Skip to content

REF: avoid getattr pattern for join_indexer #29117

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 5 commits into from
Oct 22, 2019
Merged

REF: avoid getattr pattern for join_indexer #29117

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
5 commits
Select commit Hold shift + click to select a range
4c75cc8
commit so i can rebase
jbrockmendel Oct 19, 2019
422ccd7
Merge branch 'master' of https://github.com/pandas-dev/pandas into cy…
jbrockmendel Oct 19, 2019
255c0ff
Merge branch 'master' of https://github.com/pandas-dev/pandas into cy…
jbrockmendel Oct 19, 2019
1a22e5a
Merge branch 'master' of https://github.com/pandas-dev/pandas into cy…
jbrockmendel Oct 20, 2019
7b88515
parametrize test
jbrockmendel Oct 20, 2019
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
32 changes: 0 additions & 32 deletions pandas/_libs/join.pyx
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -290,14 +290,6 @@ def left_join_indexer_unique(join_t[:] left, join_t[:] right):
return indexer


left_join_indexer_unique_float64 = left_join_indexer_unique["float64_t"]
left_join_indexer_unique_float32 = left_join_indexer_unique["float32_t"]
left_join_indexer_unique_object = left_join_indexer_unique["object"]
left_join_indexer_unique_int32 = left_join_indexer_unique["int32_t"]
left_join_indexer_unique_int64 = left_join_indexer_unique["int64_t"]
left_join_indexer_unique_uint64 = left_join_indexer_unique["uint64_t"]


@cython.wraparound(False)
@cython.boundscheck(False)
def left_join_indexer(ndarray[join_t] left, ndarray[join_t] right):
Expand Down Expand Up @@ -401,14 +393,6 @@ def left_join_indexer(ndarray[join_t] left, ndarray[join_t] right):
return result, lindexer, rindexer


left_join_indexer_float64 = left_join_indexer["float64_t"]
left_join_indexer_float32 = left_join_indexer["float32_t"]
left_join_indexer_object = left_join_indexer["object"]
left_join_indexer_int32 = left_join_indexer["int32_t"]
left_join_indexer_int64 = left_join_indexer["int64_t"]
left_join_indexer_uint64 = left_join_indexer["uint64_t"]


@cython.wraparound(False)
@cython.boundscheck(False)
def inner_join_indexer(ndarray[join_t] left, ndarray[join_t] right):
Expand Down Expand Up @@ -502,14 +486,6 @@ def inner_join_indexer(ndarray[join_t] left, ndarray[join_t] right):
return result, lindexer, rindexer


inner_join_indexer_float64 = inner_join_indexer["float64_t"]
inner_join_indexer_float32 = inner_join_indexer["float32_t"]
inner_join_indexer_object = inner_join_indexer["object"]
inner_join_indexer_int32 = inner_join_indexer["int32_t"]
inner_join_indexer_int64 = inner_join_indexer["int64_t"]
inner_join_indexer_uint64 = inner_join_indexer["uint64_t"]


@cython.wraparound(False)
@cython.boundscheck(False)
def outer_join_indexer(ndarray[join_t] left, ndarray[join_t] right):
Expand Down Expand Up @@ -639,14 +615,6 @@ def outer_join_indexer(ndarray[join_t] left, ndarray[join_t] right):
return result, lindexer, rindexer


outer_join_indexer_float64 = outer_join_indexer["float64_t"]
outer_join_indexer_float32 = outer_join_indexer["float32_t"]
outer_join_indexer_object = outer_join_indexer["object"]
outer_join_indexer_int32 = outer_join_indexer["int32_t"]
outer_join_indexer_int64 = outer_join_indexer["int64_t"]
outer_join_indexer_uint64 = outer_join_indexer["uint64_t"]


# ----------------------------------------------------------------------
# asof_join_by
# ----------------------------------------------------------------------
Expand Down
8 changes: 4 additions & 4 deletions pandas/core/indexes/datetimes.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -230,11 +230,11 @@ class DatetimeIndex(DatetimeIndexOpsMixin, Int64Index, DatetimeDelegateMixin):
def _join_i8_wrapper(joinf, **kwargs):
return DatetimeIndexOpsMixin._join_i8_wrapper(joinf, dtype="M8[ns]", **kwargs)

_inner_indexer = _join_i8_wrapper(libjoin.inner_join_indexer_int64)
_outer_indexer = _join_i8_wrapper(libjoin.outer_join_indexer_int64)
_left_indexer = _join_i8_wrapper(libjoin.left_join_indexer_int64)
_inner_indexer = _join_i8_wrapper(libjoin.inner_join_indexer)
_outer_indexer = _join_i8_wrapper(libjoin.outer_join_indexer)
_left_indexer = _join_i8_wrapper(libjoin.left_join_indexer)
_left_indexer_unique = _join_i8_wrapper(
libjoin.left_join_indexer_unique_int64, with_indexers=False
libjoin.left_join_indexer_unique, with_indexers=False
)

