From eae91012690861df3c2f6f772bd1379f6ef7c4b9 Mon Sep 17 00:00:00 2001
From: Brock <jbrockmendel@gmail.com>
Date: Wed, 7 Apr 2021 20:50:37 -0700
Subject: [PATCH 1/6] CLN: tighten cython declarations

---
 pandas/_libs/index_class_helper.pxi.in | 4 ++--
 pandas/_libs/sparse.pyx                | 2 ++
 pandas/_libs/sparse_op_helper.pxi.in   | 4 ++--
 pandas/_libs/tslibs/conversion.pxd     | 2 +-
 pandas/_libs/tslibs/conversion.pyx     | 4 ++--
 pandas/_libs/tslibs/fields.pyx         | 2 +-
 6 files changed, 10 insertions(+), 8 deletions(-)

diff --git a/pandas/_libs/index_class_helper.pxi.in b/pandas/_libs/index_class_helper.pxi.in
index 8638c2c689c3f..f0351e06f2b8c 100644
--- a/pandas/_libs/index_class_helper.pxi.in
+++ b/pandas/_libs/index_class_helper.pxi.in
@@ -44,8 +44,8 @@ cdef class {{name}}Engine(IndexEngine):
             raise KeyError(val)
     {{endif}}
 
-    cdef void _call_map_locations(self, ndarray values):
-        self.mapping.map_locations(algos.ensure_{{name.lower()}}(values))
+    cdef void _call_map_locations(self, ndarray[{{dtype}}_t] values):
+        self.mapping.map_locations(values)
 
     cdef _maybe_get_bool_indexer(self, object val):
         # Returns ndarray[bool] or int
diff --git a/pandas/_libs/sparse.pyx b/pandas/_libs/sparse.pyx
index 0c3d8915b749b..134883e159407 100644
--- a/pandas/_libs/sparse.pyx
+++ b/pandas/_libs/sparse.pyx
@@ -618,6 +618,7 @@ cdef class BlockIndex(SparseIndex):
         pass
 
 
+@cython.internal
 cdef class BlockMerge:
     """
     Object-oriented approach makes sharing state between recursive functions a
@@ -661,6 +662,7 @@ cdef class BlockMerge:
             self.yi = xi
 
 
+@cython.internal
 cdef class BlockUnion(BlockMerge):
     """
     Object-oriented approach makes sharing state between recursive functions a
diff --git a/pandas/_libs/sparse_op_helper.pxi.in b/pandas/_libs/sparse_op_helper.pxi.in
index ce665ca812131..36f22445d0373 100644
--- a/pandas/_libs/sparse_op_helper.pxi.in
+++ b/pandas/_libs/sparse_op_helper.pxi.in
@@ -302,8 +302,8 @@ cpdef sparse_{{opname}}_{{dtype}}({{dtype}}_t[:] x,
         raise NotImplementedError
 
 
-cpdef sparse_fill_{{opname}}_{{dtype}}({{dtype}}_t xfill,
-                                       {{dtype}}_t yfill):
+cdef sparse_fill_{{opname}}_{{dtype}}({{dtype}}_t xfill,
+                                      {{dtype}}_t yfill):
     return {{(opname, 'xfill', 'yfill', dtype) | get_op}}
 
 {{endfor}}
diff --git a/pandas/_libs/tslibs/conversion.pxd b/pandas/_libs/tslibs/conversion.pxd
index 1b99e855da40f..5b80193c1f27a 100644
--- a/pandas/_libs/tslibs/conversion.pxd
+++ b/pandas/_libs/tslibs/conversion.pxd
@@ -28,7 +28,7 @@ cdef _TSObject convert_datetime_to_tsobject(datetime ts, tzinfo tz,
 
 cdef int64_t get_datetime64_nanos(object val) except? -1
 
-cpdef datetime localize_pydatetime(datetime dt, object tz)
+cpdef datetime localize_pydatetime(datetime dt, tzinfo tz)
 cdef int64_t cast_from_unit(object ts, str unit) except? -1
 cpdef (int64_t, int) precision_from_unit(str unit)
 
diff --git a/pandas/_libs/tslibs/conversion.pyx b/pandas/_libs/tslibs/conversion.pyx
index 1bda35206ccef..865185f9acea7 100644
--- a/pandas/_libs/tslibs/conversion.pyx
+++ b/pandas/_libs/tslibs/conversion.pyx
@@ -810,14 +810,14 @@ cdef inline datetime _localize_pydatetime(datetime dt, tzinfo tz):
         return dt.replace(tzinfo=tz)
 
 
-cpdef inline datetime localize_pydatetime(datetime dt, object tz):
+cpdef inline datetime localize_pydatetime(datetime dt, tzinfo tz):
     """
     Take a datetime/Timestamp in UTC and localizes to timezone tz.
 
