.binlabels[0]):
             return self.binlabels[1:]
 

pandas/core/reshape/reshape.py

@@ -253,6 +253,8 @@ def get_new_values(self, values, fill_value=None):
         else:
             if isinstance(dtype, ExtensionDtype):
                 # GH#41875
+                # We are assuming that fill_value can be held by this dtype,
+                #  unlike the non-EA case that promotes.
                 cls = dtype.construct_array_type()
                 new_values = cls._empty(result_shape, dtype=dtype)
                 new_values[:] = fill_value

pandas/core/series.py

@@ -5027,7 +5027,7 @@ def _replace_single(self, to_replace, method: str, inplace: bool, limit):
             values._fill_mask_inplace(method, limit, mask)
         else:
             fill_f = missing.get_fill_func(method)
-            values, _ = fill_f(values, limit=limit, mask=mask)
+            fill_f(values, limit=limit, mask=mask)
 
         if inplace:
             return