CLN: assorted, mostly typing (#29419)

Author: jbrockmendel

pandas/_libs/algos.pyx

@@ -1150,6 +1150,77 @@ def rank_2d(rank_t[:, :] in_arr, axis=0, ties_method='average',
         return ranks
 
 
+ctypedef fused diff_t:
+    float64_t
+    float32_t
+    int8_t
+    int16_t
+    int32_t
+    int64_t
+
+ctypedef fused out_t:
+    float32_t
+    float64_t
+
+
+@cython.boundscheck(False)
+@cython.wraparound(False)
+def diff_2d(ndarray[diff_t, ndim=2] arr,
+            ndarray[out_t, ndim=2] out,
+            Py_ssize_t periods, int axis):
+    cdef:
+        Py_ssize_t i, j, sx, sy, start, stop
+        bint f_contig = arr.flags.f_contiguous
+
+    # Disable for unsupported dtype combinations,
+    #  see https://github.com/cython/cython/issues/2646
+    if (out_t is float32_t
+            and not (diff_t is float32_t or diff_t is int8_t or diff_t is int16_t)):
+        raise NotImplementedError
+    elif (out_t is float64_t
+          and (diff_t is float32_t or diff_t is int8_t or diff_t is int16_t)):
+        raise NotImplementedError
+    else:
+        # We put this inside an indented else block to avoid cython build
+        #  warnings about unreachable code
+        sx, sy = (<object>arr).shape
+        with nogil:
+            if f_contig:
+                if axis == 0:
+                    if periods >= 0:
+                        start, stop = periods, sx
+                    else:
+                        start, stop = 0, sx + periods
+                    for j in range(sy):
+                        for i in range(start, stop):
+                            out[i, j] = arr[i, j] - arr[i - periods, j]
+                else:
+                    if periods >= 0:
+                        start, stop = periods, sy
+                    else:
+                        start, stop = 0, sy + periods
+                    for j in range(start, stop):
+                        for i in range(sx):
+                            out[i, j] = arr[i, j] - arr[i, j - periods]
+            else:
+                if axis == 0:
+                    if periods >= 0:
+                        start, stop = periods, sx
+                    else:
+                        start, stop = 0, sx + periods
+                    for i in range(start, stop):
+                        for j in range(sy):
+                            out[i, j] = arr[i, j] - arr[i - periods, j]
+                else:
+                    if periods >= 0:
+                        start, stop = periods, sy
+                    else:
+                        start, stop = 0, sy + periods
+                    for i in range(sx):
+                        for j in range(start, stop):
+                            out[i, j] = arr[i, j] - arr[i, j - periods]
+
+
 # generated from template
 include "algos_common_helper.pxi"
 include "algos_take_helper.pxi"

pandas/_libs/algos_common_helper.pxi.in

@@ -4,77 +4,6 @@ Template for each `dtype` helper function using 1-d template
 WARNING: DO NOT edit .pxi FILE directly, .pxi is generated from .pxi.in
 """
 
-ctypedef fused diff_t:
-    float64_t
-    float32_t
-    int8_t
-    int16_t
-    int32_t
-    int64_t
-
-ctypedef fused out_t:
-    float32_t
-    float64_t
-
-
-@cython.boundscheck(False)
-@cython.wraparound(False)
-def diff_2d(ndarray[diff_t, ndim=2] arr,
-            ndarray[out_t, ndim=2] out,
-            Py_ssize_t periods, int axis):
-    cdef:
-        Py_ssize_t i, j, sx, sy, start, stop
-        bint f_contig = arr.flags.f_contiguous
-
-    # Disable for unsupported dtype combinations,
-    #  see https://github.com/cython/cython/issues/2646
-    if (out_t is float32_t
-            and not (diff_t is float32_t or diff_t is int8_t or diff_t is int16_t)):
-        raise NotImplementedError
-    elif (out_t is float64_t
-          and (diff_t is float32_t or diff_t is int8_t or diff_t is int16_t)):
-        raise NotImplementedError
-    else:
-        # We put this inside an indented else block to avoid cython build
-        #  warnings about unreachable code
-        sx, sy = (<object>arr).shape
-        with nogil:
-            if f_contig:
-                if axis == 0:
-                    if periods >= 0:
-                        start, stop = periods, sx
-                    else:
-                        start, stop = 0, sx + periods
-                    for j in range(sy):
-                        for i in range(start, stop):
-                            out[i, j] = arr[i, j] - arr[i - periods, j]
-                else:
-                    if periods >= 0:
-                        start, stop = periods, sy
-                    else:
-                        start, stop = 0, sy + periods
-                    for j in range(start, stop):
-                        for i in range(sx):
-                            out[i, j] = arr[i, j] - arr[i, j - periods]
-            else:
-                if axis == 0:
-                    if periods >= 0:
-                        start, stop = periods, sx
-                    else:
-                        start, stop = 0, sx + periods
-                    for i in range(start, stop):
-                        for j in range(sy):
-                            out[i, j] = arr[i, j] - arr[i - periods, j]
-                else:
-                    if periods >= 0:
-                        start, stop = periods, sy
-                    else:
-                        start, stop = 0, sy + periods
-                    for i in range(sx):
-                        for j in range(start, stop):
-                            out[i, j] = arr[i, j] - arr[i, j - periods]
-
-
 # ----------------------------------------------------------------------
 # ensure_dtype
 # ----------------------------------------------------------------------