     Parameters
     ----------
     dt : datetime or Timestamp
-    tz : tzinfo, "UTC", or None
+    tz : tzinfo or None
 
     Returns
     -------
diff --git a/pandas/_libs/tslibs/fields.pyx b/pandas/_libs/tslibs/fields.pyx
index d6ca38e57d2d8..759c31b51d780 100644
--- a/pandas/_libs/tslibs/fields.pyx
+++ b/pandas/_libs/tslibs/fields.pyx
@@ -198,7 +198,7 @@ cdef inline bint _is_on_month(int month, int compare_month, int modby) nogil:
 @cython.wraparound(False)
 @cython.boundscheck(False)
 def get_start_end_field(const int64_t[:] dtindex, str field,
-                        object freqstr=None, int month_kw=12):
+                        str freqstr=None, int month_kw=12):
     """
     Given an int64-based datetime index return array of indicators
     of whether timestamps are at the start/end of the month/quarter/year

From 3eca2fb5cf1db0d66c9bff254c1e9982e1b0d5c3 Mon Sep 17 00:00:00 2001
From: Brock <jbrockmendel@gmail.com>
Date: Thu, 8 Apr 2021 07:50:40 -0700
Subject: [PATCH 2/6] revert sparse edits

---
 pandas/_libs/sparse.pyx              | 2 --
 pandas/_libs/sparse_op_helper.pxi.in | 4 ++--
 2 files changed, 2 insertions(+), 4 deletions(-)

diff --git a/pandas/_libs/sparse.pyx b/pandas/_libs/sparse.pyx
index 134883e159407..0c3d8915b749b 100644
--- a/pandas/_libs/sparse.pyx
+++ b/pandas/_libs/sparse.pyx
@@ -618,7 +618,6 @@ cdef class BlockIndex(SparseIndex):
         pass
 
 
-@cython.internal
 cdef class BlockMerge:
     """
     Object-oriented approach makes sharing state between recursive functions a
@@ -662,7 +661,6 @@ cdef class BlockMerge:
             self.yi = xi
 
 
-@cython.internal
 cdef class BlockUnion(BlockMerge):
     """
     Object-oriented approach makes sharing state between recursive functions a
diff --git a/pandas/_libs/sparse_op_helper.pxi.in b/pandas/_libs/sparse_op_helper.pxi.in
index 36f22445d0373..ce665ca812131 100644
--- a/pandas/_libs/sparse_op_helper.pxi.in
+++ b/pandas/_libs/sparse_op_helper.pxi.in
@@ -302,8 +302,8 @@ cpdef sparse_{{opname}}_{{dtype}}({{dtype}}_t[:] x,
         raise NotImplementedError
 
 
-cdef sparse_fill_{{opname}}_{{dtype}}({{dtype}}_t xfill,
-                                      {{dtype}}_t yfill):
+cpdef sparse_fill_{{opname}}_{{dtype}}({{dtype}}_t xfill,
+                                       {{dtype}}_t yfill):
     return {{(opname, 'xfill', 'yfill', dtype) | get_op}}
 
 {{endfor}}

From 16e045ec3969b5ed26803ad907816705f245094c Mon Sep 17 00:00:00 2001
From: Brock <jbrockmendel@gmail.com>
Date: Thu, 8 Apr 2021 10:14:14 -0700
Subject: [PATCH 3/6] troubleshoot

---
 pandas/__init__.py | 11 +----------
 1 file changed, 1 insertion(+), 10 deletions(-)

diff --git a/pandas/__init__.py b/pandas/__init__.py
index 7cad3eded0585..313d3184468d9 100644
--- a/pandas/__init__.py
+++ b/pandas/__init__.py
@@ -25,16 +25,7 @@
     is_numpy_dev as _is_numpy_dev,
 )
 
