Skip to content

CLN libjoin int64->intp #40601

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 7 commits into from
Mar 24, 2021
Merged

CLN libjoin int64->intp #40601

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
7 commits
Select commit Hold shift + click to select a range
4cab96a
CLN libjoin int64->intp
jbrockmendel Mar 23, 2021
feb734b
Merge branch 'master' into typ-libjoin
jbrockmendel Mar 24, 2021
1ce3725
update join test expecteds
jbrockmendel Mar 24, 2021
48383b9
Merge branch 'master' into typ-libjoin
jbrockmendel Mar 24, 2021
9260d0c
troubleshoot windows build
jbrockmendel Mar 24, 2021
0689fa2
troubleshoot windows builds
jbrockmendel Mar 24, 2021
c6db8e5
strip troubleshooting code
jbrockmendel Mar 24, 2021
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
62 changes: 31 additions & 31 deletions pandas/_libs/join.pyx
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -231,7 +231,7 @@ cdef ndarray[intp_t] _get_result_indexer(
return res


def ffill_indexer(const intp_t[:] indexer):
def ffill_indexer(const intp_t[:] indexer) -> np.ndarray:
cdef:
Py_ssize_t i, n = len(indexer)
ndarray[intp_t] result
Expand Down Expand Up @@ -275,15 +275,15 @@ ctypedef fused join_t:
def left_join_indexer_unique(ndarray[join_t] left, ndarray[join_t] right):
cdef:
Py_ssize_t i, j, nleft, nright
ndarray[int64_t] indexer
ndarray[intp_t] indexer
join_t lval, rval

i = 0
j = 0
nleft = len(left)
nright = len(right)

indexer = np.empty(nleft, dtype=np.int64)
indexer = np.empty(nleft, dtype=np.intp)
while True:
if i == nleft:
break
Expand Down Expand Up @@ -324,7 +324,7 @@ def left_join_indexer(ndarray[join_t] left, ndarray[join_t] right):
cdef:
Py_ssize_t i, j, k, nright, nleft, count
join_t lval, rval
ndarray[int64_t] lindexer, rindexer
ndarray[intp_t] lindexer, rindexer
ndarray[join_t] result

nleft = len(left)
Expand Down Expand Up @@ -366,8 +366,8 @@ def left_join_indexer(ndarray[join_t] left, ndarray[join_t] right):

# do it again now that result size is known

lindexer = np.empty(count, dtype=np.int64)
rindexer = np.empty(count, dtype=np.int64)
lindexer = np.empty(count, dtype=np.intp)
rindexer = np.empty(count, dtype=np.intp)
result = np.empty(count, dtype=left.dtype)

i = 0
Expand Down Expand Up @@ -427,7 +427,7 @@ def inner_join_indexer(ndarray[join_t] left, ndarray[join_t] right):
cdef:
Py_ssize_t i, j, k, nright, nleft, count
join_t lval, rval
ndarray[int64_t] lindexer, rindexer
ndarray[intp_t] lindexer, rindexer
ndarray[join_t] result

nleft = len(left)
Expand Down Expand Up @@ -468,8 +468,8 @@ def inner_join_indexer(ndarray[join_t] left, ndarray[join_t] right):

# do it again now that result size is known

lindexer = np.empty(count, dtype=np.int64)
rindexer = np.empty(count, dtype=np.int64)
lindexer = np.empty(count, dtype=np.intp)
rindexer = np.empty(count, dtype=np.intp)
result = np.empty(count, dtype=left.dtype)

i = 0
Expand Down Expand Up @@ -517,7 +517,7 @@ def outer_join_indexer(ndarray[join_t] left, ndarray[join_t] right):
cdef:
Py_ssize_t i, j, nright, nleft, count
join_t lval, rval
ndarray[int64_t] lindexer, rindexer
ndarray[intp_t] lindexer, rindexer
ndarray[join_t] result

nleft = len(left)
Expand Down Expand Up @@ -564,8 +564,8 @@ def outer_join_indexer(ndarray[join_t] left, ndarray[join_t] right):
count += 1
j += 1

lindexer = np.empty(count, dtype=np.int64)
rindexer = np.empty(count, dtype=np.int64)
lindexer = np.empty(count, dtype=np.intp)
rindexer = np.empty(count, dtype=np.intp)
result = np.empty(count, dtype=left.dtype)

# do it again, but populate the indexers / result
Expand Down Expand Up @@ -673,12 +673,12 @@ def asof_join_backward_on_X_by_Y(asof_t[:] left_values,
asof_t[:] right_values,
by_t[:] left_by_values,
by_t[:] right_by_values,
bint allow_exact_matches=1,
bint allow_exact_matches=True,
tolerance=None):

cdef:
Py_ssize_t left_pos, right_pos, left_size, right_size, found_right_pos
ndarray[int64_t] left_indexer, right_indexer
ndarray[intp_t] left_indexer, right_indexer
bint has_tolerance = False
asof_t tolerance_ = 0
asof_t diff = 0
Expand All @@ -693,8 +693,8 @@ def asof_join_backward_on_X_by_Y(asof_t[:] left_values,
left_size = len(left_values)
right_size = len(right_values)