_engine_type = libindex.DatetimeEngine
Expand Down
8 changes: 4 additions & 4 deletions pandas/core/indexes/timedeltas.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -152,11 +152,11 @@ class TimedeltaIndex(
def _join_i8_wrapper(joinf, **kwargs):
return DatetimeIndexOpsMixin._join_i8_wrapper(joinf, dtype="m8[ns]", **kwargs)

_inner_indexer = _join_i8_wrapper(libjoin.inner_join_indexer_int64)
_outer_indexer = _join_i8_wrapper(libjoin.outer_join_indexer_int64)
_left_indexer = _join_i8_wrapper(libjoin.left_join_indexer_int64)
_inner_indexer = _join_i8_wrapper(libjoin.inner_join_indexer)
_outer_indexer = _join_i8_wrapper(libjoin.outer_join_indexer)
_left_indexer = _join_i8_wrapper(libjoin.left_join_indexer)
_left_indexer_unique = _join_i8_wrapper(
libjoin.left_join_indexer_unique_int64, with_indexers=False
libjoin.left_join_indexer_unique, with_indexers=False
)

_engine_type = libindex.TimedeltaEngine
Expand Down
91 changes: 44 additions & 47 deletions pandas/tests/test_join.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,4 +1,5 @@
import numpy as np
import pytest

from pandas._libs import join as _join

Expand All @@ -8,50 +9,46 @@


class TestIndexer:
def test_outer_join_indexer(self):
typemap = [
("int32", _join.outer_join_indexer_int32),
("int64", _join.outer_join_indexer_int64),
("float32", _join.outer_join_indexer_float32),
("float64", _join.outer_join_indexer_float64),
("object", _join.outer_join_indexer_object),
]

for dtype, indexer in typemap:
left = np.arange(3, dtype=dtype)
right = np.arange(2, 5, dtype=dtype)
empty = np.array([], dtype=dtype)

result, lindexer, rindexer = indexer(left, right)
assert isinstance(result, np.ndarray)
assert isinstance(lindexer, np.ndarray)
assert isinstance(rindexer, np.ndarray)
tm.assert_numpy_array_equal(result, np.arange(5, dtype=dtype))
exp = np.array([0, 1, 2, -1, -1], dtype=np.int64)
tm.assert_numpy_array_equal(lindexer, exp)
exp = np.array([-1, -1, 0, 1, 2], dtype=np.int64)
tm.assert_numpy_array_equal(rindexer, exp)

result, lindexer, rindexer = indexer(empty, right)
tm.assert_numpy_array_equal(result, right)
exp = np.array([-1, -1, -1], dtype=np.int64)
tm.assert_numpy_array_equal(lindexer, exp)
exp = np.array([0, 1, 2], dtype=np.int64)
tm.assert_numpy_array_equal(rindexer, exp)

result, lindexer, rindexer = indexer(left, empty)
tm.assert_numpy_array_equal(result, left)
exp = np.array([0, 1, 2], dtype=np.int64)
tm.assert_numpy_array_equal(lindexer, exp)
exp = np.array([-1, -1, -1], dtype=np.int64)
tm.assert_numpy_array_equal(rindexer, exp)
@pytest.mark.parametrize(
"dtype", ["int32", "int64", "float32", "float64", "object"]
Copy link
Contributor

Choose a reason for hiding this comment

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

at some point if can change to use a fixture to ensure more coverage (we may need to expand the indexers here as well), pls create a followup issue.

)
def test_outer_join_indexer(self, dtype):
indexer = _join.outer_join_indexer

left = np.arange(3, dtype=dtype)
right = np.arange(2, 5, dtype=dtype)
empty = np.array([], dtype=dtype)

result, lindexer, rindexer = indexer(left, right)
assert isinstance(result, np.ndarray)
assert isinstance(lindexer, np.ndarray)
assert isinstance(rindexer, np.ndarray)
tm.assert_numpy_array_equal(result, np.arange(5, dtype=dtype))
exp = np.array([0, 1, 2, -1, -1], dtype=np.int64)
tm.assert_numpy_array_equal(lindexer, exp)
exp = np.array([-1, -1, 0, 1, 2], dtype=np.int64)
tm.assert_numpy_array_equal(rindexer, exp)

result, lindexer, rindexer = indexer(empty, right)
tm.assert_numpy_array_equal(result, right)
exp = np.array([-1, -1, -1], dtype=np.int64)
tm.assert_numpy_array_equal(lindexer, exp)
exp = np.array([0, 1, 2], dtype=np.int64)
tm.assert_numpy_array_equal(rindexer, exp)

result, lindexer, rindexer = indexer(left, empty)
tm.assert_numpy_array_equal(result, left)
exp = np.array([0, 1, 2], dtype=np.int64)
tm.assert_numpy_array_equal(lindexer, exp)
exp = np.array([-1, -1, -1], dtype=np.int64)
tm.assert_numpy_array_equal(rindexer, exp)


def test_left_join_indexer_unique():
a = np.array([1, 2, 3, 4, 5], dtype=np.int64)
b = np.array([2, 2, 3, 4, 4], dtype=np.int64)

result = _join.left_join_indexer_unique_int64(b, a)
result = _join.left_join_indexer_unique(b, a)
expected = np.array([1, 1, 2, 3, 3], dtype=np.int64)
tm.assert_numpy_array_equal(result, expected)