-try:
-    from pandas._libs import hashtable as _hashtable, lib as _lib, tslib as _tslib
-except ImportError as e:  # pragma: no cover
-    # hack but overkill to use re
-    module = str(e).replace("cannot import name ", "")
-    raise ImportError(
-        f"C extension: {module} not built. If you want to import "
-        "pandas from the source directory, you may need to run "
-        "'python setup.py build_ext --force' to build the C extensions first."
-    ) from e
+from pandas._libs import hashtable as _hashtable, lib as _lib, tslib as _tslib
 
 from pandas._config import (
     get_option,

From 81a58d04f6768e09989e0d6571ac717380aa2644 Mon Sep 17 00:00:00 2001
From: Brock <jbrockmendel@gmail.com>
Date: Thu, 8 Apr 2021 10:33:12 -0700
Subject: [PATCH 4/6] remove defaults from get_start_end_field

---
 pandas/__init__.py                 | 11 ++++++++++-
 pandas/_libs/tslibs/fields.pyi     |  4 ++--
 pandas/_libs/tslibs/fields.pyx     |  2 +-
 pandas/tests/tslibs/test_fields.py |  2 +-
 4 files changed, 14 insertions(+), 5 deletions(-)

diff --git a/pandas/__init__.py b/pandas/__init__.py
index 313d3184468d9..7cad3eded0585 100644
--- a/pandas/__init__.py
+++ b/pandas/__init__.py
@@ -25,7 +25,16 @@
     is_numpy_dev as _is_numpy_dev,
 )
 
-from pandas._libs import hashtable as _hashtable, lib as _lib, tslib as _tslib
+try:
+    from pandas._libs import hashtable as _hashtable, lib as _lib, tslib as _tslib
+except ImportError as e:  # pragma: no cover
+    # hack but overkill to use re
+    module = str(e).replace("cannot import name ", "")
+    raise ImportError(
+        f"C extension: {module} not built. If you want to import "
+        "pandas from the source directory, you may need to run "
+        "'python setup.py build_ext --force' to build the C extensions first."
+    ) from e
 
 from pandas._config import (
     get_option,
diff --git a/pandas/_libs/tslibs/fields.pyi b/pandas/_libs/tslibs/fields.pyi
index 22ae156d78b7d..cc6f8e95a6818 100644
--- a/pandas/_libs/tslibs/fields.pyi
+++ b/pandas/_libs/tslibs/fields.pyi
@@ -15,8 +15,8 @@ def get_date_name_field(
 def get_start_end_field(
     dtindex: np.ndarray,  # const int64_t[:]
     field: str,
-    freqstr: str | None = ...,
-    month_kw: int = ...
+    freqstr: str | None,
+    month_kw: int,
 ) -> np.ndarray: ...  # np.ndarray[bool]
 
 
diff --git a/pandas/_libs/tslibs/fields.pyx b/pandas/_libs/tslibs/fields.pyx
index 759c31b51d780..8de7e4331aff7 100644
--- a/pandas/_libs/tslibs/fields.pyx
+++ b/pandas/_libs/tslibs/fields.pyx
@@ -198,7 +198,7 @@ cdef inline bint _is_on_month(int month, int compare_month, int modby) nogil:
 @cython.wraparound(False)
 @cython.boundscheck(False)
 def get_start_end_field(const int64_t[:] dtindex, str field,
-                        str freqstr=None, int month_kw=12):
+                        str freqstr, int month_kw):
     """
     Given an int64-based datetime index return array of indicators
     of whether timestamps are at the start/end of the month/quarter/year
diff --git a/pandas/tests/tslibs/test_fields.py b/pandas/tests/tslibs/test_fields.py
index e5fe998923f8d..b851032a8fcaa 100644
--- a/pandas/tests/tslibs/test_fields.py
+++ b/pandas/tests/tslibs/test_fields.py
@@ -19,7 +19,7 @@ def test_fields_readonly():
     expected = np.array([1970, 1970, 1970, 1970, 1970], dtype=np.int32)
     tm.assert_numpy_array_equal(result, expected)
 
-    result = fields.get_start_end_field(dtindex, "is_month_start", None)
+    result = fields.get_start_end_field(dtindex, "is_month_start", None, 12)
     expected = np.array([True, False, False, False, False], dtype=np.bool_)
     tm.assert_numpy_array_equal(result, expected)
 

From 9f14f0550cac1fd240e8d195ebeaf5b12d99c3c2 Mon Sep 17 00:00:00 2001
From: Brock <jbrockmendel@gmail.com>
Date: Thu, 8 Apr 2021 15:57:25 -0700
Subject: [PATCH 5/6] annotations

