-
-
Notifications
You must be signed in to change notification settings - Fork 18.4k
Backport PR #32166 on branch 1.0.x #32269
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.
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
jreback
merged 1 commit into
pandas-dev:1.0.x
from
jbrockmendel:auto-backport-of-pr-32166-on-1.0.x
Feb 27, 2020
Merged
Changes from all commits
Commits
File filter
Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
There are no files selected for viewing
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,144 @@ | ||
from datetime import datetime | ||
|
||
import numpy as np | ||
import pytest | ||
|
||
from pandas import DatetimeIndex, Index, Timestamp, date_range, to_datetime | ||
import pandas._testing as tm | ||
|
||
from pandas.tseries.offsets import BDay, BMonthEnd | ||
|
||
|
||
class TestJoin: | ||
def test_does_not_convert_mixed_integer(self): | ||
df = tm.makeCustomDataframe( | ||
10, | ||
10, | ||
data_gen_f=lambda *args, **kwargs: np.random.randn(), | ||
r_idx_type="i", | ||
c_idx_type="dt", | ||
) | ||
cols = df.columns.join(df.index, how="outer") | ||
joined = cols.join(df.columns) | ||
assert cols.dtype == np.dtype("O") | ||
assert cols.dtype == joined.dtype | ||
tm.assert_numpy_array_equal(cols.values, joined.values) | ||
|
||
def test_join_self(self, join_type): | ||
index = date_range("1/1/2000", periods=10) | ||
joined = index.join(index, how=join_type) | ||
assert index is joined | ||
|
||
def test_join_with_period_index(self, join_type): | ||
df = tm.makeCustomDataframe( | ||
10, | ||
10, | ||
data_gen_f=lambda *args: np.random.randint(2), | ||
c_idx_type="p", | ||
r_idx_type="dt", | ||
) | ||
s = df.iloc[:5, 0] | ||
|
||
expected = df.columns.astype("O").join(s.index, how=join_type) | ||
result = df.columns.join(s.index, how=join_type) | ||
tm.assert_index_equal(expected, result) | ||
|
||
def test_join_object_index(self): | ||
rng = date_range("1/1/2000", periods=10) | ||
idx = Index(["a", "b", "c", "d"]) | ||
|
||
result = rng.join(idx, how="outer") | ||
assert isinstance(result[0], Timestamp) | ||
|
||
def test_join_utc_convert(self, join_type): | ||
rng = date_range("1/1/2011", periods=100, freq="H", tz="utc") | ||
|
||
left = rng.tz_convert("US/Eastern") | ||
right = rng.tz_convert("Europe/Berlin") | ||
|
||
result = left.join(left[:-5], how=join_type) | ||
assert isinstance(result, DatetimeIndex) | ||
assert result.tz == left.tz | ||
|
||
result = left.join(right[:-5], how=join_type) | ||
assert isinstance(result, DatetimeIndex) | ||
assert result.tz.zone == "UTC" | ||
|
||
@pytest.mark.parametrize("sort", [None, False]) | ||
def test_datetimeindex_union_join_empty(self, sort): | ||
dti = date_range(start="1/1/2001", end="2/1/2001", freq="D") | ||
empty = Index([]) | ||
|
||
result = dti.union(empty, sort=sort) | ||
expected = dti.astype("O") | ||
tm.assert_index_equal(result, expected) | ||
|
||
result = dti.join(empty) | ||
assert isinstance(result, DatetimeIndex) | ||
tm.assert_index_equal(result, dti) | ||
|
||
def test_join_nonunique(self): | ||
idx1 = to_datetime(["2012-11-06 16:00:11.477563", "2012-11-06 16:00:11.477563"]) | ||
idx2 = to_datetime(["2012-11-06 15:11:09.006507", "2012-11-06 15:11:09.006507"]) | ||
rs = idx1.join(idx2, how="outer") | ||
assert rs.is_monotonic | ||
|
||
@pytest.mark.parametrize("freq", ["B", "C"]) | ||
def test_outer_join(self, freq): | ||
# should just behave as union | ||
start, end = datetime(2009, 1, 1), datetime(2010, 1, 1) | ||
rng = date_range(start=start, end=end, freq=freq) | ||
|
||
# overlapping | ||
left = rng[:10] | ||
right = rng[5:10] | ||
|
