Skip to content
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

Jump to bottom

FIX-#2566: Ensure Series.unique does not return a scalar when there is only one unique value #2567

Merged
merged 3 commits into from
Dec 23, 2020
Merged

FIX-#2566: Ensure Series.unique does not return a scalar when there is only one unique value #2567

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
ba59173
FIX-#2566: Ensure unique doesn't return a scalar using np.atleast_1d
richardlin047 Dec 20, 2020
87df768
FIX-#2566: Check array shapes match for test_unique
richardlin047 Dec 20, 2020
0148c13
FIX-#2566: Reduce unique dimensions using constructor instead
richardlin047 Dec 23, 2020
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
4 changes: 3 additions & 1 deletion modin/pandas/series.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1345,7 +1345,9 @@ def truncate(self, before=None, after=None, axis=None, copy=True):
)

def unique(self):
return self._query_compiler.unique().to_numpy().squeeze()
return self.__constructor__(
query_compiler=self._query_compiler.unique()
).to_numpy()

def update(self, other):
if not isinstance(other, Series):
Expand Down
6 changes: 6 additions & 0 deletions modin/pandas/test/test_general.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -528,10 +528,12 @@ def test_unique():
modin_result = pd.unique([2, 1, 3, 3])
pandas_result = pandas.unique([2, 1, 3, 3])
assert_array_equal(modin_result, pandas_result)
assert modin_result.shape == pandas_result.shape

modin_result = pd.unique(pd.Series([2] + [1] * 5))
pandas_result = pandas.unique(pandas.Series([2] + [1] * 5))
assert_array_equal(modin_result, pandas_result)
assert modin_result.shape == pandas_result.shape

modin_result = pd.unique(
pd.Series([pd.Timestamp("20160101"), pd.Timestamp("20160101")])
Expand All @@ -540,6 +542,7 @@ def test_unique():
pandas.Series([pandas.Timestamp("20160101"), pandas.Timestamp("20160101")])
)
assert_array_equal(modin_result, pandas_result)
assert modin_result.shape == pandas_result.shape

modin_result = pd.unique(
pd.Series(
Expand All @@ -558,6 +561,7 @@ def test_unique():
)
)
assert_array_equal(modin_result, pandas_result)
assert modin_result.shape == pandas_result.shape

modin_result = pd.unique(
pd.Index(
Expand All @@ -576,10 +580,12 @@ def test_unique():
)
)
assert_array_equal(modin_result, pandas_result)
assert modin_result.shape == pandas_result.shape

modin_result = pd.unique(pd.Series(pd.Categorical(list("baabc"))))
pandas_result = pandas.unique(pandas.Series(pandas.Categorical(list("baabc"))))
assert_array_equal(modin_result, pandas_result)
assert modin_result.shape == pandas_result.shape


@pytest.mark.parametrize("normalize, bins, dropna", [(True, 3, False)])
Expand Down
6 changes: 6 additions & 0 deletions modin/pandas/test/test_series.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3287,16 +3287,19 @@ def test_unique(data):
modin_result = modin_series.unique()
pandas_result = pandas_series.unique()
assert_array_equal(modin_result, pandas_result)
assert modin_result.shape == pandas_result.shape

modin_result = pd.Series([2, 1, 3, 3], name="A").unique()
pandas_result = pandas.Series([2, 1, 3, 3], name="A").unique()
assert_array_equal(modin_result, pandas_result)
assert modin_result.shape == pandas_result.shape

modin_result = pd.Series([pd.Timestamp("2016-01-01") for _ in range(3)]).unique()
pandas_result = pandas.Series(
[pd.Timestamp("2016-01-01") for _ in range(3)]
).unique()
assert_array_equal(modin_result, pandas_result)
assert modin_result.shape == pandas_result.shape

modin_result = pd.Series(
[pd.Timestamp("2016-01-01", tz="US/Eastern") for _ in range(3)]
Expand All @@ -3305,10 +3308,12 @@ def test_unique(data):
[pd.Timestamp("2016-01-01", tz="US/Eastern") for _ in range(3)]
).unique()
assert_array_equal(modin_result, pandas_result)
assert modin_result.shape == pandas_result.shape

modin_result = pandas.Series(pd.Categorical(list("baabc"))).unique()
pandas_result = pd.Series(pd.Categorical(list("baabc"))).unique()
assert_array_equal(modin_result, pandas_result)
assert modin_result.shape == pandas_result.shape

modin_result = pd.Series(
pd.Categorical(list("baabc"), categories=list("abc"), ordered=True)
Expand All @@ -3317,6 +3322,7 @@ def test_unique(data):
pd.Categorical(list("baabc"), categories=list("abc"), ordered=True)
).unique()
assert_array_equal(modin_result, pandas_result)
assert modin_result.shape == pandas_result.shape


@pytest.mark.parametrize("data", test_data_values, ids=test_data_keys)
Expand Down