---
 pandas/_libs/index.pyx               |  3 +++
 pandas/_libs/intervaltree.pxi.in     | 12 ++++++------
 pandas/_libs/sparse.pyx              |  2 ++
 pandas/_libs/sparse_op_helper.pxi.in |  4 ++--
 pandas/_libs/tslibs/fields.pyi       |  4 ++--
 pandas/_libs/tslibs/fields.pyx       |  2 +-
 pandas/tests/tslibs/test_fields.py   |  2 +-
 7 files changed, 17 insertions(+), 12 deletions(-)

diff --git a/pandas/_libs/index.pyx b/pandas/_libs/index.pyx
index f1f56c6c0c855..f7cec262ca302 100644
--- a/pandas/_libs/index.pyx
+++ b/pandas/_libs/index.pyx
@@ -74,6 +74,7 @@ cdef class IndexEngine:
         return val in self.mapping
 
     cpdef get_loc(self, object val):
+        # -> Py_ssize_t | slice | ndarray[bool]
         cdef:
             Py_ssize_t loc
 
@@ -109,6 +110,7 @@ cdef class IndexEngine:
             raise KeyError(val)
 
     cdef inline _get_loc_duplicates(self, object val):
+        # -> Py_ssize_t | slice | ndarray[bool]
         cdef:
             Py_ssize_t diff
 
@@ -142,6 +144,7 @@ cdef class IndexEngine:
     cdef _unpack_bool_indexer(self,
                               ndarray[uint8_t, ndim=1, cast=True] indexer,
                               object val):
+        # Returns ndarray[bool] or int
         cdef:
             ndarray[intp_t, ndim=1] found
             int count
diff --git a/pandas/_libs/intervaltree.pxi.in b/pandas/_libs/intervaltree.pxi.in
index 1af5b23e3393f..0fb01a2188a57 100644
--- a/pandas/_libs/intervaltree.pxi.in
+++ b/pandas/_libs/intervaltree.pxi.in
@@ -73,7 +73,7 @@ cdef class IntervalTree(IntervalMixin):
         self.root = node_cls(self.left, self.right, indices, leaf_size)
 
     @property
-    def left_sorter(self):
+    def left_sorter(self) -> np.ndarray:
         """How to sort the left labels; this is used for binary search
         """
         if self._left_sorter is None:
@@ -81,7 +81,7 @@ cdef class IntervalTree(IntervalMixin):
         return self._left_sorter
 
     @property
-    def right_sorter(self):
+    def right_sorter(self) -> np.ndarray:
         """How to sort the right labels
         """
         if self._right_sorter is None:
@@ -89,7 +89,7 @@ cdef class IntervalTree(IntervalMixin):
         return self._right_sorter
 
     @property
-    def is_overlapping(self):
+    def is_overlapping(self) -> bool:
         """
         Determine if the IntervalTree contains overlapping intervals.
         Cached as self._is_overlapping.
@@ -109,7 +109,7 @@ cdef class IntervalTree(IntervalMixin):
         return self._is_overlapping
 
     @property
-    def is_monotonic_increasing(self):
+    def is_monotonic_increasing(self) -> bool:
         """
         Return True if the IntervalTree is monotonic increasing (only equal or
         increasing values), else False
@@ -119,7 +119,7 @@ cdef class IntervalTree(IntervalMixin):
         sort_order = np.lexsort(values)
         return is_monotonic(sort_order, False)[0]
 
-    def get_indexer(self, scalar_t[:] target):
+    def get_indexer(self, scalar_t[:] target) -> np.ndarray:
         """Return the positions corresponding to unique intervals that overlap
         with the given array of scalar targets.
         """
@@ -180,7 +180,7 @@ cdef class IntervalTree(IntervalMixin):
                     n_elements=self.root.n_elements))
 
     # compat with IndexEngine interface
-    def clear_mapping(self):
+    def clear_mapping(self) -> None:
         pass
 
 
diff --git a/pandas/_libs/sparse.pyx b/pandas/_libs/sparse.pyx
index 0c3d8915b749b..134883e159407 100644
--- a/pandas/_libs/sparse.pyx
+++ b/pandas/_libs/sparse.pyx
@@ -618,6 +618,7 @@ cdef class BlockIndex(SparseIndex):
         pass
 
 
+@cython.internal
 cdef class BlockMerge:
     """
     Object-oriented approach makes sharing state between recursive functions a
@@ -661,6 +662,7 @@ cdef class BlockMerge:
             self.yi = xi
 