||
the_join = left.join(right, how="outer") | ||
assert isinstance(the_join, DatetimeIndex) | ||
|
||
# non-overlapping, gap in middle | ||
left = rng[:5] | ||
right = rng[10:] | ||
|
||
the_join = left.join(right, how="outer") | ||
assert isinstance(the_join, DatetimeIndex) | ||
assert the_join.freq is None | ||
|
||
# non-overlapping, no gap | ||
left = rng[:5] | ||
right = rng[5:10] | ||
|
||
the_join = left.join(right, how="outer") | ||
assert isinstance(the_join, DatetimeIndex) | ||
|
||
# overlapping, but different offset | ||
other = date_range(start, end, freq=BMonthEnd()) | ||
|
||
the_join = rng.join(other, how="outer") | ||
assert isinstance(the_join, DatetimeIndex) | ||
assert the_join.freq is None | ||
|
||
def test_naive_aware_conflicts(self): | ||
start, end = datetime(2009, 1, 1), datetime(2010, 1, 1) | ||
naive = date_range(start, end, freq=BDay(), tz=None) | ||
aware = date_range(start, end, freq=BDay(), tz="Asia/Hong_Kong") | ||
|
||
msg = "tz-naive.*tz-aware" | ||
with pytest.raises(TypeError, match=msg): | ||
naive.join(aware) | ||
|
||
with pytest.raises(TypeError, match=msg): | ||
aware.join(naive) | ||
|
||
@pytest.mark.parametrize("tz", [None, "US/Pacific"]) | ||
def test_join_preserves_freq(self, tz): | ||
There was a problem hiding this comment. Choose a reason for hiding this commentThe reason will be displayed to describe this comment to others. Learn more. only this test should be backported |
||
# GH#32157 | ||
dti = date_range("2016-01-01", periods=10, tz=tz) | ||
result = dti[:5].join(dti[5:], how="outer") | ||
assert result.freq == dti.freq | ||
tm.assert_index_equal(result, dti) | ||
|
||
result = dti[:5].join(dti[6:], how="outer") | ||
assert result.freq is None | ||
expected = dti.delete(5) | ||
tm.assert_index_equal(result, expected) |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,49 @@ | ||
import numpy as np | ||
|
||
from pandas import Index, Timedelta, timedelta_range | ||
import pandas._testing as tm | ||
|
||
|
||
class TestJoin: | ||
def test_append_join_nondatetimeindex(self): | ||
rng = timedelta_range("1 days", periods=10) | ||
idx = Index(["a", "b", "c", "d"]) | ||
|
||
result = rng.append(idx) | ||
assert isinstance(result[0], Timedelta) | ||
|
||
# it works | ||
rng.join(idx, how="outer") | ||
|
||
def test_join_self(self, join_type): | ||
index = timedelta_range("1 day", periods=10) | ||
joined = index.join(index, how=join_type) | ||
tm.assert_index_equal(index, joined) | ||
|
||
def test_does_not_convert_mixed_integer(self): | ||
df = tm.makeCustomDataframe( | ||
10, | ||
10, | ||
data_gen_f=lambda *args, **kwargs: np.random.randn(), | ||
r_idx_type="i", | ||
c_idx_type="td", | ||
) | ||
str(df) | ||
|
||
cols = df.columns.join(df.index, how="outer") | ||
joined = cols.join(df.columns) | ||
assert cols.dtype == np.dtype("O") | ||
assert cols.dtype == joined.dtype | ||
tm.assert_index_equal(cols, joined) | ||
|
||
def test_join_preserves_freq(self): | ||
There was a problem hiding this comment. Choose a reason for hiding this commentThe reason will be displayed to describe this comment to others. Learn more. only this test should be backported |
||
# GH#32157 | ||
tdi = timedelta_range("1 day", periods=10) | ||
result = tdi[:5].join(tdi[5:], how="outer") | ||
assert result.freq == tdi.freq | ||
tm.assert_index_equal(result, tdi) | ||
|
||
result = tdi[:5].join(tdi[6:], how="outer") | ||
assert result.freq is None | ||
expected = tdi.delete(5) | ||
tm.assert_index_equal(result, expected) |
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
can you add a comment why the type:ignore has been added.