left_indexer = np.empty(left_size, dtype=np.int64)
right_indexer = np.empty(left_size, dtype=np.int64)
left_indexer = np.empty(left_size, dtype=np.intp)
right_indexer = np.empty(left_size, dtype=np.intp)

if by_t is object:
hash_table = PyObjectHashTable(right_size)
Expand Down Expand Up @@ -747,7 +747,7 @@ def asof_join_forward_on_X_by_Y(asof_t[:] left_values,

cdef:
Py_ssize_t left_pos, right_pos, left_size, right_size, found_right_pos
ndarray[int64_t] left_indexer, right_indexer
ndarray[intp_t] left_indexer, right_indexer
bint has_tolerance = False
asof_t tolerance_ = 0
asof_t diff = 0
Expand All @@ -762,8 +762,8 @@ def asof_join_forward_on_X_by_Y(asof_t[:] left_values,
left_size = len(left_values)
right_size = len(right_values)

left_indexer = np.empty(left_size, dtype=np.int64)
right_indexer = np.empty(left_size, dtype=np.int64)
left_indexer = np.empty(left_size, dtype=np.intp)
right_indexer = np.empty(left_size, dtype=np.intp)

if by_t is object:
hash_table = PyObjectHashTable(right_size)
Expand Down Expand Up @@ -816,14 +816,14 @@ def asof_join_nearest_on_X_by_Y(asof_t[:] left_values,

cdef:
Py_ssize_t left_size, right_size, i
ndarray[int64_t] left_indexer, right_indexer, bli, bri, fli, fri
ndarray[intp_t] left_indexer, right_indexer, bli, bri, fli, fri
asof_t bdiff, fdiff

left_size = len(left_values)
right_size = len(right_values)

left_indexer = np.empty(left_size, dtype=np.int64)
right_indexer = np.empty(left_size, dtype=np.int64)
left_indexer = np.empty(left_size, dtype=np.intp)
right_indexer = np.empty(left_size, dtype=np.intp)

# search both forward and backward
bli, bri = asof_join_backward_on_X_by_Y(
Expand Down Expand Up @@ -867,7 +867,7 @@ def asof_join_backward(asof_t[:] left_values,

cdef:
Py_ssize_t left_pos, right_pos, left_size, right_size
ndarray[int64_t] left_indexer, right_indexer
ndarray[intp_t] left_indexer, right_indexer
bint has_tolerance = False
asof_t tolerance_ = 0
asof_t diff = 0
Expand All @@ -880,8 +880,8 @@ def asof_join_backward(asof_t[:] left_values,
left_size = len(left_values)
right_size = len(right_values)

left_indexer = np.empty(left_size, dtype=np.int64)
right_indexer = np.empty(left_size, dtype=np.int64)
left_indexer = np.empty(left_size, dtype=np.intp)
right_indexer = np.empty(left_size, dtype=np.intp)

right_pos = 0
for left_pos in range(left_size):
Expand Down Expand Up @@ -920,7 +920,7 @@ def asof_join_forward(asof_t[:] left_values,

cdef:
Py_ssize_t left_pos, right_pos, left_size, right_size
ndarray[int64_t] left_indexer, right_indexer
ndarray[intp_t] left_indexer, right_indexer
bint has_tolerance = False
asof_t tolerance_ = 0
asof_t diff = 0
Expand All @@ -933,8 +933,8 @@ def asof_join_forward(asof_t[:] left_values,
left_size = len(left_values)
right_size = len(right_values)

left_indexer = np.empty(left_size, dtype=np.int64)
right_indexer = np.empty(left_size, dtype=np.int64)
left_indexer = np.empty(left_size, dtype=np.intp)
right_indexer = np.empty(left_size, dtype=np.intp)

right_pos = right_size - 1
for left_pos in range(left_size - 1, -1, -1):
Expand Down Expand Up @@ -974,14 +974,14 @@ def asof_join_nearest(asof_t[:] left_values,

cdef:
Py_ssize_t left_size, right_size, i
ndarray[int64_t] left_indexer, right_indexer, bli, bri, fli, fri
ndarray[intp_t] left_indexer, right_indexer, bli, bri, fli, fri
asof_t bdiff, fdiff

left_size = len(left_values)
right_size = len(right_values)

left_indexer = np.empty(left_size, dtype=np.int64)
right_indexer = np.empty(left_size, dtype=np.int64)
left_indexer = np.empty(left_size, dtype=np.intp)
right_indexer = np.empty(left_size, dtype=np.intp)

# search both forward and backward
bli, bri = asof_join_backward(left_values, right_values,
Expand Down
4 changes: 2 additions & 2 deletions pandas/core/indexes/base.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3925,15 +3925,15 @@ def join(
if len(other) == 0 and how in ("left", "outer"):
join_index = self._view()
if return_indexers:
rindexer = np.repeat(-1, len(join_index))
rindexer = np.repeat(np.intp(-1), len(join_index))
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

odd that there isn't a dtype arg

return join_index, None, rindexer
else:
return join_index

if len(self) == 0 and how in ("right", "outer"):
join_index = other._view()
if return_indexers:
lindexer = np.repeat(-1, len(join_index))
lindexer = np.repeat(np.intp(-1), len(join_index))
return join_index, lindexer, None
else:
return join_index
Expand Down
Loading