 
+@cython.internal
 cdef class BlockUnion(BlockMerge):
     """
     Object-oriented approach makes sharing state between recursive functions a
diff --git a/pandas/_libs/sparse_op_helper.pxi.in b/pandas/_libs/sparse_op_helper.pxi.in
index ce665ca812131..36f22445d0373 100644
--- a/pandas/_libs/sparse_op_helper.pxi.in
+++ b/pandas/_libs/sparse_op_helper.pxi.in
@@ -302,8 +302,8 @@ cpdef sparse_{{opname}}_{{dtype}}({{dtype}}_t[:] x,
         raise NotImplementedError
 
 
-cpdef sparse_fill_{{opname}}_{{dtype}}({{dtype}}_t xfill,
-                                       {{dtype}}_t yfill):
+cdef sparse_fill_{{opname}}_{{dtype}}({{dtype}}_t xfill,
+                                      {{dtype}}_t yfill):
     return {{(opname, 'xfill', 'yfill', dtype) | get_op}}
 
 {{endfor}}
diff --git a/pandas/_libs/tslibs/fields.pyi b/pandas/_libs/tslibs/fields.pyi
index cc6f8e95a6818..22ae156d78b7d 100644
--- a/pandas/_libs/tslibs/fields.pyi
+++ b/pandas/_libs/tslibs/fields.pyi
@@ -15,8 +15,8 @@ def get_date_name_field(
 def get_start_end_field(
     dtindex: np.ndarray,  # const int64_t[:]
     field: str,
-    freqstr: str | None,
-    month_kw: int,
+    freqstr: str | None = ...,
+    month_kw: int = ...
 ) -> np.ndarray: ...  # np.ndarray[bool]
 
 
diff --git a/pandas/_libs/tslibs/fields.pyx b/pandas/_libs/tslibs/fields.pyx
index 8de7e4331aff7..d6ca38e57d2d8 100644
--- a/pandas/_libs/tslibs/fields.pyx
+++ b/pandas/_libs/tslibs/fields.pyx
@@ -198,7 +198,7 @@ cdef inline bint _is_on_month(int month, int compare_month, int modby) nogil:
 @cython.wraparound(False)
 @cython.boundscheck(False)
 def get_start_end_field(const int64_t[:] dtindex, str field,
-                        str freqstr, int month_kw):
+                        object freqstr=None, int month_kw=12):
     """
     Given an int64-based datetime index return array of indicators
     of whether timestamps are at the start/end of the month/quarter/year
diff --git a/pandas/tests/tslibs/test_fields.py b/pandas/tests/tslibs/test_fields.py
index b851032a8fcaa..e5fe998923f8d 100644
--- a/pandas/tests/tslibs/test_fields.py
+++ b/pandas/tests/tslibs/test_fields.py
@@ -19,7 +19,7 @@ def test_fields_readonly():
     expected = np.array([1970, 1970, 1970, 1970, 1970], dtype=np.int32)
     tm.assert_numpy_array_equal(result, expected)
 
-    result = fields.get_start_end_field(dtindex, "is_month_start", None, 12)
+    result = fields.get_start_end_field(dtindex, "is_month_start", None)
     expected = np.array([True, False, False, False, False], dtype=np.bool_)
     tm.assert_numpy_array_equal(result, expected)
 

From 5d542c29f49794dda7ccc890e39e6b1ecbd095c4 Mon Sep 17 00:00:00 2001
From: Brock <jbrockmendel@gmail.com>
Date: Thu, 8 Apr 2021 16:29:24 -0700
Subject: [PATCH 6/6] revert sparse edit

---
 pandas/_libs/sparse_op_helper.pxi.in | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/pandas/_libs/sparse_op_helper.pxi.in b/pandas/_libs/sparse_op_helper.pxi.in
index 36f22445d0373..ce665ca812131 100644
--- a/pandas/_libs/sparse_op_helper.pxi.in
+++ b/pandas/_libs/sparse_op_helper.pxi.in
@@ -302,8 +302,8 @@ cpdef sparse_{{opname}}_{{dtype}}({{dtype}}_t[:] x,
         raise NotImplementedError
 
 
-cdef sparse_fill_{{opname}}_{{dtype}}({{dtype}}_t xfill,
-                                      {{dtype}}_t yfill):
+cpdef sparse_fill_{{opname}}_{{dtype}}({{dtype}}_t xfill,
+                                       {{dtype}}_t yfill):
     return {{(opname, 'xfill', 'yfill', dtype) | get_op}}
 
 {{endfor}}