pandas/_libs/missing.pyx

@@ -121,7 +121,7 @@ cpdef ndarray[uint8_t] isnaobj(ndarray arr):
 
 @cython.wraparound(False)
 @cython.boundscheck(False)
-def isnaobj_old(ndarray arr):
+def isnaobj_old(arr: ndarray) -> ndarray:
     """
     Return boolean mask denoting which elements of a 1-D array are na-like,
     defined as being any of:
@@ -156,7 +156,7 @@ def isnaobj_old(ndarray arr):
 
 @cython.wraparound(False)
 @cython.boundscheck(False)
-def isnaobj2d(ndarray arr):
+def isnaobj2d(arr: ndarray) -> ndarray:
     """
     Return boolean mask denoting which elements of a 2-D array are na-like,
     according to the criteria defined in `checknull`:
@@ -198,7 +198,7 @@ def isnaobj2d(ndarray arr):
 
 @cython.wraparound(False)
 @cython.boundscheck(False)
-def isnaobj2d_old(ndarray arr):
+def isnaobj2d_old(arr: ndarray) -> ndarray:
     """
     Return boolean mask denoting which elements of a 2-D array are na-like,
     according to the criteria defined in `checknull_old`:

pandas/_libs/window.pyx

@@ -69,8 +69,8 @@ def _check_minp(win, minp, N, floor=None) -> int:
     if not util.is_integer_object(minp):
         raise ValueError("min_periods must be an integer")
     if minp > win:
-        raise ValueError("min_periods (%d) must be <= "
-                         "window (%d)" % (minp, win))
+        raise ValueError("min_periods (minp) must be <= "
+                         "window (win)".format(minp=minp, win=win))
     elif minp > N:
         minp = N + 1
     elif minp < 0:

pandas/core/base.py

@@ -207,7 +207,7 @@ def _selected_obj(self):
             return self.obj[self._selection]
 
     @cache_readonly
-    def ndim(self):
+    def ndim(self) -> int:
         return self._selected_obj.ndim
 
     @cache_readonly
@@ -339,7 +339,7 @@ def _aggregate(self, arg, *args, **kwargs):
 
             obj = self._selected_obj
 
-            def nested_renaming_depr(level=4):
+            def nested_renaming_depr(level: int = 4):
                 # deprecation of nested renaming
                 # GH 15931
                 msg = textwrap.dedent(
@@ -488,11 +488,11 @@ def _agg(arg, func):
 
             # combine results
 
-            def is_any_series():
+            def is_any_series() -> bool:
                 # return a boolean if we have *any* nested series
                 return any(isinstance(r, ABCSeries) for r in result.values())
 
-            def is_any_frame():
+            def is_any_frame() -> bool:
                 # return a boolean if we have *any* nested series
                 return any(isinstance(r, ABCDataFrame) for r in result.values())
 

pandas/core/groupby/categorical.py

@@ -8,7 +8,7 @@
 )
 
 
-def recode_for_groupby(c, sort, observed):
+def recode_for_groupby(c: Categorical, sort: bool, observed: bool):
     """
     Code the categories to ensure we can groupby for categoricals.
 
@@ -74,7 +74,7 @@ def recode_for_groupby(c, sort, observed):
     return c.reorder_categories(cat.categories), None
 
 
-def recode_from_groupby(c, sort, ci):
+def recode_from_groupby(c: Categorical, sort: bool, ci):
     """
     Reverse the codes_to_groupby to account for sort / observed.