Expand Down Expand Up @@ -182,7 +179,7 @@ def test_inner_join_indexer():
a = np.array([1, 2, 3, 4, 5], dtype=np.int64)
b = np.array([0, 3, 5, 7, 9], dtype=np.int64)

index, ares, bres = _join.inner_join_indexer_int64(a, b)
index, ares, bres = _join.inner_join_indexer(a, b)

index_exp = np.array([3, 5], dtype=np.int64)
assert_almost_equal(index, index_exp)
Expand All @@ -195,7 +192,7 @@ def test_inner_join_indexer():
a = np.array([5], dtype=np.int64)
b = np.array([5], dtype=np.int64)

index, ares, bres = _join.inner_join_indexer_int64(a, b)
index, ares, bres = _join.inner_join_indexer(a, b)
tm.assert_numpy_array_equal(index, np.array([5], dtype=np.int64))
tm.assert_numpy_array_equal(ares, np.array([0], dtype=np.int64))
tm.assert_numpy_array_equal(bres, np.array([0], dtype=np.int64))
Expand All @@ -205,7 +202,7 @@ def test_outer_join_indexer():
a = np.array([1, 2, 3, 4, 5], dtype=np.int64)
b = np.array([0, 3, 5, 7, 9], dtype=np.int64)

index, ares, bres = _join.outer_join_indexer_int64(a, b)
index, ares, bres = _join.outer_join_indexer(a, b)

index_exp = np.array([0, 1, 2, 3, 4, 5, 7, 9], dtype=np.int64)
assert_almost_equal(index, index_exp)
Expand All @@ -218,7 +215,7 @@ def test_outer_join_indexer():
a = np.array([5], dtype=np.int64)
b = np.array([5], dtype=np.int64)

index, ares, bres = _join.outer_join_indexer_int64(a, b)
index, ares, bres = _join.outer_join_indexer(a, b)
tm.assert_numpy_array_equal(index, np.array([5], dtype=np.int64))
tm.assert_numpy_array_equal(ares, np.array([0], dtype=np.int64))
tm.assert_numpy_array_equal(bres, np.array([0], dtype=np.int64))
Expand All @@ -228,7 +225,7 @@ def test_left_join_indexer():
a = np.array([1, 2, 3, 4, 5], dtype=np.int64)
b = np.array([0, 3, 5, 7, 9], dtype=np.int64)

index, ares, bres = _join.left_join_indexer_int64(a, b)
index, ares, bres = _join.left_join_indexer(a, b)

assert_almost_equal(index, a)

Expand All @@ -240,7 +237,7 @@ def test_left_join_indexer():
a = np.array([5], dtype=np.int64)
b = np.array([5], dtype=np.int64)

index, ares, bres = _join.left_join_indexer_int64(a, b)
index, ares, bres = _join.left_join_indexer(a, b)
tm.assert_numpy_array_equal(index, np.array([5], dtype=np.int64))
tm.assert_numpy_array_equal(ares, np.array([0], dtype=np.int64))
tm.assert_numpy_array_equal(bres, np.array([0], dtype=np.int64))
Expand All @@ -250,7 +247,7 @@ def test_left_join_indexer2():
idx = Index([1, 1, 2, 5])
idx2 = Index([1, 2, 5, 7, 9])

res, lidx, ridx = _join.left_join_indexer_int64(idx2.values, idx.values)
res, lidx, ridx = _join.left_join_indexer(idx2.values, idx.values)

exp_res = np.array([1, 1, 2, 5, 7, 9], dtype=np.int64)
assert_almost_equal(res, exp_res)
Expand All @@ -266,7 +263,7 @@ def test_outer_join_indexer2():
idx = Index([1, 1, 2, 5])
idx2 = Index([1, 2, 5, 7, 9])

res, lidx, ridx = _join.outer_join_indexer_int64(idx2.values, idx.values)
res, lidx, ridx = _join.outer_join_indexer(idx2.values, idx.values)

exp_res = np.array([1, 1, 2, 5, 7, 9], dtype=np.int64)
assert_almost_equal(res, exp_res)
Expand All @@ -282,7 +279,7 @@ def test_inner_join_indexer2():
idx = Index([1, 1, 2, 5])
idx2 = Index([1, 2, 5, 7, 9])

res, lidx, ridx = _join.inner_join_indexer_int64(idx2.values, idx.values)
res, lidx, ridx = _join.inner_join_indexer(idx2.values, idx.values)

exp_res = np.array([1, 1, 2, 5], dtype=np.int64)
assert_almost_equal(res, exp_res)
Expand Down